diff --git a/README.md b/README.md
index 7de0aee..baac250 100644
--- a/README.md
+++ b/README.md
@@ -1 +1,19 @@
-# 2022-mtx-not-in-mgx-pairs
+# Identifying sequences that are in a metatranscriptome but not in a metagenome
+
+This repository curates a set of paired metagenomes and metatranscriptomes and provides a pipeline to rapidly identify the fraction of sequences in a metatranscriptome that are not in a metagenome.
+The pipeline is shaped around a metadata file, 'inputs/metadata-paired-mgx-mtx.tsv', that contains a sample name (`sample_name`), metagenome SRA run accession (`mgx_run_accession`; `SRR*`, `ERR*`, `DRR*`), metatranscriptome SRA run accession (`mtx_run_accession`), and a sample type (`sample_type`).
+Using the run accessions, it downloads the sequencing data from the SRA and generates a [FracMinHash sketch](https://www.biorxiv.org/content/10.1101/2022.01.11.475838v2.abstract) of each run.
+Then, it uses the paired information encoded in the metadata table to subtract the metagenome sketch from the metatranscriptome sketch.
+This produces an estimate of the fraction metatranscriptome sequences not found in the paired metagenome.
+These estimates are also clustered by `sample_type` to generate biome-specific estimates.
+The pipeline also analyzes the fraction of metatranscriptome-specific sequences that are shared between samples to discover what fraction of sequences we are systematically missing within and across biomes.
+
+Some metagenome and metatranscripome pairs are true pairs that were extracted from the same sample while others are from separate samples taken from the same location at the same time.
+
+## Getting started with this repository
+
+TBD
+
+## Next steps
+
+TBD
diff --git a/inputs/metadata-paired-mgx-mtx.tsv b/inputs/metadata-paired-mgx-mtx.tsv
new file mode 100644
index 0000000..1a633a4
--- /dev/null
+++ b/inputs/metadata-paired-mgx-mtx.tsv
@@ -0,0 +1,1281 @@
+sample_name	mtx_study_accession	mtx_run_accession	mgx_study_accession	mgx_run_accession	sample_type
+C_2_1	PRJNA406858	SRR6032600	PRJNA406858	SRR6032602	activated_sludge
+B_2_1	PRJNA406858	SRR6032604	PRJNA406858	SRR6032601	activated_sludge
+E_2_1	PRJNA406858	SRR6032605	PRJNA406858	SRR6032603	activated_sludge
+rumen_microbiome_of_beef_cattle_101	PRJNA448333	SRR8416057	PRJNA448333	SRR8397906	cattle_rumen
+rumen_microbiome_of_beef_cattle_103	PRJNA448333	SRR8416058	PRJNA448333	SRR8404214	cattle_rumen
+rumen_microbiome_of_beef_cattle_104	PRJNA448333	SRR8416055	PRJNA448333	SRR8397905	cattle_rumen
+rumen_microbiome_of_beef_cattle_105	PRJNA448333	SRR8416056	PRJNA448333	SRR8397904	cattle_rumen
+rumen_microbiome_of_beef_cattle_106	PRJNA448333	SRR8416061	PRJNA448333	SRR8397903	cattle_rumen
+rumen_microbiome_of_beef_cattle_107	PRJNA448333	SRR8416062	PRJNA448333	SRR8397910	cattle_rumen
+rumen_microbiome_of_beef_cattle_112	PRJNA448333	SRR8416059	PRJNA448333	SRR8397909	cattle_rumen
+rumen_microbiome_of_beef_cattle_201	PRJNA448333	SRR8416060	PRJNA448333	SRR8397908	cattle_rumen
+rumen_microbiome_of_beef_cattle_202	PRJNA448333	SRR8416064	PRJNA448333	SRR8397907	cattle_rumen
+rumen_microbiome_of_beef_cattle_203	PRJNA448333	SRR8416065	PRJNA448333	SRR8397902	cattle_rumen
+rumen_microbiome_of_beef_cattle_205	PRJNA448333	SRR8416069	PRJNA448333	SRR8397901	cattle_rumen
+rumen_microbiome_of_beef_cattle_206	PRJNA448333	SRR8416070	PRJNA448333	SRR8397884	cattle_rumen
+rumen_microbiome_of_beef_cattle_207	PRJNA448333	SRR8416067	PRJNA448333	SRR8397883	cattle_rumen
+rumen_microbiome_of_beef_cattle_208	PRJNA448333	SRR8416068	PRJNA448333	SRR8397886	cattle_rumen
+rumen_microbiome_of_beef_cattle_209	PRJNA448333	SRR8416073	PRJNA448333	SRR8397885	cattle_rumen
+rumen_microbiome_of_beef_cattle_210	PRJNA448333	SRR8416074	PRJNA448333	SRR8397888	cattle_rumen
+rumen_microbiome_of_beef_cattle_301	PRJNA448333	SRR8416071	PRJNA448333	SRR8397887	cattle_rumen
+rumen_microbiome_of_beef_cattle_302	PRJNA448333	SRR8416072	PRJNA448333	SRR8397890	cattle_rumen
+rumen_microbiome_of_beef_cattle_303	PRJNA448333	SRR8416075	PRJNA448333	SRR8397889	cattle_rumen
+rumen_microbiome_of_beef_cattle_304	PRJNA448333	SRR8416076	PRJNA448333	SRR8397882	cattle_rumen
+rumen_microbiome_of_beef_cattle_305	PRJNA448333	SRR8416092	PRJNA448333	SRR8397881	cattle_rumen
+rumen_microbiome_of_beef_cattle_307	PRJNA448333	SRR8416091	PRJNA448333	SRR8397917	cattle_rumen
+rumen_microbiome_of_beef_cattle_308	PRJNA448333	SRR8416090	PRJNA448333	SRR8397918	cattle_rumen
+rumen_microbiome_of_beef_cattle_401	PRJNA448333	SRR8416089	PRJNA448333	SRR8397919	cattle_rumen
+rumen_microbiome_of_beef_cattle_402	PRJNA448333	SRR8416096	PRJNA448333	SRR8397920	cattle_rumen
+rumen_microbiome_of_beef_cattle_403	PRJNA448333	SRR8416095	PRJNA448333	SRR8397913	cattle_rumen
+rumen_microbiome_of_beef_cattle_404	PRJNA448333	SRR8416094	PRJNA448333	SRR8397914	cattle_rumen
+rumen_microbiome_of_beef_cattle_407	PRJNA448333	SRR8416093	PRJNA448333	SRR8397915	cattle_rumen
+rumen_microbiome_of_beef_cattle_501	PRJNA448333	SRR8416088	PRJNA448333	SRR8397916	cattle_rumen
+rumen_microbiome_of_beef_cattle_503	PRJNA448333	SRR8416087	PRJNA448333	SRR8397911	cattle_rumen
+rumen_microbiome_of_beef_cattle_505	PRJNA448333	SRR8416102	PRJNA448333	SRR8397912	cattle_rumen
+rumen_microbiome_of_beef_cattle_506	PRJNA448333	SRR8416083	PRJNA448333	SRR8397894	cattle_rumen
+rumen_microbiome_of_beef_cattle_601	PRJNA448333	SRR8416063	PRJNA448333	SRR8397893	cattle_rumen
+rumen_microbiome_of_beef_cattle_604	PRJNA448333	SRR8416066	PRJNA448333	SRR8397892	cattle_rumen
+rumen_microbiome_of_beef_cattle_608	PRJNA448333	SRR8416097	PRJNA448333	SRR8397891	cattle_rumen
+rumen_microbiome_of_beef_cattle_611	PRJNA448333	SRR8416098	PRJNA448333	SRR8397898	cattle_rumen
+rumen_microbiome_of_beef_cattle_612	PRJNA448333	SRR8416099	PRJNA448333	SRR8397897	cattle_rumen
+rumen_microbiome_of_beef_cattle_701	PRJNA448333	SRR8416100	PRJNA448333	SRR8397896	cattle_rumen
+rumen_microbiome_of_beef_cattle_702	PRJNA448333	SRR8416077	PRJNA448333	SRR8397895	cattle_rumen
+rumen_microbiome_of_beef_cattle_703	PRJNA448333	SRR8416078	PRJNA448333	SRR8397900	cattle_rumen
+rumen_microbiome_of_beef_cattle_704	PRJNA448333	SRR8416082	PRJNA448333	SRR8397899	cattle_rumen
+rumen_microbiome_of_beef_cattle_705	PRJNA448333	SRR8416081	PRJNA448333	SRR8397926	cattle_rumen
+rumen_microbiome_of_beef_cattle_706	PRJNA448333	SRR8416086	PRJNA448333	SRR8397927	cattle_rumen
+rumen_microbiome_of_beef_cattle_707	PRJNA448333	SRR8416084	PRJNA448333	SRR8397924	cattle_rumen
+rumen_microbiome_of_beef_cattle_708	PRJNA448333	SRR8416101	PRJNA448333	SRR8397925	cattle_rumen
+rumen_microbiome_of_beef_cattle_709	PRJNA448333	SRR8416085	PRJNA448333	SRR8397922	cattle_rumen
+rumen_microbiome_of_beef_cattle_710	PRJNA448333	SRR8416080	PRJNA448333	SRR8397923	cattle_rumen
+rumen_microbiome_of_beef_cattle_712	PRJNA448333	SRR8416079	PRJNA448333	SRR8397921	cattle_rumen
+HiTCE_2d	PRJNA344005	SRR4308224	PRJNA344005	SRR4308227	groundwater
+HiTCEB12_2d	PRJNA344005	SRR4308225	PRJNA344005	SRR4308226	groundwater
+CS-Sed16-2cmA	PRJNA453733	SRR7083928	PRJNA453733	SRR7083931	lake
+amazon_plume_2_0um_from_station_10	PRJNA237345	SRR1193190	PRJNA237344	SRR1205250	river
+amazon_plume_2_0um_from_station_2	PRJNA237345	SRR1193177	PRJNA237344	SRR1182511	river
+amazon_plume_2_0um_from_station_23	PRJNA237345	SRR1193237	PRJNA237344	SRR1202089	river
+amazon_plume_2_0um_from_station_27	PRJNA237345	SRR1193629	PRJNA237344	SRR1183643	river
+amazon_plume_2_0um_from_station_3	PRJNA237345	SRR1193226	PRJNA237344	SRR1199272	river
+amazon_plume_0_2_2_0um_from_station_10	PRJNA237345	SRR1186930	PRJNA237344	SRR1199271	river
+amazon_plume_0_2_2_0um_from_station_2	PRJNA237345	SRR1193205	PRJNA237344	SRR1182512	river
+amazon_plume_0_2_2_0um_from_station_23	PRJNA237345	SRR1193632	PRJNA237344	SRR1186214	river
+amazon_plume_0_2_2_0um_from_station_25	PRJNA237345	SRR1204579	PRJNA237344	SRR1202090	river
+amazon_plume_0_2_2_0um_from_station_27	PRJNA237345	SRR1193627	PRJNA237344	SRR1183650	river
+amazon_plume_0_2_2_0um_from_station_3	PRJNA237345	SRR1193215	PRJNA237344	SRR1185413	river
+amazon_river_0_2_2_0um_from_belem	PRJNA237345	SRR1781804	PRJNA237344	SRR1790489	river
+amazon_river_0_2_2_0um_from_macapa_north_channel	PRJNA237345	SRR1785209	PRJNA237344	SRR1786279	river
+amazon_river_0_2_2_0um_from_macapa_south_channel	PRJNA237345	SRR1784299	PRJNA237344	SRR1787940	river
+amazon_river_0_2_2_0um_from_obidos	PRJNA237345	SRR1781945	PRJNA237344	SRR1790676	river
+amazon_river_0_2_2_0um_from_tapajos_depth	PRJNA237345	SRR1779221	PRJNA237344	SRR1792674	river
+amazon_river_0_2_2_0um_from_tapajos_surface	PRJNA237345	SRR1777513	PRJNA237344	SRR1796116	river
+amazon_river_2_0_297um_from_belem	PRJNA237345	SRR1781811	PRJNA237344	SRR1790644	river
+amazon_river_2_0_297um_from_macapa_north_channel	PRJNA237345	SRR1785350	PRJNA237344	SRR1786281	river
+amazon_river_2_0_297um_from_macapa_south_channel	PRJNA237345	SRR1784304	PRJNA237344	SRR1787943	river
+amazon_river_2_0_297um_from_obidos	PRJNA237345	SRR1782579	PRJNA237344	SRR1790678	river
+amazon_river_2_0_297um_from_tapajos_depth	PRJNA237345	SRR1781711	PRJNA237344	SRR1792852	river
+amazon_river_2_0_297um_from_tapajos_surface	PRJNA237345	SRR1778024	PRJNA237344	SRR1796118	river
+26	PRJNA502453	SRR8361532	PRJNA467728	SRR7592711	ocean
+58_r	PRJNA502454	SRR8361534	PRJNA467772	SRR7609573	ocean
+125_r	PRJNA468332	SRR7962480	PRJNA467773	SRR7609569	ocean
+8	PRJNA502455	SRR8297879	PRJNA467724	SRR7592287	ocean
+85	PRJNA502456	SRR8297845	PRJNA467765	SRR7609362	ocean
+76	PRJNA468305	SRR7949679	PRJNA467757	SRR7608731	ocean
+40	PRJNA467774	SRR7609608	PRJNA467736	SRR7595425	ocean
+53	PRJNA468299	SRR7609574	PRJNA502421	SRR8361352	ocean
+73	PRJNA468306	SRR7949683	PRJNA467754	SRR7608223	ocean
+23	PRJNA467775	SRR7609632	PRJNA467727	SRR7633009	ocean
+49	PRJNA467776	SRR7609653	PRJNA502442	SRR8361104	ocean
+14	PRJNA468308	SRR7949682	PRJNA502410	SRR8360542	ocean
+44	PRJNA502457	SRR8361579	PRJNA467738	SRR7600393	ocean
+29	PRJNA468309	SRR7949681	PRJNA467730	SRR7593831	ocean
+18	PRJNA467777	SRR7609655	PRJNA502413	SRR8360544	ocean
+24	PRJNA502458	SRR8361603	PRJNA502440	SRR8360549	ocean
+79	PRJNA468143	SRR7609654	PRJNA467760	SRR7609143	ocean
+22	PRJNA468300	SRR7609599	PRJNA502414	SRR8360545	ocean
+21	PRJNA468310	SRR7949678	PRJNA468208	SRR7592488	ocean
+60	PRJNA467778	SRR7609828	PRJNA502425	SRR8361517	ocean
+15	PRJNA468144	SRR7609827	PRJNA502411	SRR8360457	ocean
+75	PRJNA502459	SRR8361602	PRJNA467756	SRR7608423	ocean
+3	PRJNA468311	SRR7949692	PRJNA467722	SRR7592226	ocean
+20	PRJNA467779	SRR7609829	PRJNA467726	SRR7592489	ocean
+91	PRJNA468312	SRR7949677	PRJNA467769	SRR7609461	ocean
+56	PRJNA468152	SRR7615220	PRJNA467743	SRR7601261	ocean
+46	PRJNA502460	SRR8297843	PRJNA468213	SRR7600395	ocean
+2	PRJNA468313	SRR7609607	PRJNA467721	SRR7592225	ocean
+38	PRJNA468301	SRR7609600	PRJNA468211	SRR7594461	ocean
+45	PRJNA468314	SRR7962234	PRJNA467739	SRR7600394	ocean
+36	PRJNA502461	SRR8361605	PRJNA467733	SRR7594165	ocean
+39	PRJNA502462	SRR8297856	PRJNA467735	SRR7594967	ocean
+68	PRJNA502463	SRR8361604	PRJNA467751	SRR7608008	ocean
+30	PRJNA468315	SRR7962336	PRJNA502416	SRR8361099	ocean
+48	PRJNA502464	SRR8361607	PRJNA467741	SRR7600453	ocean
+42	PRJNA468316	SRR7962340	PRJNA502418	SRR8361100	ocean
+25	PRJNA467780	SRR7609843	PRJNA502415	SRR8361103	ocean
+78	PRJNA468317	SRR7962339	PRJNA467759	SRR7608833	ocean
+63	PRJNA468318	SRR7962244	PRJNA467746	SRR7601694	ocean
+43	PRJNA468302	SRR7815156	PRJNA468212	SRR7600353	ocean
+66	PRJNA467781	SRR7609844	PRJNA467749	SRR7607748	ocean
+54	PRJNA468319	SRR7962337	PRJNA468214	SRR7601174	ocean
+41	PRJNA467782	SRR7609846	PRJNA467737	SRR7599849	ocean
+28	PRJNA468320	SRR7962297	PRJNA467729	SRR7592826	ocean
+32	PRJNA468321	SRR7962267	PRJNA468210	SRR7594064	ocean
+81	PRJNA468145	SRR7610454	PRJNA467762	SRR7609163	ocean
+70	PRJNA468322	SRR7962239	PRJNA467752	SRR7608010	ocean
+67	PRJNA468323	SRR7962329	PRJNA467750	SRR7607757	ocean
+33	PRJNA467783	SRR7610453	PRJNA502417	SRR8361102	ocean
+27	PRJNA468331	SRR7962479	PRJNA468209	SRR7593830	ocean
+34	PRJNA502465	SRR8297868	PRJNA467732	SRR7594085	ocean
+4	PRJNA468146	SRR7610452	PRJNA467723	SRR7592236	ocean
+57	PRJNA468147	SRR7610935	PRJNA502423	SRR8361526	ocean
+1	PRJNA502466	SRR8361608	PRJNA467720	SRR7592212	ocean
+47	PRJNA468148	SRR7610853	PRJNA467740	SRR7600454	ocean
+9	PRJNA502467	SRR8297869	PRJNA502408	SRR8360547	ocean
+77	PRJNA468324	SRR7962474	PRJNA467758	SRR7608832	ocean
+55	PRJNA467784	SRR7610867	PRJNA502422	SRR8361371	ocean
+10	PRJNA468325	SRR7962473	PRJNA502409	SRR8360543	ocean
+11	PRJNA468326	SRR7962475	PRJNA467725	SRR7592321	ocean
+58	PRJNA502468	SRR8297878	PRJNA502424	SRR8361527	ocean
+52	PRJNA468327	SRR7962478	PRJNA467742	SRR7600455	ocean
+51	PRJNA468149	SRR7611057	PRJNA502420	SRR8361350	ocean
+50	PRJNA468328	SRR7962477	PRJNA502419	SRR8361349	ocean
+90	PRJNA467785	SRR7611056	PRJNA467768	SRR7609452	ocean
+80	PRJNA467786	SRR7611058	PRJNA467761	SRR7609166	ocean
+89	PRJNA468150	SRR7611500	PRJNA467766	SRR7609363	ocean
+35	PRJNA467787	SRR7612580	PRJNA502441	SRR8361101	ocean
+71	PRJNA468329	SRR7962476	PRJNA467753	SRR7608017	ocean
+31	PRJNA468151	SRR7611499	PRJNA467731	SRR7593934	ocean
+84	PRJNA502451	SRR8393198	PRJNA467764	SRR7609361	ocean
+61	PRJNA467788	SRR7615219	PRJNA502426	SRR8361516	ocean
+36_r	PRJNA468330	SRR7962481	PRJNA467770	SRR7609462	ocean
+82	PRJNA502452	SRR8361531	PRJNA467763	SRR7609344	ocean
+sample_106	PRJNA603240	SRR10968230	PRJNA603240	SRR10968263	deadwood
+sample_069	PRJNA603240	SRR10968231	PRJNA603240	SRR10968264	deadwood
+sample_055	PRJNA603240	SRR10968232	PRJNA603240	SRR10968265	deadwood
+sample_049	PRJNA603240	SRR10968233	PRJNA603240	SRR10968266	deadwood
+sample_031	PRJNA603240	SRR10968234	PRJNA603240	SRR10968267	deadwood
+sample_116	PRJNA603240	SRR10968236	PRJNA603240	SRR10968225	deadwood
+sample_110	PRJNA603240	SRR10968237	PRJNA603240	SRR10968226	deadwood
+sample_044	PRJNA603240	SRR10968238	PRJNA603240	SRR10968227	deadwood
+sample_007	PRJNA603240	SRR10968239	PRJNA603240	SRR10968228	deadwood
+sample_006	PRJNA603240	SRR10968240	PRJNA603240	SRR10968229	deadwood
+Tag1363-1	PRJNA202380	SRR1138694	PRJNA202380	SRR1267595	sheep_rumen
+Tag1111-1	PRJNA202380	SRR1138697	PRJNA202380	SRR1222429	sheep_rumen
+Tag1111-2	PRJNA202380	SRR1138702	PRJNA202380	SRR1222431	sheep_rumen
+Tag1234-1	PRJNA202380	SRR1206249	PRJNA202380	SRR1206671	sheep_rumen
+Tag1494-1	PRJNA202380	SRR873450	PRJNA202380	SRR873595	sheep_rumen
+Tag1283-1	PRJNA202380	SRR873451	PRJNA202380	SRR873596	sheep_rumen
+Tag1435-1	PRJNA202380	SRR873452	PRJNA202380	SRR873597	sheep_rumen
+Tag1494-2	PRJNA202380	SRR873453	PRJNA202380	SRR873598	sheep_rumen
+Tag1265-1	PRJNA202380	SRR873454	PRJNA202380	SRR873599	sheep_rumen
+Tag1435-2	PRJNA202380	SRR873455	PRJNA202380	SRR873600	sheep_rumen
+Tag1283-2	PRJNA202380	SRR873456	PRJNA202380	SRR873601	sheep_rumen
+Tag1265-2	PRJNA202380	SRR873457	PRJNA202380	SRR873602	sheep_rumen
+Tag1363-2	PRJNA202380	SRR873458	PRJNA202380	SRR873603	sheep_rumen
+Tag1174-1	PRJNA202380	SRR873459	PRJNA202380	SRR873604	sheep_rumen
+Tag1234-2	PRJNA202380	SRR873460	PRJNA202380	SRR873605	sheep_rumen
+Tag1586-1	PRJNA202380	SRR873461	PRJNA202380	SRR873606	sheep_rumen
+Tag1586-2	PRJNA202380	SRR873462	PRJNA202380	SRR873607	sheep_rumen
+Tag1333-1	PRJNA202380	SRR873463	PRJNA202380	SRR873608	sheep_rumen
+Tag1174-2	PRJNA202380	SRR873464	PRJNA202380	SRR873609	sheep_rumen
+Tag1333-2	PRJNA202380	SRR873465	PRJNA202380	SRR873610	sheep_rumen
+Ahn.Mel47	PRJNA541981	SRR9118109	PRJNA541981	SRR9033724	human_skin
+Ahn.Mel44	PRJNA541981	SRR9118110	PRJNA541981	SRR9033723	human_skin
+Ahn.Mel46	PRJNA541981	SRR9118111	PRJNA541981	SRR9033725	human_skin
+Ahn.Mel42	PRJNA541981	SRR9118112	PRJNA541981	SRR9033716	human_skin
+Ahn.Mel43	PRJNA541981	SRR9118113	PRJNA541981	SRR9033715	human_skin
+Ahn.Mel37	PRJNA541981	SRR9118114	PRJNA541981	SRR9033753	human_skin
+Ahn.Mel38	PRJNA541981	SRR9118115	PRJNA541981	SRR9033754	human_skin
+Ahn.Mel34	PRJNA541981	SRR9118116	PRJNA541981	SRR9033749	human_skin
+Ahn.Mel35	PRJNA541981	SRR9118117	PRJNA541981	SRR9033750	human_skin
+Ahn.Mel28	PRJNA541981	SRR9118118	PRJNA541981	SRR9033748	human_skin
+Ahn.Mel32	PRJNA541981	SRR9118119	PRJNA541981	SRR9033752	human_skin
+Ahn.Mel19	PRJNA541981	SRR9118120	PRJNA541981	SRR9033727	human_skin
+Ahn.Mel26	PRJNA541981	SRR9118121	PRJNA541981	SRR9033720	human_skin
+Ahn.Mel10	PRJNA541981	SRR9118122	PRJNA541981	SRR9033737	human_skin
+Ahn.Mel13	PRJNA541981	SRR9118123	PRJNA541981	SRR9033742	human_skin
+Ahn.Mel01	PRJNA541981	SRR9118124	PRJNA541981	SRR9033738	human_skin
+Ahn.Mel04	PRJNA541981	SRR9118125	PRJNA541981	SRR9033719	human_skin
+UAB088_W2D1	PRJNA797778	SRR17858151	PRJNA797778	SRR17635672	human_vagina
+UAB082_W10D2	PRJNA797778	SRR17858152	PRJNA797778	SRR17635674	human_vagina
+UAB082_W5D7	PRJNA797778	SRR17858153	PRJNA797778	SRR17635676	human_vagina
+UAB082_W3D7	PRJNA797778	SRR17858154	PRJNA797778	SRR17635677	human_vagina
+UAB082_W2D5	PRJNA797778	SRR17858155	PRJNA797778	SRR17635678	human_vagina
+UAB079_W10D1	PRJNA797778	SRR17858156	PRJNA797778	SRR17635679	human_vagina
+UAB079_W7D6	PRJNA797778	SRR17858157	PRJNA797778	SRR17635680	human_vagina
+UAB079_W6D7	PRJNA797778	SRR17858158	PRJNA797778	SRR17635681	human_vagina
+UAB079_W3D7	PRJNA797778	SRR17858159	PRJNA797778	SRR17635682	human_vagina
+UAB079_W2D2	PRJNA797778	SRR17858160	PRJNA797778	SRR17635683	human_vagina
+UAB006_W2D2	PRJNA797778	SRR17858161	PRJNA797778	SRR17635801	human_vagina
+UAB077_W9D7	PRJNA797778	SRR17858162	PRJNA797778	SRR17635685	human_vagina
+UAB077_W8D2	PRJNA797778	SRR17858163	PRJNA797778	SRR17635686	human_vagina
+UAB077_W5D7	PRJNA797778	SRR17858164	PRJNA797778	SRR17635687	human_vagina
+UAB077_W3D1	PRJNA797778	SRR17858165	PRJNA797778	SRR17635688	human_vagina
+UAB077_W1D7	PRJNA797778	SRR17858166	PRJNA797778	SRR17635689	human_vagina
+UAB071_W10D2	PRJNA797778	SRR17858167	PRJNA797778	SRR17635690	human_vagina
+UAB071_W7D7	PRJNA797778	SRR17858168	PRJNA797778	SRR17635691	human_vagina
+UAB071_W5D7	PRJNA797778	SRR17858169	PRJNA797778	SRR17635692	human_vagina
+UAB071_W3D7	PRJNA797778	SRR17858170	PRJNA797778	SRR17635693	human_vagina
+UAB071_W1D7	PRJNA797778	SRR17858171	PRJNA797778	SRR17635694	human_vagina
+UAB002_W5D7	PRJNA797778	SRR17858172	PRJNA797778	SRR17635804	human_vagina
+AYAC02_W9D3	PRJNA797778	SRR17858173	PRJNA797778	SRR17635818	human_vagina
+UAB060_W10D2	PRJNA797778	SRR17858174	PRJNA797778	SRR17635696	human_vagina
+UAB060_W7D7	PRJNA797778	SRR17858175	PRJNA797778	SRR17635697	human_vagina
+UAB060_W5D7	PRJNA797778	SRR17858176	PRJNA797778	SRR17635698	human_vagina
+UAB060_W3D7	PRJNA797778	SRR17858177	PRJNA797778	SRR17635763	human_vagina
+UAB060_W1D6	PRJNA797778	SRR17858178	PRJNA797778	SRR17635764	human_vagina
+UAB052_W10D2	PRJNA797778	SRR17858179	PRJNA797778	SRR17635765	human_vagina
+UAB052_W8D3	PRJNA797778	SRR17858180	PRJNA797778	SRR17635766	human_vagina
+UAB052_W5D7	PRJNA797778	SRR17858181	PRJNA797778	SRR17635767	human_vagina
+UAB052_W4D2	PRJNA797778	SRR17858182	PRJNA797778	SRR17635768	human_vagina
+UAB002_W1D4	PRJNA797778	SRR17858183	PRJNA797778	SRR17635806	human_vagina
+UAB052_W1D5	PRJNA797778	SRR17858184	PRJNA797778	SRR17635769	human_vagina
+UAB048_W9D7	PRJNA797778	SRR17858185	PRJNA797778	SRR17635771	human_vagina
+UAB048_W7D7	PRJNA797778	SRR17858186	PRJNA797778	SRR17635772	human_vagina
+UAB048_W5D2	PRJNA797778	SRR17858187	PRJNA797778	SRR17635773	human_vagina
+UAB048_W3D7	PRJNA797778	SRR17858188	PRJNA797778	SRR17635774	human_vagina
+UAB048_W1D7	PRJNA797778	SRR17858189	PRJNA797778	SRR17635775	human_vagina
+UAB044_W9D7	PRJNA797778	SRR17858190	PRJNA797778	SRR17635776	human_vagina
+UAB044_W7D7	PRJNA797778	SRR17858191	PRJNA797778	SRR17635777	human_vagina
+UAB044_W5D7	PRJNA797778	SRR17858192	PRJNA797778	SRR17635778	human_vagina
+UAB044_W3D7	PRJNA797778	SRR17858193	PRJNA797778	SRR17635779	human_vagina
+AYAC09_W5D7	PRJNA797778	SRR17858194	PRJNA797778	SRR17635747	human_vagina
+UAB044_W1D7	PRJNA797778	SRR17858195	PRJNA797778	SRR17635780	human_vagina
+UAB028_W9D7	PRJNA797778	SRR17858196	PRJNA797778	SRR17635598	human_vagina
+UAB028_W7D7	PRJNA797778	SRR17858197	PRJNA797778	SRR17635599	human_vagina
+UAB022_W10D1	PRJNA797778	SRR17858198	PRJNA797778	SRR17635466	human_vagina
+UAB022_W6D1	PRJNA797778	SRR17858199	PRJNA797778	SRR17635468	human_vagina
+UAB021_W8D3	PRJNA797778	SRR17858200	PRJNA797778	SRR17635471	human_vagina
+UAB021_W5D7	PRJNA797778	SRR17858201	PRJNA797778	SRR17635472	human_vagina
+UAB015_W10D7	PRJNA797778	SRR17858202	PRJNA797778	SRR17635475	human_vagina
+UAB015_W9D4	PRJNA797778	SRR17858203	PRJNA797778	SRR17635477	human_vagina
+UAB011_W9D7	PRJNA797778	SRR17858204	PRJNA797778	SRR17635481	human_vagina
+AYAC03_W4D7	PRJNA797778	SRR17858205	PRJNA797778	SRR17635796	human_vagina
+UAB011_W7D7	PRJNA797778	SRR17858206	PRJNA797778	SRR17635482	human_vagina
+UAB011_W7D1	PRJNA797778	SRR17858207	PRJNA797778	SRR17635483	human_vagina
+UAB039_W9D7	PRJNA797778	SRR17858208	PRJNA797778	SRR17635782	human_vagina
+UAB039_W7D7	PRJNA797778	SRR17858209	PRJNA797778	SRR17635783	human_vagina
+UAB039_W5D7	PRJNA797778	SRR17858210	PRJNA797778	SRR17635784	human_vagina
+UAB039_W3D6	PRJNA797778	SRR17858211	PRJNA797778	SRR17635785	human_vagina
+UAB039_W1D7	PRJNA797778	SRR17858212	PRJNA797778	SRR17635786	human_vagina
+UAB038_W9D7	PRJNA797778	SRR17858213	PRJNA797778	SRR17635787	human_vagina
+UAB038_W7D4	PRJNA797778	SRR17858214	PRJNA797778	SRR17635788	human_vagina
+UAB038_W5D7	PRJNA797778	SRR17858215	PRJNA797778	SRR17635789	human_vagina
+AYAC03_W1D7	PRJNA797778	SRR17858216	PRJNA797778	SRR17635807	human_vagina
+UAB038_W3D7	PRJNA797778	SRR17858217	PRJNA797778	SRR17635790	human_vagina
+UAB038_W2D2	PRJNA797778	SRR17858218	PRJNA797778	SRR17635791	human_vagina
+UAB035_W9D7	PRJNA797778	SRR17858219	PRJNA797778	SRR17635593	human_vagina
+UAB035_W7D4	PRJNA797778	SRR17858220	PRJNA797778	SRR17635594	human_vagina
+UAB035_W5D7	PRJNA797778	SRR17858221	PRJNA797778	SRR17635595	human_vagina
+UAB035_W3D6	PRJNA797778	SRR17858222	PRJNA797778	SRR17635596	human_vagina
+UAB035_W2D7	PRJNA797778	SRR17858223	PRJNA797778	SRR17635597	human_vagina
+AYAC03_W7D5	PRJNA797778	SRR17858224	PRJNA797778	SRR17635487	human_vagina
+AYAC02_W7D5	PRJNA797778	SRR17858225	PRJNA797778	SRR17635635	human_vagina
+UAB010_W7D5	PRJNA797778	SRR17858226	PRJNA797778	SRR17635489	human_vagina
+AYAC02_W5D6	PRJNA797778	SRR17858227	PRJNA797778	SRR17635576	human_vagina
+UAB007_W9D7	PRJNA797778	SRR17858228	PRJNA797778	SRR17635493	human_vagina
+UAB007_W7D7	PRJNA797778	SRR17858229	PRJNA797778	SRR17635494	human_vagina
+UAB007_W6D3	PRJNA797778	SRR17858230	PRJNA797778	SRR17635495	human_vagina
+UAB006_W9D7	PRJNA797778	SRR17858231	PRJNA797778	SRR17635797	human_vagina
+UAB006_W7D7	PRJNA797778	SRR17858232	PRJNA797778	SRR17635798	human_vagina
+UAB002_W9D7	PRJNA797778	SRR17858233	PRJNA797778	SRR17635802	human_vagina
+UAB002_W7D7	PRJNA797778	SRR17858234	PRJNA797778	SRR17635803	human_vagina
+UAB028_W5D5	PRJNA797778	SRR17858235	PRJNA797778	SRR17635600	human_vagina
+UAB028_W3D7	PRJNA797778	SRR17858236	PRJNA797778	SRR17635601	human_vagina
+UAB028_W1D7	PRJNA797778	SRR17858237	PRJNA797778	SRR17635602	human_vagina
+AYAC02_W3D1	PRJNA797778	SRR17858238	PRJNA797778	SRR17635793	human_vagina
+UAB022_W4D1	PRJNA797778	SRR17858239	PRJNA797778	SRR17635469	human_vagina
+UAB022_W2D1	PRJNA797778	SRR17858240	PRJNA797778	SRR17635470	human_vagina
+AYAC10_W9D5	PRJNA797778	SRR17858241	PRJNA797778	SRR17635531	human_vagina
+AYAC10_W8D1	PRJNA797778	SRR17858242	PRJNA797778	SRR17635542	human_vagina
+AYAC10_W5D4	PRJNA797778	SRR17858243	PRJNA797778	SRR17635553	human_vagina
+AYAC10_W2D7	PRJNA797778	SRR17858244	PRJNA797778	SRR17635564	human_vagina
+AYAC10_W1D7	PRJNA797778	SRR17858245	PRJNA797778	SRR17635575	human_vagina
+AYAC09_W9D7	PRJNA797778	SRR17858246	PRJNA797778	SRR17635587	human_vagina
+AYAC09_W7D4	PRJNA797778	SRR17858247	PRJNA797778	SRR17635736	human_vagina
+EM11_W9D7	PRJNA797778	SRR17858248	PRJNA797778	SRR17635808	human_vagina
+EM11_W7D7	PRJNA797778	SRR17858249	PRJNA797778	SRR17635809	human_vagina
+EM11_W5D7	PRJNA797778	SRR17858250	PRJNA797778	SRR17635810	human_vagina
+UAB021_W3D7	PRJNA797778	SRR17858251	PRJNA797778	SRR17635473	human_vagina
+EM11_W3D6	PRJNA797778	SRR17858252	PRJNA797778	SRR17635811	human_vagina
+EM11_W1D7	PRJNA797778	SRR17858253	PRJNA797778	SRR17635812	human_vagina
+EM10_W8D7	PRJNA797778	SRR17858254	PRJNA797778	SRR17635813	human_vagina
+EM10_W6D5	PRJNA797778	SRR17858255	PRJNA797778	SRR17635814	human_vagina
+EM10_W4D7	PRJNA797778	SRR17858256	PRJNA797778	SRR17635815	human_vagina
+EM10_W3D2	PRJNA797778	SRR17858257	PRJNA797778	SRR17635816	human_vagina
+EM10_W1D7	PRJNA797778	SRR17858258	PRJNA797778	SRR17635817	human_vagina
+EM09_W9D6	PRJNA797778	SRR17858259	PRJNA797778	SRR17635819	human_vagina
+EM09_W8D5	PRJNA797778	SRR17858260	PRJNA797778	SRR17635820	human_vagina
+EM09_W6D7	PRJNA797778	SRR17858261	PRJNA797778	SRR17635459	human_vagina
+UAB015_W3D1	PRJNA797778	SRR17858262	PRJNA797778	SRR17635479	human_vagina
+AYAC05_W9D7	PRJNA797778	SRR17858263	PRJNA797778	SRR17635684	human_vagina
+AYAC05_W7D7	PRJNA797778	SRR17858264	PRJNA797778	SRR17635695	human_vagina
+AYAC03_W9D7	PRJNA797778	SRR17858265	PRJNA797778	SRR17635465	human_vagina
+AYAC03_W8D6	PRJNA797778	SRR17858266	PRJNA797778	SRR17635476	human_vagina
+AYAC09_W3D4	PRJNA797778	SRR17858267	PRJNA797778	SRR17635758	human_vagina
+AYAC09_W1D7	PRJNA797778	SRR17858268	PRJNA797778	SRR17635673	human_vagina
+AYAC05_W5D5	PRJNA797778	SRR17858269	PRJNA797778	SRR17635770	human_vagina
+AYAC05_W3D7	PRJNA797778	SRR17858270	PRJNA797778	SRR17635781	human_vagina
+AYAC05_W1D6	PRJNA797778	SRR17858271	PRJNA797778	SRR17635792	human_vagina
+EM09_W4D4	PRJNA797778	SRR17858272	PRJNA797778	SRR17635462	human_vagina
+UAB015_W1D5	PRJNA797778	SRR17858273	PRJNA797778	SRR17635480	human_vagina
+EM09_W2D3	PRJNA797778	SRR17858274	PRJNA797778	SRR17635611	human_vagina
+EM04_W1D7	PRJNA797778	SRR17858275	PRJNA797778	SRR17635722	human_vagina
+UAB129_W10D2	PRJNA797778	SRR17858276	PRJNA797778	SRR17635577	human_vagina
+UAB129_W7D7	PRJNA797778	SRR17858277	PRJNA797778	SRR17635578	human_vagina
+UAB129_W5D7	PRJNA797778	SRR17858278	PRJNA797778	SRR17635579	human_vagina
+UAB129_W3D3	PRJNA797778	SRR17858279	PRJNA797778	SRR17635580	human_vagina
+UAB129_W1D7	PRJNA797778	SRR17858280	PRJNA797778	SRR17635581	human_vagina
+UAB122_W9D6	PRJNA797778	SRR17858281	PRJNA797778	SRR17635582	human_vagina
+UAB122_W6D5	PRJNA797778	SRR17858282	PRJNA797778	SRR17635583	human_vagina
+UAB122_W4D7	PRJNA797778	SRR17858283	PRJNA797778	SRR17635584	human_vagina
+UAB011_W3D6	PRJNA797778	SRR17858284	PRJNA797778	SRR17635484	human_vagina
+UAB122_W3D4	PRJNA797778	SRR17858285	PRJNA797778	SRR17635585	human_vagina
+UAB122_W1D7	PRJNA797778	SRR17858286	PRJNA797778	SRR17635586	human_vagina
+UAB119_W9D7	PRJNA797778	SRR17858287	PRJNA797778	SRR17635588	human_vagina
+UAB119_W7D7	PRJNA797778	SRR17858288	PRJNA797778	SRR17635589	human_vagina
+UAB119_W5D7	PRJNA797778	SRR17858289	PRJNA797778	SRR17635590	human_vagina
+UAB119_W3D7	PRJNA797778	SRR17858290	PRJNA797778	SRR17635591	human_vagina
+UAB119_W1D7	PRJNA797778	SRR17858291	PRJNA797778	SRR17635592	human_vagina
+UAB117_W9D6	PRJNA797778	SRR17858292	PRJNA797778	SRR17635731	human_vagina
+UAB117_W8D1	PRJNA797778	SRR17858293	PRJNA797778	SRR17635732	human_vagina
+UAB117_W5D6	PRJNA797778	SRR17858294	PRJNA797778	SRR17635733	human_vagina
+UAB011_W1D7	PRJNA797778	SRR17858295	PRJNA797778	SRR17635485	human_vagina
+UAB117_W3D6	PRJNA797778	SRR17858296	PRJNA797778	SRR17635734	human_vagina
+UAB117_W1D6	PRJNA797778	SRR17858297	PRJNA797778	SRR17635735	human_vagina
+UAB116_W9D6	PRJNA797778	SRR17858298	PRJNA797778	SRR17635737	human_vagina
+UAB116_W6D7	PRJNA797778	SRR17858299	PRJNA797778	SRR17635738	human_vagina
+UAB116_W4D6	PRJNA797778	SRR17858300	PRJNA797778	SRR17635739	human_vagina
+UAB116_W1D7	PRJNA797778	SRR17858301	PRJNA797778	SRR17635741	human_vagina
+UAB110_W10D4	PRJNA797778	SRR17858302	PRJNA797778	SRR17635742	human_vagina
+UAB110_W7D7	PRJNA797778	SRR17858303	PRJNA797778	SRR17635743	human_vagina
+UAB110_W6D2	PRJNA797778	SRR17858304	PRJNA797778	SRR17635744	human_vagina
+UAB110_W3D7	PRJNA797778	SRR17858305	PRJNA797778	SRR17635745	human_vagina
+UAB010_W5D6	PRJNA797778	SRR17858306	PRJNA797778	SRR17635490	human_vagina
+UAB110_W1D7	PRJNA797778	SRR17858307	PRJNA797778	SRR17635746	human_vagina
+UAB106_W9D7	PRJNA797778	SRR17858308	PRJNA797778	SRR17635748	human_vagina
+UAB106_W7D7	PRJNA797778	SRR17858309	PRJNA797778	SRR17635749	human_vagina
+UAB106_W5D4	PRJNA797778	SRR17858310	PRJNA797778	SRR17635750	human_vagina
+UAB106_W3D7	PRJNA797778	SRR17858311	PRJNA797778	SRR17635751	human_vagina
+UAB106_W1D7	PRJNA797778	SRR17858312	PRJNA797778	SRR17635752	human_vagina
+UAB096_W9D7	PRJNA797778	SRR17858313	PRJNA797778	SRR17635753	human_vagina
+UAB096_W7D3	PRJNA797778	SRR17858314	PRJNA797778	SRR17635754	human_vagina
+UAB096_W5D3	PRJNA797778	SRR17858315	PRJNA797778	SRR17635755	human_vagina
+UAB096_W3D3	PRJNA797778	SRR17858316	PRJNA797778	SRR17635756	human_vagina
+UAB010_W3D1	PRJNA797778	SRR17858317	PRJNA797778	SRR17635491	human_vagina
+UAB096_W1D5	PRJNA797778	SRR17858318	PRJNA797778	SRR17635757	human_vagina
+UAB093_W9D6	PRJNA797778	SRR17858319	PRJNA797778	SRR17635759	human_vagina
+UAB093_W7D7	PRJNA797778	SRR17858320	PRJNA797778	SRR17635760	human_vagina
+UAB093_W5D7	PRJNA797778	SRR17858321	PRJNA797778	SRR17635761	human_vagina
+UAB093_W4D2	PRJNA797778	SRR17858322	PRJNA797778	SRR17635762	human_vagina
+UAB093_W1D7	PRJNA797778	SRR17858323	PRJNA797778	SRR17635667	human_vagina
+UAB088_W10D1	PRJNA797778	SRR17858324	PRJNA797778	SRR17635668	human_vagina
+UAB088_W7D6	PRJNA797778	SRR17858325	PRJNA797778	SRR17635669	human_vagina
+UAB088_W6D1	PRJNA797778	SRR17858326	PRJNA797778	SRR17635670	human_vagina
+UAB088_W4D1	PRJNA797778	SRR17858327	PRJNA797778	SRR17635671	human_vagina
+UAB007_W1D7	PRJNA797778	SRR17858328	PRJNA797778	SRR17635795	human_vagina
+AYAC02_W1D7	PRJNA797778	SRR17858329	PRJNA797778	SRR17635794	human_vagina
+EM04_W3D7	PRJNA797778	SRR17858330	PRJNA797778	SRR17635711	human_vagina
+MV_FEI4_t2Q15	PRJNA339914	SRR4100706	PRJNA339914	SRR4052039	human_gut
+MV_FEI5_t3Q15	PRJNA339914	SRR4100707	PRJNA339914	SRR4052042	human_gut
+MV_FEM4_t2Q15	PRJNA339914	SRR4100708	PRJNA339914	SRR4052025	human_gut
+MV_FEM5_t3Q15	PRJNA339914	SRR4100709	PRJNA339914	SRR4052028	human_gut
+M1	PRJEB33889	ERR3473664	PRJEB33889	ERR3473656	mouse_cecum
+M2	PRJEB33889	ERR3473665	PRJEB33889	ERR3473657	mouse_cecum
+M3	PRJEB33889	ERR3473666	PRJEB33889	ERR3473658	mouse_cecum
+M4	PRJEB33889	ERR3473667	PRJEB33889	ERR3473659	mouse_cecum
+M5	PRJEB33889	ERR3473668	PRJEB33889	ERR3473660	mouse_cecum
+M6	PRJEB33889	ERR3473669	PRJEB33889	ERR3473661	mouse_cecum
+M7	PRJEB33889	ERR3473670	PRJEB33889	ERR3473662	mouse_cecum
+M8	PRJEB33889	ERR3473671	PRJEB33889	ERR3473663	mouse_cecum
+ad_supplemented_with_nitrogen_data_2	PRJNA698464	SRR13618127	PRJNA698464	SRR13618123	bioreactor
+ad_supplemented_with_nitrogen_data_1	PRJNA698464	SRR13618128	PRJNA698464	SRR13618124	bioreactor
+ad_supplemented_with_hydrogen_data_2	PRJNA698464	SRR13618129	PRJNA698464	SRR13618125	bioreactor
+ad_supplemented_with_hydrogen_data_1	PRJNA698464	SRR13618130	PRJNA698464	SRR13618126	bioreactor
+X4074	PRJNA396840	SRR5892181	PRJNA396840	SRR5892217	human_oral
+X4080	PRJNA396840	SRR5892182	PRJNA396840	SRR5892216	human_oral
+X4068	PRJNA396840	SRR5892183	PRJNA396840	SRR5892215	human_oral
+X4072	PRJNA396840	SRR5892184	PRJNA396840	SRR5892214	human_oral
+X4060	PRJNA396840	SRR5892185	PRJNA396840	SRR5892213	human_oral
+X4064	PRJNA396840	SRR5892186	PRJNA396840	SRR5892212	human_oral
+X4050	PRJNA396840	SRR5892187	PRJNA396840	SRR5892211	human_oral
+X4056	PRJNA396840	SRR5892188	PRJNA396840	SRR5892210	human_oral
+X4108	PRJNA396840	SRR5892189	PRJNA396840	SRR5892233	human_oral
+X4082	PRJNA396840	SRR5892190	PRJNA396840	SRR5892209	human_oral
+X4088	PRJNA396840	SRR5892191	PRJNA396840	SRR5892208	human_oral
+X4124	PRJNA396840	SRR5892192	PRJNA396840	SRR5892236	human_oral
+X4120	PRJNA396840	SRR5892195	PRJNA396840	SRR5892235	human_oral
+X4096	PRJNA396840	SRR5892200	PRJNA396840	SRR5892238	human_oral
+X4092	PRJNA396840	SRR5892204	PRJNA396840	SRR5892237	human_oral
+X4104	PRJNA396840	SRR5892205	PRJNA396840	SRR5892240	human_oral
+X4100	PRJNA396840	SRR5892207	PRJNA396840	SRR5892239	human_oral
+X4024	PRJNA396840	SRR5892218	PRJNA396840	SRR5892196	human_oral
+X4020	PRJNA396840	SRR5892219	PRJNA396840	SRR5892197	human_oral
+X4014	PRJNA396840	SRR5892220	PRJNA396840	SRR5892198	human_oral
+X4012	PRJNA396840	SRR5892221	PRJNA396840	SRR5892199	human_oral
+X4040	PRJNA396840	SRR5892222	PRJNA396840	SRR5892206	human_oral
+X4036	PRJNA396840	SRR5892223	PRJNA396840	SRR5892201	human_oral
+X4032	PRJNA396840	SRR5892224	PRJNA396840	SRR5892202	human_oral
+X4028	PRJNA396840	SRR5892225	PRJNA396840	SRR5892203	human_oral
+X4048	PRJNA396840	SRR5892226	PRJNA396840	SRR5892193	human_oral
+X4044	PRJNA396840	SRR5892227	PRJNA396840	SRR5892194	human_oral
+X4132	PRJNA396840	SRR5892228	PRJNA396840	SRR5892232	human_oral
+X4128	PRJNA396840	SRR5892229	PRJNA396840	SRR5892231	human_oral
+X4116	PRJNA396840	SRR5892230	PRJNA396840	SRR5892234	human_oral
+L2	PRJNA492158	SRR7880350	PRJNA492158	SRR7880198	human_gut
+L3	PRJNA492158	SRR7880351	PRJNA492158	SRR7880201	human_gut
+L5	PRJNA492158	SRR7880352	PRJNA492158	SRR7880203	human_gut
+L6	PRJNA492158	SRR7880353	PRJNA492158	SRR7880202	human_gut
+L7	PRJNA492158	SRR7880354	PRJNA492158	SRR7880205	human_gut
+L8	PRJNA492158	SRR7880355	PRJNA492158	SRR7880204	human_gut
+L9	PRJNA492158	SRR7880356	PRJNA492158	SRR7880207	human_gut
+L11	PRJNA492158	SRR7880357	PRJNA492158	SRR7880227	human_gut
+L12	PRJNA492158	SRR7880358	PRJNA492158	SRR7880226	human_gut
+O1	PRJNA492158	SRR7880359	PRJNA492158	SRR7880225	human_gut
+V6	PRJNA492158	SRR7880360	PRJNA492158	SRR7880217	human_gut
+V5	PRJNA492158	SRR7880361	PRJNA492158	SRR7880216	human_gut
+V8	PRJNA492158	SRR7880362	PRJNA492158	SRR7880218	human_gut
+V7	PRJNA492158	SRR7880363	PRJNA492158	SRR7880219	human_gut
+V11	PRJNA492158	SRR7880364	PRJNA492158	SRR7880223	human_gut
+V9	PRJNA492158	SRR7880365	PRJNA492158	SRR7880197	human_gut
+O6	PRJNA492158	SRR7880366	PRJNA492158	SRR7880228	human_gut
+O8	PRJNA492158	SRR7880367	PRJNA492158	SRR7880220	human_gut
+O9	PRJNA492158	SRR7880368	PRJNA492158	SRR7880210	human_gut
+O10	PRJNA492158	SRR7880369	PRJNA492158	SRR7880211	human_gut
+O2	PRJNA492158	SRR7880370	PRJNA492158	SRR7880224	human_gut
+O3	PRJNA492158	SRR7880371	PRJNA492158	SRR7880231	human_gut
+O4	PRJNA492158	SRR7880372	PRJNA492158	SRR7880230	human_gut
+O5	PRJNA492158	SRR7880373	PRJNA492158	SRR7880229	human_gut
+O11	PRJNA492158	SRR7880374	PRJNA492158	SRR7880208	human_gut
+O12	PRJNA492158	SRR7880375	PRJNA492158	SRR7880209	human_gut
+3m_Station6_GOM	PRJNA278075	SRR1918203	PRJNA278075	SRR2001210	ocean
+CRF2_7	PRJEB38017	ERR4077213	PRJEB38017	ERR4073751	cocoa_box_fermentation
+CRF2_20	PRJEB38017	ERR4077214	PRJEB38017	ERR4073752	cocoa_box_fermentation
+CRF2_68	PRJEB38017	ERR4077215	PRJEB38017	ERR4073754	cocoa_box_fermentation
+HP_AsLow	PRJNA616041	SRR11450577	PRJNA616041	SRR11450583	paddy_soil
+SKS_AsHig	PRJNA616041	SRR11450578	PRJNA616041	SRR11450584	paddy_soil
+CZ_AsHig	PRJNA616041	SRR11450579	PRJNA616041	SRR11450587	paddy_soil
+CL_AsHig	PRJNA616041	SRR11450580	PRJNA616041	SRR11450588	paddy_soil
+YCP_AsLow	PRJNA616041	SRR11450585	PRJNA616041	SRR11450581	paddy_soil
+LH_AsLow	PRJNA616041	SRR11450586	PRJNA616041	SRR11450582	paddy_soil
+GZ-C-35-D5	PRJNA395125	SRR5868086	PRJNA393770	SRR5892338	bioreactor
+GZ-C-35-Mid	PRJNA395125	SRR5868087	PRJNA393770	SRR5892352	bioreactor
+SWH-C-35-D5	PRJNA395125	SRR5868115	PRJNA393770	SRR5894891	bioreactor
+SWH-C-35-Mid	PRJNA395125	SRR5868116	PRJNA393770	SRR5894892	bioreactor
+GZ-X-35-Mid	PRJNA395125	SRR5868138	PRJNA393770	SRR5894899	bioreactor
+SWH-X-35-Mid	PRJNA395125	SRR5868139	PRJNA393770	SRR5894900	bioreactor
+SWH-C-55-Mid	PRJNA395125	SRR5868141	PRJNA393770	SRR5894893	bioreactor
+AH1	PRJEB12284	ERR1198915	PRJEB12083	ERR1191817	wastewater
+AH4	PRJEB12284	ERR1198916	PRJEB12083	ERR1191820	wastewater
+AH5	PRJEB12284	ERR1198917	PRJEB12083	ERR1191821	wastewater
+AH6	PRJEB12284	ERR1198918	PRJEB12083	ERR1191822	wastewater
+DF1	PRJEB12284	ERR1198919	PRJEB12083	ERR1193331	wastewater
+DF4	PRJEB12284	ERR1198920	PRJEB12083	ERR1193299	wastewater
+DF5	PRJEB12284	ERR1198921	PRJEB12083	ERR1193300	wastewater
+DF6	PRJEB12284	ERR1198922	PRJEB12083	ERR1193301	wastewater
+BazoSym_LS-ET_5	PRJEB32788	ERR3342479	PRJEB32787	ERR3342499	mussel_gill
+BazoSym_LS-ET_4	PRJEB32788	ERR3342480	PRJEB32787	ERR3342500	mussel_gill
+BazoSym_LS-MS_3	PRJEB32788	ERR3342481	PRJEB32787	ERR3342501	mussel_gill
+BazoSym_LS-MS_2	PRJEB32788	ERR3342482	PRJEB32787	ERR3342502	mussel_gill
+BazoSym_LS-MS_1	PRJEB32788	ERR3342483	PRJEB32787	ERR3342503	mussel_gill
+BspSym_Li_5	PRJEB32788	ERR3342467	PRJEB32787	ERR3342486	mussel_gill
+BspSym_Li_4	PRJEB32788	ERR3342468	PRJEB32787	ERR3342487	mussel_gill
+BspSym_Li_3	PRJEB32788	ERR3342469	PRJEB32787	ERR3342488	mussel_gill
+BspSym_Li_2	PRJEB32788	ERR3342470	PRJEB32787	ERR3342489	mussel_gill
+BspSym_Li_1	PRJEB32788	ERR3342471	PRJEB32787	ERR3342490	mussel_gill
+BspSym_Cl_4	PRJEB32788	ERR3342472	PRJEB32787	ERR3342492	mussel_gill
+BspSym_Cl_3	PRJEB32788	ERR3342473	PRJEB32787	ERR3342493	mussel_gill
+BspSym_Cl_2	PRJEB32788	ERR3342474	PRJEB32787	ERR3342494	mussel_gill
+BspSym_Cl_1	PRJEB32788	ERR3342475	PRJEB32787	ERR3342495	mussel_gill
+BputSym_Se-AL_3	PRJEB32788	ERR3342476	PRJEB32787	ERR3342496	mussel_gill
+BputSym_Se-AL_2	PRJEB32788	ERR3342477	PRJEB32787	ERR3342497	mussel_gill
+BputSym_Se-AL_1	PRJEB32788	ERR3342478	PRJEB32787	ERR3342498	mussel_gill
+CSM67UC6	PRJNA398089	SRR5949109	PRJNA398089	SRR5936217	human_gut
+CSM67UDY	PRJNA398089	SRR5949110	PRJNA398089	SRR5936216	human_gut
+HSM67VI9	PRJNA398089	SRR5949111	PRJNA398089	SRR5936212	human_gut
+HSM6XRTQ	PRJNA398089	SRR5949112	PRJNA398089	SRR5936211	human_gut
+CSM79HHM	PRJNA398089	SRR5949113	PRJNA398089	SRR5946811	human_gut
+CSM79HIR	PRJNA398089	SRR5949114	PRJNA398089	SRR5936215	human_gut
+CSM79HJO	PRJNA398089	SRR5949115	PRJNA398089	SRR5947089	human_gut
+HSM67VEI	PRJNA398089	SRR5949116	PRJNA398089	SRR5936210	human_gut
+MSM79H9K	PRJNA398089	SRR5949117	PRJNA398089	SRR5935975	human_gut
+MSM79HAH	PRJNA398089	SRR5949118	PRJNA398089	SRR5935976	human_gut
+HSM7J4L5	PRJNA398089	SRR5949119	PRJNA398089	SRR5935953	human_gut
+MSM79H7E	PRJNA398089	SRR5949120	PRJNA398089	SRR5935950	human_gut
+PSM7J17Z	PRJNA398089	SRR5949121	PRJNA398089	SRR5935951	human_gut
+PSM7J18G	PRJNA398089	SRR5949122	PRJNA398089	SRR5935952	human_gut
+MSM79HDI	PRJNA398089	SRR5949123	PRJNA398089	SRR5935954	human_gut
+HSM7J4JH	PRJNA398089	SRR5949124	PRJNA398089	SRR5935955	human_gut
+HSM7J4HU	PRJNA398089	SRR5949125	PRJNA398089	SRR5935956	human_gut
+PSM7J1CI	PRJNA398089	SRR5949126	PRJNA398089	SRR5935957	human_gut
+HSM7CZ36	PRJNA398089	SRR5949127	PRJNA398089	SRR5936016	human_gut
+CSM7KOJW	PRJNA398089	SRR5949128	PRJNA398089	SRR5947102	human_gut
+MSM79HDM	PRJNA398089	SRR5949129	PRJNA398089	SRR5936018	human_gut
+PSM6XBTP	PRJNA398089	SRR5949130	PRJNA398089	SRR5936066	human_gut
+MSM79HF9	PRJNA398089	SRR5949131	PRJNA398089	SRR5936064	human_gut
+CSM79HQF	PRJNA398089	SRR5949132	PRJNA398089	SRR5936119	human_gut
+MSM79H9A	PRJNA398089	SRR5949133	PRJNA398089	SRR5936118	human_gut
+HSM7CZ3E	PRJNA398089	SRR5949134	PRJNA398089	SRR5936121	human_gut
+CSM79HP4	PRJNA398089	SRR5949135	PRJNA398089	SRR5946645	human_gut
+HSM7CYY7	PRJNA398089	SRR5949136	PRJNA398089	SRR5936117	human_gut
+CSM79HLC	PRJNA398089	SRR5949137	PRJNA398089	SRR5936176	human_gut
+MSM79H5K	PRJNA398089	SRR5949138	PRJNA398089	SRR5936132	human_gut
+HSM6XRV8	PRJNA398089	SRR5949139	PRJNA398089	SRR5935785	human_gut
+CSM79HIZ	PRJNA398089	SRR5949140	PRJNA398089	SRR5935786	human_gut
+CSM79HIB	PRJNA398089	SRR5949141	PRJNA398089	SRR5935794	human_gut
+HSM7CZ1A	PRJNA398089	SRR5949142	PRJNA398089	SRR5935798	human_gut
+CSM79HIN	PRJNA398089	SRR5949143	PRJNA398089	SRR5935792	human_gut
+MSM79H6F	PRJNA398089	SRR5949144	PRJNA398089	SRR5935793	human_gut
+HSM6XRVC	PRJNA398089	SRR5949145	PRJNA398089	SRR5936043	human_gut
+PSM7J199	PRJNA398089	SRR5949146	PRJNA398089	SRR5936131	human_gut
+HSM7CYX6	PRJNA398089	SRR5949147	PRJNA398089	SRR5936134	human_gut
+CSM7KORM	PRJNA398089	SRR5949148	PRJNA398089	SRR5950794	human_gut
+PSM7J12J	PRJNA398089	SRR5949149	PRJNA398089	SRR5936100	human_gut
+ESM5MEBS	PRJNA398089	SRR5949150	PRJNA398089	SRR5935857	human_gut
+MSM6J2IE	PRJNA398089	SRR5949151	PRJNA398089	SRR5935858	human_gut
+MSM5LLDS	PRJNA398089	SRR5949152	PRJNA398089	SRR5935763	human_gut
+CSM7KOJY	PRJNA398089	SRR5949153	PRJNA398089	SRR5946685	human_gut
+HSM5FZBZ	PRJNA398089	SRR5949154	PRJNA398089	SRR5946845	human_gut
+CSM5FZ4M	PRJNA398089	SRR5949155	PRJNA398089	SRR5935761	human_gut
+HSM5MD5B	PRJNA398089	SRR5949156	PRJNA398089	SRR5935768	human_gut
+HSM5MD53	PRJNA398089	SRR5949157	PRJNA398089	SRR5947002	human_gut
+CSM5MCUO	PRJNA398089	SRR5949158	PRJNA398089	SRR5935859	human_gut
+CSM5MCXD	PRJNA398089	SRR5949159	PRJNA398089	SRR5935860	human_gut
+PSM6XBS4	PRJNA398089	SRR5949160	PRJNA398089	SRR5935964	human_gut
+HSM6XRUN	PRJNA398089	SRR5949161	PRJNA398089	SRR5935816	human_gut
+MSM6J2QP	PRJNA398089	SRR5949162	PRJNA398089	SRR5935817	human_gut
+CSM67UEW	PRJNA398089	SRR5949163	PRJNA398089	SRR5935962	human_gut
+HSM6XRQO	PRJNA398089	SRR5949164	PRJNA398089	SRR5936154	human_gut
+HSM67VD4	PRJNA398089	SRR5949165	PRJNA398089	SRR5936160	human_gut
+HSM67VI3	PRJNA398089	SRR5949166	PRJNA398089	SRR5936159	human_gut
+CSM67UEA	PRJNA398089	SRR5949167	PRJNA398089	SRR5936162	human_gut
+HSM67VES	PRJNA398089	SRR5949168	PRJNA398089	SRR5935813	human_gut
+HSM6XRTM	PRJNA398089	SRR5949169	PRJNA398089	SRR5935815	human_gut
+ESM5MEC5	PRJNA398089	SRR5949170	PRJNA398089	SRR5935758	human_gut
+CSM67UAW	PRJNA398089	SRR5949171	PRJNA398089	SRR5935755	human_gut
+HSM6XRQU	PRJNA398089	SRR5949172	PRJNA398089	SRR5935901	human_gut
+CSM67UBH	PRJNA398089	SRR5949173	PRJNA398089	SRR5935900	human_gut
+CSM67UAM	PRJNA398089	SRR5949174	PRJNA398089	SRR5935904	human_gut
+CSM67UAA	PRJNA398089	SRR5949175	PRJNA398089	SRR5935903	human_gut
+CSM67UDF	PRJNA398089	SRR5949176	PRJNA398089	SRR5935908	human_gut
+MSM6J2Q3	PRJNA398089	SRR5949177	PRJNA398089	SRR5935907	human_gut
+MSM6J2LL	PRJNA398089	SRR5949178	PRJNA398089	SRR5935899	human_gut
+ESM5MEBG	PRJNA398089	SRR5949179	PRJNA398089	SRR5935902	human_gut
+MSM6J2PU	PRJNA398089	SRR5949180	PRJNA398089	SRR5935892	human_gut
+HSM7CYZV	PRJNA398089	SRR5949181	PRJNA398089	SRR5935891	human_gut
+CSM79HKB	PRJNA398089	SRR5949182	PRJNA398089	SRR5935890	human_gut
+HSM7CYZJ	PRJNA398089	SRR5949183	PRJNA398089	SRR5935889	human_gut
+CSM79HLG	PRJNA398089	SRR5949184	PRJNA398089	SRR5936005	human_gut
+CSM79HI7	PRJNA398089	SRR5949185	PRJNA398089	SRR5935894	human_gut
+CSM79HIV	PRJNA398089	SRR5949186	PRJNA398089	SRR5935895	human_gut
+HSM67VGG	PRJNA398089	SRR5949187	PRJNA398089	SRR5935893	human_gut
+MSM6J2MH	PRJNA398089	SRR5949188	PRJNA398089	SRR5935888	human_gut
+CSM79HGZ	PRJNA398089	SRR5949189	PRJNA398089	SRR5946660	human_gut
+MSM6J2QF	PRJNA398089	SRR5949190	PRJNA398089	SRR5936052	human_gut
+CSM79HLA	PRJNA398089	SRR5949191	PRJNA398089	SRR5936051	human_gut
+HSM67VHD	PRJNA398089	SRR5949192	PRJNA398089	SRR5936232	human_gut
+HSM6XRQ8	PRJNA398089	SRR5949193	PRJNA398089	SRR5936229	human_gut
+CSM67UF5	PRJNA398089	SRR5949194	PRJNA398089	SRR5936234	human_gut
+MSM6J2RS	PRJNA398089	SRR5949195	PRJNA398089	SRR5936238	human_gut
+HSM6XRVM	PRJNA398089	SRR5949196	PRJNA398089	SRR5936226	human_gut
+HSM67VEK	PRJNA398089	SRR5949197	PRJNA398089	SRR5936230	human_gut
+HSM67VHW	PRJNA398089	SRR5949198	PRJNA398089	SRR5936227	human_gut
+HSM67VFR	PRJNA398089	SRR5949199	PRJNA398089	SRR5936228	human_gut
+CSM7KONK	PRJNA398089	SRR5949200	PRJNA398089	SRR5950508	human_gut
+MSM9VZEK	PRJNA398089	SRR5949201	PRJNA398089	SRR5935847	human_gut
+MSM79H8D	PRJNA398089	SRR5949202	PRJNA398089	SRR5935843	human_gut
+CSM7KOSV	PRJNA398089	SRR5949203	PRJNA398089	SRR5950509	human_gut
+HSM7J4IC	PRJNA398089	SRR5949204	PRJNA398089	SRR5935838	human_gut
+CSM7KON8	PRJNA398089	SRR5949205	PRJNA398089	SRR5935837	human_gut
+HSM7J4L9	PRJNA398089	SRR5949206	PRJNA398089	SRR5935846	human_gut
+HSM7J4IQ	PRJNA398089	SRR5949207	PRJNA398089	SRR5935842	human_gut
+HSM7J4MY	PRJNA398089	SRR5949208	PRJNA398089	SRR5935910	human_gut
+HSM7J4QT	PRJNA398089	SRR5949209	PRJNA398089	SRR5935844	human_gut
+CSM5MCX3	PRJNA398089	SRR5949210	PRJNA398089	SRR5935942	human_gut
+CSM7KOKD	PRJNA398089	SRR5949211	PRJNA398089	SRR5950676	human_gut
+CSM7KOOH	PRJNA398089	SRR5949212	PRJNA398089	SRR5950642	human_gut
+HSM7J4LD	PRJNA398089	SRR5949213	PRJNA398089	SRR5935991	human_gut
+HSM7CYY9	PRJNA398089	SRR5949214	PRJNA398089	SRR5935990	human_gut
+CSM7KOJO	PRJNA398089	SRR5949215	PRJNA398089	SRR5936062	human_gut
+MSM79HDQ	PRJNA398089	SRR5949216	PRJNA398089	SRR5936063	human_gut
+MSM79HCP	PRJNA398089	SRR5949217	PRJNA398089	SRR5936056	human_gut
+MSM79H9Q	PRJNA398089	SRR5949218	PRJNA398089	SRR5936058	human_gut
+PSM7J1BF	PRJNA398089	SRR5949219	PRJNA398089	SRR5935994	human_gut
+CSM7KON2	PRJNA398089	SRR5949220	PRJNA398089	SRR5935992	human_gut
+HSM7J4HS	PRJNA398089	SRR5949221	PRJNA398089	SRR5935783	human_gut
+MSM79H7C	PRJNA398089	SRR5949222	PRJNA398089	SRR5935741	human_gut
+HSM7J4LP	PRJNA398089	SRR5949223	PRJNA398089	SRR5935743	human_gut
+PSM7J18E	PRJNA398089	SRR5949224	PRJNA398089	SRR5935744	human_gut
+HSM7J4I5	PRJNA398089	SRR5949225	PRJNA398089	SRR5935745	human_gut
+PSM7J17L	PRJNA398089	SRR5949226	PRJNA398089	SRR5936015	human_gut
+MSM79HDG	PRJNA398089	SRR5949227	PRJNA398089	SRR5935750	human_gut
+PSM7J17X	PRJNA398089	SRR5949228	PRJNA398089	SRR5935747	human_gut
+CSM67UAU	PRJNA398089	SRR5949229	PRJNA398089	SRR5935807	human_gut
+HSM6XRQI	PRJNA398089	SRR5949230	PRJNA398089	SRR5935805	human_gut
+CSM7KOLE	PRJNA398089	SRR5949231	PRJNA398089	SRR5935967	human_gut
+PSM7J16U	PRJNA398089	SRR5949232	PRJNA398089	SRR5935781	human_gut
+CSM79HHO	PRJNA398089	SRR5949233	PRJNA398089	SRR5946885	human_gut
+HSM67VD6	PRJNA398089	SRR5949234	PRJNA398089	SRR5936073	human_gut
+CSM67UB3	PRJNA398089	SRR5949235	PRJNA398089	SRR5936068	human_gut
+MSM6J2LB	PRJNA398089	SRR5949236	PRJNA398089	SRR5936069	human_gut
+MSM6J2RO	PRJNA398089	SRR5949237	PRJNA398089	SRR5935810	human_gut
+CSM79HGP	PRJNA398089	SRR5949238	PRJNA398089	SRR5935808	human_gut
+CSM67UDR	PRJNA398089	SRR5949239	PRJNA398089	SRR5935814	human_gut
+HSM67VGA	PRJNA398089	SRR5949240	PRJNA398089	SRR5935958	human_gut
+MSM6J2LV	PRJNA398089	SRR5949241	PRJNA398089	SRR5935812	human_gut
+CSM67UBN	PRJNA398089	SRR5949242	PRJNA398089	SRR5935811	human_gut
+HSM7J4NO	PRJNA398089	SRR5949243	PRJNA398089	SRR5935875	human_gut
+HSM7J4KQ	PRJNA398089	SRR5949244	PRJNA398089	SRR5936173	human_gut
+MSM9VZMA	PRJNA398089	SRR5949245	PRJNA398089	SRR5935773	human_gut
+MSM9VZNH	PRJNA398089	SRR5949246	PRJNA398089	SRR5935774	human_gut
+HSM7J4PI	PRJNA398089	SRR5949247	PRJNA398089	SRR5936189	human_gut
+CSM79HRG	PRJNA398089	SRR5949248	PRJNA398089	SRR5950737	human_gut
+HSM7J4HC	PRJNA398089	SRR5949249	PRJNA398089	SRR5936025	human_gut
+PSM7J1A6	PRJNA398089	SRR5949250	PRJNA398089	SRR5936021	human_gut
+MSM79H9M	PRJNA398089	SRR5949251	PRJNA398089	SRR5936020	human_gut
+MSM79HCI	PRJNA398089	SRR5949252	PRJNA398089	SRR5936019	human_gut
+MSM79HDA	PRJNA398089	SRR5949253	PRJNA398089	SRR5936026	human_gut
+PSM7J1BB	PRJNA398089	SRR5949254	PRJNA398089	SRR5936024	human_gut
+PSM6XBUK	PRJNA398089	SRR5949255	PRJNA398089	SRR5936023	human_gut
+HSM7J4HM	PRJNA398089	SRR5949256	PRJNA398089	SRR5936022	human_gut
+MSM79H5Q	PRJNA398089	SRR5949257	PRJNA398089	SRR5936112	human_gut
+HSM67VHJ	PRJNA398089	SRR5949258	PRJNA398089	SRR5936114	human_gut
+PSM6XBT9	PRJNA398089	SRR5949259	PRJNA398089	SRR5935789	human_gut
+HSM67VGK	PRJNA398089	SRR5949260	PRJNA398089	SRR5935788	human_gut
+CSM79HOL	PRJNA398089	SRR5949261	PRJNA398089	SRR5936109	human_gut
+ESM5ME9U	PRJNA398089	SRR5949262	PRJNA398089	SRR5936113	human_gut
+HSM7CZ1V	PRJNA398089	SRR5949263	PRJNA398089	SRR5936110	human_gut
+CSM79HPK	PRJNA398089	SRR5949264	PRJNA398089	SRR5936111	human_gut
+CSM79HPA	PRJNA398089	SRR5949265	PRJNA398089	SRR5946615	human_gut
+PSM6XBV4	PRJNA398089	SRR5949266	PRJNA398089	SRR5935791	human_gut
+CSM7KORO	PRJNA398089	SRR5949267	PRJNA398089	SRR5950523	human_gut
+CSM7KOPI	PRJNA398089	SRR5949268	PRJNA398089	SRR5935974	human_gut
+HSM7J4J7	PRJNA398089	SRR5949269	PRJNA398089	SRR5935977	human_gut
+HSM7J4LH	PRJNA398089	SRR5949270	PRJNA398089	SRR5935973	human_gut
+CSM7KOPU	PRJNA398089	SRR5949271	PRJNA398089	SRR5950627	human_gut
+HSM7J4IO	PRJNA398089	SRR5949272	PRJNA398089	SRR5935972	human_gut
+MSM79H81	PRJNA398089	SRR5949273	PRJNA398089	SRR5935971	human_gut
+MSM79H7O	PRJNA398089	SRR5949274	PRJNA398089	SRR5935970	human_gut
+CSM7KOOV	PRJNA398089	SRR5949275	PRJNA398089	SRR5950665	human_gut
+MSM79H9G	PRJNA398089	SRR5949276	PRJNA398089	SRR5935968	human_gut
+HSM5MD7S	PRJNA398089	SRR5949277	PRJNA398089	SRR5935936	human_gut
+MSM6J2JZ	PRJNA398089	SRR5949278	PRJNA398089	SRR5935833	human_gut
+CSM5MCWQ	PRJNA398089	SRR5949279	PRJNA398089	SRR5935887	human_gut
+HSM5MD7K	PRJNA398089	SRR5949280	PRJNA398089	SRR5936086	human_gut
+MSM6J2HP	PRJNA398089	SRR5949281	PRJNA398089	SRR5936084	human_gut
+CSM5MCW6	PRJNA398089	SRR5949282	PRJNA398089	SRR5936088	human_gut
+HSM5MD66	PRJNA398089	SRR5949283	PRJNA398089	SRR5936089	human_gut
+MSM6J2J5	PRJNA398089	SRR5949284	PRJNA398089	SRR5935829	human_gut
+MSM5LLDA	PRJNA398089	SRR5949285	PRJNA398089	SRR5935828	human_gut
+MSM6J2JN	PRJNA398089	SRR5949286	PRJNA398089	SRR5935827	human_gut
+HSM5MD4N	PRJNA398089	SRR5949287	PRJNA398089	SRR5936235	human_gut
+CSM7KOL4	PRJNA398089	SRR5949288	PRJNA398089	SRR5935869	human_gut
+PSM7J1A2	PRJNA398089	SRR5949289	PRJNA398089	SRR5935868	human_gut
+HSM7CZ14	PRJNA398089	SRR5949290	PRJNA398089	SRR5936208	human_gut
+HSM67VIL	PRJNA398089	SRR5949291	PRJNA398089	SRR5935871	human_gut
+HSM7J4PQ	PRJNA398089	SRR5949292	PRJNA398089	SRR5935870	human_gut
+MSM79HC4	PRJNA398089	SRR5949293	PRJNA398089	SRR5935866	human_gut
+CSM7KOKR	PRJNA398089	SRR5949294	PRJNA398089	SRR5946854	human_gut
+ESM7F5C5	PRJNA398089	SRR5949295	PRJNA398089	SRR5935867	human_gut
+CSM7KOKJ	PRJNA398089	SRR5949296	PRJNA398089	SRR5947013	human_gut
+CSM7KOJU	PRJNA398089	SRR5949297	PRJNA398089	SRR5946674	human_gut
+HSM67VCZ	PRJNA398089	SRR5949298	PRJNA398089	SRR5935760	human_gut
+MSM6J2R2	PRJNA398089	SRR5949299	PRJNA398089	SRR5935759	human_gut
+CSM67U9D	PRJNA398089	SRR5949300	PRJNA398089	SRR5935754	human_gut
+MSM6J2QR	PRJNA398089	SRR5949301	PRJNA398089	SRR5935753	human_gut
+CSM67UBZ	PRJNA398089	SRR5949302	PRJNA398089	SRR5936012	human_gut
+HSM5MD7U	PRJNA398089	SRR5949303	PRJNA398089	SRR5936017	human_gut
+ESM718V8	PRJNA398089	SRR5949304	PRJNA398089	SRR5935757	human_gut
+HSM6XRSG	PRJNA398089	SRR5949305	PRJNA398089	SRR5935752	human_gut
+HSM67VEO	PRJNA398089	SRR5949306	PRJNA398089	SRR5936014	human_gut
+HSM6XRQW	PRJNA398089	SRR5949307	PRJNA398089	SRR5936008	human_gut
+MSM79H7Q	PRJNA398089	SRR5949308	PRJNA398089	SRR5936095	human_gut
+CSM67UAK	PRJNA398089	SRR5949309	PRJNA398089	SRR5935931	human_gut
+CSM5MCZ3	PRJNA398089	SRR5949310	PRJNA398089	SRR5936239	human_gut
+CSM7KORC	PRJNA398089	SRR5949311	PRJNA398089	SRR5950734	human_gut
+HSM6XRR7	PRJNA398089	SRR5949312	PRJNA398089	SRR5935935	human_gut
+CSM5MCXR	PRJNA398089	SRR5949313	PRJNA398089	SRR5935933	human_gut
+MSM6J2IO	PRJNA398089	SRR5949314	PRJNA398089	SRR5935932	human_gut
+ESM5MEDF	PRJNA398089	SRR5949315	PRJNA398089	SRR5935934	human_gut
+MSM6J2KM	PRJNA398089	SRR5949316	PRJNA398089	SRR5936236	human_gut
+HSM7J4M8	PRJNA398089	SRR5949317	PRJNA398089	SRR5936094	human_gut
+HSM6XRS4	PRJNA398089	SRR5949318	PRJNA398089	SRR5935905	human_gut
+HSM6XRQK	PRJNA398089	SRR5949319	PRJNA398089	SRR5935906	human_gut
+CSM7KOR2	PRJNA398089	SRR5949320	PRJNA398089	SRR5950790	human_gut
+CSM67UGO	PRJNA398089	SRR5949321	PRJNA398089	SRR5936075	human_gut
+ESM718TK	PRJNA398089	SRR5949322	PRJNA398089	SRR5936077	human_gut
+MSM6J2MB	PRJNA398089	SRR5949323	PRJNA398089	SRR5936076	human_gut
+HSM67VF9	PRJNA398089	SRR5949324	PRJNA398089	SRR5936071	human_gut
+CSM79HJM	PRJNA398089	SRR5949325	PRJNA398089	SRR5946750	human_gut
+ESM5MECL	PRJNA398089	SRR5949326	PRJNA398089	SRR5936070	human_gut
+CSM79HGF	PRJNA398089	SRR5949327	PRJNA398089	SRR5935959	human_gut
+MSM6J2R8	PRJNA398089	SRR5949328	PRJNA398089	SRR5936072	human_gut
+MSM6J2HR	PRJNA398089	SRR5949329	PRJNA398089	SRR5935916	human_gut
+HSM7J4QF	PRJNA398089	SRR5949330	PRJNA398089	SRR5936196	human_gut
+MSM79HFY	PRJNA398089	SRR5949331	PRJNA398089	SRR5936195	human_gut
+HSM7J4N4	PRJNA398089	SRR5949332	PRJNA398089	SRR5936028	human_gut
+MSM79H7Y	PRJNA398089	SRR5949333	PRJNA398089	SRR5936099	human_gut
+CSM7KOOD	PRJNA398089	SRR5949334	PRJNA398089	SRR5950527	human_gut
+MSM9VZGO	PRJNA398089	SRR5949335	PRJNA398089	SRR5936105	human_gut
+HSM7J4JN	PRJNA398089	SRR5949336	PRJNA398089	SRR5936102	human_gut
+PSM7J186	PRJNA398089	SRR5949337	PRJNA398089	SRR5936103	human_gut
+PSM7J177	PRJNA398089	SRR5949338	PRJNA398089	SRR5936187	human_gut
+MSM79HC8	PRJNA398089	SRR5949339	PRJNA398089	SRR5936191	human_gut
+PSM7J1AU	PRJNA398089	SRR5949340	PRJNA398089	SRR5936194	human_gut
+HSM7CZ38	PRJNA398089	SRR5949341	PRJNA398089	SRR5936188	human_gut
+CSM7KOKN	PRJNA398089	SRR5949342	PRJNA398089	SRR5950725	human_gut
+MSM79HCK	PRJNA398089	SRR5949343	PRJNA398089	SRR5936198	human_gut
+PSM7J1CC	PRJNA398089	SRR5949344	PRJNA398089	SRR5936193	human_gut
+HSM7J4I3	PRJNA398089	SRR5949345	PRJNA398089	SRR5936192	human_gut
+PSM6XBV2	PRJNA398089	SRR5949346	PRJNA398089	SRR5935982	human_gut
+HSM6XRV6	PRJNA398089	SRR5949347	PRJNA398089	SRR5935983	human_gut
+CSM79HLE	PRJNA398089	SRR5949348	PRJNA398089	SRR5935826	human_gut
+CSM79HIL	PRJNA398089	SRR5949349	PRJNA398089	SRR5946873	human_gut
+MSM6J2MJ	PRJNA398089	SRR5949350	PRJNA398089	SRR5935832	human_gut
+PSM6XBSU	PRJNA398089	SRR5949351	PRJNA398089	SRR5936106	human_gut
+CSM79HJA	PRJNA398089	SRR5949352	PRJNA398089	SRR5946871	human_gut
+HSM67VG8	PRJNA398089	SRR5949353	PRJNA398089	SRR5936104	human_gut
+CSM79HIX	PRJNA398089	SRR5949354	PRJNA398089	SRR5936108	human_gut
+HSM7CYX4	PRJNA398089	SRR5949355	PRJNA398089	SRR5936107	human_gut
+HSM7J4JZ	PRJNA398089	SRR5949356	PRJNA398089	SRR5935839	human_gut
+PSM7J182	PRJNA398089	SRR5949357	PRJNA398089	SRR5935840	human_gut
+PSM7J1A8	PRJNA398089	SRR5949358	PRJNA398089	SRR5935801	human_gut
+MSM79HDC	PRJNA398089	SRR5949359	PRJNA398089	SRR5935800	human_gut
+MSM79HEY	PRJNA398089	SRR5949360	PRJNA398089	SRR5935795	human_gut
+PSM7J19J	PRJNA398089	SRR5949361	PRJNA398089	SRR5935806	human_gut
+HSM7CYYD	PRJNA398089	SRR5949362	PRJNA398089	SRR5935802	human_gut
+CSM79HR6	PRJNA398089	SRR5949363	PRJNA398089	SRR5950716	human_gut
+MSM79HAJ	PRJNA398089	SRR5949364	PRJNA398089	SRR5935799	human_gut
+HSM7J4G1	PRJNA398089	SRR5949365	PRJNA398089	SRR5935797	human_gut
+CSM7KOKB	PRJNA398089	SRR5949366	PRJNA398089	SRR5950714	human_gut
+CSM7KOMP	PRJNA398089	SRR5949367	PRJNA398089	SRR5935796	human_gut
+HSM5MD43	PRJNA398089	SRR5949368	PRJNA398089	SRR5935969	human_gut
+MSM6J2KC	PRJNA398089	SRR5949369	PRJNA398089	SRR5936085	human_gut
+ESM5MEDN	PRJNA398089	SRR5949370	PRJNA398089	SRR5936184	human_gut
+CSM5MCVN	PRJNA398089	SRR5949371	PRJNA398089	SRR5935841	human_gut
+HSM5MD62	PRJNA398089	SRR5949372	PRJNA398089	SRR5936183	human_gut
+HSM5MD5D	PRJNA398089	SRR5949373	PRJNA398089	SRR5935966	human_gut
+MSM5LLF4	PRJNA398089	SRR5949374	PRJNA398089	SRR5936079	human_gut
+ESM5MEBU	PRJNA398089	SRR5949375	PRJNA398089	SRR5936083	human_gut
+CSM5MCWC	PRJNA398089	SRR5949376	PRJNA398089	SRR5936186	human_gut
+CSM5MCXJ	PRJNA398089	SRR5949377	PRJNA398089	SRR5936080	human_gut
+ESM7F5CB	PRJNA398089	SRR5949378	PRJNA398089	SRR5936203	human_gut
+PSM7J19N	PRJNA398089	SRR5949379	PRJNA398089	SRR5936204	human_gut
+CSM7KOK5	PRJNA398089	SRR5949380	PRJNA398089	SRR5936205	human_gut
+CSM7KOJG	PRJNA398089	SRR5949381	PRJNA398089	SRR5936207	human_gut
+PSM7J19P	PRJNA398089	SRR5949382	PRJNA398089	SRR5936201	human_gut
+CSM79HR8	PRJNA398089	SRR5949383	PRJNA398089	SRR5946700	human_gut
+HSM7CZ3C	PRJNA398089	SRR5949384	PRJNA398089	SRR5936206	human_gut
+HSM7CZ32	PRJNA398089	SRR5949385	PRJNA398089	SRR5936200	human_gut
+HSM7CYXA	PRJNA398089	SRR5949386	PRJNA398089	SRR5936209	human_gut
+PSM6XBUI	PRJNA398089	SRR5949387	PRJNA398089	SRR5936202	human_gut
+CSM67UAY	PRJNA398089	SRR5949388	PRJNA398089	SRR5936011	human_gut
+HSM5MD6W	PRJNA398089	SRR5949389	PRJNA398089	SRR5936010	human_gut
+CSM67UB9	PRJNA398089	SRR5949390	PRJNA398089	SRR5962905	human_gut
+CSM67UDJ	PRJNA398089	SRR5949391	PRJNA398089	SRR5936009	human_gut
+HSM67VD2	PRJNA398089	SRR5949392	PRJNA398089	SRR5936006	human_gut
+CSM67UAO	PRJNA398089	SRR5949393	PRJNA398089	SRR5946754	human_gut
+HSM6XRSI	PRJNA398089	SRR5949394	PRJNA398089	SRR5935997	human_gut
+HSM6XRST	PRJNA398089	SRR5949395	PRJNA398089	SRR5936001	human_gut
+HSM6XRQM	PRJNA398089	SRR5949396	PRJNA398089	SRR5935998	human_gut
+CSM67UE7	PRJNA398089	SRR5949397	PRJNA398089	SRR5935999	human_gut
+HSM7J4IP	PRJNA398089	SRR5949398	PRJNA398089	SRR5935949	human_gut
+PSM7J193	PRJNA398089	SRR5949399	PRJNA398089	SRR5936093	human_gut
+HSM5MD7O	PRJNA398089	SRR5949400	PRJNA398089	SRR5935941	human_gut
+HSM5MD3Y	PRJNA398089	SRR5949401	PRJNA398089	SRR5935940	human_gut
+HSM5MD6A	PRJNA398089	SRR5949402	PRJNA398089	SRR5935939	human_gut
+HSM6XRQB	PRJNA398089	SRR5949403	PRJNA398089	SRR5935765	human_gut
+CSM7KOO9	PRJNA398089	SRR5949404	PRJNA398089	SRR5950486	human_gut
+CSM5MCZB	PRJNA398089	SRR5949405	PRJNA398089	SRR5935945	human_gut
+CSM5MCXN	PRJNA398089	SRR5949406	PRJNA398089	SRR5935909	human_gut
+ESM5GEXY	PRJNA398089	SRR5949407	PRJNA398089	SRR5935911	human_gut
+HSM6XRT8	PRJNA398089	SRR5949408	PRJNA398089	SRR5935915	human_gut
+HSM6XRSX	PRJNA398089	SRR5949409	PRJNA398089	SRR5935769	human_gut
+CSM7KOPK	PRJNA398089	SRR5949410	PRJNA398089	SRR5950484	human_gut
+HSM7J4MK	PRJNA398089	SRR5949411	PRJNA398089	SRR5935948	human_gut
+HSM5MD5P	PRJNA398089	SRR5949412	PRJNA398089	SRR5935918	human_gut
+PSM7J18I	PRJNA398089	SRR5949413	PRJNA398089	SRR5936101	human_gut
+CSM79HID	PRJNA398089	SRR5949414	PRJNA398089	SRR5936030	human_gut
+HSM6XRUR	PRJNA398089	SRR5949415	PRJNA398089	SRR5936033	human_gut
+HSM67VHB	PRJNA398089	SRR5949416	PRJNA398089	SRR5936029	human_gut
+CSM79HJW	PRJNA398089	SRR5949417	PRJNA398089	SRR5936218	human_gut
+HSM67VF3	PRJNA398089	SRR5949418	PRJNA398089	SRR5936041	human_gut
+HSM67VEU	PRJNA398089	SRR5949419	PRJNA398089	SRR5936037	human_gut
+HSM67VFZ	PRJNA398089	SRR5949420	PRJNA398089	SRR5936031	human_gut
+CSM79HH4	PRJNA398089	SRR5949421	PRJNA398089	SRR5947037	human_gut
+MSM9VZEU	PRJNA398089	SRR5949422	PRJNA398089	SRR5936092	human_gut
+CSM79HIF	PRJNA398089	SRR5949423	PRJNA398089	SRR5946749	human_gut
+CSM79HI3	PRJNA398089	SRR5949424	PRJNA398089	SRR5936222	human_gut
+HSM7J4JJ	PRJNA398089	SRR5949425	PRJNA398089	SRR5936091	human_gut
+MSM79H87	PRJNA398089	SRR5949426	PRJNA398089	SRR5935872	human_gut
+MSM79HB6	PRJNA398089	SRR5949427	PRJNA398089	SRR5935850	human_gut
+HSM7J4LN	PRJNA398089	SRR5949428	PRJNA398089	SRR5935851	human_gut
+PSM7J17F	PRJNA398089	SRR5949429	PRJNA398089	SRR5936096	human_gut
+MSM6J2K2	PRJNA398089	SRR5949430	PRJNA398089	SRR5935914	human_gut
+HSM7J4NE	PRJNA398089	SRR5949431	PRJNA398089	SRR5936174	human_gut
+PSM7J18K	PRJNA398089	SRR5949432	PRJNA398089	SRR5935861	human_gut
+PSM7J136	PRJNA398089	SRR5949433	PRJNA398089	SRR5936172	human_gut
+CSM7KOPO	PRJNA398089	SRR5949434	PRJNA398089	SRR5950771	human_gut
+CSM7KORU	PRJNA398089	SRR5949435	PRJNA398089	SRR5950772	human_gut
+MSM79H83	PRJNA398089	SRR5949436	PRJNA398089	SRR5936098	human_gut
+CSM79HPS	PRJNA398089	SRR5949437	PRJNA398089	SRR5935865	human_gut
+PSM7J1AM	PRJNA398089	SRR5949438	PRJNA398089	SRR5935864	human_gut
+ESM718T7	PRJNA398089	SRR5949439	PRJNA398089	SRR5935886	human_gut
+HSM6XRVW	PRJNA398089	SRR5949440	PRJNA398089	SRR5935874	human_gut
+HSM7J4PS	PRJNA398089	SRR5949441	PRJNA398089	SRR5935873	human_gut
+HSM7CYXC	PRJNA398089	SRR5949442	PRJNA398089	SRR5935930	human_gut
+MSM79HEU	PRJNA398089	SRR5949443	PRJNA398089	SRR5936081	human_gut
+CSM79HR2	PRJNA398089	SRR5949444	PRJNA398089	SRR5946648	human_gut
+HSM7CZ2Z	PRJNA398089	SRR5949445	PRJNA398089	SRR5936128	human_gut
+CSM79HN6	PRJNA398089	SRR5949446	PRJNA398089	SRR5946941	human_gut
+HSM67VFJ	PRJNA398089	SRR5949447	PRJNA398089	SRR5936129	human_gut
+HSM6XRVK	PRJNA398089	SRR5949448	PRJNA398089	SRR5936130	human_gut
+CSM79HMT	PRJNA398089	SRR5949449	PRJNA398089	SRR5936185	human_gut
+CSM79HPC	PRJNA398089	SRR5949450	PRJNA398089	SRR5947074	human_gut
+HSM7CYXI	PRJNA398089	SRR5949451	PRJNA398089	SRR5936141	human_gut
+HSM7CYYH	PRJNA398089	SRR5949452	PRJNA398089	SRR5936127	human_gut
+HSM7J4PO	PRJNA398089	SRR5949453	PRJNA398089	SRR5935885	human_gut
+HSM67VGY	PRJNA398089	SRR5949454	PRJNA398089	SRR5935883	human_gut
+CSM7KOO5	PRJNA398089	SRR5949455	PRJNA398089	SRR5950636	human_gut
+HSM7J4OZ	PRJNA398089	SRR5949456	PRJNA398089	SRR5935779	human_gut
+MSM9VZF1	PRJNA398089	SRR5949457	PRJNA398089	SRR5935777	human_gut
+CSM7KOSP	PRJNA398089	SRR5949458	PRJNA398089	SRR5950565	human_gut
+MSM9VZMO	PRJNA398089	SRR5949459	PRJNA398089	SRR5935778	human_gut
+PSM7J18Q	PRJNA398089	SRR5949460	PRJNA398089	SRR5935775	human_gut
+HSM7J4K6	PRJNA398089	SRR5949461	PRJNA398089	SRR5935776	human_gut
+HSM7J4O3	PRJNA398089	SRR5949462	PRJNA398089	SRR5935772	human_gut
+CSM7KOU9	PRJNA398089	SRR5949463	PRJNA398089	SRR5950609	human_gut
+HSM5MD48	PRJNA398089	SRR5949464	PRJNA398089	SRR5935853	human_gut
+MSM5LLDC	PRJNA398089	SRR5949465	PRJNA398089	SRR5935854	human_gut
+MSM5LLEP	PRJNA398089	SRR5949466	PRJNA398089	SRR5935855	human_gut
+MSM6J2HB	PRJNA398089	SRR5949467	PRJNA398089	SRR5935856	human_gut
+CSM5MCY4	PRJNA398089	SRR5949468	PRJNA398089	SRR5936178	human_gut
+MSM6J2J3	PRJNA398089	SRR5949469	PRJNA398089	SRR5936177	human_gut
+MSM6J2IQ	PRJNA398089	SRR5949470	PRJNA398089	SRR5935862	human_gut
+CSM5MCXH	PRJNA398089	SRR5949471	PRJNA398089	SRR5935863	human_gut
+MSM5LLHC	PRJNA398089	SRR5949472	PRJNA398089	SRR5936181	human_gut
+CSM5MCXT	PRJNA398089	SRR5949473	PRJNA398089	SRR5936179	human_gut
+HSM67VEE	PRJNA398089	SRR5949474	PRJNA398089	SRR5936155	human_gut
+HSM6XRRB	PRJNA398089	SRR5949475	PRJNA398089	SRR5936161	human_gut
+CSM5MCY8	PRJNA398089	SRR5949476	PRJNA398089	SRR5935919	human_gut
+CSM67UCK	PRJNA398089	SRR5949477	PRJNA398089	SRR5936002	human_gut
+HSM6XRRJ	PRJNA398089	SRR5949478	PRJNA398089	SRR5936000	human_gut
+HSM67VEC	PRJNA398089	SRR5949479	PRJNA398089	SRR5936004	human_gut
+HSM6XRRV	PRJNA398089	SRR5949480	PRJNA398089	SRR5936003	human_gut
+MSM6J2QH	PRJNA398089	SRR5949481	PRJNA398089	SRR5935995	human_gut
+HSM6XRUL	PRJNA398089	SRR5949482	PRJNA398089	SRR5936156	human_gut
+CSM67UDN	PRJNA398089	SRR5949483	PRJNA398089	SRR5936157	human_gut
+CSM67UFZ	PRJNA398089	SRR5949484	PRJNA398089	SRR5936158	human_gut
+CSM5MCXL	PRJNA398089	SRR5949485	PRJNA398089	SRR5935830	human_gut
+CSM5MCWE	PRJNA398089	SRR5949486	PRJNA398089	SRR5935831	human_gut
+HSM5MD6Y	PRJNA398089	SRR5949487	PRJNA398089	SRR5935834	human_gut
+MSM6J2RC	PRJNA398089	SRR5949488	PRJNA398089	SRR5935986	human_gut
+MSM79H54	PRJNA398089	SRR5949489	PRJNA398089	SRR5935984	human_gut
+CSM79HKT	PRJNA398089	SRR5949490	PRJNA398089	SRR5935980	human_gut
+CSM79HO1	PRJNA398089	SRR5949491	PRJNA398089	SRR5935979	human_gut
+MSM6J2SK	PRJNA398089	SRR5949492	PRJNA398089	SRR5935985	human_gut
+MSM79H5G	PRJNA398089	SRR5949493	PRJNA398089	SRR5935981	human_gut
+CSM79HNO	PRJNA398089	SRR5949494	PRJNA398089	SRR5946940	human_gut
+CSM79HJS	PRJNA398089	SRR5949495	PRJNA398089	SRR5946694	human_gut
+ESM718TF	PRJNA398089	SRR5949496	PRJNA398089	SRR5935896	human_gut
+HSM7CYX2	PRJNA398089	SRR5949497	PRJNA398089	SRR5935897	human_gut
+HSM5MD6I	PRJNA398089	SRR5949498	PRJNA398089	SRR5935770	human_gut
+MSM6J2KE	PRJNA398089	SRR5949499	PRJNA398089	SRR5935913	human_gut
+MSM6J2JP	PRJNA398089	SRR5949500	PRJNA398089	SRR5935912	human_gut
+HSM7J4MA	PRJNA398089	SRR5949501	PRJNA398089	SRR5936171	human_gut
+CSM7KOSL	PRJNA398089	SRR5949502	PRJNA398089	SRR5950776	human_gut
+MSM9VZFL	PRJNA398089	SRR5949503	PRJNA398089	SRR5936168	human_gut
+MSM9VZEW	PRJNA398089	SRR5949504	PRJNA398089	SRR5936167	human_gut
+HSM7J4IR	PRJNA398089	SRR5949505	PRJNA398089	SRR5936170	human_gut
+PSM7J184	PRJNA398089	SRR5949506	PRJNA398089	SRR5936169	human_gut
+CSM7KOPM	PRJNA398089	SRR5949507	PRJNA398089	SRR5950504	human_gut
+HSM7J4KC	PRJNA398089	SRR5949508	PRJNA398089	SRR5936165	human_gut
+CSM7KOSX	PRJNA398089	SRR5949509	PRJNA398089	SRR5950775	human_gut
+PSM7J1CU	PRJNA398089	SRR5949510	PRJNA398089	SRR5936164	human_gut
+CSM7KOPW	PRJNA398089	SRR5949511	PRJNA398089	SRR5950485	human_gut
+MSM79H9W	PRJNA398089	SRR5949512	PRJNA398089	SRR5936097	human_gut
+PSM7J179	PRJNA398089	SRR5949513	PRJNA398089	SRR5936055	human_gut
+CSM7KOMB	PRJNA398089	SRR5949514	PRJNA398089	SRR5950681	human_gut
+HSM7J4GD	PRJNA398089	SRR5949515	PRJNA398089	SRR5936060	human_gut
+HSM7J4HO	PRJNA398089	SRR5949516	PRJNA398089	SRR5936059	human_gut
+PSM6XBUQ	PRJNA398089	SRR5949517	PRJNA398089	SRR5935803	human_gut
+CSM7KOLA	PRJNA398089	SRR5949518	PRJNA398089	SRR5935804	human_gut
+CSM7KOLM	PRJNA398089	SRR5949519	PRJNA398089	SRR5950680	human_gut
+HSM7J4PW	PRJNA398089	SRR5949520	PRJNA398089	SRR5936054	human_gut
+HSM7J4R2	PRJNA398089	SRR5949521	PRJNA398089	SRR5936065	human_gut
+HSM7J4PK	PRJNA398089	SRR5949522	PRJNA398089	SRR5936061	human_gut
+CSM7KOPS	PRJNA398089	SRR5949523	PRJNA398089	SRR5950674	human_gut
+CSM7KOMT	PRJNA398089	SRR5949524	PRJNA398089	SRR5935748	human_gut
+CSM7KOKZ	PRJNA398089	SRR5949525	PRJNA398089	SRR5950635	human_gut
+PSM7J1BR	PRJNA398089	SRR5949526	PRJNA398089	SRR5936139	human_gut
+MSM79HCR	PRJNA398089	SRR5949527	PRJNA398089	SRR5936137	human_gut
+HSM7CYYB	PRJNA398089	SRR5949528	PRJNA398089	SRR5936138	human_gut
+HSM7J4PM	PRJNA398089	SRR5949529	PRJNA398089	SRR5936135	human_gut
+PSM7J17B	PRJNA398089	SRR5949530	PRJNA398089	SRR5936136	human_gut
+HSM7J4QJ	PRJNA398089	SRR5949531	PRJNA398089	SRR5936175	human_gut
+HSM7J4PY	PRJNA398089	SRR5949532	PRJNA398089	SRR5936133	human_gut
+HSM67VGC	PRJNA398089	SRR5949533	PRJNA398089	SRR5936213	human_gut
+CSM79HIJ	PRJNA398089	SRR5949534	PRJNA398089	SRR5946657	human_gut
+MSM6J2QD	PRJNA398089	SRR5949535	PRJNA398089	SRR5935746	human_gut
+CSM67UEI	PRJNA398089	SRR5949536	PRJNA398089	SRR5935742	human_gut
+HSM67VEM	PRJNA398089	SRR5949537	PRJNA398089	SRR5936125	human_gut
+MSM79H5E	PRJNA398089	SRR5949538	PRJNA398089	SRR5935740	human_gut
+HSM67VIB	PRJNA398089	SRR5949539	PRJNA398089	SRR5936126	human_gut
+HSM6XRVO	PRJNA398089	SRR5949540	PRJNA398089	SRR5936122	human_gut
+HSM67VHF	PRJNA398089	SRR5949541	PRJNA398089	SRR5936120	human_gut
+HSM7CYZ7	PRJNA398089	SRR5949542	PRJNA398089	SRR5936124	human_gut
+HSM6XRV4	PRJNA398089	SRR5949543	PRJNA398089	SRR5936123	human_gut
+CSM79HRC	PRJNA398089	SRR5949544	PRJNA398089	SRR5946784	human_gut
+CSM79HHU	PRJNA398089	SRR5949545	PRJNA398089	SRR5946653	human_gut
+CSM79HOZ	PRJNA398089	SRR5949546	PRJNA398089	SRR5946946	human_gut
+MSM6J2OP	PRJNA398089	SRR5949547	PRJNA398089	SRR5936053	human_gut
+CSM79HH8	PRJNA398089	SRR5949548	PRJNA398089	SRR5946908	human_gut
+CSM79HGX	PRJNA398089	SRR5949549	PRJNA398089	SRR5946740	human_gut
+PSM6XBVK	PRJNA398089	SRR5949550	PRJNA398089	SRR5936047	human_gut
+ESM7F5AK	PRJNA398089	SRR5949551	PRJNA398089	SRR5936050	human_gut
+CSM79HIT	PRJNA398089	SRR5949552	PRJNA398089	SRR5936046	human_gut
+HSM67VFD	PRJNA398089	SRR5949553	PRJNA398089	SRR5936044	human_gut
+HSM7CYZT	PRJNA398089	SRR5949554	PRJNA398089	SRR5936048	human_gut
+HSM7J4K4	PRJNA398089	SRR5949555	PRJNA398089	SRR5936078	human_gut
+HSM7J4MC	PRJNA398089	SRR5949556	PRJNA398089	SRR5936067	human_gut
+MSM9VZMM	PRJNA398089	SRR5949557	PRJNA398089	SRR5936197	human_gut
+MSM9VZEY	PRJNA398089	SRR5949558	PRJNA398089	SRR5936199	human_gut
+MSM79HBB	PRJNA398089	SRR5949559	PRJNA398089	SRR5935825	human_gut
+CSM7KOOR	PRJNA398089	SRR5949560	PRJNA398089	SRR5950530	human_gut
+HSM7J4K2	PRJNA398089	SRR5949561	PRJNA398089	SRR5935852	human_gut
+HSM7J4JD	PRJNA398089	SRR5949562	PRJNA398089	SRR5935822	human_gut
+CSM7KOTC	PRJNA398089	SRR5949563	PRJNA398089	SRR5950564	human_gut
+HSM7J4IS	PRJNA398089	SRR5949564	PRJNA398089	SRR5936090	human_gut
+PSM7J18M	PRJNA398089	SRR5949565	PRJNA398089	SRR5936147	human_gut
+MSM79H9Y	PRJNA398089	SRR5949566	PRJNA398089	SRR5936115	human_gut
+PSM7J19F	PRJNA398089	SRR5949567	PRJNA398089	SRR5936116	human_gut
+MSM79HF5	PRJNA398089	SRR5949568	PRJNA398089	SRR5935884	human_gut
+PSM7J17V	PRJNA398089	SRR5949569	PRJNA398089	SRR5935818	human_gut
+HSM7J4MS	PRJNA398089	SRR5949570	PRJNA398089	SRR5935819	human_gut
+CSM7KONU	PRJNA398089	SRR5949571	PRJNA398089	SRR5936190	human_gut
+MSM79HAL	PRJNA398089	SRR5949572	PRJNA398089	SRR5936140	human_gut
+HSM7J4HQ	PRJNA398089	SRR5949573	PRJNA398089	SRR5935987	human_gut
+MSM79HDE	PRJNA398089	SRR5949574	PRJNA398089	SRR5935988	human_gut
+MSM79HA3	PRJNA398089	SRR5949575	PRJNA398089	SRR5935989	human_gut
+HSM7J4GR	PRJNA398089	SRR5949576	PRJNA398089	SRR5935993	human_gut
+CSM79HNU	PRJNA398089	SRR5949577	PRJNA398089	SRR5946826	human_gut
+HSM7CYX8	PRJNA398089	SRR5949578	PRJNA398089	SRR5935880	human_gut
+MSM79H5Y	PRJNA398089	SRR5949579	PRJNA398089	SRR5935876	human_gut
+PSM7J19B	PRJNA398089	SRR5949580	PRJNA398089	SRR5935877	human_gut
+HSM67VH1	PRJNA398089	SRR5949581	PRJNA398089	SRR5936142	human_gut
+HSM7CZ1Z	PRJNA398089	SRR5949582	PRJNA398089	SRR5935881	human_gut
+HSM7CZ3A	PRJNA398089	SRR5949583	PRJNA398089	SRR5935882	human_gut
+PSM6XBUG	PRJNA398089	SRR5949584	PRJNA398089	SRR5935879	human_gut
+HSM7J4NY	PRJNA398089	SRR5949585	PRJNA398089	SRR5950717	human_gut
+MSM79H7M	PRJNA398089	SRR5949586	PRJNA398089	SRR5935782	human_gut
+HSM7J4ME	PRJNA398089	SRR5949587	PRJNA398089	SRR5936027	human_gut
+HSM6XRR5	PRJNA398089	SRR5949588	PRJNA398089	SRR5936042	human_gut
+MSM6J2JD	PRJNA398089	SRR5949589	PRJNA398089	SRR5936040	human_gut
+HSM5MD41	PRJNA398089	SRR5949590	PRJNA398089	SRR5936039	human_gut
+MSM6J2LJ	PRJNA398089	SRR5949591	PRJNA398089	SRR5936038	human_gut
+HSM6XRSN	PRJNA398089	SRR5949592	PRJNA398089	SRR5936045	human_gut
+CSM5MCZF	PRJNA398089	SRR5949593	PRJNA398089	SRR5936166	human_gut
+MSM6J2JR	PRJNA398089	SRR5949594	PRJNA398089	SRR5935784	human_gut
+ESM5MED2	PRJNA398089	SRR5949595	PRJNA398089	SRR5936049	human_gut
+MSM6J2HT	PRJNA398089	SRR5949596	PRJNA398089	SRR5935749	human_gut
+HSM5MD73	PRJNA398089	SRR5949597	PRJNA398089	SRR5936220	human_gut
+CSM5MCXP	PRJNA398089	SRR5949598	PRJNA398089	SRR5936224	human_gut
+CSM67UA2	PRJNA398089	SRR5949599	PRJNA398089	SRR5935780	human_gut
+ESM5MEB7	PRJNA398089	SRR5949600	PRJNA398089	SRR5935947	human_gut
+CSM67U9H	PRJNA398089	SRR5949601	PRJNA398089	SRR5935767	human_gut
+CSM5MCZD	PRJNA398089	SRR5949602	PRJNA398089	SRR5935946	human_gut
+HSM5MD6K	PRJNA398089	SRR5949603	PRJNA398089	SRR5935764	human_gut
+HSM5MD7Q	PRJNA398089	SRR5949604	PRJNA398089	SRR5936223	human_gut
+CSM5MCY2	PRJNA398089	SRR5949605	PRJNA398089	SRR5936163	human_gut
+MSM6J2SE	PRJNA398089	SRR5949606	PRJNA398089	SRR5936035	human_gut
+MSM6J2PK	PRJNA398089	SRR5949607	PRJNA398089	SRR5936036	human_gut
+PSM6XBSE	PRJNA398089	SRR5949608	PRJNA398089	SRR5935961	human_gut
+MSM9VZOU	PRJNA398089	SRR5950246	PRJNA398089	SRR5947080	human_gut
+HSMA33O3	PRJNA398089	SRR5950247	PRJNA398089	SRR5947083	human_gut
+PSM7J15S	PRJNA398089	SRR5950248	PRJNA398089	SRR5947077	human_gut
+HSMA33OR	PRJNA398089	SRR5950249	PRJNA398089	SRR5946855	human_gut
+PSM7J163	PRJNA398089	SRR5950250	PRJNA398089	SRR5947079	human_gut
+PSM7J14R	PRJNA398089	SRR5950251	PRJNA398089	SRR5947078	human_gut
+PSM7J14T	PRJNA398089	SRR5950252	PRJNA398089	SRR5947087	human_gut
+MSM9VZJZ	PRJNA398089	SRR5950253	PRJNA398089	SRR5947081	human_gut
+MSMB4LYH	PRJNA398089	SRR5950254	PRJNA398089	SRR5946709	human_gut
+MSM5LLDI	PRJNA398089	SRR5950255	PRJNA398089	SRR5946771	human_gut
+MSM5LLDK	PRJNA398089	SRR5950256	PRJNA398089	SRR5946775	human_gut
+PSMB4MC5	PRJNA398089	SRR5950257	PRJNA398089	SRR5946710	human_gut
+CSM9X22S	PRJNA398089	SRR5950258	PRJNA398089	SRR5950514	human_gut
+PSMA267R	PRJNA398089	SRR5950259	PRJNA398089	SRR5946765	human_gut
+HSMA33QY	PRJNA398089	SRR5950260	PRJNA398089	SRR5946767	human_gut
+HSMA33PZ	PRJNA398089	SRR5950261	PRJNA398089	SRR5946764	human_gut
+MSM5LLDU	PRJNA398089	SRR5950262	PRJNA398089	SRR5946769	human_gut
+MSM5LLDM	PRJNA398089	SRR5950263	PRJNA398089	SRR5946770	human_gut
+PSMA267H	PRJNA398089	SRR5950264	PRJNA398089	SRR5946766	human_gut
+MSM5LLDQ	PRJNA398089	SRR5950265	PRJNA398089	SRR5946768	human_gut
+PSM7J4EF	PRJNA398089	SRR5950266	PRJNA398089	SRR5946734	human_gut
+HSMA33IA	PRJNA398089	SRR5950267	PRJNA398089	SRR5946738	human_gut
+HSMA33P6	PRJNA398089	SRR5950268	PRJNA398089	SRR5946732	human_gut
+HSMA33OD	PRJNA398089	SRR5950269	PRJNA398089	SRR5946736	human_gut
+MSM9VZKC	PRJNA398089	SRR5950270	PRJNA398089	SRR5946731	human_gut
+CSMAIG7X	PRJNA398089	SRR5950271	PRJNA398089	SRR5950539	human_gut
+HSMA33OT	PRJNA398089	SRR5950272	PRJNA398089	SRR5947084	human_gut
+PSM7J15U	PRJNA398089	SRR5950273	PRJNA398089	SRR5946735	human_gut
+CSM9X1YV	PRJNA398089	SRR5950274	PRJNA398089	SRR5950587	human_gut
+MSM9VZMI	PRJNA398089	SRR5950275	PRJNA398089	SRR5946737	human_gut
+PSMA267P	PRJNA398089	SRR5950276	PRJNA398089	SRR5946763	human_gut
+HSMA33LJ	PRJNA398089	SRR5950277	PRJNA398089	SRR5946717	human_gut
+CSM9X22K	PRJNA398089	SRR5950278	PRJNA398089	SRR5950551	human_gut
+MSMA26BR	PRJNA398089	SRR5950279	PRJNA398089	SRR5946723	human_gut
+MSM9VZI6	PRJNA398089	SRR5950280	PRJNA398089	SRR5946725	human_gut
+MSMA26AV	PRJNA398089	SRR5950281	PRJNA398089	SRR5946722	human_gut
+PSMA269G	PRJNA398089	SRR5950282	PRJNA398089	SRR5946727	human_gut
+PSMA269S	PRJNA398089	SRR5950283	PRJNA398089	SRR5946724	human_gut
+HSMA33MK	PRJNA398089	SRR5950284	PRJNA398089	SRR5946718	human_gut
+HSMA33LH	PRJNA398089	SRR5950285	PRJNA398089	SRR5946726	human_gut
+HSMA33M8	PRJNA398089	SRR5950286	PRJNA398089	SRR5946894	human_gut
+HSMA33RF	PRJNA398089	SRR5950287	PRJNA398089	SRR5946898	human_gut
+CSM9X23B	PRJNA398089	SRR5950288	PRJNA398089	SRR5950553	human_gut
+MSMB4LXY	PRJNA398089	SRR5950289	PRJNA398089	SRR5946639	human_gut
+PSMB4MBK	PRJNA398089	SRR5950290	PRJNA398089	SRR5946635	human_gut
+MSMAPC64	PRJNA398089	SRR5950291	PRJNA398089	SRR5946637	human_gut
+CSM9X23N	PRJNA398089	SRR5950292	PRJNA398089	SRR5950710	human_gut
+HSMA33RT	PRJNA398089	SRR5950293	PRJNA398089	SRR5946636	human_gut
+MSMB4LXW	PRJNA398089	SRR5950294	PRJNA398089	SRR5946632	human_gut
+MSMAPC5D	PRJNA398089	SRR5950295	PRJNA398089	SRR5946630	human_gut
+CSM9X219	PRJNA398089	SRR5950296	PRJNA398089	SRR5950623	human_gut
+PSMA265X	PRJNA398089	SRR5950297	PRJNA398089	SRR5946743	human_gut
+PSMA264S	PRJNA398089	SRR5950298	PRJNA398089	SRR5947062	human_gut
+PSMA265N	PRJNA398089	SRR5950299	PRJNA398089	SRR5946926	human_gut
+MSM9VZKE	PRJNA398089	SRR5950300	PRJNA398089	SRR5946925	human_gut
+MSM9VZL5	PRJNA398089	SRR5950301	PRJNA398089	SRR5946924	human_gut
+HSMA33SK	PRJNA398089	SRR5950302	PRJNA398089	SRR5946708	human_gut
+MSMB4LZ8	PRJNA398089	SRR5950303	PRJNA398089	SRR5946707	human_gut
+MSMAPC5L	PRJNA398089	SRR5950304	PRJNA398089	SRR5946891	human_gut
+MSMAPC6G	PRJNA398089	SRR5950305	PRJNA398089	SRR5946887	human_gut
+HSMA33RD	PRJNA398089	SRR5950306	PRJNA398089	SRR5946888	human_gut
+CSM9X237	PRJNA398089	SRR5950307	PRJNA398089	SRR5950556	human_gut
+MSMAPC7T	PRJNA398089	SRR5950308	PRJNA398089	SRR5946825	human_gut
+MSMAPC59	PRJNA398089	SRR5950309	PRJNA398089	SRR5946892	human_gut
+PSMA269O	PRJNA398089	SRR5950310	PRJNA398089	SRR5946893	human_gut
+MSMAPC6K	PRJNA398089	SRR5950311	PRJNA398089	SRR5946889	human_gut
+MSMB4LZR	PRJNA398089	SRR5950312	PRJNA398089	SRR5946714	human_gut
+MSMB4LZC	PRJNA398089	SRR5950313	PRJNA398089	SRR5946713	human_gut
+HSMA33SI	PRJNA398089	SRR5950314	PRJNA398089	SRR5946712	human_gut
+MSMB4LZX	PRJNA398089	SRR5950315	PRJNA398089	SRR5946711	human_gut
+HSMA33Q6	PRJNA398089	SRR5950316	PRJNA398089	SRR5946886	human_gut
+PSMA26A3	PRJNA398089	SRR5950317	PRJNA398089	SRR5946890	human_gut
+PSMB4MC7	PRJNA398089	SRR5950318	PRJNA398089	SRR5946633	human_gut
+PSMB4MBS	PRJNA398089	SRR5950319	PRJNA398089	SRR5946634	human_gut
+HSMA33IC	PRJNA398089	SRR5950320	PRJNA398089	SRR5946809	human_gut
+CSM9X1Z4	PRJNA398089	SRR5950321	PRJNA398089	SRR5950616	human_gut
+HSMA33SG	PRJNA398089	SRR5950322	PRJNA398089	SRR5946640	human_gut
+HSMA33KE	PRJNA398089	SRR5950323	PRJNA398089	SRR5946807	human_gut
+HSMA33JR	PRJNA398089	SRR5950324	PRJNA398089	SRR5946678	human_gut
+PSMA2668	PRJNA398089	SRR5950325	PRJNA398089	SRR5946677	human_gut
+HSMA33J3	PRJNA398089	SRR5950326	PRJNA398089	SRR5946931	human_gut
+HSMA33IK	PRJNA398089	SRR5950327	PRJNA398089	SRR5946932	human_gut
+HSMA33OZ	PRJNA398089	SRR5950328	PRJNA398089	SRR5947016	human_gut
+MSMA26DM	PRJNA398089	SRR5950329	PRJNA398089	SRR5947017	human_gut
+PSMA265L	PRJNA398089	SRR5950330	PRJNA398089	SRR5946676	human_gut
+MSM9VZP3	PRJNA398089	SRR5950331	PRJNA398089	SRR5946679	human_gut
+CSM9X1Y3	PRJNA398089	SRR5950332	PRJNA398089	SRR5950580	human_gut
+MSM9VZJB	PRJNA398089	SRR5950333	PRJNA398089	SRR5947020	human_gut
+MSMA267V	PRJNA398089	SRR5950334	PRJNA398089	SRR5947018	human_gut
+MSM9VZKI	PRJNA398089	SRR5950335	PRJNA398089	SRR5947019	human_gut
+CSMA9J65	PRJNA398089	SRR5950336	PRJNA398089	SRR5950645	human_gut
+MSM9VZLP	PRJNA398089	SRR5950337	PRJNA398089	SRR5935978	human_gut
+HSM7J4K8	PRJNA398089	SRR5950338	PRJNA398089	SRR5936144	human_gut
+CSM7KOUL	PRJNA398089	SRR5950339	PRJNA398089	SRR5950650	human_gut
+HSM7J4N6	PRJNA398089	SRR5950340	PRJNA398089	SRR5936145	human_gut
+PSM7J12R	PRJNA398089	SRR5950341	PRJNA398089	SRR5936146	human_gut
+MSM9VZF3	PRJNA398089	SRR5950342	PRJNA398089	SRR5935923	human_gut
+PSM7J15W	PRJNA398089	SRR5950343	PRJNA398089	SRR5935921	human_gut
+PSM7J14L	PRJNA398089	SRR5950344	PRJNA398089	SRR5935920	human_gut
+MSM9VZFF	PRJNA398089	SRR5950345	PRJNA398089	SRR5936143	human_gut
+MSM9VZOQ	PRJNA398089	SRR5950346	PRJNA398089	SRR5946808	human_gut
+MSM9VZLT	PRJNA398089	SRR5950347	PRJNA398089	SRR5946929	human_gut
+MSMA26BX	PRJNA398089	SRR5950348	PRJNA398089	SRR5946834	human_gut
+MSMAPC7J	PRJNA398089	SRR5950349	PRJNA398089	SRR5946831	human_gut
+MSMAPC6A	PRJNA398089	SRR5950350	PRJNA398089	SRR5946833	human_gut
+PSMA269W	PRJNA398089	SRR5950351	PRJNA398089	SRR5946835	human_gut
+MSMAPC7R	PRJNA398089	SRR5950352	PRJNA398089	SRR5946829	human_gut
+CSM9X235	PRJNA398089	SRR5950353	PRJNA398089	SRR5950595	human_gut
+HSMA33M2	PRJNA398089	SRR5950354	PRJNA398089	SRR5946830	human_gut
+CSM9X22U	PRJNA398089	SRR5950355	PRJNA398089	SRR5950591	human_gut
+HSMA33RX	PRJNA398089	SRR5950356	PRJNA398089	SRR5946705	human_gut
+MSMB4LYB	PRJNA398089	SRR5950357	PRJNA398089	SRR5946706	human_gut
+HSMA33R5	PRJNA398089	SRR5950358	PRJNA398089	SRR5946827	human_gut
+HSMA33QO	PRJNA398089	SRR5950359	PRJNA398089	SRR5946828	human_gut
+MSMB4LZK	PRJNA398089	SRR5950360	PRJNA398089	SRR5947057	human_gut
+MSM9VZIY	PRJNA398089	SRR5950361	PRJNA398089	SRR5947023	human_gut
+MSM9VZHJ	PRJNA398089	SRR5950362	PRJNA398089	SRR5947022	human_gut
+PSMA266I	PRJNA398089	SRR5950363	PRJNA398089	SRR5946813	human_gut
+MSM9VZHB	PRJNA398089	SRR5950364	PRJNA398089	SRR5946803	human_gut
+PSMA264U	PRJNA398089	SRR5950365	PRJNA398089	SRR5946804	human_gut
+HSMA33JD	PRJNA398089	SRR5950366	PRJNA398089	SRR5946805	human_gut
+MSM9VZP1	PRJNA398089	SRR5950367	PRJNA398089	SRR5947021	human_gut
+MSM9VZIM	PRJNA398089	SRR5950368	PRJNA398089	SRR5947025	human_gut
+HSMA33J5	PRJNA398089	SRR5950369	PRJNA398089	SRR5947024	human_gut
+MSM9VZLB	PRJNA398089	SRR5950370	PRJNA398089	SRR5946905	human_gut
+PSM7J15O	PRJNA398089	SRR5950371	PRJNA398089	SRR5935836	human_gut
+PSM7J14N	PRJNA398089	SRR5950372	PRJNA398089	SRR5935878	human_gut
+HSMA33NA	PRJNA398089	SRR5950373	PRJNA398089	SRR5936149	human_gut
+MSM9VZES	PRJNA398089	SRR5950374	PRJNA398089	SRR5936148	human_gut
+MSM79H7G	PRJNA398089	SRR5950375	PRJNA398089	SRR5936152	human_gut
+PSM7J13M	PRJNA398089	SRR5950376	PRJNA398089	SRR5936151	human_gut
+CSM9X1XU	PRJNA398089	SRR5950377	PRJNA398089	SRR5950643	human_gut
+HSM7J4KK	PRJNA398089	SRR5950378	PRJNA398089	SRR5935848	human_gut
+MSM9VZPH	PRJNA398089	SRR5950379	PRJNA398089	SRR5935845	human_gut
+CSM7KOTS	PRJNA398089	SRR5950380	PRJNA398089	SRR5950688	human_gut
+PSMA265F	PRJNA398089	SRR5950381	PRJNA398089	SRR5946806	human_gut
+HSMA33LB	PRJNA398089	SRR5950382	PRJNA398089	SRR5947067	human_gut
+MSMA26AX	PRJNA398089	SRR5950383	PRJNA398089	SRR5947066	human_gut
+MSM9VZHF	PRJNA398089	SRR5950384	PRJNA398089	SRR5946895	human_gut
+PSMA265H	PRJNA398089	SRR5950385	PRJNA398089	SRR5946896	human_gut
+HSMA33KU	PRJNA398089	SRR5950386	PRJNA398089	SRR5946900	human_gut
+PSMA265B	PRJNA398089	SRR5950387	PRJNA398089	SRR5946901	human_gut
+PSMA265T	PRJNA398089	SRR5950388	PRJNA398089	SRR5946897	human_gut
+PSMA266M	PRJNA398089	SRR5950389	PRJNA398089	SRR5946899	human_gut
+MSM9VZL9	PRJNA398089	SRR5950390	PRJNA398089	SRR5946923	human_gut
+PSMA267J	PRJNA398089	SRR5950391	PRJNA398089	SRR5947065	human_gut
+MSMA26EJ	PRJNA398089	SRR5950392	PRJNA398089	SRR5947064	human_gut
+HSMA33MZ	PRJNA398089	SRR5950393	PRJNA398089	SRR5946963	human_gut
+MSM9VZNL	PRJNA398089	SRR5950394	PRJNA398089	SRR5946966	human_gut
+PSMA266U	PRJNA398089	SRR5950395	PRJNA398089	SRR5946810	human_gut
+PSM7J13E	PRJNA398089	SRR5950396	PRJNA398089	SRR5935824	human_gut
+PSM7J141	PRJNA398089	SRR5950397	PRJNA398089	SRR5935823	human_gut
+MSM9VZOG	PRJNA398089	SRR5950398	PRJNA398089	SRR5935849	human_gut
+MSM9VZF5	PRJNA398089	SRR5950399	PRJNA398089	SRR5935898	human_gut
+CSM7KOUN	PRJNA398089	SRR5950400	PRJNA398089	SRR5950694	human_gut
+HSM7J4NU	PRJNA398089	SRR5950401	PRJNA398089	SRR5946964	human_gut
+HSM7J4KA	PRJNA398089	SRR5950402	PRJNA398089	SRR5935821	human_gut
+PSM7J16Y	PRJNA398089	SRR5950403	PRJNA398089	SRR5935820	human_gut
+HSMA33JB	PRJNA398089	SRR5950404	PRJNA398089	SRR5946928	human_gut
+MSM9VZOS	PRJNA398089	SRR5950405	PRJNA398089	SRR5946927	human_gut
+MSMA26EH	PRJNA398089	SRR5950406	PRJNA398089	SRR5946655	human_gut
+MSM9VZHN	PRJNA398089	SRR5950407	PRJNA398089	SRR5946670	human_gut
+HSMA33MA	PRJNA398089	SRR5950408	PRJNA398089	SRR5946906	human_gut
+MSM9VZJ3	PRJNA398089	SRR5950409	PRJNA398089	SRR5946902	human_gut
+MSM9VZHX	PRJNA398089	SRR5950410	PRJNA398089	SRR5946672	human_gut
+PSMA263W	PRJNA398089	SRR5950411	PRJNA398089	SRR5946673	human_gut
+PSMA265J	PRJNA398089	SRR5950412	PRJNA398089	SRR5946610	human_gut
+HSMA33OJ	PRJNA398089	SRR5950413	PRJNA398089	SRR5946675	human_gut
+HSMA33OV	PRJNA398089	SRR5950414	PRJNA398089	SRR5946739	human_gut
+PSMA266Y	PRJNA398089	SRR5950415	PRJNA398089	SRR5946904	human_gut
+MSM9VZIQ	PRJNA398089	SRR5950416	PRJNA398089	SRR5946903	human_gut
+PSM7J14P	PRJNA398089	SRR5950417	PRJNA398089	SRR5946859	human_gut
+HSMA33IE	PRJNA398089	SRR5950418	PRJNA398089	SRR5946860	human_gut
+PSM7J154	PRJNA398089	SRR5950419	PRJNA398089	SRR5946861	human_gut
+MSM9VZLJ	PRJNA398089	SRR5950420	PRJNA398089	SRR5946971	human_gut
+HSMA33NO	PRJNA398089	SRR5950421	PRJNA398089	SRR5946972	human_gut
+MSM9VZOY	PRJNA398089	SRR5950422	PRJNA398089	SRR5946968	human_gut
+MSM9VZMU	PRJNA398089	SRR5950423	PRJNA398089	SRR5946969	human_gut
+PSM7J15Q	PRJNA398089	SRR5950424	PRJNA398089	SRR5946970	human_gut
+CSM7KORG	PRJNA398089	SRR5950425	PRJNA398089	SRR5950750	human_gut
+MSM7J16J	PRJNA398089	SRR5950426	PRJNA398089	SRR5946965	human_gut
+PSM7J15A	PRJNA398089	SRR5950427	PRJNA398089	SRR5935922	human_gut
+MSM79H8L	PRJNA398089	SRR5950428	PRJNA398089	SRR5935924	human_gut
+MSMB4LZ4	PRJNA398089	SRR5950429	PRJNA398089	SRR5946638	human_gut
+CSM7KOTQ	PRJNA398089	SRR5950430	PRJNA398089	SRR5950604	human_gut
+PSM7J14X	PRJNA398089	SRR5950431	PRJNA398089	SRR5935771	human_gut
+HSM7J4OP	PRJNA398089	SRR5950432	PRJNA398089	SRR5935927	human_gut
+HSM7J4NS	PRJNA398089	SRR5950433	PRJNA398089	SRR5935925	human_gut
+CSM7KORK	PRJNA398089	SRR5950434	PRJNA398089	SRR5950600	human_gut
+MSM9VZFR	PRJNA398089	SRR5950435	PRJNA398089	SRR5935929	human_gut
+HSM7J4OE	PRJNA398089	SRR5950436	PRJNA398089	SRR5935928	human_gut
+MSM9VZLN	PRJNA398089	SRR5950437	PRJNA398089	SRR5935926	human_gut
+CSM9X1ZC	PRJNA398089	SRR5950438	PRJNA398089	SRR5950786	human_gut
+MSMA26DO	PRJNA398089	SRR5950439	PRJNA398089	SRR5946955	human_gut
+HSMA33MG	PRJNA398089	SRR5950440	PRJNA398089	SRR5946956	human_gut
+HSMA33L1	PRJNA398089	SRR5950441	PRJNA398089	SRR5946960	human_gut
+MSM9VZIU	PRJNA398089	SRR5950442	PRJNA398089	SRR5946961	human_gut
+MSMA26ET	PRJNA398089	SRR5950443	PRJNA398089	SRR5946962	human_gut
+HSMA33MS	PRJNA398089	SRR5950444	PRJNA398089	SRR5946959	human_gut
+MSM9VZHT	PRJNA398089	SRR5950445	PRJNA398089	SRR5946952	human_gut
+PSMA2675	PRJNA398089	SRR5950446	PRJNA398089	SRR5946953	human_gut
+HSMA33PL	PRJNA398089	SRR5950447	PRJNA398089	SRR5946721	human_gut
+MSM9VZPL	PRJNA398089	SRR5950448	PRJNA398089	SRR5946856	human_gut
+CSMAG78W	PRJNA398089	SRR5950449	PRJNA398089	SRR5950490	human_gut
+HSM7J4O9	PRJNA398089	SRR5950450	PRJNA398089	SRR5946857	human_gut
+PSM7J161	PRJNA398089	SRR5950451	PRJNA398089	SRR5946864	human_gut
+HSM7J4OT	PRJNA398089	SRR5950452	PRJNA398089	SRR5946863	human_gut
+MSM9VZOK	PRJNA398089	SRR5950453	PRJNA398089	SRR5946866	human_gut
+MSM9VZNX	PRJNA398089	SRR5950454	PRJNA398089	SRR5946862	human_gut
+CSM7KOTU	PRJNA398089	SRR5950455	PRJNA398089	SRR5950754	human_gut
+CSM7KOTK	PRJNA398089	SRR5950456	PRJNA398089	SRR5950760	human_gut
+CSM7KOOF	PRJNA398089	SRR5950457	PRJNA398089	SRR5950761	human_gut
+MSMA26DI	PRJNA398089	SRR5950458	PRJNA398089	SRR5946958	human_gut
+PSMA266Q	PRJNA398089	SRR5950459	PRJNA398089	SRR5946957	human_gut
+CSM9X21J	PRJNA398089	SRR5950460	PRJNA398089	SRR5950788	human_gut
+MSMA26BB	PRJNA398089	SRR5950461	PRJNA398089	SRR5947072	human_gut
+HSMA33NQ	PRJNA398089	SRR5950462	PRJNA398089	SRR5947076	human_gut
+MSMA26EL	PRJNA398089	SRR5950463	PRJNA398089	SRR5947073	human_gut
+MSMA26AZ	PRJNA398089	SRR5950464	PRJNA398089	SRR5947071	human_gut
+HSMA33ME	PRJNA398089	SRR5950465	PRJNA398089	SRR5947068	human_gut
+CSM9X21T	PRJNA398089	SRR5950466	PRJNA398089	SRR5950655	human_gut
+MSM9VZGY	PRJNA398089	SRR5950467	PRJNA398089	SRR5947069	human_gut
+MSM9VZI2	PRJNA398089	SRR5950468	PRJNA398089	SRR5947070	human_gut
+CSM9X213	PRJNA398089	SRR5950469	PRJNA398089	SRR5950619	human_gut
+MSM9VZLV	PRJNA398089	SRR5950470	PRJNA398089	SRR5947082	human_gut
+PSM7J171	PRJNA398089	SRR5963912	PRJNA398089	SRR5946967	human_gut
+PSM6XBVI	PRJNA398089	SRR5963913	PRJNA398089	SRR5936034	human_gut
+PSM7J12D	PRJNA398089	SRR5963914	PRJNA398089	SRR5936150	human_gut
+PSM6XBSO	PRJNA398089	SRR5963915	PRJNA398089	SRR5936032	human_gut
+PSM6XBT3	PRJNA398089	SRR5963916	PRJNA398089	SRR5936057	human_gut
+PSM6XBSI	PRJNA398089	SRR5963917	PRJNA398089	SRR5936074	human_gut
+PSM6XBSM	PRJNA398089	SRR5963918	PRJNA398089	SRR5950713	human_gut
+MSM79HDQ_TR	PRJNA398089	SRR5963920	PRJNA398089	SRR5962901	human_gut
+MSM79HDG_TR	PRJNA398089	SRR5963921	PRJNA398089	SRR5962900	human_gut
+MSM9VZEK_TR	PRJNA398089	SRR5963922	PRJNA398089	SRR5962903	human_gut
+MSM9VZMA_TR	PRJNA398089	SRR5963923	PRJNA398089	SRR5962902	human_gut
+PSMA265J_TR	PRJNA398089	SRR5963924	PRJNA398089	SRR5962904	human_gut
+MSMA26AZ_TR	PRJNA398089	SRR5963925	PRJNA398089	SRR5962908	human_gut
+HSMA33LH_TR	PRJNA398089	SRR5963926	PRJNA398089	SRR5962907	human_gut
+MSM9VZNH_TR	PRJNA398089	SRR5963927	PRJNA398089	SRR5962906	human_gut
+HSMA33RX_TR	PRJNA398089	SRR5963928	PRJNA398089	SRR5962885	human_gut
+PSM6XBQY_TR	PRJNA398089	SRR5963929	PRJNA398089	SRR5962895	human_gut
+CSM79HLA_TR	PRJNA398089	SRR5963930	PRJNA398089	SRR5962894	human_gut
+HSM6XRVC_TR	PRJNA398089	SRR5963931	PRJNA398089	SRR5962893	human_gut
+HSM5MD6A_TR	PRJNA398089	SRR5963932	PRJNA398089	SRR5962891	human_gut
+PSM6XBRK_TR	PRJNA398089	SRR5963933	PRJNA398089	SRR5962890	human_gut
+CSM67UEW_TR	PRJNA398089	SRR5963934	PRJNA398089	SRR5962889	human_gut
+HSM67VEM_TR	PRJNA398089	SRR5963935	PRJNA398089	SRR5962892	human_gut
+CSM67UDR_TR	PRJNA398089	SRR5963936	PRJNA398089	SRR5962888	human_gut
+PSM6XBSU_TR	PRJNA398089	SRR5963937	PRJNA398089	SRR5962897	human_gut
+MSM79HF9_TR	PRJNA398089	SRR5963938	PRJNA398089	SRR5962898	human_gut
+PSM6XBRK	PRJNA398089	SRR5963939	PRJNA398089	SRR5935960	human_gut
+PSM6XBQY	PRJNA398089	SRR5963940	PRJNA398089	SRR5935809	human_gut
+MSMA26EP	PRJNA398089	SRR5963941	PRJNA398089	SRR5946720	human_gut
+MSM9VZOW	PRJNA398089	SRR5963942	PRJNA398089	SRR5946733	human_gut
+PSM6XBQU	PRJNA398089	SRR5963943	PRJNA398089	SRR5936007	human_gut
+MSMAPC5Z	PRJNA398089	SRR5963944	PRJNA398089	SRR5946832	human_gut
+MSM6J2M3	PRJNA398089	SRR5963945	PRJNA398089	SRR5935963	human_gut
+MSM6J2K6	PRJNA398089	SRR5963946	PRJNA398089	SRR5935938	human_gut
+MSM6J2Q1	PRJNA398089	SRR5963947	PRJNA398089	SRR5936013	human_gut
+MSM6J2PS	PRJNA398089	SRR5963948	PRJNA398089	SRR5936231	human_gut
+Amar_Carlsberg-38I-DV129-2-N2	PRJNA632343	SRR11781625	PRJNA632343	SRR11781636	snail_gut
+Amar_Carlsberg-38I-DV131-6-Intestine	PRJNA632343	SRR11781640	PRJNA632343	SRR11781639	snail_gut
+Amar_Carlsberg-38I-DV129-15-Intestine	PRJNA632343	SRR11781643	PRJNA632343	SRR11781642	snail_gut
+Amar_Carlsberg-38I-DV129-5-Intestine	PRJNA632343	SRR11781646	PRJNA632343	SRR11781645	snail_gut
+BATS_256_C3_1B	PRJNA242360	SRR1230757	PRJNA242360	SRR1230754	ocean
+BATS_261_C2_B2	PRJNA242360	SRR1230758	PRJNA242360	SRR1230755	ocean
+BATS_261_C8_F2	PRJNA242360	SRR1230759	PRJNA242360	SRR1230756	ocean
+BATS_256_C10_5A	PRJNA242360	SRR1238005	PRJNA242360	SRR1230729	ocean
+ES_08072017_CAT2012July	PRJEB12234	ERR2088997	PRJEB12234	ERR2094669	ocean
+ES_08072017_CAT2012October	PRJEB12234	ERR2088998	PRJEB12234	ERR2094670	ocean
+ES_08072017_CAT2013January	PRJEB12234	ERR2088999	PRJEB12234	ERR2094671	ocean
+ES_08072017_CAT2013April	PRJEB12234	ERR2089000	PRJEB12234	ERR2094672	ocean
+ES_08072017_POLA2012July	PRJEB12234	ERR2089001	PRJEB12234	ERR2094673	ocean
+ES_08072017_POLA2012October	PRJEB12234	ERR2089002	PRJEB12234	ERR2094674	ocean
+ES_08072017_POLA2013January	PRJEB12234	ERR2089003	PRJEB12234	ERR2094675	ocean
+ES_08072017_POLA2013April	PRJEB12234	ERR2089004	PRJEB12234	ERR2094676	ocean
+ES_08072017_SPOT2012July	PRJEB12234	ERR2089005	PRJEB12234	ERR2094677	ocean
+ES_08072017_SPOT2012October	PRJEB12234	ERR2089006	PRJEB12234	ERR2094678	ocean
+ES_08072017_SPOT2013January	PRJEB12234	ERR2089007	PRJEB12234	ERR2094679	ocean
+ES_08072017_SPOT2013April	PRJEB12234	ERR2089008	PRJEB12234	ERR2094680	ocean
+ES_08072017_neg_reads	PRJEB12234	ERR2089009	PRJEB12234	ERR2097133	ocean
+E2A	PRJNA340003	SRR4342131	PRJNA340003	SRR4342135	ocean
+E4	PRJNA340003	SRR4342132	PRJNA340003	SRR4342136	ocean
+D1	PRJNA340003	SRR4342137	PRJNA340003	SRR4342129	ocean
+D2	PRJNA340003	SRR4342138	PRJNA340003	SRR4342130	ocean
+D3	PRJNA340003	SRR4342139	PRJNA340003	SRR4342133	ocean
+E2	PRJNA340003	SRR4342140	PRJNA340003	SRR4342134	ocean
diff --git a/inputs/metadata-parse-paired-mgx-mtx.ipynb b/inputs/metadata-parse-paired-mgx-mtx.ipynb
new file mode 100644
index 0000000..3d17930
--- /dev/null
+++ b/inputs/metadata-parse-paired-mgx-mtx.ipynb
@@ -0,0 +1,5114 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "3910cfa9",
+   "metadata": {},
+   "source": [
+    "# Generate a metadata table specifying paired metagenomes and metatranscriptomes from diverse biomes using publicly available data\n",
+    "\n",
+    "This notebook processes metadata associated with paired metagenome and metatranscriptome samples. \n",
+    "When possible, the ENA BioProject pages were parsed to determine sample pairs.\n",
+    "This was done programmatically using the following URL (with more metadata fields specified) which uses the ENA API to resolve a TSV for each run in a specified bioproject.\n",
+    "\n",
+    "`\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA406858&result=read_run&fields=study_accession,first_created&format=tsv&download=true&limit=0\"`\n",
+    "\n",
+    "\n",
+    "By and large, each project encoded sample identifiers and paired information differently, so each parsing chunk is unique.\n",
+    "Given this, I chose not to create a parsing function.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "6232c715",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "setwd(\"..\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "ca7b2c35",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "library(dplyr)\n",
+    "library(readr)\n",
+    "library(janitor)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3206624e",
+   "metadata": {},
+   "source": [
+    "## PRJNA406858"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "b79e6ec7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna406858 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA406858&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "32481186",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 6 × 3</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>study_accession</th><th scope=col>run_accession</th><th scope=col>library_name</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>PRJNA406858</td><td>SRR6032600</td><td>C_2_cDNA_1</td></tr>\n",
+       "\t<tr><td>PRJNA406858</td><td>SRR6032601</td><td>B_2_1     </td></tr>\n",
+       "\t<tr><td>PRJNA406858</td><td>SRR6032602</td><td>C_2_1     </td></tr>\n",
+       "\t<tr><td>PRJNA406858</td><td>SRR6032603</td><td>E_2_1     </td></tr>\n",
+       "\t<tr><td>PRJNA406858</td><td>SRR6032604</td><td>B_2_cDNA_1</td></tr>\n",
+       "\t<tr><td>PRJNA406858</td><td>SRR6032605</td><td>E_2_cDNA_1</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 6 × 3\n",
+       "\\begin{tabular}{lll}\n",
+       " study\\_accession & run\\_accession & library\\_name\\\\\n",
+       " <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t PRJNA406858 & SRR6032600 & C\\_2\\_cDNA\\_1\\\\\n",
+       "\t PRJNA406858 & SRR6032601 & B\\_2\\_1     \\\\\n",
+       "\t PRJNA406858 & SRR6032602 & C\\_2\\_1     \\\\\n",
+       "\t PRJNA406858 & SRR6032603 & E\\_2\\_1     \\\\\n",
+       "\t PRJNA406858 & SRR6032604 & B\\_2\\_cDNA\\_1\\\\\n",
+       "\t PRJNA406858 & SRR6032605 & E\\_2\\_cDNA\\_1\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 6 × 3\n",
+       "\n",
+       "| study_accession &lt;chr&gt; | run_accession &lt;chr&gt; | library_name &lt;chr&gt; |\n",
+       "|---|---|---|\n",
+       "| PRJNA406858 | SRR6032600 | C_2_cDNA_1 |\n",
+       "| PRJNA406858 | SRR6032601 | B_2_1      |\n",
+       "| PRJNA406858 | SRR6032602 | C_2_1      |\n",
+       "| PRJNA406858 | SRR6032603 | E_2_1      |\n",
+       "| PRJNA406858 | SRR6032604 | B_2_cDNA_1 |\n",
+       "| PRJNA406858 | SRR6032605 | E_2_cDNA_1 |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  study_accession run_accession library_name\n",
+       "1 PRJNA406858     SRR6032600    C_2_cDNA_1  \n",
+       "2 PRJNA406858     SRR6032601    B_2_1       \n",
+       "3 PRJNA406858     SRR6032602    C_2_1       \n",
+       "4 PRJNA406858     SRR6032603    E_2_1       \n",
+       "5 PRJNA406858     SRR6032604    B_2_cDNA_1  \n",
+       "6 PRJNA406858     SRR6032605    E_2_cDNA_1  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna406858 <- prjna406858 %>% \n",
+    "  arrange(sample_alias) %>%\n",
+    "  select(study_accession, run_accession, library_name)\n",
+    "\n",
+    "head(prjna406858)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "998e512d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna406858 <- prjna406858 %>%\n",
+    "  mutate(sample_name = gsub(\"_cDNA\", \"\", library_name))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "59810eff",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 3 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>C_2_1</td><td>PRJNA406858</td><td>SRR6032600</td><td>PRJNA406858</td><td>SRR6032602</td><td>activated_sludge</td></tr>\n",
+       "\t<tr><td>B_2_1</td><td>PRJNA406858</td><td>SRR6032604</td><td>PRJNA406858</td><td>SRR6032601</td><td>activated_sludge</td></tr>\n",
+       "\t<tr><td>E_2_1</td><td>PRJNA406858</td><td>SRR6032605</td><td>PRJNA406858</td><td>SRR6032603</td><td>activated_sludge</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 3 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t C\\_2\\_1 & PRJNA406858 & SRR6032600 & PRJNA406858 & SRR6032602 & activated\\_sludge\\\\\n",
+       "\t B\\_2\\_1 & PRJNA406858 & SRR6032604 & PRJNA406858 & SRR6032601 & activated\\_sludge\\\\\n",
+       "\t E\\_2\\_1 & PRJNA406858 & SRR6032605 & PRJNA406858 & SRR6032603 & activated\\_sludge\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 3 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| C_2_1 | PRJNA406858 | SRR6032600 | PRJNA406858 | SRR6032602 | activated_sludge |\n",
+       "| B_2_1 | PRJNA406858 | SRR6032604 | PRJNA406858 | SRR6032601 | activated_sludge |\n",
+       "| E_2_1 | PRJNA406858 | SRR6032605 | PRJNA406858 | SRR6032603 | activated_sludge |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  sample_name mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1 C_2_1       PRJNA406858         SRR6032600        PRJNA406858        \n",
+       "2 B_2_1       PRJNA406858         SRR6032604        PRJNA406858        \n",
+       "3 E_2_1       PRJNA406858         SRR6032605        PRJNA406858        \n",
+       "  mgx_run_accession sample_type     \n",
+       "1 SRR6032602        activated_sludge\n",
+       "2 SRR6032601        activated_sludge\n",
+       "3 SRR6032603        activated_sludge"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna406858_mtx <- prjna406858 %>%\n",
+    "  filter(grepl(\"cDNA\", library_name)) %>%\n",
+    "  select(sample_name,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna406858_mgx <- prjna406858 %>%\n",
+    "  filter(!grepl(\"cDNA\", library_name)) %>%\n",
+    "  select(mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession, \n",
+    "         sample_name)\n",
+    "\n",
+    "prjna406858_mtx_vs_mgx <- left_join(prjna406858_mtx, prjna406858_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"activated_sludge\")\n",
+    "\n",
+    "prjna406858_mtx_vs_mgx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "efa62e72",
+   "metadata": {},
+   "source": [
+    "## PRJNA448333"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "ab5a6d12",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna448333 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA448333&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "3a4dec6c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 6 × 4</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>study_accession</th><th scope=col>run_accession</th><th scope=col>library_name</th><th scope=col>sample_alias</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>PRJNA448333</td><td>SRR8397906</td><td>Metagenome 101                       </td><td>Rumen microbiome of beef cattle 101</td></tr>\n",
+       "\t<tr><td>PRJNA448333</td><td>SRR8399431</td><td>Total-RNA-based metatranscriptome 101</td><td>Rumen microbiome of beef cattle 101</td></tr>\n",
+       "\t<tr><td>PRJNA448333</td><td>SRR8416057</td><td>mRNA-enriched metatranscriptome 101  </td><td>Rumen microbiome of beef cattle 101</td></tr>\n",
+       "\t<tr><td>PRJNA448333</td><td>SRR8404214</td><td>Metagenome 103                       </td><td>Rumen microbiome of beef cattle 103</td></tr>\n",
+       "\t<tr><td>PRJNA448333</td><td>SRR8416058</td><td>mRNA-enriched metatranscriptome 103  </td><td>Rumen microbiome of beef cattle 103</td></tr>\n",
+       "\t<tr><td>PRJNA448333</td><td>SRR8420492</td><td>Total-RNA-based metatranscriptome 103</td><td>Rumen microbiome of beef cattle 103</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 6 × 4\n",
+       "\\begin{tabular}{llll}\n",
+       " study\\_accession & run\\_accession & library\\_name & sample\\_alias\\\\\n",
+       " <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t PRJNA448333 & SRR8397906 & Metagenome 101                        & Rumen microbiome of beef cattle 101\\\\\n",
+       "\t PRJNA448333 & SRR8399431 & Total-RNA-based metatranscriptome 101 & Rumen microbiome of beef cattle 101\\\\\n",
+       "\t PRJNA448333 & SRR8416057 & mRNA-enriched metatranscriptome 101   & Rumen microbiome of beef cattle 101\\\\\n",
+       "\t PRJNA448333 & SRR8404214 & Metagenome 103                        & Rumen microbiome of beef cattle 103\\\\\n",
+       "\t PRJNA448333 & SRR8416058 & mRNA-enriched metatranscriptome 103   & Rumen microbiome of beef cattle 103\\\\\n",
+       "\t PRJNA448333 & SRR8420492 & Total-RNA-based metatranscriptome 103 & Rumen microbiome of beef cattle 103\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 6 × 4\n",
+       "\n",
+       "| study_accession &lt;chr&gt; | run_accession &lt;chr&gt; | library_name &lt;chr&gt; | sample_alias &lt;chr&gt; |\n",
+       "|---|---|---|---|\n",
+       "| PRJNA448333 | SRR8397906 | Metagenome 101                        | Rumen microbiome of beef cattle 101 |\n",
+       "| PRJNA448333 | SRR8399431 | Total-RNA-based metatranscriptome 101 | Rumen microbiome of beef cattle 101 |\n",
+       "| PRJNA448333 | SRR8416057 | mRNA-enriched metatranscriptome 101   | Rumen microbiome of beef cattle 101 |\n",
+       "| PRJNA448333 | SRR8404214 | Metagenome 103                        | Rumen microbiome of beef cattle 103 |\n",
+       "| PRJNA448333 | SRR8416058 | mRNA-enriched metatranscriptome 103   | Rumen microbiome of beef cattle 103 |\n",
+       "| PRJNA448333 | SRR8420492 | Total-RNA-based metatranscriptome 103 | Rumen microbiome of beef cattle 103 |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  study_accession run_accession library_name                         \n",
+       "1 PRJNA448333     SRR8397906    Metagenome 101                       \n",
+       "2 PRJNA448333     SRR8399431    Total-RNA-based metatranscriptome 101\n",
+       "3 PRJNA448333     SRR8416057    mRNA-enriched metatranscriptome 101  \n",
+       "4 PRJNA448333     SRR8404214    Metagenome 103                       \n",
+       "5 PRJNA448333     SRR8416058    mRNA-enriched metatranscriptome 103  \n",
+       "6 PRJNA448333     SRR8420492    Total-RNA-based metatranscriptome 103\n",
+       "  sample_alias                       \n",
+       "1 Rumen microbiome of beef cattle 101\n",
+       "2 Rumen microbiome of beef cattle 101\n",
+       "3 Rumen microbiome of beef cattle 101\n",
+       "4 Rumen microbiome of beef cattle 103\n",
+       "5 Rumen microbiome of beef cattle 103\n",
+       "6 Rumen microbiome of beef cattle 103"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna448333 <- prjna448333 %>% \n",
+    "  arrange(sample_alias) %>%\n",
+    "  select(study_accession, run_accession, library_name, sample_alias)\n",
+    "\n",
+    "head(prjna448333)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6cc53500",
+   "metadata": {},
+   "source": [
+    "PRJNA448333 has total RNA and mRNA-enriched RNA metatranscriptomes. I included mRNA-enriched samples as these likely contain more of the sequences we're interested in."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "535d6fcf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna448333_mtx <- prjna448333 %>% \n",
+    "  filter(grepl(\"mRNA-enriched\", library_name)) %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna448333_mgx <- prjna448333 %>% \n",
+    "  filter(grepl(\"Metagenome\", library_name)) %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "958b2644",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna448333_mtx_vs_mgx <- left_join(prjna448333_mtx, prjna448333_mgx, by = c(\"sample_name\")) %>%\n",
+    "  mutate(sample_name = make_clean_names(sample_name),\n",
+    "         sample_type = \"cattle_rumen\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "3da0c395",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 48 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_101</td><td>PRJNA448333</td><td>SRR8416057</td><td>PRJNA448333</td><td>SRR8397906</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_103</td><td>PRJNA448333</td><td>SRR8416058</td><td>PRJNA448333</td><td>SRR8404214</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_104</td><td>PRJNA448333</td><td>SRR8416055</td><td>PRJNA448333</td><td>SRR8397905</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_105</td><td>PRJNA448333</td><td>SRR8416056</td><td>PRJNA448333</td><td>SRR8397904</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_106</td><td>PRJNA448333</td><td>SRR8416061</td><td>PRJNA448333</td><td>SRR8397903</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_107</td><td>PRJNA448333</td><td>SRR8416062</td><td>PRJNA448333</td><td>SRR8397910</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_112</td><td>PRJNA448333</td><td>SRR8416059</td><td>PRJNA448333</td><td>SRR8397909</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_201</td><td>PRJNA448333</td><td>SRR8416060</td><td>PRJNA448333</td><td>SRR8397908</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_202</td><td>PRJNA448333</td><td>SRR8416064</td><td>PRJNA448333</td><td>SRR8397907</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_203</td><td>PRJNA448333</td><td>SRR8416065</td><td>PRJNA448333</td><td>SRR8397902</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_205</td><td>PRJNA448333</td><td>SRR8416069</td><td>PRJNA448333</td><td>SRR8397901</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_206</td><td>PRJNA448333</td><td>SRR8416070</td><td>PRJNA448333</td><td>SRR8397884</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_207</td><td>PRJNA448333</td><td>SRR8416067</td><td>PRJNA448333</td><td>SRR8397883</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_208</td><td>PRJNA448333</td><td>SRR8416068</td><td>PRJNA448333</td><td>SRR8397886</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_209</td><td>PRJNA448333</td><td>SRR8416073</td><td>PRJNA448333</td><td>SRR8397885</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_210</td><td>PRJNA448333</td><td>SRR8416074</td><td>PRJNA448333</td><td>SRR8397888</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_301</td><td>PRJNA448333</td><td>SRR8416071</td><td>PRJNA448333</td><td>SRR8397887</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_302</td><td>PRJNA448333</td><td>SRR8416072</td><td>PRJNA448333</td><td>SRR8397890</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_303</td><td>PRJNA448333</td><td>SRR8416075</td><td>PRJNA448333</td><td>SRR8397889</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_304</td><td>PRJNA448333</td><td>SRR8416076</td><td>PRJNA448333</td><td>SRR8397882</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_305</td><td>PRJNA448333</td><td>SRR8416092</td><td>PRJNA448333</td><td>SRR8397881</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_307</td><td>PRJNA448333</td><td>SRR8416091</td><td>PRJNA448333</td><td>SRR8397917</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_308</td><td>PRJNA448333</td><td>SRR8416090</td><td>PRJNA448333</td><td>SRR8397918</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_401</td><td>PRJNA448333</td><td>SRR8416089</td><td>PRJNA448333</td><td>SRR8397919</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_402</td><td>PRJNA448333</td><td>SRR8416096</td><td>PRJNA448333</td><td>SRR8397920</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_403</td><td>PRJNA448333</td><td>SRR8416095</td><td>PRJNA448333</td><td>SRR8397913</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_404</td><td>PRJNA448333</td><td>SRR8416094</td><td>PRJNA448333</td><td>SRR8397914</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_407</td><td>PRJNA448333</td><td>SRR8416093</td><td>PRJNA448333</td><td>SRR8397915</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_501</td><td>PRJNA448333</td><td>SRR8416088</td><td>PRJNA448333</td><td>SRR8397916</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_503</td><td>PRJNA448333</td><td>SRR8416087</td><td>PRJNA448333</td><td>SRR8397911</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_505</td><td>PRJNA448333</td><td>SRR8416102</td><td>PRJNA448333</td><td>SRR8397912</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_506</td><td>PRJNA448333</td><td>SRR8416083</td><td>PRJNA448333</td><td>SRR8397894</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_601</td><td>PRJNA448333</td><td>SRR8416063</td><td>PRJNA448333</td><td>SRR8397893</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_604</td><td>PRJNA448333</td><td>SRR8416066</td><td>PRJNA448333</td><td>SRR8397892</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_608</td><td>PRJNA448333</td><td>SRR8416097</td><td>PRJNA448333</td><td>SRR8397891</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_611</td><td>PRJNA448333</td><td>SRR8416098</td><td>PRJNA448333</td><td>SRR8397898</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_612</td><td>PRJNA448333</td><td>SRR8416099</td><td>PRJNA448333</td><td>SRR8397897</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_701</td><td>PRJNA448333</td><td>SRR8416100</td><td>PRJNA448333</td><td>SRR8397896</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_702</td><td>PRJNA448333</td><td>SRR8416077</td><td>PRJNA448333</td><td>SRR8397895</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_703</td><td>PRJNA448333</td><td>SRR8416078</td><td>PRJNA448333</td><td>SRR8397900</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_704</td><td>PRJNA448333</td><td>SRR8416082</td><td>PRJNA448333</td><td>SRR8397899</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_705</td><td>PRJNA448333</td><td>SRR8416081</td><td>PRJNA448333</td><td>SRR8397926</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_706</td><td>PRJNA448333</td><td>SRR8416086</td><td>PRJNA448333</td><td>SRR8397927</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_707</td><td>PRJNA448333</td><td>SRR8416084</td><td>PRJNA448333</td><td>SRR8397924</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_708</td><td>PRJNA448333</td><td>SRR8416101</td><td>PRJNA448333</td><td>SRR8397925</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_709</td><td>PRJNA448333</td><td>SRR8416085</td><td>PRJNA448333</td><td>SRR8397922</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_710</td><td>PRJNA448333</td><td>SRR8416080</td><td>PRJNA448333</td><td>SRR8397923</td><td>cattle_rumen</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_712</td><td>PRJNA448333</td><td>SRR8416079</td><td>PRJNA448333</td><td>SRR8397921</td><td>cattle_rumen</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 48 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_101 & PRJNA448333 & SRR8416057 & PRJNA448333 & SRR8397906 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_103 & PRJNA448333 & SRR8416058 & PRJNA448333 & SRR8404214 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_104 & PRJNA448333 & SRR8416055 & PRJNA448333 & SRR8397905 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_105 & PRJNA448333 & SRR8416056 & PRJNA448333 & SRR8397904 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_106 & PRJNA448333 & SRR8416061 & PRJNA448333 & SRR8397903 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_107 & PRJNA448333 & SRR8416062 & PRJNA448333 & SRR8397910 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_112 & PRJNA448333 & SRR8416059 & PRJNA448333 & SRR8397909 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_201 & PRJNA448333 & SRR8416060 & PRJNA448333 & SRR8397908 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_202 & PRJNA448333 & SRR8416064 & PRJNA448333 & SRR8397907 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_203 & PRJNA448333 & SRR8416065 & PRJNA448333 & SRR8397902 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_205 & PRJNA448333 & SRR8416069 & PRJNA448333 & SRR8397901 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_206 & PRJNA448333 & SRR8416070 & PRJNA448333 & SRR8397884 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_207 & PRJNA448333 & SRR8416067 & PRJNA448333 & SRR8397883 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_208 & PRJNA448333 & SRR8416068 & PRJNA448333 & SRR8397886 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_209 & PRJNA448333 & SRR8416073 & PRJNA448333 & SRR8397885 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_210 & PRJNA448333 & SRR8416074 & PRJNA448333 & SRR8397888 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_301 & PRJNA448333 & SRR8416071 & PRJNA448333 & SRR8397887 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_302 & PRJNA448333 & SRR8416072 & PRJNA448333 & SRR8397890 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_303 & PRJNA448333 & SRR8416075 & PRJNA448333 & SRR8397889 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_304 & PRJNA448333 & SRR8416076 & PRJNA448333 & SRR8397882 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_305 & PRJNA448333 & SRR8416092 & PRJNA448333 & SRR8397881 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_307 & PRJNA448333 & SRR8416091 & PRJNA448333 & SRR8397917 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_308 & PRJNA448333 & SRR8416090 & PRJNA448333 & SRR8397918 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_401 & PRJNA448333 & SRR8416089 & PRJNA448333 & SRR8397919 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_402 & PRJNA448333 & SRR8416096 & PRJNA448333 & SRR8397920 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_403 & PRJNA448333 & SRR8416095 & PRJNA448333 & SRR8397913 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_404 & PRJNA448333 & SRR8416094 & PRJNA448333 & SRR8397914 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_407 & PRJNA448333 & SRR8416093 & PRJNA448333 & SRR8397915 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_501 & PRJNA448333 & SRR8416088 & PRJNA448333 & SRR8397916 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_503 & PRJNA448333 & SRR8416087 & PRJNA448333 & SRR8397911 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_505 & PRJNA448333 & SRR8416102 & PRJNA448333 & SRR8397912 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_506 & PRJNA448333 & SRR8416083 & PRJNA448333 & SRR8397894 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_601 & PRJNA448333 & SRR8416063 & PRJNA448333 & SRR8397893 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_604 & PRJNA448333 & SRR8416066 & PRJNA448333 & SRR8397892 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_608 & PRJNA448333 & SRR8416097 & PRJNA448333 & SRR8397891 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_611 & PRJNA448333 & SRR8416098 & PRJNA448333 & SRR8397898 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_612 & PRJNA448333 & SRR8416099 & PRJNA448333 & SRR8397897 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_701 & PRJNA448333 & SRR8416100 & PRJNA448333 & SRR8397896 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_702 & PRJNA448333 & SRR8416077 & PRJNA448333 & SRR8397895 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_703 & PRJNA448333 & SRR8416078 & PRJNA448333 & SRR8397900 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_704 & PRJNA448333 & SRR8416082 & PRJNA448333 & SRR8397899 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_705 & PRJNA448333 & SRR8416081 & PRJNA448333 & SRR8397926 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_706 & PRJNA448333 & SRR8416086 & PRJNA448333 & SRR8397927 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_707 & PRJNA448333 & SRR8416084 & PRJNA448333 & SRR8397924 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_708 & PRJNA448333 & SRR8416101 & PRJNA448333 & SRR8397925 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_709 & PRJNA448333 & SRR8416085 & PRJNA448333 & SRR8397922 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_710 & PRJNA448333 & SRR8416080 & PRJNA448333 & SRR8397923 & cattle\\_rumen\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_712 & PRJNA448333 & SRR8416079 & PRJNA448333 & SRR8397921 & cattle\\_rumen\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 48 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| rumen_microbiome_of_beef_cattle_101 | PRJNA448333 | SRR8416057 | PRJNA448333 | SRR8397906 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_103 | PRJNA448333 | SRR8416058 | PRJNA448333 | SRR8404214 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_104 | PRJNA448333 | SRR8416055 | PRJNA448333 | SRR8397905 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_105 | PRJNA448333 | SRR8416056 | PRJNA448333 | SRR8397904 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_106 | PRJNA448333 | SRR8416061 | PRJNA448333 | SRR8397903 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_107 | PRJNA448333 | SRR8416062 | PRJNA448333 | SRR8397910 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_112 | PRJNA448333 | SRR8416059 | PRJNA448333 | SRR8397909 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_201 | PRJNA448333 | SRR8416060 | PRJNA448333 | SRR8397908 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_202 | PRJNA448333 | SRR8416064 | PRJNA448333 | SRR8397907 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_203 | PRJNA448333 | SRR8416065 | PRJNA448333 | SRR8397902 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_205 | PRJNA448333 | SRR8416069 | PRJNA448333 | SRR8397901 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_206 | PRJNA448333 | SRR8416070 | PRJNA448333 | SRR8397884 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_207 | PRJNA448333 | SRR8416067 | PRJNA448333 | SRR8397883 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_208 | PRJNA448333 | SRR8416068 | PRJNA448333 | SRR8397886 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_209 | PRJNA448333 | SRR8416073 | PRJNA448333 | SRR8397885 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_210 | PRJNA448333 | SRR8416074 | PRJNA448333 | SRR8397888 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_301 | PRJNA448333 | SRR8416071 | PRJNA448333 | SRR8397887 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_302 | PRJNA448333 | SRR8416072 | PRJNA448333 | SRR8397890 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_303 | PRJNA448333 | SRR8416075 | PRJNA448333 | SRR8397889 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_304 | PRJNA448333 | SRR8416076 | PRJNA448333 | SRR8397882 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_305 | PRJNA448333 | SRR8416092 | PRJNA448333 | SRR8397881 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_307 | PRJNA448333 | SRR8416091 | PRJNA448333 | SRR8397917 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_308 | PRJNA448333 | SRR8416090 | PRJNA448333 | SRR8397918 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_401 | PRJNA448333 | SRR8416089 | PRJNA448333 | SRR8397919 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_402 | PRJNA448333 | SRR8416096 | PRJNA448333 | SRR8397920 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_403 | PRJNA448333 | SRR8416095 | PRJNA448333 | SRR8397913 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_404 | PRJNA448333 | SRR8416094 | PRJNA448333 | SRR8397914 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_407 | PRJNA448333 | SRR8416093 | PRJNA448333 | SRR8397915 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_501 | PRJNA448333 | SRR8416088 | PRJNA448333 | SRR8397916 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_503 | PRJNA448333 | SRR8416087 | PRJNA448333 | SRR8397911 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_505 | PRJNA448333 | SRR8416102 | PRJNA448333 | SRR8397912 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_506 | PRJNA448333 | SRR8416083 | PRJNA448333 | SRR8397894 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_601 | PRJNA448333 | SRR8416063 | PRJNA448333 | SRR8397893 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_604 | PRJNA448333 | SRR8416066 | PRJNA448333 | SRR8397892 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_608 | PRJNA448333 | SRR8416097 | PRJNA448333 | SRR8397891 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_611 | PRJNA448333 | SRR8416098 | PRJNA448333 | SRR8397898 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_612 | PRJNA448333 | SRR8416099 | PRJNA448333 | SRR8397897 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_701 | PRJNA448333 | SRR8416100 | PRJNA448333 | SRR8397896 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_702 | PRJNA448333 | SRR8416077 | PRJNA448333 | SRR8397895 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_703 | PRJNA448333 | SRR8416078 | PRJNA448333 | SRR8397900 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_704 | PRJNA448333 | SRR8416082 | PRJNA448333 | SRR8397899 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_705 | PRJNA448333 | SRR8416081 | PRJNA448333 | SRR8397926 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_706 | PRJNA448333 | SRR8416086 | PRJNA448333 | SRR8397927 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_707 | PRJNA448333 | SRR8416084 | PRJNA448333 | SRR8397924 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_708 | PRJNA448333 | SRR8416101 | PRJNA448333 | SRR8397925 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_709 | PRJNA448333 | SRR8416085 | PRJNA448333 | SRR8397922 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_710 | PRJNA448333 | SRR8416080 | PRJNA448333 | SRR8397923 | cattle_rumen |\n",
+       "| rumen_microbiome_of_beef_cattle_712 | PRJNA448333 | SRR8416079 | PRJNA448333 | SRR8397921 | cattle_rumen |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "   sample_name                         mtx_study_accession mtx_run_accession\n",
+       "1  rumen_microbiome_of_beef_cattle_101 PRJNA448333         SRR8416057       \n",
+       "2  rumen_microbiome_of_beef_cattle_103 PRJNA448333         SRR8416058       \n",
+       "3  rumen_microbiome_of_beef_cattle_104 PRJNA448333         SRR8416055       \n",
+       "4  rumen_microbiome_of_beef_cattle_105 PRJNA448333         SRR8416056       \n",
+       "5  rumen_microbiome_of_beef_cattle_106 PRJNA448333         SRR8416061       \n",
+       "6  rumen_microbiome_of_beef_cattle_107 PRJNA448333         SRR8416062       \n",
+       "7  rumen_microbiome_of_beef_cattle_112 PRJNA448333         SRR8416059       \n",
+       "8  rumen_microbiome_of_beef_cattle_201 PRJNA448333         SRR8416060       \n",
+       "9  rumen_microbiome_of_beef_cattle_202 PRJNA448333         SRR8416064       \n",
+       "10 rumen_microbiome_of_beef_cattle_203 PRJNA448333         SRR8416065       \n",
+       "11 rumen_microbiome_of_beef_cattle_205 PRJNA448333         SRR8416069       \n",
+       "12 rumen_microbiome_of_beef_cattle_206 PRJNA448333         SRR8416070       \n",
+       "13 rumen_microbiome_of_beef_cattle_207 PRJNA448333         SRR8416067       \n",
+       "14 rumen_microbiome_of_beef_cattle_208 PRJNA448333         SRR8416068       \n",
+       "15 rumen_microbiome_of_beef_cattle_209 PRJNA448333         SRR8416073       \n",
+       "16 rumen_microbiome_of_beef_cattle_210 PRJNA448333         SRR8416074       \n",
+       "17 rumen_microbiome_of_beef_cattle_301 PRJNA448333         SRR8416071       \n",
+       "18 rumen_microbiome_of_beef_cattle_302 PRJNA448333         SRR8416072       \n",
+       "19 rumen_microbiome_of_beef_cattle_303 PRJNA448333         SRR8416075       \n",
+       "20 rumen_microbiome_of_beef_cattle_304 PRJNA448333         SRR8416076       \n",
+       "21 rumen_microbiome_of_beef_cattle_305 PRJNA448333         SRR8416092       \n",
+       "22 rumen_microbiome_of_beef_cattle_307 PRJNA448333         SRR8416091       \n",
+       "23 rumen_microbiome_of_beef_cattle_308 PRJNA448333         SRR8416090       \n",
+       "24 rumen_microbiome_of_beef_cattle_401 PRJNA448333         SRR8416089       \n",
+       "25 rumen_microbiome_of_beef_cattle_402 PRJNA448333         SRR8416096       \n",
+       "26 rumen_microbiome_of_beef_cattle_403 PRJNA448333         SRR8416095       \n",
+       "27 rumen_microbiome_of_beef_cattle_404 PRJNA448333         SRR8416094       \n",
+       "28 rumen_microbiome_of_beef_cattle_407 PRJNA448333         SRR8416093       \n",
+       "29 rumen_microbiome_of_beef_cattle_501 PRJNA448333         SRR8416088       \n",
+       "30 rumen_microbiome_of_beef_cattle_503 PRJNA448333         SRR8416087       \n",
+       "31 rumen_microbiome_of_beef_cattle_505 PRJNA448333         SRR8416102       \n",
+       "32 rumen_microbiome_of_beef_cattle_506 PRJNA448333         SRR8416083       \n",
+       "33 rumen_microbiome_of_beef_cattle_601 PRJNA448333         SRR8416063       \n",
+       "34 rumen_microbiome_of_beef_cattle_604 PRJNA448333         SRR8416066       \n",
+       "35 rumen_microbiome_of_beef_cattle_608 PRJNA448333         SRR8416097       \n",
+       "36 rumen_microbiome_of_beef_cattle_611 PRJNA448333         SRR8416098       \n",
+       "37 rumen_microbiome_of_beef_cattle_612 PRJNA448333         SRR8416099       \n",
+       "38 rumen_microbiome_of_beef_cattle_701 PRJNA448333         SRR8416100       \n",
+       "39 rumen_microbiome_of_beef_cattle_702 PRJNA448333         SRR8416077       \n",
+       "40 rumen_microbiome_of_beef_cattle_703 PRJNA448333         SRR8416078       \n",
+       "41 rumen_microbiome_of_beef_cattle_704 PRJNA448333         SRR8416082       \n",
+       "42 rumen_microbiome_of_beef_cattle_705 PRJNA448333         SRR8416081       \n",
+       "43 rumen_microbiome_of_beef_cattle_706 PRJNA448333         SRR8416086       \n",
+       "44 rumen_microbiome_of_beef_cattle_707 PRJNA448333         SRR8416084       \n",
+       "45 rumen_microbiome_of_beef_cattle_708 PRJNA448333         SRR8416101       \n",
+       "46 rumen_microbiome_of_beef_cattle_709 PRJNA448333         SRR8416085       \n",
+       "47 rumen_microbiome_of_beef_cattle_710 PRJNA448333         SRR8416080       \n",
+       "48 rumen_microbiome_of_beef_cattle_712 PRJNA448333         SRR8416079       \n",
+       "   mgx_study_accession mgx_run_accession sample_type \n",
+       "1  PRJNA448333         SRR8397906        cattle_rumen\n",
+       "2  PRJNA448333         SRR8404214        cattle_rumen\n",
+       "3  PRJNA448333         SRR8397905        cattle_rumen\n",
+       "4  PRJNA448333         SRR8397904        cattle_rumen\n",
+       "5  PRJNA448333         SRR8397903        cattle_rumen\n",
+       "6  PRJNA448333         SRR8397910        cattle_rumen\n",
+       "7  PRJNA448333         SRR8397909        cattle_rumen\n",
+       "8  PRJNA448333         SRR8397908        cattle_rumen\n",
+       "9  PRJNA448333         SRR8397907        cattle_rumen\n",
+       "10 PRJNA448333         SRR8397902        cattle_rumen\n",
+       "11 PRJNA448333         SRR8397901        cattle_rumen\n",
+       "12 PRJNA448333         SRR8397884        cattle_rumen\n",
+       "13 PRJNA448333         SRR8397883        cattle_rumen\n",
+       "14 PRJNA448333         SRR8397886        cattle_rumen\n",
+       "15 PRJNA448333         SRR8397885        cattle_rumen\n",
+       "16 PRJNA448333         SRR8397888        cattle_rumen\n",
+       "17 PRJNA448333         SRR8397887        cattle_rumen\n",
+       "18 PRJNA448333         SRR8397890        cattle_rumen\n",
+       "19 PRJNA448333         SRR8397889        cattle_rumen\n",
+       "20 PRJNA448333         SRR8397882        cattle_rumen\n",
+       "21 PRJNA448333         SRR8397881        cattle_rumen\n",
+       "22 PRJNA448333         SRR8397917        cattle_rumen\n",
+       "23 PRJNA448333         SRR8397918        cattle_rumen\n",
+       "24 PRJNA448333         SRR8397919        cattle_rumen\n",
+       "25 PRJNA448333         SRR8397920        cattle_rumen\n",
+       "26 PRJNA448333         SRR8397913        cattle_rumen\n",
+       "27 PRJNA448333         SRR8397914        cattle_rumen\n",
+       "28 PRJNA448333         SRR8397915        cattle_rumen\n",
+       "29 PRJNA448333         SRR8397916        cattle_rumen\n",
+       "30 PRJNA448333         SRR8397911        cattle_rumen\n",
+       "31 PRJNA448333         SRR8397912        cattle_rumen\n",
+       "32 PRJNA448333         SRR8397894        cattle_rumen\n",
+       "33 PRJNA448333         SRR8397893        cattle_rumen\n",
+       "34 PRJNA448333         SRR8397892        cattle_rumen\n",
+       "35 PRJNA448333         SRR8397891        cattle_rumen\n",
+       "36 PRJNA448333         SRR8397898        cattle_rumen\n",
+       "37 PRJNA448333         SRR8397897        cattle_rumen\n",
+       "38 PRJNA448333         SRR8397896        cattle_rumen\n",
+       "39 PRJNA448333         SRR8397895        cattle_rumen\n",
+       "40 PRJNA448333         SRR8397900        cattle_rumen\n",
+       "41 PRJNA448333         SRR8397899        cattle_rumen\n",
+       "42 PRJNA448333         SRR8397926        cattle_rumen\n",
+       "43 PRJNA448333         SRR8397927        cattle_rumen\n",
+       "44 PRJNA448333         SRR8397924        cattle_rumen\n",
+       "45 PRJNA448333         SRR8397925        cattle_rumen\n",
+       "46 PRJNA448333         SRR8397922        cattle_rumen\n",
+       "47 PRJNA448333         SRR8397923        cattle_rumen\n",
+       "48 PRJNA448333         SRR8397921        cattle_rumen"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna448333_mtx_vs_mgx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a6509917",
+   "metadata": {},
+   "source": [
+    "## PRJNA344005"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "543d0709",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna344005 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA344005&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F) %>%\n",
+    "    mutate(sample_name = gsub(\"_[DR]NA*.\", \"\", library_name)) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "f44db485",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna344005_pairs <- prjna344005 %>%\n",
+    "  group_by(sample_name) %>%\n",
+    "  tally() %>%\n",
+    "  filter(n == 2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "7883c2cd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna344005 <- prjna344005 %>%\n",
+    "  filter(sample_name %in% prjna344005_pairs$sample_name) %>%\n",
+    "  select(study_accession, run_accession, sample_name, library_strategy)\n",
+    "\n",
+    "prjna344005_mtx <- prjna344005 %>%\n",
+    "  filter(library_strategy == \"RNA-Seq\") %>%\n",
+    "  select(sample_name,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna344005_mgx <- prjna344005 %>%\n",
+    "  filter(library_strategy == \"WGS\") %>%\n",
+    "  select(sample_name,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "f8e7fd2f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 2 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>HiTCE_2d   </td><td>PRJNA344005</td><td>SRR4308224</td><td>PRJNA344005</td><td>SRR4308227</td><td>groundwater</td></tr>\n",
+       "\t<tr><td>HiTCEB12_2d</td><td>PRJNA344005</td><td>SRR4308225</td><td>PRJNA344005</td><td>SRR4308226</td><td>groundwater</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 2 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t HiTCE\\_2d    & PRJNA344005 & SRR4308224 & PRJNA344005 & SRR4308227 & groundwater\\\\\n",
+       "\t HiTCEB12\\_2d & PRJNA344005 & SRR4308225 & PRJNA344005 & SRR4308226 & groundwater\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 2 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| HiTCE_2d    | PRJNA344005 | SRR4308224 | PRJNA344005 | SRR4308227 | groundwater |\n",
+       "| HiTCEB12_2d | PRJNA344005 | SRR4308225 | PRJNA344005 | SRR4308226 | groundwater |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  sample_name mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1 HiTCE_2d    PRJNA344005         SRR4308224        PRJNA344005        \n",
+       "2 HiTCEB12_2d PRJNA344005         SRR4308225        PRJNA344005        \n",
+       "  mgx_run_accession sample_type\n",
+       "1 SRR4308227        groundwater\n",
+       "2 SRR4308226        groundwater"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna344005_mtx_vs_mgx <- left_join(prjna344005_mtx, prjna344005_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"groundwater\")\n",
+    "\n",
+    "prjna344005_mtx_vs_mgx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e0ae555e",
+   "metadata": {},
+   "source": [
+    "## PRJNA237345 (mtx) & PRJNA237344 (mgx)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "16d89c6e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna237345 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA237345&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)\n",
+    "prjna237344 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA237344&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "d9d8f133",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1m\u001b[22mJoining, by = \"sample_name\"\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A grouped_df: 23 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>amazon_plume_2_0um_from_station_10              </td><td>PRJNA237345</td><td>SRR1193190</td><td>PRJNA237344</td><td>SRR1205250</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_plume_2_0um_from_station_2               </td><td>PRJNA237345</td><td>SRR1193177</td><td>PRJNA237344</td><td>SRR1182511</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_plume_2_0um_from_station_23              </td><td>PRJNA237345</td><td>SRR1193237</td><td>PRJNA237344</td><td>SRR1202089</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_plume_2_0um_from_station_27              </td><td>PRJNA237345</td><td>SRR1193629</td><td>PRJNA237344</td><td>SRR1183643</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_plume_2_0um_from_station_3               </td><td>PRJNA237345</td><td>SRR1193226</td><td>PRJNA237344</td><td>SRR1199272</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_plume_0_2_2_0um_from_station_10          </td><td>PRJNA237345</td><td>SRR1186930</td><td>PRJNA237344</td><td>SRR1199271</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_plume_0_2_2_0um_from_station_2           </td><td>PRJNA237345</td><td>SRR1193205</td><td>PRJNA237344</td><td>SRR1182512</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_plume_0_2_2_0um_from_station_23          </td><td>PRJNA237345</td><td>SRR1193632</td><td>PRJNA237344</td><td>SRR1186214</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_plume_0_2_2_0um_from_station_25          </td><td>PRJNA237345</td><td>SRR1204579</td><td>PRJNA237344</td><td>SRR1202090</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_plume_0_2_2_0um_from_station_27          </td><td>PRJNA237345</td><td>SRR1193627</td><td>PRJNA237344</td><td>SRR1183650</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_plume_0_2_2_0um_from_station_3           </td><td>PRJNA237345</td><td>SRR1193215</td><td>PRJNA237344</td><td>SRR1185413</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_river_0_2_2_0um_from_belem               </td><td>PRJNA237345</td><td>SRR1781804</td><td>PRJNA237344</td><td>SRR1790489</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_river_0_2_2_0um_from_macapa_north_channel</td><td>PRJNA237345</td><td>SRR1785209</td><td>PRJNA237344</td><td>SRR1786279</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_river_0_2_2_0um_from_macapa_south_channel</td><td>PRJNA237345</td><td>SRR1784299</td><td>PRJNA237344</td><td>SRR1787940</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_river_0_2_2_0um_from_obidos              </td><td>PRJNA237345</td><td>SRR1781945</td><td>PRJNA237344</td><td>SRR1790676</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_river_0_2_2_0um_from_tapajos_depth       </td><td>PRJNA237345</td><td>SRR1779221</td><td>PRJNA237344</td><td>SRR1792674</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_river_0_2_2_0um_from_tapajos_surface     </td><td>PRJNA237345</td><td>SRR1777513</td><td>PRJNA237344</td><td>SRR1796116</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_river_2_0_297um_from_belem               </td><td>PRJNA237345</td><td>SRR1781811</td><td>PRJNA237344</td><td>SRR1790644</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_river_2_0_297um_from_macapa_north_channel</td><td>PRJNA237345</td><td>SRR1785350</td><td>PRJNA237344</td><td>SRR1786281</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_river_2_0_297um_from_macapa_south_channel</td><td>PRJNA237345</td><td>SRR1784304</td><td>PRJNA237344</td><td>SRR1787943</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_river_2_0_297um_from_obidos              </td><td>PRJNA237345</td><td>SRR1782579</td><td>PRJNA237344</td><td>SRR1790678</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_river_2_0_297um_from_tapajos_depth       </td><td>PRJNA237345</td><td>SRR1781711</td><td>PRJNA237344</td><td>SRR1792852</td><td>river</td></tr>\n",
+       "\t<tr><td>amazon_river_2_0_297um_from_tapajos_surface     </td><td>PRJNA237345</td><td>SRR1778024</td><td>PRJNA237344</td><td>SRR1796118</td><td>river</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A grouped\\_df: 23 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t amazon\\_plume\\_2\\_0um\\_from\\_station\\_10               & PRJNA237345 & SRR1193190 & PRJNA237344 & SRR1205250 & river\\\\\n",
+       "\t amazon\\_plume\\_2\\_0um\\_from\\_station\\_2                & PRJNA237345 & SRR1193177 & PRJNA237344 & SRR1182511 & river\\\\\n",
+       "\t amazon\\_plume\\_2\\_0um\\_from\\_station\\_23               & PRJNA237345 & SRR1193237 & PRJNA237344 & SRR1202089 & river\\\\\n",
+       "\t amazon\\_plume\\_2\\_0um\\_from\\_station\\_27               & PRJNA237345 & SRR1193629 & PRJNA237344 & SRR1183643 & river\\\\\n",
+       "\t amazon\\_plume\\_2\\_0um\\_from\\_station\\_3                & PRJNA237345 & SRR1193226 & PRJNA237344 & SRR1199272 & river\\\\\n",
+       "\t amazon\\_plume\\_0\\_2\\_2\\_0um\\_from\\_station\\_10           & PRJNA237345 & SRR1186930 & PRJNA237344 & SRR1199271 & river\\\\\n",
+       "\t amazon\\_plume\\_0\\_2\\_2\\_0um\\_from\\_station\\_2            & PRJNA237345 & SRR1193205 & PRJNA237344 & SRR1182512 & river\\\\\n",
+       "\t amazon\\_plume\\_0\\_2\\_2\\_0um\\_from\\_station\\_23           & PRJNA237345 & SRR1193632 & PRJNA237344 & SRR1186214 & river\\\\\n",
+       "\t amazon\\_plume\\_0\\_2\\_2\\_0um\\_from\\_station\\_25           & PRJNA237345 & SRR1204579 & PRJNA237344 & SRR1202090 & river\\\\\n",
+       "\t amazon\\_plume\\_0\\_2\\_2\\_0um\\_from\\_station\\_27           & PRJNA237345 & SRR1193627 & PRJNA237344 & SRR1183650 & river\\\\\n",
+       "\t amazon\\_plume\\_0\\_2\\_2\\_0um\\_from\\_station\\_3            & PRJNA237345 & SRR1193215 & PRJNA237344 & SRR1185413 & river\\\\\n",
+       "\t amazon\\_river\\_0\\_2\\_2\\_0um\\_from\\_belem                & PRJNA237345 & SRR1781804 & PRJNA237344 & SRR1790489 & river\\\\\n",
+       "\t amazon\\_river\\_0\\_2\\_2\\_0um\\_from\\_macapa\\_north\\_channel & PRJNA237345 & SRR1785209 & PRJNA237344 & SRR1786279 & river\\\\\n",
+       "\t amazon\\_river\\_0\\_2\\_2\\_0um\\_from\\_macapa\\_south\\_channel & PRJNA237345 & SRR1784299 & PRJNA237344 & SRR1787940 & river\\\\\n",
+       "\t amazon\\_river\\_0\\_2\\_2\\_0um\\_from\\_obidos               & PRJNA237345 & SRR1781945 & PRJNA237344 & SRR1790676 & river\\\\\n",
+       "\t amazon\\_river\\_0\\_2\\_2\\_0um\\_from\\_tapajos\\_depth        & PRJNA237345 & SRR1779221 & PRJNA237344 & SRR1792674 & river\\\\\n",
+       "\t amazon\\_river\\_0\\_2\\_2\\_0um\\_from\\_tapajos\\_surface      & PRJNA237345 & SRR1777513 & PRJNA237344 & SRR1796116 & river\\\\\n",
+       "\t amazon\\_river\\_2\\_0\\_297um\\_from\\_belem                & PRJNA237345 & SRR1781811 & PRJNA237344 & SRR1790644 & river\\\\\n",
+       "\t amazon\\_river\\_2\\_0\\_297um\\_from\\_macapa\\_north\\_channel & PRJNA237345 & SRR1785350 & PRJNA237344 & SRR1786281 & river\\\\\n",
+       "\t amazon\\_river\\_2\\_0\\_297um\\_from\\_macapa\\_south\\_channel & PRJNA237345 & SRR1784304 & PRJNA237344 & SRR1787943 & river\\\\\n",
+       "\t amazon\\_river\\_2\\_0\\_297um\\_from\\_obidos               & PRJNA237345 & SRR1782579 & PRJNA237344 & SRR1790678 & river\\\\\n",
+       "\t amazon\\_river\\_2\\_0\\_297um\\_from\\_tapajos\\_depth        & PRJNA237345 & SRR1781711 & PRJNA237344 & SRR1792852 & river\\\\\n",
+       "\t amazon\\_river\\_2\\_0\\_297um\\_from\\_tapajos\\_surface      & PRJNA237345 & SRR1778024 & PRJNA237344 & SRR1796118 & river\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A grouped_df: 23 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| amazon_plume_2_0um_from_station_10               | PRJNA237345 | SRR1193190 | PRJNA237344 | SRR1205250 | river |\n",
+       "| amazon_plume_2_0um_from_station_2                | PRJNA237345 | SRR1193177 | PRJNA237344 | SRR1182511 | river |\n",
+       "| amazon_plume_2_0um_from_station_23               | PRJNA237345 | SRR1193237 | PRJNA237344 | SRR1202089 | river |\n",
+       "| amazon_plume_2_0um_from_station_27               | PRJNA237345 | SRR1193629 | PRJNA237344 | SRR1183643 | river |\n",
+       "| amazon_plume_2_0um_from_station_3                | PRJNA237345 | SRR1193226 | PRJNA237344 | SRR1199272 | river |\n",
+       "| amazon_plume_0_2_2_0um_from_station_10           | PRJNA237345 | SRR1186930 | PRJNA237344 | SRR1199271 | river |\n",
+       "| amazon_plume_0_2_2_0um_from_station_2            | PRJNA237345 | SRR1193205 | PRJNA237344 | SRR1182512 | river |\n",
+       "| amazon_plume_0_2_2_0um_from_station_23           | PRJNA237345 | SRR1193632 | PRJNA237344 | SRR1186214 | river |\n",
+       "| amazon_plume_0_2_2_0um_from_station_25           | PRJNA237345 | SRR1204579 | PRJNA237344 | SRR1202090 | river |\n",
+       "| amazon_plume_0_2_2_0um_from_station_27           | PRJNA237345 | SRR1193627 | PRJNA237344 | SRR1183650 | river |\n",
+       "| amazon_plume_0_2_2_0um_from_station_3            | PRJNA237345 | SRR1193215 | PRJNA237344 | SRR1185413 | river |\n",
+       "| amazon_river_0_2_2_0um_from_belem                | PRJNA237345 | SRR1781804 | PRJNA237344 | SRR1790489 | river |\n",
+       "| amazon_river_0_2_2_0um_from_macapa_north_channel | PRJNA237345 | SRR1785209 | PRJNA237344 | SRR1786279 | river |\n",
+       "| amazon_river_0_2_2_0um_from_macapa_south_channel | PRJNA237345 | SRR1784299 | PRJNA237344 | SRR1787940 | river |\n",
+       "| amazon_river_0_2_2_0um_from_obidos               | PRJNA237345 | SRR1781945 | PRJNA237344 | SRR1790676 | river |\n",
+       "| amazon_river_0_2_2_0um_from_tapajos_depth        | PRJNA237345 | SRR1779221 | PRJNA237344 | SRR1792674 | river |\n",
+       "| amazon_river_0_2_2_0um_from_tapajos_surface      | PRJNA237345 | SRR1777513 | PRJNA237344 | SRR1796116 | river |\n",
+       "| amazon_river_2_0_297um_from_belem                | PRJNA237345 | SRR1781811 | PRJNA237344 | SRR1790644 | river |\n",
+       "| amazon_river_2_0_297um_from_macapa_north_channel | PRJNA237345 | SRR1785350 | PRJNA237344 | SRR1786281 | river |\n",
+       "| amazon_river_2_0_297um_from_macapa_south_channel | PRJNA237345 | SRR1784304 | PRJNA237344 | SRR1787943 | river |\n",
+       "| amazon_river_2_0_297um_from_obidos               | PRJNA237345 | SRR1782579 | PRJNA237344 | SRR1790678 | river |\n",
+       "| amazon_river_2_0_297um_from_tapajos_depth        | PRJNA237345 | SRR1781711 | PRJNA237344 | SRR1792852 | river |\n",
+       "| amazon_river_2_0_297um_from_tapajos_surface      | PRJNA237345 | SRR1778024 | PRJNA237344 | SRR1796118 | river |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "   sample_name                                      mtx_study_accession\n",
+       "1  amazon_plume_2_0um_from_station_10               PRJNA237345        \n",
+       "2  amazon_plume_2_0um_from_station_2                PRJNA237345        \n",
+       "3  amazon_plume_2_0um_from_station_23               PRJNA237345        \n",
+       "4  amazon_plume_2_0um_from_station_27               PRJNA237345        \n",
+       "5  amazon_plume_2_0um_from_station_3                PRJNA237345        \n",
+       "6  amazon_plume_0_2_2_0um_from_station_10           PRJNA237345        \n",
+       "7  amazon_plume_0_2_2_0um_from_station_2            PRJNA237345        \n",
+       "8  amazon_plume_0_2_2_0um_from_station_23           PRJNA237345        \n",
+       "9  amazon_plume_0_2_2_0um_from_station_25           PRJNA237345        \n",
+       "10 amazon_plume_0_2_2_0um_from_station_27           PRJNA237345        \n",
+       "11 amazon_plume_0_2_2_0um_from_station_3            PRJNA237345        \n",
+       "12 amazon_river_0_2_2_0um_from_belem                PRJNA237345        \n",
+       "13 amazon_river_0_2_2_0um_from_macapa_north_channel PRJNA237345        \n",
+       "14 amazon_river_0_2_2_0um_from_macapa_south_channel PRJNA237345        \n",
+       "15 amazon_river_0_2_2_0um_from_obidos               PRJNA237345        \n",
+       "16 amazon_river_0_2_2_0um_from_tapajos_depth        PRJNA237345        \n",
+       "17 amazon_river_0_2_2_0um_from_tapajos_surface      PRJNA237345        \n",
+       "18 amazon_river_2_0_297um_from_belem                PRJNA237345        \n",
+       "19 amazon_river_2_0_297um_from_macapa_north_channel PRJNA237345        \n",
+       "20 amazon_river_2_0_297um_from_macapa_south_channel PRJNA237345        \n",
+       "21 amazon_river_2_0_297um_from_obidos               PRJNA237345        \n",
+       "22 amazon_river_2_0_297um_from_tapajos_depth        PRJNA237345        \n",
+       "23 amazon_river_2_0_297um_from_tapajos_surface      PRJNA237345        \n",
+       "   mtx_run_accession mgx_study_accession mgx_run_accession sample_type\n",
+       "1  SRR1193190        PRJNA237344         SRR1205250        river      \n",
+       "2  SRR1193177        PRJNA237344         SRR1182511        river      \n",
+       "3  SRR1193237        PRJNA237344         SRR1202089        river      \n",
+       "4  SRR1193629        PRJNA237344         SRR1183643        river      \n",
+       "5  SRR1193226        PRJNA237344         SRR1199272        river      \n",
+       "6  SRR1186930        PRJNA237344         SRR1199271        river      \n",
+       "7  SRR1193205        PRJNA237344         SRR1182512        river      \n",
+       "8  SRR1193632        PRJNA237344         SRR1186214        river      \n",
+       "9  SRR1204579        PRJNA237344         SRR1202090        river      \n",
+       "10 SRR1193627        PRJNA237344         SRR1183650        river      \n",
+       "11 SRR1193215        PRJNA237344         SRR1185413        river      \n",
+       "12 SRR1781804        PRJNA237344         SRR1790489        river      \n",
+       "13 SRR1785209        PRJNA237344         SRR1786279        river      \n",
+       "14 SRR1784299        PRJNA237344         SRR1787940        river      \n",
+       "15 SRR1781945        PRJNA237344         SRR1790676        river      \n",
+       "16 SRR1779221        PRJNA237344         SRR1792674        river      \n",
+       "17 SRR1777513        PRJNA237344         SRR1796116        river      \n",
+       "18 SRR1781811        PRJNA237344         SRR1790644        river      \n",
+       "19 SRR1785350        PRJNA237344         SRR1786281        river      \n",
+       "20 SRR1784304        PRJNA237344         SRR1787943        river      \n",
+       "21 SRR1782579        PRJNA237344         SRR1790678        river      \n",
+       "22 SRR1781711        PRJNA237344         SRR1792852        river      \n",
+       "23 SRR1778024        PRJNA237344         SRR1796118        river      "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "tmp1 <- prjna237345 %>% \n",
+    "  select(sample_name = experiment_title, mtx_study_accession = study_accession, mtx_run_accession = run_accession) %>%\n",
+    "  mutate(sample_name = gsub(\"Metatranscriptome \", \"\", sample_name),\n",
+    "         sample_name = gsub(\"\\\\(.*\", \"\", sample_name))\n",
+    "\n",
+    "tmp2 <- prjna237344 %>% \n",
+    "  select(sample_name = experiment_title, mgx_study_accession = study_accession, mgx_run_accession = run_accession) %>%\n",
+    "  mutate(sample_name = gsub(\"Metagenome \", \"\", sample_name),\n",
+    "         sample_name = gsub(\"\\\\(.*\", \"\", sample_name))\n",
+    "\n",
+    "prjna237345_vs_prjna237344 <- left_join(tmp1, tmp2) %>%\n",
+    "  filter(!is.na(mgx_study_accession)) %>%\n",
+    "  mutate(sample_name = gsub(\"Illumina Genome Analyzer IIx sequencing; May-June 2010 \", \"\", sample_name),\n",
+    "         sample_name = gsub(\"Illumina HiSeq 2500 sequencing; May 2011 \", \"\", sample_name)) %>%\n",
+    "  group_by(sample_name) %>%\n",
+    "  slice(n = 1) %>%\n",
+    "  mutate(sample_name = make_clean_names(sample_name),\n",
+    "         sample_type = \"river\")\n",
+    "\n",
+    "prjna237345_vs_prjna237344"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "49c6b061",
+   "metadata": {},
+   "source": [
+    "## PRJNA453733"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "f074e2aa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna453733 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA453733&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F) %>%\n",
+    "    filter(library_strategy == \"OTHER\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "947b707d",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 5 × 5</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>study_accession</th><th scope=col>run_accession</th><th scope=col>sample_alias</th><th scope=col>library_strategy</th><th scope=col>library_source</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>PRJNA453733</td><td>SRR7083928</td><td>CS-Sed16-2cmA</td><td>OTHER</td><td>METATRANSCRIPTOMIC</td></tr>\n",
+       "\t<tr><td>PRJNA453733</td><td>SRR7083929</td><td>CS-Sed16-2cmB</td><td>OTHER</td><td>METAGENOMIC       </td></tr>\n",
+       "\t<tr><td>PRJNA453733</td><td>SRR7083930</td><td>CS-Br16      </td><td>OTHER</td><td>METAGENOMIC       </td></tr>\n",
+       "\t<tr><td>PRJNA453733</td><td>SRR7083931</td><td>CS-Sed16-2cmA</td><td>OTHER</td><td>METAGENOMIC       </td></tr>\n",
+       "\t<tr><td>PRJNA453733</td><td>SRR7083934</td><td>CS-Sed16-5cm </td><td>OTHER</td><td>METAGENOMIC       </td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 5 × 5\n",
+       "\\begin{tabular}{lllll}\n",
+       " study\\_accession & run\\_accession & sample\\_alias & library\\_strategy & library\\_source\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t PRJNA453733 & SRR7083928 & CS-Sed16-2cmA & OTHER & METATRANSCRIPTOMIC\\\\\n",
+       "\t PRJNA453733 & SRR7083929 & CS-Sed16-2cmB & OTHER & METAGENOMIC       \\\\\n",
+       "\t PRJNA453733 & SRR7083930 & CS-Br16       & OTHER & METAGENOMIC       \\\\\n",
+       "\t PRJNA453733 & SRR7083931 & CS-Sed16-2cmA & OTHER & METAGENOMIC       \\\\\n",
+       "\t PRJNA453733 & SRR7083934 & CS-Sed16-5cm  & OTHER & METAGENOMIC       \\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 5 × 5\n",
+       "\n",
+       "| study_accession &lt;chr&gt; | run_accession &lt;chr&gt; | sample_alias &lt;chr&gt; | library_strategy &lt;chr&gt; | library_source &lt;chr&gt; |\n",
+       "|---|---|---|---|---|\n",
+       "| PRJNA453733 | SRR7083928 | CS-Sed16-2cmA | OTHER | METATRANSCRIPTOMIC |\n",
+       "| PRJNA453733 | SRR7083929 | CS-Sed16-2cmB | OTHER | METAGENOMIC        |\n",
+       "| PRJNA453733 | SRR7083930 | CS-Br16       | OTHER | METAGENOMIC        |\n",
+       "| PRJNA453733 | SRR7083931 | CS-Sed16-2cmA | OTHER | METAGENOMIC        |\n",
+       "| PRJNA453733 | SRR7083934 | CS-Sed16-5cm  | OTHER | METAGENOMIC        |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  study_accession run_accession sample_alias  library_strategy\n",
+       "1 PRJNA453733     SRR7083928    CS-Sed16-2cmA OTHER           \n",
+       "2 PRJNA453733     SRR7083929    CS-Sed16-2cmB OTHER           \n",
+       "3 PRJNA453733     SRR7083930    CS-Br16       OTHER           \n",
+       "4 PRJNA453733     SRR7083931    CS-Sed16-2cmA OTHER           \n",
+       "5 PRJNA453733     SRR7083934    CS-Sed16-5cm  OTHER           \n",
+       "  library_source    \n",
+       "1 METATRANSCRIPTOMIC\n",
+       "2 METAGENOMIC       \n",
+       "3 METAGENOMIC       \n",
+       "4 METAGENOMIC       \n",
+       "5 METAGENOMIC       "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna453733 %>% \n",
+    "  select(study_accession, run_accession, sample_alias, library_strategy, library_source)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "18b6e2a1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 1 × 2</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_alias</th><th scope=col>n</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;int&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>CS-Sed16-2cmA</td><td>2</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 1 × 2\n",
+       "\\begin{tabular}{ll}\n",
+       " sample\\_alias & n\\\\\n",
+       " <chr> & <int>\\\\\n",
+       "\\hline\n",
+       "\t CS-Sed16-2cmA & 2\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 1 × 2\n",
+       "\n",
+       "| sample_alias &lt;chr&gt; | n &lt;int&gt; |\n",
+       "|---|---|\n",
+       "| CS-Sed16-2cmA | 2 |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  sample_alias  n\n",
+       "1 CS-Sed16-2cmA 2"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna453733_pairs <- prjna453733 %>%\n",
+    "  group_by(sample_alias) %>%\n",
+    "  tally() %>%\n",
+    "  filter(n == 2)\n",
+    "\n",
+    "prjna453733_pairs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "9016f1ab",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 1 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>CS-Sed16-2cmA</td><td>PRJNA453733</td><td>SRR7083928</td><td>PRJNA453733</td><td>SRR7083931</td><td>lake</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 1 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t CS-Sed16-2cmA & PRJNA453733 & SRR7083928 & PRJNA453733 & SRR7083931 & lake\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 1 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| CS-Sed16-2cmA | PRJNA453733 | SRR7083928 | PRJNA453733 | SRR7083931 | lake |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  sample_name   mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1 CS-Sed16-2cmA PRJNA453733         SRR7083928        PRJNA453733        \n",
+       "  mgx_run_accession sample_type\n",
+       "1 SRR7083931        lake       "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna453733_mtx <- prjna453733 %>%\n",
+    "  filter(sample_alias %in% prjna453733_pairs$sample_alias) %>%\n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mtx_study_accession = study_accession, \n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna453733_mgx <- prjna453733 %>%\n",
+    "  filter(sample_alias %in% prjna453733_pairs$sample_alias) %>%\n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mgx_study_accession = study_accession, \n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjna453733_mtx_vs_mgx <- left_join(prjna453733_mtx, prjna453733_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"lake\")\n",
+    "prjna453733_mtx_vs_mgx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7e95696f",
+   "metadata": {},
+   "source": [
+    "## Microbial metagenomes and metatranscriptomes during a coastal phytoplankton bloom (one PRJNA per sample)\n",
+    "The samples published in the above title each have there own study accession and run accession. \n",
+    "This section of the notebook parses two supplementary files from the publication to get all of the sample bioproject numbers and to determine which bioproject numbers represent pairs of samples."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "eee996ab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "download.file(url = \"https://static-content.springer.com/esm/art%3A10.1038%2Fs41597-019-0132-4/MediaObjects/41597_2019_132_MOESM1_ESM.zip\",\n",
+    "              destfile = \"inputs/metadata/41597_2019_132_MOESM1_ESM.zip\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "89777aca",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "unzip(\"inputs/metadata/41597_2019_132_MOESM1_ESM.zip\", exdir = \"inputs/metadata/41597_2019_132_MOESM1_ESM\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "102b69b1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "moran010B_mgx <- read_tsv(\"inputs/metadata/41597_2019_132_MOESM1_ESM/a_Moran010B_dna.txt\", show_col_types = F) %>%\n",
+    "  clean_names() %>%\n",
+    "  select(sample_name, mgx_study_accession = assay_name) %>%\n",
+    "  mutate(sample_name = gsub(\"D\", \"\", sample_name))\n",
+    "\n",
+    "moran010B_mtx <- read_tsv(\"inputs/metadata/41597_2019_132_MOESM1_ESM/a_Moran010B_rna.txt\", show_col_types = F) %>%\n",
+    "  clean_names() %>%\n",
+    "  select(sample_name, mtx_study_accession = assay_name) %>%\n",
+    "  mutate(sample_name = gsub(\"R\", \"\", sample_name))\n",
+    "\n",
+    "moran010B <- inner_join(moran010B_mtx, moran010B_mgx, by = \"sample_name\") "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "bbc1cf54",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# use the moran010B study accessions to programatically generate URLs to get run accessions for each sample\n",
+    "moran010B_run_accessions <- data.frame()\n",
+    "for(study_accession in c(moran010B$mtx_study_accession, moran010B_mgx$mgx_study_accession)){\n",
+    "    url <- paste0(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=\", study_accession, \"&result=read_run&fields=study_accession,run_accession&format=tsv&download=true&limit=0\")\n",
+    "    run_accession <- read_tsv(url, show_col_types = F) \n",
+    "    moran010B_run_accessions <- bind_rows(moran010B_run_accessions, run_accession)\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "5207828e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 74 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>26   </td><td>PRJNA502453</td><td>SRR8361532</td><td>PRJNA467728</td><td>SRR7592711</td><td>ocean</td></tr>\n",
+       "\t<tr><td>58_r </td><td>PRJNA502454</td><td>SRR8361534</td><td>PRJNA467772</td><td>SRR7609573</td><td>ocean</td></tr>\n",
+       "\t<tr><td>125_r</td><td>PRJNA468332</td><td>SRR7962480</td><td>PRJNA467773</td><td>SRR7609569</td><td>ocean</td></tr>\n",
+       "\t<tr><td>8    </td><td>PRJNA502455</td><td>SRR8297879</td><td>PRJNA467724</td><td>SRR7592287</td><td>ocean</td></tr>\n",
+       "\t<tr><td>85   </td><td>PRJNA502456</td><td>SRR8297845</td><td>PRJNA467765</td><td>SRR7609362</td><td>ocean</td></tr>\n",
+       "\t<tr><td>76   </td><td>PRJNA468305</td><td>SRR7949679</td><td>PRJNA467757</td><td>SRR7608731</td><td>ocean</td></tr>\n",
+       "\t<tr><td>40   </td><td>PRJNA467774</td><td>SRR7609608</td><td>PRJNA467736</td><td>SRR7595425</td><td>ocean</td></tr>\n",
+       "\t<tr><td>53   </td><td>PRJNA468299</td><td>SRR7609574</td><td>PRJNA502421</td><td>SRR8361352</td><td>ocean</td></tr>\n",
+       "\t<tr><td>73   </td><td>PRJNA468306</td><td>SRR7949683</td><td>PRJNA467754</td><td>SRR7608223</td><td>ocean</td></tr>\n",
+       "\t<tr><td>23   </td><td>PRJNA467775</td><td>SRR7609632</td><td>PRJNA467727</td><td>SRR7633009</td><td>ocean</td></tr>\n",
+       "\t<tr><td>49   </td><td>PRJNA467776</td><td>SRR7609653</td><td>PRJNA502442</td><td>SRR8361104</td><td>ocean</td></tr>\n",
+       "\t<tr><td>14   </td><td>PRJNA468308</td><td>SRR7949682</td><td>PRJNA502410</td><td>SRR8360542</td><td>ocean</td></tr>\n",
+       "\t<tr><td>44   </td><td>PRJNA502457</td><td>SRR8361579</td><td>PRJNA467738</td><td>SRR7600393</td><td>ocean</td></tr>\n",
+       "\t<tr><td>29   </td><td>PRJNA468309</td><td>SRR7949681</td><td>PRJNA467730</td><td>SRR7593831</td><td>ocean</td></tr>\n",
+       "\t<tr><td>18   </td><td>PRJNA467777</td><td>SRR7609655</td><td>PRJNA502413</td><td>SRR8360544</td><td>ocean</td></tr>\n",
+       "\t<tr><td>24   </td><td>PRJNA502458</td><td>SRR8361603</td><td>PRJNA502440</td><td>SRR8360549</td><td>ocean</td></tr>\n",
+       "\t<tr><td>79   </td><td>PRJNA468143</td><td>SRR7609654</td><td>PRJNA467760</td><td>SRR7609143</td><td>ocean</td></tr>\n",
+       "\t<tr><td>22   </td><td>PRJNA468300</td><td>SRR7609599</td><td>PRJNA502414</td><td>SRR8360545</td><td>ocean</td></tr>\n",
+       "\t<tr><td>21   </td><td>PRJNA468310</td><td>SRR7949678</td><td>PRJNA468208</td><td>SRR7592488</td><td>ocean</td></tr>\n",
+       "\t<tr><td>60   </td><td>PRJNA467778</td><td>SRR7609828</td><td>PRJNA502425</td><td>SRR8361517</td><td>ocean</td></tr>\n",
+       "\t<tr><td>15   </td><td>PRJNA468144</td><td>SRR7609827</td><td>PRJNA502411</td><td>SRR8360457</td><td>ocean</td></tr>\n",
+       "\t<tr><td>75   </td><td>PRJNA502459</td><td>SRR8361602</td><td>PRJNA467756</td><td>SRR7608423</td><td>ocean</td></tr>\n",
+       "\t<tr><td>3    </td><td>PRJNA468311</td><td>SRR7949692</td><td>PRJNA467722</td><td>SRR7592226</td><td>ocean</td></tr>\n",
+       "\t<tr><td>20   </td><td>PRJNA467779</td><td>SRR7609829</td><td>PRJNA467726</td><td>SRR7592489</td><td>ocean</td></tr>\n",
+       "\t<tr><td>91   </td><td>PRJNA468312</td><td>SRR7949677</td><td>PRJNA467769</td><td>SRR7609461</td><td>ocean</td></tr>\n",
+       "\t<tr><td>56   </td><td>PRJNA468152</td><td>SRR7615220</td><td>PRJNA467743</td><td>SRR7601261</td><td>ocean</td></tr>\n",
+       "\t<tr><td>46   </td><td>PRJNA502460</td><td>SRR8297843</td><td>PRJNA468213</td><td>SRR7600395</td><td>ocean</td></tr>\n",
+       "\t<tr><td>2    </td><td>PRJNA468313</td><td>SRR7609607</td><td>PRJNA467721</td><td>SRR7592225</td><td>ocean</td></tr>\n",
+       "\t<tr><td>38   </td><td>PRJNA468301</td><td>SRR7609600</td><td>PRJNA468211</td><td>SRR7594461</td><td>ocean</td></tr>\n",
+       "\t<tr><td>45   </td><td>PRJNA468314</td><td>SRR7962234</td><td>PRJNA467739</td><td>SRR7600394</td><td>ocean</td></tr>\n",
+       "\t<tr><td>⋮</td><td>⋮</td><td>⋮</td><td>⋮</td><td>⋮</td><td>⋮</td></tr>\n",
+       "\t<tr><td>32  </td><td>PRJNA468321</td><td>SRR7962267</td><td>PRJNA468210</td><td>SRR7594064</td><td>ocean</td></tr>\n",
+       "\t<tr><td>81  </td><td>PRJNA468145</td><td>SRR7610454</td><td>PRJNA467762</td><td>SRR7609163</td><td>ocean</td></tr>\n",
+       "\t<tr><td>70  </td><td>PRJNA468322</td><td>SRR7962239</td><td>PRJNA467752</td><td>SRR7608010</td><td>ocean</td></tr>\n",
+       "\t<tr><td>67  </td><td>PRJNA468323</td><td>SRR7962329</td><td>PRJNA467750</td><td>SRR7607757</td><td>ocean</td></tr>\n",
+       "\t<tr><td>33  </td><td>PRJNA467783</td><td>SRR7610453</td><td>PRJNA502417</td><td>SRR8361102</td><td>ocean</td></tr>\n",
+       "\t<tr><td>27  </td><td>PRJNA468331</td><td>SRR7962479</td><td>PRJNA468209</td><td>SRR7593830</td><td>ocean</td></tr>\n",
+       "\t<tr><td>34  </td><td>PRJNA502465</td><td>SRR8297868</td><td>PRJNA467732</td><td>SRR7594085</td><td>ocean</td></tr>\n",
+       "\t<tr><td>4   </td><td>PRJNA468146</td><td>SRR7610452</td><td>PRJNA467723</td><td>SRR7592236</td><td>ocean</td></tr>\n",
+       "\t<tr><td>57  </td><td>PRJNA468147</td><td>SRR7610935</td><td>PRJNA502423</td><td>SRR8361526</td><td>ocean</td></tr>\n",
+       "\t<tr><td>1   </td><td>PRJNA502466</td><td>SRR8361608</td><td>PRJNA467720</td><td>SRR7592212</td><td>ocean</td></tr>\n",
+       "\t<tr><td>47  </td><td>PRJNA468148</td><td>SRR7610853</td><td>PRJNA467740</td><td>SRR7600454</td><td>ocean</td></tr>\n",
+       "\t<tr><td>9   </td><td>PRJNA502467</td><td>SRR8297869</td><td>PRJNA502408</td><td>SRR8360547</td><td>ocean</td></tr>\n",
+       "\t<tr><td>77  </td><td>PRJNA468324</td><td>SRR7962474</td><td>PRJNA467758</td><td>SRR7608832</td><td>ocean</td></tr>\n",
+       "\t<tr><td>55  </td><td>PRJNA467784</td><td>SRR7610867</td><td>PRJNA502422</td><td>SRR8361371</td><td>ocean</td></tr>\n",
+       "\t<tr><td>10  </td><td>PRJNA468325</td><td>SRR7962473</td><td>PRJNA502409</td><td>SRR8360543</td><td>ocean</td></tr>\n",
+       "\t<tr><td>11  </td><td>PRJNA468326</td><td>SRR7962475</td><td>PRJNA467725</td><td>SRR7592321</td><td>ocean</td></tr>\n",
+       "\t<tr><td>58  </td><td>PRJNA502468</td><td>SRR8297878</td><td>PRJNA502424</td><td>SRR8361527</td><td>ocean</td></tr>\n",
+       "\t<tr><td>52  </td><td>PRJNA468327</td><td>SRR7962478</td><td>PRJNA467742</td><td>SRR7600455</td><td>ocean</td></tr>\n",
+       "\t<tr><td>51  </td><td>PRJNA468149</td><td>SRR7611057</td><td>PRJNA502420</td><td>SRR8361350</td><td>ocean</td></tr>\n",
+       "\t<tr><td>50  </td><td>PRJNA468328</td><td>SRR7962477</td><td>PRJNA502419</td><td>SRR8361349</td><td>ocean</td></tr>\n",
+       "\t<tr><td>90  </td><td>PRJNA467785</td><td>SRR7611056</td><td>PRJNA467768</td><td>SRR7609452</td><td>ocean</td></tr>\n",
+       "\t<tr><td>80  </td><td>PRJNA467786</td><td>SRR7611058</td><td>PRJNA467761</td><td>SRR7609166</td><td>ocean</td></tr>\n",
+       "\t<tr><td>89  </td><td>PRJNA468150</td><td>SRR7611500</td><td>PRJNA467766</td><td>SRR7609363</td><td>ocean</td></tr>\n",
+       "\t<tr><td>35  </td><td>PRJNA467787</td><td>SRR7612580</td><td>PRJNA502441</td><td>SRR8361101</td><td>ocean</td></tr>\n",
+       "\t<tr><td>71  </td><td>PRJNA468329</td><td>SRR7962476</td><td>PRJNA467753</td><td>SRR7608017</td><td>ocean</td></tr>\n",
+       "\t<tr><td>31  </td><td>PRJNA468151</td><td>SRR7611499</td><td>PRJNA467731</td><td>SRR7593934</td><td>ocean</td></tr>\n",
+       "\t<tr><td>84  </td><td>PRJNA502451</td><td>SRR8393198</td><td>PRJNA467764</td><td>SRR7609361</td><td>ocean</td></tr>\n",
+       "\t<tr><td>61  </td><td>PRJNA467788</td><td>SRR7615219</td><td>PRJNA502426</td><td>SRR8361516</td><td>ocean</td></tr>\n",
+       "\t<tr><td>36_r</td><td>PRJNA468330</td><td>SRR7962481</td><td>PRJNA467770</td><td>SRR7609462</td><td>ocean</td></tr>\n",
+       "\t<tr><td>82  </td><td>PRJNA502452</td><td>SRR8361531</td><td>PRJNA467763</td><td>SRR7609344</td><td>ocean</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 74 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t 26    & PRJNA502453 & SRR8361532 & PRJNA467728 & SRR7592711 & ocean\\\\\n",
+       "\t 58\\_r  & PRJNA502454 & SRR8361534 & PRJNA467772 & SRR7609573 & ocean\\\\\n",
+       "\t 125\\_r & PRJNA468332 & SRR7962480 & PRJNA467773 & SRR7609569 & ocean\\\\\n",
+       "\t 8     & PRJNA502455 & SRR8297879 & PRJNA467724 & SRR7592287 & ocean\\\\\n",
+       "\t 85    & PRJNA502456 & SRR8297845 & PRJNA467765 & SRR7609362 & ocean\\\\\n",
+       "\t 76    & PRJNA468305 & SRR7949679 & PRJNA467757 & SRR7608731 & ocean\\\\\n",
+       "\t 40    & PRJNA467774 & SRR7609608 & PRJNA467736 & SRR7595425 & ocean\\\\\n",
+       "\t 53    & PRJNA468299 & SRR7609574 & PRJNA502421 & SRR8361352 & ocean\\\\\n",
+       "\t 73    & PRJNA468306 & SRR7949683 & PRJNA467754 & SRR7608223 & ocean\\\\\n",
+       "\t 23    & PRJNA467775 & SRR7609632 & PRJNA467727 & SRR7633009 & ocean\\\\\n",
+       "\t 49    & PRJNA467776 & SRR7609653 & PRJNA502442 & SRR8361104 & ocean\\\\\n",
+       "\t 14    & PRJNA468308 & SRR7949682 & PRJNA502410 & SRR8360542 & ocean\\\\\n",
+       "\t 44    & PRJNA502457 & SRR8361579 & PRJNA467738 & SRR7600393 & ocean\\\\\n",
+       "\t 29    & PRJNA468309 & SRR7949681 & PRJNA467730 & SRR7593831 & ocean\\\\\n",
+       "\t 18    & PRJNA467777 & SRR7609655 & PRJNA502413 & SRR8360544 & ocean\\\\\n",
+       "\t 24    & PRJNA502458 & SRR8361603 & PRJNA502440 & SRR8360549 & ocean\\\\\n",
+       "\t 79    & PRJNA468143 & SRR7609654 & PRJNA467760 & SRR7609143 & ocean\\\\\n",
+       "\t 22    & PRJNA468300 & SRR7609599 & PRJNA502414 & SRR8360545 & ocean\\\\\n",
+       "\t 21    & PRJNA468310 & SRR7949678 & PRJNA468208 & SRR7592488 & ocean\\\\\n",
+       "\t 60    & PRJNA467778 & SRR7609828 & PRJNA502425 & SRR8361517 & ocean\\\\\n",
+       "\t 15    & PRJNA468144 & SRR7609827 & PRJNA502411 & SRR8360457 & ocean\\\\\n",
+       "\t 75    & PRJNA502459 & SRR8361602 & PRJNA467756 & SRR7608423 & ocean\\\\\n",
+       "\t 3     & PRJNA468311 & SRR7949692 & PRJNA467722 & SRR7592226 & ocean\\\\\n",
+       "\t 20    & PRJNA467779 & SRR7609829 & PRJNA467726 & SRR7592489 & ocean\\\\\n",
+       "\t 91    & PRJNA468312 & SRR7949677 & PRJNA467769 & SRR7609461 & ocean\\\\\n",
+       "\t 56    & PRJNA468152 & SRR7615220 & PRJNA467743 & SRR7601261 & ocean\\\\\n",
+       "\t 46    & PRJNA502460 & SRR8297843 & PRJNA468213 & SRR7600395 & ocean\\\\\n",
+       "\t 2     & PRJNA468313 & SRR7609607 & PRJNA467721 & SRR7592225 & ocean\\\\\n",
+       "\t 38    & PRJNA468301 & SRR7609600 & PRJNA468211 & SRR7594461 & ocean\\\\\n",
+       "\t 45    & PRJNA468314 & SRR7962234 & PRJNA467739 & SRR7600394 & ocean\\\\\n",
+       "\t ⋮ & ⋮ & ⋮ & ⋮ & ⋮ & ⋮\\\\\n",
+       "\t 32   & PRJNA468321 & SRR7962267 & PRJNA468210 & SRR7594064 & ocean\\\\\n",
+       "\t 81   & PRJNA468145 & SRR7610454 & PRJNA467762 & SRR7609163 & ocean\\\\\n",
+       "\t 70   & PRJNA468322 & SRR7962239 & PRJNA467752 & SRR7608010 & ocean\\\\\n",
+       "\t 67   & PRJNA468323 & SRR7962329 & PRJNA467750 & SRR7607757 & ocean\\\\\n",
+       "\t 33   & PRJNA467783 & SRR7610453 & PRJNA502417 & SRR8361102 & ocean\\\\\n",
+       "\t 27   & PRJNA468331 & SRR7962479 & PRJNA468209 & SRR7593830 & ocean\\\\\n",
+       "\t 34   & PRJNA502465 & SRR8297868 & PRJNA467732 & SRR7594085 & ocean\\\\\n",
+       "\t 4    & PRJNA468146 & SRR7610452 & PRJNA467723 & SRR7592236 & ocean\\\\\n",
+       "\t 57   & PRJNA468147 & SRR7610935 & PRJNA502423 & SRR8361526 & ocean\\\\\n",
+       "\t 1    & PRJNA502466 & SRR8361608 & PRJNA467720 & SRR7592212 & ocean\\\\\n",
+       "\t 47   & PRJNA468148 & SRR7610853 & PRJNA467740 & SRR7600454 & ocean\\\\\n",
+       "\t 9    & PRJNA502467 & SRR8297869 & PRJNA502408 & SRR8360547 & ocean\\\\\n",
+       "\t 77   & PRJNA468324 & SRR7962474 & PRJNA467758 & SRR7608832 & ocean\\\\\n",
+       "\t 55   & PRJNA467784 & SRR7610867 & PRJNA502422 & SRR8361371 & ocean\\\\\n",
+       "\t 10   & PRJNA468325 & SRR7962473 & PRJNA502409 & SRR8360543 & ocean\\\\\n",
+       "\t 11   & PRJNA468326 & SRR7962475 & PRJNA467725 & SRR7592321 & ocean\\\\\n",
+       "\t 58   & PRJNA502468 & SRR8297878 & PRJNA502424 & SRR8361527 & ocean\\\\\n",
+       "\t 52   & PRJNA468327 & SRR7962478 & PRJNA467742 & SRR7600455 & ocean\\\\\n",
+       "\t 51   & PRJNA468149 & SRR7611057 & PRJNA502420 & SRR8361350 & ocean\\\\\n",
+       "\t 50   & PRJNA468328 & SRR7962477 & PRJNA502419 & SRR8361349 & ocean\\\\\n",
+       "\t 90   & PRJNA467785 & SRR7611056 & PRJNA467768 & SRR7609452 & ocean\\\\\n",
+       "\t 80   & PRJNA467786 & SRR7611058 & PRJNA467761 & SRR7609166 & ocean\\\\\n",
+       "\t 89   & PRJNA468150 & SRR7611500 & PRJNA467766 & SRR7609363 & ocean\\\\\n",
+       "\t 35   & PRJNA467787 & SRR7612580 & PRJNA502441 & SRR8361101 & ocean\\\\\n",
+       "\t 71   & PRJNA468329 & SRR7962476 & PRJNA467753 & SRR7608017 & ocean\\\\\n",
+       "\t 31   & PRJNA468151 & SRR7611499 & PRJNA467731 & SRR7593934 & ocean\\\\\n",
+       "\t 84   & PRJNA502451 & SRR8393198 & PRJNA467764 & SRR7609361 & ocean\\\\\n",
+       "\t 61   & PRJNA467788 & SRR7615219 & PRJNA502426 & SRR8361516 & ocean\\\\\n",
+       "\t 36\\_r & PRJNA468330 & SRR7962481 & PRJNA467770 & SRR7609462 & ocean\\\\\n",
+       "\t 82   & PRJNA502452 & SRR8361531 & PRJNA467763 & SRR7609344 & ocean\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 74 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| 26    | PRJNA502453 | SRR8361532 | PRJNA467728 | SRR7592711 | ocean |\n",
+       "| 58_r  | PRJNA502454 | SRR8361534 | PRJNA467772 | SRR7609573 | ocean |\n",
+       "| 125_r | PRJNA468332 | SRR7962480 | PRJNA467773 | SRR7609569 | ocean |\n",
+       "| 8     | PRJNA502455 | SRR8297879 | PRJNA467724 | SRR7592287 | ocean |\n",
+       "| 85    | PRJNA502456 | SRR8297845 | PRJNA467765 | SRR7609362 | ocean |\n",
+       "| 76    | PRJNA468305 | SRR7949679 | PRJNA467757 | SRR7608731 | ocean |\n",
+       "| 40    | PRJNA467774 | SRR7609608 | PRJNA467736 | SRR7595425 | ocean |\n",
+       "| 53    | PRJNA468299 | SRR7609574 | PRJNA502421 | SRR8361352 | ocean |\n",
+       "| 73    | PRJNA468306 | SRR7949683 | PRJNA467754 | SRR7608223 | ocean |\n",
+       "| 23    | PRJNA467775 | SRR7609632 | PRJNA467727 | SRR7633009 | ocean |\n",
+       "| 49    | PRJNA467776 | SRR7609653 | PRJNA502442 | SRR8361104 | ocean |\n",
+       "| 14    | PRJNA468308 | SRR7949682 | PRJNA502410 | SRR8360542 | ocean |\n",
+       "| 44    | PRJNA502457 | SRR8361579 | PRJNA467738 | SRR7600393 | ocean |\n",
+       "| 29    | PRJNA468309 | SRR7949681 | PRJNA467730 | SRR7593831 | ocean |\n",
+       "| 18    | PRJNA467777 | SRR7609655 | PRJNA502413 | SRR8360544 | ocean |\n",
+       "| 24    | PRJNA502458 | SRR8361603 | PRJNA502440 | SRR8360549 | ocean |\n",
+       "| 79    | PRJNA468143 | SRR7609654 | PRJNA467760 | SRR7609143 | ocean |\n",
+       "| 22    | PRJNA468300 | SRR7609599 | PRJNA502414 | SRR8360545 | ocean |\n",
+       "| 21    | PRJNA468310 | SRR7949678 | PRJNA468208 | SRR7592488 | ocean |\n",
+       "| 60    | PRJNA467778 | SRR7609828 | PRJNA502425 | SRR8361517 | ocean |\n",
+       "| 15    | PRJNA468144 | SRR7609827 | PRJNA502411 | SRR8360457 | ocean |\n",
+       "| 75    | PRJNA502459 | SRR8361602 | PRJNA467756 | SRR7608423 | ocean |\n",
+       "| 3     | PRJNA468311 | SRR7949692 | PRJNA467722 | SRR7592226 | ocean |\n",
+       "| 20    | PRJNA467779 | SRR7609829 | PRJNA467726 | SRR7592489 | ocean |\n",
+       "| 91    | PRJNA468312 | SRR7949677 | PRJNA467769 | SRR7609461 | ocean |\n",
+       "| 56    | PRJNA468152 | SRR7615220 | PRJNA467743 | SRR7601261 | ocean |\n",
+       "| 46    | PRJNA502460 | SRR8297843 | PRJNA468213 | SRR7600395 | ocean |\n",
+       "| 2     | PRJNA468313 | SRR7609607 | PRJNA467721 | SRR7592225 | ocean |\n",
+       "| 38    | PRJNA468301 | SRR7609600 | PRJNA468211 | SRR7594461 | ocean |\n",
+       "| 45    | PRJNA468314 | SRR7962234 | PRJNA467739 | SRR7600394 | ocean |\n",
+       "| ⋮ | ⋮ | ⋮ | ⋮ | ⋮ | ⋮ |\n",
+       "| 32   | PRJNA468321 | SRR7962267 | PRJNA468210 | SRR7594064 | ocean |\n",
+       "| 81   | PRJNA468145 | SRR7610454 | PRJNA467762 | SRR7609163 | ocean |\n",
+       "| 70   | PRJNA468322 | SRR7962239 | PRJNA467752 | SRR7608010 | ocean |\n",
+       "| 67   | PRJNA468323 | SRR7962329 | PRJNA467750 | SRR7607757 | ocean |\n",
+       "| 33   | PRJNA467783 | SRR7610453 | PRJNA502417 | SRR8361102 | ocean |\n",
+       "| 27   | PRJNA468331 | SRR7962479 | PRJNA468209 | SRR7593830 | ocean |\n",
+       "| 34   | PRJNA502465 | SRR8297868 | PRJNA467732 | SRR7594085 | ocean |\n",
+       "| 4    | PRJNA468146 | SRR7610452 | PRJNA467723 | SRR7592236 | ocean |\n",
+       "| 57   | PRJNA468147 | SRR7610935 | PRJNA502423 | SRR8361526 | ocean |\n",
+       "| 1    | PRJNA502466 | SRR8361608 | PRJNA467720 | SRR7592212 | ocean |\n",
+       "| 47   | PRJNA468148 | SRR7610853 | PRJNA467740 | SRR7600454 | ocean |\n",
+       "| 9    | PRJNA502467 | SRR8297869 | PRJNA502408 | SRR8360547 | ocean |\n",
+       "| 77   | PRJNA468324 | SRR7962474 | PRJNA467758 | SRR7608832 | ocean |\n",
+       "| 55   | PRJNA467784 | SRR7610867 | PRJNA502422 | SRR8361371 | ocean |\n",
+       "| 10   | PRJNA468325 | SRR7962473 | PRJNA502409 | SRR8360543 | ocean |\n",
+       "| 11   | PRJNA468326 | SRR7962475 | PRJNA467725 | SRR7592321 | ocean |\n",
+       "| 58   | PRJNA502468 | SRR8297878 | PRJNA502424 | SRR8361527 | ocean |\n",
+       "| 52   | PRJNA468327 | SRR7962478 | PRJNA467742 | SRR7600455 | ocean |\n",
+       "| 51   | PRJNA468149 | SRR7611057 | PRJNA502420 | SRR8361350 | ocean |\n",
+       "| 50   | PRJNA468328 | SRR7962477 | PRJNA502419 | SRR8361349 | ocean |\n",
+       "| 90   | PRJNA467785 | SRR7611056 | PRJNA467768 | SRR7609452 | ocean |\n",
+       "| 80   | PRJNA467786 | SRR7611058 | PRJNA467761 | SRR7609166 | ocean |\n",
+       "| 89   | PRJNA468150 | SRR7611500 | PRJNA467766 | SRR7609363 | ocean |\n",
+       "| 35   | PRJNA467787 | SRR7612580 | PRJNA502441 | SRR8361101 | ocean |\n",
+       "| 71   | PRJNA468329 | SRR7962476 | PRJNA467753 | SRR7608017 | ocean |\n",
+       "| 31   | PRJNA468151 | SRR7611499 | PRJNA467731 | SRR7593934 | ocean |\n",
+       "| 84   | PRJNA502451 | SRR8393198 | PRJNA467764 | SRR7609361 | ocean |\n",
+       "| 61   | PRJNA467788 | SRR7615219 | PRJNA502426 | SRR8361516 | ocean |\n",
+       "| 36_r | PRJNA468330 | SRR7962481 | PRJNA467770 | SRR7609462 | ocean |\n",
+       "| 82   | PRJNA502452 | SRR8361531 | PRJNA467763 | SRR7609344 | ocean |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "   sample_name mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1  26          PRJNA502453         SRR8361532        PRJNA467728        \n",
+       "2  58_r        PRJNA502454         SRR8361534        PRJNA467772        \n",
+       "3  125_r       PRJNA468332         SRR7962480        PRJNA467773        \n",
+       "4  8           PRJNA502455         SRR8297879        PRJNA467724        \n",
+       "5  85          PRJNA502456         SRR8297845        PRJNA467765        \n",
+       "6  76          PRJNA468305         SRR7949679        PRJNA467757        \n",
+       "7  40          PRJNA467774         SRR7609608        PRJNA467736        \n",
+       "8  53          PRJNA468299         SRR7609574        PRJNA502421        \n",
+       "9  73          PRJNA468306         SRR7949683        PRJNA467754        \n",
+       "10 23          PRJNA467775         SRR7609632        PRJNA467727        \n",
+       "11 49          PRJNA467776         SRR7609653        PRJNA502442        \n",
+       "12 14          PRJNA468308         SRR7949682        PRJNA502410        \n",
+       "13 44          PRJNA502457         SRR8361579        PRJNA467738        \n",
+       "14 29          PRJNA468309         SRR7949681        PRJNA467730        \n",
+       "15 18          PRJNA467777         SRR7609655        PRJNA502413        \n",
+       "16 24          PRJNA502458         SRR8361603        PRJNA502440        \n",
+       "17 79          PRJNA468143         SRR7609654        PRJNA467760        \n",
+       "18 22          PRJNA468300         SRR7609599        PRJNA502414        \n",
+       "19 21          PRJNA468310         SRR7949678        PRJNA468208        \n",
+       "20 60          PRJNA467778         SRR7609828        PRJNA502425        \n",
+       "21 15          PRJNA468144         SRR7609827        PRJNA502411        \n",
+       "22 75          PRJNA502459         SRR8361602        PRJNA467756        \n",
+       "23 3           PRJNA468311         SRR7949692        PRJNA467722        \n",
+       "24 20          PRJNA467779         SRR7609829        PRJNA467726        \n",
+       "25 91          PRJNA468312         SRR7949677        PRJNA467769        \n",
+       "26 56          PRJNA468152         SRR7615220        PRJNA467743        \n",
+       "27 46          PRJNA502460         SRR8297843        PRJNA468213        \n",
+       "28 2           PRJNA468313         SRR7609607        PRJNA467721        \n",
+       "29 38          PRJNA468301         SRR7609600        PRJNA468211        \n",
+       "30 45          PRJNA468314         SRR7962234        PRJNA467739        \n",
+       "⋮  ⋮           ⋮                   ⋮                 ⋮                  \n",
+       "45 32          PRJNA468321         SRR7962267        PRJNA468210        \n",
+       "46 81          PRJNA468145         SRR7610454        PRJNA467762        \n",
+       "47 70          PRJNA468322         SRR7962239        PRJNA467752        \n",
+       "48 67          PRJNA468323         SRR7962329        PRJNA467750        \n",
+       "49 33          PRJNA467783         SRR7610453        PRJNA502417        \n",
+       "50 27          PRJNA468331         SRR7962479        PRJNA468209        \n",
+       "51 34          PRJNA502465         SRR8297868        PRJNA467732        \n",
+       "52 4           PRJNA468146         SRR7610452        PRJNA467723        \n",
+       "53 57          PRJNA468147         SRR7610935        PRJNA502423        \n",
+       "54 1           PRJNA502466         SRR8361608        PRJNA467720        \n",
+       "55 47          PRJNA468148         SRR7610853        PRJNA467740        \n",
+       "56 9           PRJNA502467         SRR8297869        PRJNA502408        \n",
+       "57 77          PRJNA468324         SRR7962474        PRJNA467758        \n",
+       "58 55          PRJNA467784         SRR7610867        PRJNA502422        \n",
+       "59 10          PRJNA468325         SRR7962473        PRJNA502409        \n",
+       "60 11          PRJNA468326         SRR7962475        PRJNA467725        \n",
+       "61 58          PRJNA502468         SRR8297878        PRJNA502424        \n",
+       "62 52          PRJNA468327         SRR7962478        PRJNA467742        \n",
+       "63 51          PRJNA468149         SRR7611057        PRJNA502420        \n",
+       "64 50          PRJNA468328         SRR7962477        PRJNA502419        \n",
+       "65 90          PRJNA467785         SRR7611056        PRJNA467768        \n",
+       "66 80          PRJNA467786         SRR7611058        PRJNA467761        \n",
+       "67 89          PRJNA468150         SRR7611500        PRJNA467766        \n",
+       "68 35          PRJNA467787         SRR7612580        PRJNA502441        \n",
+       "69 71          PRJNA468329         SRR7962476        PRJNA467753        \n",
+       "70 31          PRJNA468151         SRR7611499        PRJNA467731        \n",
+       "71 84          PRJNA502451         SRR8393198        PRJNA467764        \n",
+       "72 61          PRJNA467788         SRR7615219        PRJNA502426        \n",
+       "73 36_r        PRJNA468330         SRR7962481        PRJNA467770        \n",
+       "74 82          PRJNA502452         SRR8361531        PRJNA467763        \n",
+       "   mgx_run_accession sample_type\n",
+       "1  SRR7592711        ocean      \n",
+       "2  SRR7609573        ocean      \n",
+       "3  SRR7609569        ocean      \n",
+       "4  SRR7592287        ocean      \n",
+       "5  SRR7609362        ocean      \n",
+       "6  SRR7608731        ocean      \n",
+       "7  SRR7595425        ocean      \n",
+       "8  SRR8361352        ocean      \n",
+       "9  SRR7608223        ocean      \n",
+       "10 SRR7633009        ocean      \n",
+       "11 SRR8361104        ocean      \n",
+       "12 SRR8360542        ocean      \n",
+       "13 SRR7600393        ocean      \n",
+       "14 SRR7593831        ocean      \n",
+       "15 SRR8360544        ocean      \n",
+       "16 SRR8360549        ocean      \n",
+       "17 SRR7609143        ocean      \n",
+       "18 SRR8360545        ocean      \n",
+       "19 SRR7592488        ocean      \n",
+       "20 SRR8361517        ocean      \n",
+       "21 SRR8360457        ocean      \n",
+       "22 SRR7608423        ocean      \n",
+       "23 SRR7592226        ocean      \n",
+       "24 SRR7592489        ocean      \n",
+       "25 SRR7609461        ocean      \n",
+       "26 SRR7601261        ocean      \n",
+       "27 SRR7600395        ocean      \n",
+       "28 SRR7592225        ocean      \n",
+       "29 SRR7594461        ocean      \n",
+       "30 SRR7600394        ocean      \n",
+       "⋮  ⋮                 ⋮          \n",
+       "45 SRR7594064        ocean      \n",
+       "46 SRR7609163        ocean      \n",
+       "47 SRR7608010        ocean      \n",
+       "48 SRR7607757        ocean      \n",
+       "49 SRR8361102        ocean      \n",
+       "50 SRR7593830        ocean      \n",
+       "51 SRR7594085        ocean      \n",
+       "52 SRR7592236        ocean      \n",
+       "53 SRR8361526        ocean      \n",
+       "54 SRR7592212        ocean      \n",
+       "55 SRR7600454        ocean      \n",
+       "56 SRR8360547        ocean      \n",
+       "57 SRR7608832        ocean      \n",
+       "58 SRR8361371        ocean      \n",
+       "59 SRR8360543        ocean      \n",
+       "60 SRR7592321        ocean      \n",
+       "61 SRR8361527        ocean      \n",
+       "62 SRR7600455        ocean      \n",
+       "63 SRR8361350        ocean      \n",
+       "64 SRR8361349        ocean      \n",
+       "65 SRR7609452        ocean      \n",
+       "66 SRR7609166        ocean      \n",
+       "67 SRR7609363        ocean      \n",
+       "68 SRR8361101        ocean      \n",
+       "69 SRR7608017        ocean      \n",
+       "70 SRR7593934        ocean      \n",
+       "71 SRR7609361        ocean      \n",
+       "72 SRR8361516        ocean      \n",
+       "73 SRR7609462        ocean      \n",
+       "74 SRR7609344        ocean      "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "moran010B_mtx_vs_mgx <- moran010B %>%\n",
+    "  left_join(moran010B_run_accessions, by = c(\"mtx_study_accession\" = \"study_accession\")) %>%\n",
+    "  select(sample_name, mtx_study_accession, mtx_run_accession = run_accession, mgx_study_accession) %>%\n",
+    "  left_join(moran010B_run_accessions, by = c(\"mgx_study_accession\" = \"study_accession\")) %>%\n",
+    "  select(sample_name, mtx_study_accession, mtx_run_accession, mgx_study_accession, mgx_run_accession = run_accession) %>%\n",
+    "  mutate(sample_type = \"ocean\")\n",
+    "\n",
+    "moran010B_mtx_vs_mgx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2261971e",
+   "metadata": {},
+   "source": [
+    "## PRJNA603240"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "1c8d6131",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna603240 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA603240&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "155a92e3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 10 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>sample_106</td><td>PRJNA603240</td><td>SRR10968230</td><td>PRJNA603240</td><td>SRR10968263</td><td>deadwood</td></tr>\n",
+       "\t<tr><td>sample_069</td><td>PRJNA603240</td><td>SRR10968231</td><td>PRJNA603240</td><td>SRR10968264</td><td>deadwood</td></tr>\n",
+       "\t<tr><td>sample_055</td><td>PRJNA603240</td><td>SRR10968232</td><td>PRJNA603240</td><td>SRR10968265</td><td>deadwood</td></tr>\n",
+       "\t<tr><td>sample_049</td><td>PRJNA603240</td><td>SRR10968233</td><td>PRJNA603240</td><td>SRR10968266</td><td>deadwood</td></tr>\n",
+       "\t<tr><td>sample_031</td><td>PRJNA603240</td><td>SRR10968234</td><td>PRJNA603240</td><td>SRR10968267</td><td>deadwood</td></tr>\n",
+       "\t<tr><td>sample_116</td><td>PRJNA603240</td><td>SRR10968236</td><td>PRJNA603240</td><td>SRR10968225</td><td>deadwood</td></tr>\n",
+       "\t<tr><td>sample_110</td><td>PRJNA603240</td><td>SRR10968237</td><td>PRJNA603240</td><td>SRR10968226</td><td>deadwood</td></tr>\n",
+       "\t<tr><td>sample_044</td><td>PRJNA603240</td><td>SRR10968238</td><td>PRJNA603240</td><td>SRR10968227</td><td>deadwood</td></tr>\n",
+       "\t<tr><td>sample_007</td><td>PRJNA603240</td><td>SRR10968239</td><td>PRJNA603240</td><td>SRR10968228</td><td>deadwood</td></tr>\n",
+       "\t<tr><td>sample_006</td><td>PRJNA603240</td><td>SRR10968240</td><td>PRJNA603240</td><td>SRR10968229</td><td>deadwood</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 10 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t sample\\_106 & PRJNA603240 & SRR10968230 & PRJNA603240 & SRR10968263 & deadwood\\\\\n",
+       "\t sample\\_069 & PRJNA603240 & SRR10968231 & PRJNA603240 & SRR10968264 & deadwood\\\\\n",
+       "\t sample\\_055 & PRJNA603240 & SRR10968232 & PRJNA603240 & SRR10968265 & deadwood\\\\\n",
+       "\t sample\\_049 & PRJNA603240 & SRR10968233 & PRJNA603240 & SRR10968266 & deadwood\\\\\n",
+       "\t sample\\_031 & PRJNA603240 & SRR10968234 & PRJNA603240 & SRR10968267 & deadwood\\\\\n",
+       "\t sample\\_116 & PRJNA603240 & SRR10968236 & PRJNA603240 & SRR10968225 & deadwood\\\\\n",
+       "\t sample\\_110 & PRJNA603240 & SRR10968237 & PRJNA603240 & SRR10968226 & deadwood\\\\\n",
+       "\t sample\\_044 & PRJNA603240 & SRR10968238 & PRJNA603240 & SRR10968227 & deadwood\\\\\n",
+       "\t sample\\_007 & PRJNA603240 & SRR10968239 & PRJNA603240 & SRR10968228 & deadwood\\\\\n",
+       "\t sample\\_006 & PRJNA603240 & SRR10968240 & PRJNA603240 & SRR10968229 & deadwood\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 10 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| sample_106 | PRJNA603240 | SRR10968230 | PRJNA603240 | SRR10968263 | deadwood |\n",
+       "| sample_069 | PRJNA603240 | SRR10968231 | PRJNA603240 | SRR10968264 | deadwood |\n",
+       "| sample_055 | PRJNA603240 | SRR10968232 | PRJNA603240 | SRR10968265 | deadwood |\n",
+       "| sample_049 | PRJNA603240 | SRR10968233 | PRJNA603240 | SRR10968266 | deadwood |\n",
+       "| sample_031 | PRJNA603240 | SRR10968234 | PRJNA603240 | SRR10968267 | deadwood |\n",
+       "| sample_116 | PRJNA603240 | SRR10968236 | PRJNA603240 | SRR10968225 | deadwood |\n",
+       "| sample_110 | PRJNA603240 | SRR10968237 | PRJNA603240 | SRR10968226 | deadwood |\n",
+       "| sample_044 | PRJNA603240 | SRR10968238 | PRJNA603240 | SRR10968227 | deadwood |\n",
+       "| sample_007 | PRJNA603240 | SRR10968239 | PRJNA603240 | SRR10968228 | deadwood |\n",
+       "| sample_006 | PRJNA603240 | SRR10968240 | PRJNA603240 | SRR10968229 | deadwood |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "   sample_name mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1  sample_106  PRJNA603240         SRR10968230       PRJNA603240        \n",
+       "2  sample_069  PRJNA603240         SRR10968231       PRJNA603240        \n",
+       "3  sample_055  PRJNA603240         SRR10968232       PRJNA603240        \n",
+       "4  sample_049  PRJNA603240         SRR10968233       PRJNA603240        \n",
+       "5  sample_031  PRJNA603240         SRR10968234       PRJNA603240        \n",
+       "6  sample_116  PRJNA603240         SRR10968236       PRJNA603240        \n",
+       "7  sample_110  PRJNA603240         SRR10968237       PRJNA603240        \n",
+       "8  sample_044  PRJNA603240         SRR10968238       PRJNA603240        \n",
+       "9  sample_007  PRJNA603240         SRR10968239       PRJNA603240        \n",
+       "10 sample_006  PRJNA603240         SRR10968240       PRJNA603240        \n",
+       "   mgx_run_accession sample_type\n",
+       "1  SRR10968263       deadwood   \n",
+       "2  SRR10968264       deadwood   \n",
+       "3  SRR10968265       deadwood   \n",
+       "4  SRR10968266       deadwood   \n",
+       "5  SRR10968267       deadwood   \n",
+       "6  SRR10968225       deadwood   \n",
+       "7  SRR10968226       deadwood   \n",
+       "8  SRR10968227       deadwood   \n",
+       "9  SRR10968228       deadwood   \n",
+       "10 SRR10968229       deadwood   "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna603240_mtx <- prjna603240 %>% \n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  filter(library_selection == \"RANDOM PCR\") %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna603240_mgx <- prjna603240 %>% \n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjna603240_mtx_vs_mgx <- left_join(prjna603240_mtx, prjna603240_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"deadwood\")\n",
+    "\n",
+    "prjna603240_mtx_vs_mgx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4bf62859",
+   "metadata": {},
+   "source": [
+    "## PRJNA202380"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "10459508",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna202380 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA202380&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "de539bd6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna202380 <- prjna202380 %>%\n",
+    "  filter(instrument_platform == \"ILLUMINA\") %>%\n",
+    "  mutate(sample_name = gsub(\"Illumina HiSeq 2000 paired end sequencing; \", \"\", experiment_title),\n",
+    "         sample_name = gsub(\" metatranscri[op]tomic sample\", \"\", sample_name),\n",
+    "         sample_name = gsub(\" metagenomic sample\", \"\", sample_name),\n",
+    "         sample_name = gsub(\"Illumina HiSeq 2000 sequencing; \", \"\", sample_name)) %>%\n",
+    "  select(study_accession, run_accession,library_source, sample_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "4b7fc613",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 20 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>Tag1363-1</td><td>PRJNA202380</td><td>SRR1138694</td><td>PRJNA202380</td><td>SRR1267595</td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1111-1</td><td>PRJNA202380</td><td>SRR1138697</td><td>PRJNA202380</td><td>SRR1222429</td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1111-2</td><td>PRJNA202380</td><td>SRR1138702</td><td>PRJNA202380</td><td>SRR1222431</td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1234-1</td><td>PRJNA202380</td><td>SRR1206249</td><td>PRJNA202380</td><td>SRR1206671</td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1494-1</td><td>PRJNA202380</td><td>SRR873450 </td><td>PRJNA202380</td><td>SRR873595 </td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1283-1</td><td>PRJNA202380</td><td>SRR873451 </td><td>PRJNA202380</td><td>SRR873596 </td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1435-1</td><td>PRJNA202380</td><td>SRR873452 </td><td>PRJNA202380</td><td>SRR873597 </td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1494-2</td><td>PRJNA202380</td><td>SRR873453 </td><td>PRJNA202380</td><td>SRR873598 </td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1265-1</td><td>PRJNA202380</td><td>SRR873454 </td><td>PRJNA202380</td><td>SRR873599 </td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1435-2</td><td>PRJNA202380</td><td>SRR873455 </td><td>PRJNA202380</td><td>SRR873600 </td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1283-2</td><td>PRJNA202380</td><td>SRR873456 </td><td>PRJNA202380</td><td>SRR873601 </td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1265-2</td><td>PRJNA202380</td><td>SRR873457 </td><td>PRJNA202380</td><td>SRR873602 </td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1363-2</td><td>PRJNA202380</td><td>SRR873458 </td><td>PRJNA202380</td><td>SRR873603 </td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1174-1</td><td>PRJNA202380</td><td>SRR873459 </td><td>PRJNA202380</td><td>SRR873604 </td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1234-2</td><td>PRJNA202380</td><td>SRR873460 </td><td>PRJNA202380</td><td>SRR873605 </td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1586-1</td><td>PRJNA202380</td><td>SRR873461 </td><td>PRJNA202380</td><td>SRR873606 </td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1586-2</td><td>PRJNA202380</td><td>SRR873462 </td><td>PRJNA202380</td><td>SRR873607 </td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1333-1</td><td>PRJNA202380</td><td>SRR873463 </td><td>PRJNA202380</td><td>SRR873608 </td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1174-2</td><td>PRJNA202380</td><td>SRR873464 </td><td>PRJNA202380</td><td>SRR873609 </td><td>sheep_rumen</td></tr>\n",
+       "\t<tr><td>Tag1333-2</td><td>PRJNA202380</td><td>SRR873465 </td><td>PRJNA202380</td><td>SRR873610 </td><td>sheep_rumen</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 20 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t Tag1363-1 & PRJNA202380 & SRR1138694 & PRJNA202380 & SRR1267595 & sheep\\_rumen\\\\\n",
+       "\t Tag1111-1 & PRJNA202380 & SRR1138697 & PRJNA202380 & SRR1222429 & sheep\\_rumen\\\\\n",
+       "\t Tag1111-2 & PRJNA202380 & SRR1138702 & PRJNA202380 & SRR1222431 & sheep\\_rumen\\\\\n",
+       "\t Tag1234-1 & PRJNA202380 & SRR1206249 & PRJNA202380 & SRR1206671 & sheep\\_rumen\\\\\n",
+       "\t Tag1494-1 & PRJNA202380 & SRR873450  & PRJNA202380 & SRR873595  & sheep\\_rumen\\\\\n",
+       "\t Tag1283-1 & PRJNA202380 & SRR873451  & PRJNA202380 & SRR873596  & sheep\\_rumen\\\\\n",
+       "\t Tag1435-1 & PRJNA202380 & SRR873452  & PRJNA202380 & SRR873597  & sheep\\_rumen\\\\\n",
+       "\t Tag1494-2 & PRJNA202380 & SRR873453  & PRJNA202380 & SRR873598  & sheep\\_rumen\\\\\n",
+       "\t Tag1265-1 & PRJNA202380 & SRR873454  & PRJNA202380 & SRR873599  & sheep\\_rumen\\\\\n",
+       "\t Tag1435-2 & PRJNA202380 & SRR873455  & PRJNA202380 & SRR873600  & sheep\\_rumen\\\\\n",
+       "\t Tag1283-2 & PRJNA202380 & SRR873456  & PRJNA202380 & SRR873601  & sheep\\_rumen\\\\\n",
+       "\t Tag1265-2 & PRJNA202380 & SRR873457  & PRJNA202380 & SRR873602  & sheep\\_rumen\\\\\n",
+       "\t Tag1363-2 & PRJNA202380 & SRR873458  & PRJNA202380 & SRR873603  & sheep\\_rumen\\\\\n",
+       "\t Tag1174-1 & PRJNA202380 & SRR873459  & PRJNA202380 & SRR873604  & sheep\\_rumen\\\\\n",
+       "\t Tag1234-2 & PRJNA202380 & SRR873460  & PRJNA202380 & SRR873605  & sheep\\_rumen\\\\\n",
+       "\t Tag1586-1 & PRJNA202380 & SRR873461  & PRJNA202380 & SRR873606  & sheep\\_rumen\\\\\n",
+       "\t Tag1586-2 & PRJNA202380 & SRR873462  & PRJNA202380 & SRR873607  & sheep\\_rumen\\\\\n",
+       "\t Tag1333-1 & PRJNA202380 & SRR873463  & PRJNA202380 & SRR873608  & sheep\\_rumen\\\\\n",
+       "\t Tag1174-2 & PRJNA202380 & SRR873464  & PRJNA202380 & SRR873609  & sheep\\_rumen\\\\\n",
+       "\t Tag1333-2 & PRJNA202380 & SRR873465  & PRJNA202380 & SRR873610  & sheep\\_rumen\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 20 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| Tag1363-1 | PRJNA202380 | SRR1138694 | PRJNA202380 | SRR1267595 | sheep_rumen |\n",
+       "| Tag1111-1 | PRJNA202380 | SRR1138697 | PRJNA202380 | SRR1222429 | sheep_rumen |\n",
+       "| Tag1111-2 | PRJNA202380 | SRR1138702 | PRJNA202380 | SRR1222431 | sheep_rumen |\n",
+       "| Tag1234-1 | PRJNA202380 | SRR1206249 | PRJNA202380 | SRR1206671 | sheep_rumen |\n",
+       "| Tag1494-1 | PRJNA202380 | SRR873450  | PRJNA202380 | SRR873595  | sheep_rumen |\n",
+       "| Tag1283-1 | PRJNA202380 | SRR873451  | PRJNA202380 | SRR873596  | sheep_rumen |\n",
+       "| Tag1435-1 | PRJNA202380 | SRR873452  | PRJNA202380 | SRR873597  | sheep_rumen |\n",
+       "| Tag1494-2 | PRJNA202380 | SRR873453  | PRJNA202380 | SRR873598  | sheep_rumen |\n",
+       "| Tag1265-1 | PRJNA202380 | SRR873454  | PRJNA202380 | SRR873599  | sheep_rumen |\n",
+       "| Tag1435-2 | PRJNA202380 | SRR873455  | PRJNA202380 | SRR873600  | sheep_rumen |\n",
+       "| Tag1283-2 | PRJNA202380 | SRR873456  | PRJNA202380 | SRR873601  | sheep_rumen |\n",
+       "| Tag1265-2 | PRJNA202380 | SRR873457  | PRJNA202380 | SRR873602  | sheep_rumen |\n",
+       "| Tag1363-2 | PRJNA202380 | SRR873458  | PRJNA202380 | SRR873603  | sheep_rumen |\n",
+       "| Tag1174-1 | PRJNA202380 | SRR873459  | PRJNA202380 | SRR873604  | sheep_rumen |\n",
+       "| Tag1234-2 | PRJNA202380 | SRR873460  | PRJNA202380 | SRR873605  | sheep_rumen |\n",
+       "| Tag1586-1 | PRJNA202380 | SRR873461  | PRJNA202380 | SRR873606  | sheep_rumen |\n",
+       "| Tag1586-2 | PRJNA202380 | SRR873462  | PRJNA202380 | SRR873607  | sheep_rumen |\n",
+       "| Tag1333-1 | PRJNA202380 | SRR873463  | PRJNA202380 | SRR873608  | sheep_rumen |\n",
+       "| Tag1174-2 | PRJNA202380 | SRR873464  | PRJNA202380 | SRR873609  | sheep_rumen |\n",
+       "| Tag1333-2 | PRJNA202380 | SRR873465  | PRJNA202380 | SRR873610  | sheep_rumen |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "   sample_name mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1  Tag1363-1   PRJNA202380         SRR1138694        PRJNA202380        \n",
+       "2  Tag1111-1   PRJNA202380         SRR1138697        PRJNA202380        \n",
+       "3  Tag1111-2   PRJNA202380         SRR1138702        PRJNA202380        \n",
+       "4  Tag1234-1   PRJNA202380         SRR1206249        PRJNA202380        \n",
+       "5  Tag1494-1   PRJNA202380         SRR873450         PRJNA202380        \n",
+       "6  Tag1283-1   PRJNA202380         SRR873451         PRJNA202380        \n",
+       "7  Tag1435-1   PRJNA202380         SRR873452         PRJNA202380        \n",
+       "8  Tag1494-2   PRJNA202380         SRR873453         PRJNA202380        \n",
+       "9  Tag1265-1   PRJNA202380         SRR873454         PRJNA202380        \n",
+       "10 Tag1435-2   PRJNA202380         SRR873455         PRJNA202380        \n",
+       "11 Tag1283-2   PRJNA202380         SRR873456         PRJNA202380        \n",
+       "12 Tag1265-2   PRJNA202380         SRR873457         PRJNA202380        \n",
+       "13 Tag1363-2   PRJNA202380         SRR873458         PRJNA202380        \n",
+       "14 Tag1174-1   PRJNA202380         SRR873459         PRJNA202380        \n",
+       "15 Tag1234-2   PRJNA202380         SRR873460         PRJNA202380        \n",
+       "16 Tag1586-1   PRJNA202380         SRR873461         PRJNA202380        \n",
+       "17 Tag1586-2   PRJNA202380         SRR873462         PRJNA202380        \n",
+       "18 Tag1333-1   PRJNA202380         SRR873463         PRJNA202380        \n",
+       "19 Tag1174-2   PRJNA202380         SRR873464         PRJNA202380        \n",
+       "20 Tag1333-2   PRJNA202380         SRR873465         PRJNA202380        \n",
+       "   mgx_run_accession sample_type\n",
+       "1  SRR1267595        sheep_rumen\n",
+       "2  SRR1222429        sheep_rumen\n",
+       "3  SRR1222431        sheep_rumen\n",
+       "4  SRR1206671        sheep_rumen\n",
+       "5  SRR873595         sheep_rumen\n",
+       "6  SRR873596         sheep_rumen\n",
+       "7  SRR873597         sheep_rumen\n",
+       "8  SRR873598         sheep_rumen\n",
+       "9  SRR873599         sheep_rumen\n",
+       "10 SRR873600         sheep_rumen\n",
+       "11 SRR873601         sheep_rumen\n",
+       "12 SRR873602         sheep_rumen\n",
+       "13 SRR873603         sheep_rumen\n",
+       "14 SRR873604         sheep_rumen\n",
+       "15 SRR873605         sheep_rumen\n",
+       "16 SRR873606         sheep_rumen\n",
+       "17 SRR873607         sheep_rumen\n",
+       "18 SRR873608         sheep_rumen\n",
+       "19 SRR873609         sheep_rumen\n",
+       "20 SRR873610         sheep_rumen"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna202380_mtx <- prjna202380 %>% \n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  select(sample_name,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna202380_mgx <- prjna202380 %>% \n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  select(sample_name,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjna202380_mtx_vs_mgx <- left_join(prjna202380_mtx, prjna202380_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"sheep_rumen\")\n",
+    "\n",
+    "prjna202380_mtx_vs_mgx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cde73933",
+   "metadata": {},
+   "source": [
+    "## PRJNA541981"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "1a764bbb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna541981 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA541981&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "378b1ac3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna541981_mtx <- prjna541981 %>% \n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna541981_mgx <- prjna541981 %>% \n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  filter(library_strategy == \"WGS\") %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjna541981_mtx_vs_mgx <- left_join(prjna541981_mtx, prjna541981_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"human_skin\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ae3f271d",
+   "metadata": {},
+   "source": [
+    "## PRJNA797778"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "a1b07276",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna797778 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA797778&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "id": "d479bfe9",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 180 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>UAB088_W2D1 </td><td>PRJNA797778</td><td>SRR17858151</td><td>PRJNA797778</td><td>SRR17635672</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB082_W10D2</td><td>PRJNA797778</td><td>SRR17858152</td><td>PRJNA797778</td><td>SRR17635674</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB082_W5D7 </td><td>PRJNA797778</td><td>SRR17858153</td><td>PRJNA797778</td><td>SRR17635676</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB082_W3D7 </td><td>PRJNA797778</td><td>SRR17858154</td><td>PRJNA797778</td><td>SRR17635677</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB082_W2D5 </td><td>PRJNA797778</td><td>SRR17858155</td><td>PRJNA797778</td><td>SRR17635678</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB079_W10D1</td><td>PRJNA797778</td><td>SRR17858156</td><td>PRJNA797778</td><td>SRR17635679</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB079_W7D6 </td><td>PRJNA797778</td><td>SRR17858157</td><td>PRJNA797778</td><td>SRR17635680</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB079_W6D7 </td><td>PRJNA797778</td><td>SRR17858158</td><td>PRJNA797778</td><td>SRR17635681</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB079_W3D7 </td><td>PRJNA797778</td><td>SRR17858159</td><td>PRJNA797778</td><td>SRR17635682</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB079_W2D2 </td><td>PRJNA797778</td><td>SRR17858160</td><td>PRJNA797778</td><td>SRR17635683</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB006_W2D2 </td><td>PRJNA797778</td><td>SRR17858161</td><td>PRJNA797778</td><td>SRR17635801</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB077_W9D7 </td><td>PRJNA797778</td><td>SRR17858162</td><td>PRJNA797778</td><td>SRR17635685</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB077_W8D2 </td><td>PRJNA797778</td><td>SRR17858163</td><td>PRJNA797778</td><td>SRR17635686</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB077_W5D7 </td><td>PRJNA797778</td><td>SRR17858164</td><td>PRJNA797778</td><td>SRR17635687</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB077_W3D1 </td><td>PRJNA797778</td><td>SRR17858165</td><td>PRJNA797778</td><td>SRR17635688</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB077_W1D7 </td><td>PRJNA797778</td><td>SRR17858166</td><td>PRJNA797778</td><td>SRR17635689</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB071_W10D2</td><td>PRJNA797778</td><td>SRR17858167</td><td>PRJNA797778</td><td>SRR17635690</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB071_W7D7 </td><td>PRJNA797778</td><td>SRR17858168</td><td>PRJNA797778</td><td>SRR17635691</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB071_W5D7 </td><td>PRJNA797778</td><td>SRR17858169</td><td>PRJNA797778</td><td>SRR17635692</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB071_W3D7 </td><td>PRJNA797778</td><td>SRR17858170</td><td>PRJNA797778</td><td>SRR17635693</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB071_W1D7 </td><td>PRJNA797778</td><td>SRR17858171</td><td>PRJNA797778</td><td>SRR17635694</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB002_W5D7 </td><td>PRJNA797778</td><td>SRR17858172</td><td>PRJNA797778</td><td>SRR17635804</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>AYAC02_W9D3 </td><td>PRJNA797778</td><td>SRR17858173</td><td>PRJNA797778</td><td>SRR17635818</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB060_W10D2</td><td>PRJNA797778</td><td>SRR17858174</td><td>PRJNA797778</td><td>SRR17635696</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB060_W7D7 </td><td>PRJNA797778</td><td>SRR17858175</td><td>PRJNA797778</td><td>SRR17635697</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB060_W5D7 </td><td>PRJNA797778</td><td>SRR17858176</td><td>PRJNA797778</td><td>SRR17635698</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB060_W3D7 </td><td>PRJNA797778</td><td>SRR17858177</td><td>PRJNA797778</td><td>SRR17635763</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB060_W1D6 </td><td>PRJNA797778</td><td>SRR17858178</td><td>PRJNA797778</td><td>SRR17635764</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB052_W10D2</td><td>PRJNA797778</td><td>SRR17858179</td><td>PRJNA797778</td><td>SRR17635765</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB052_W8D3 </td><td>PRJNA797778</td><td>SRR17858180</td><td>PRJNA797778</td><td>SRR17635766</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>⋮</td><td>⋮</td><td>⋮</td><td>⋮</td><td>⋮</td><td>⋮</td></tr>\n",
+       "\t<tr><td>UAB116_W1D7 </td><td>PRJNA797778</td><td>SRR17858301</td><td>PRJNA797778</td><td>SRR17635741</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB110_W10D4</td><td>PRJNA797778</td><td>SRR17858302</td><td>PRJNA797778</td><td>SRR17635742</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB110_W7D7 </td><td>PRJNA797778</td><td>SRR17858303</td><td>PRJNA797778</td><td>SRR17635743</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB110_W6D2 </td><td>PRJNA797778</td><td>SRR17858304</td><td>PRJNA797778</td><td>SRR17635744</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB110_W3D7 </td><td>PRJNA797778</td><td>SRR17858305</td><td>PRJNA797778</td><td>SRR17635745</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB010_W5D6 </td><td>PRJNA797778</td><td>SRR17858306</td><td>PRJNA797778</td><td>SRR17635490</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB110_W1D7 </td><td>PRJNA797778</td><td>SRR17858307</td><td>PRJNA797778</td><td>SRR17635746</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB106_W9D7 </td><td>PRJNA797778</td><td>SRR17858308</td><td>PRJNA797778</td><td>SRR17635748</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB106_W7D7 </td><td>PRJNA797778</td><td>SRR17858309</td><td>PRJNA797778</td><td>SRR17635749</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB106_W5D4 </td><td>PRJNA797778</td><td>SRR17858310</td><td>PRJNA797778</td><td>SRR17635750</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB106_W3D7 </td><td>PRJNA797778</td><td>SRR17858311</td><td>PRJNA797778</td><td>SRR17635751</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB106_W1D7 </td><td>PRJNA797778</td><td>SRR17858312</td><td>PRJNA797778</td><td>SRR17635752</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB096_W9D7 </td><td>PRJNA797778</td><td>SRR17858313</td><td>PRJNA797778</td><td>SRR17635753</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB096_W7D3 </td><td>PRJNA797778</td><td>SRR17858314</td><td>PRJNA797778</td><td>SRR17635754</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB096_W5D3 </td><td>PRJNA797778</td><td>SRR17858315</td><td>PRJNA797778</td><td>SRR17635755</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB096_W3D3 </td><td>PRJNA797778</td><td>SRR17858316</td><td>PRJNA797778</td><td>SRR17635756</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB010_W3D1 </td><td>PRJNA797778</td><td>SRR17858317</td><td>PRJNA797778</td><td>SRR17635491</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB096_W1D5 </td><td>PRJNA797778</td><td>SRR17858318</td><td>PRJNA797778</td><td>SRR17635757</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB093_W9D6 </td><td>PRJNA797778</td><td>SRR17858319</td><td>PRJNA797778</td><td>SRR17635759</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB093_W7D7 </td><td>PRJNA797778</td><td>SRR17858320</td><td>PRJNA797778</td><td>SRR17635760</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB093_W5D7 </td><td>PRJNA797778</td><td>SRR17858321</td><td>PRJNA797778</td><td>SRR17635761</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB093_W4D2 </td><td>PRJNA797778</td><td>SRR17858322</td><td>PRJNA797778</td><td>SRR17635762</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB093_W1D7 </td><td>PRJNA797778</td><td>SRR17858323</td><td>PRJNA797778</td><td>SRR17635667</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB088_W10D1</td><td>PRJNA797778</td><td>SRR17858324</td><td>PRJNA797778</td><td>SRR17635668</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB088_W7D6 </td><td>PRJNA797778</td><td>SRR17858325</td><td>PRJNA797778</td><td>SRR17635669</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB088_W6D1 </td><td>PRJNA797778</td><td>SRR17858326</td><td>PRJNA797778</td><td>SRR17635670</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB088_W4D1 </td><td>PRJNA797778</td><td>SRR17858327</td><td>PRJNA797778</td><td>SRR17635671</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>UAB007_W1D7 </td><td>PRJNA797778</td><td>SRR17858328</td><td>PRJNA797778</td><td>SRR17635795</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>AYAC02_W1D7 </td><td>PRJNA797778</td><td>SRR17858329</td><td>PRJNA797778</td><td>SRR17635794</td><td>human_vagina</td></tr>\n",
+       "\t<tr><td>EM04_W3D7   </td><td>PRJNA797778</td><td>SRR17858330</td><td>PRJNA797778</td><td>SRR17635711</td><td>human_vagina</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 180 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t UAB088\\_W2D1  & PRJNA797778 & SRR17858151 & PRJNA797778 & SRR17635672 & human\\_vagina\\\\\n",
+       "\t UAB082\\_W10D2 & PRJNA797778 & SRR17858152 & PRJNA797778 & SRR17635674 & human\\_vagina\\\\\n",
+       "\t UAB082\\_W5D7  & PRJNA797778 & SRR17858153 & PRJNA797778 & SRR17635676 & human\\_vagina\\\\\n",
+       "\t UAB082\\_W3D7  & PRJNA797778 & SRR17858154 & PRJNA797778 & SRR17635677 & human\\_vagina\\\\\n",
+       "\t UAB082\\_W2D5  & PRJNA797778 & SRR17858155 & PRJNA797778 & SRR17635678 & human\\_vagina\\\\\n",
+       "\t UAB079\\_W10D1 & PRJNA797778 & SRR17858156 & PRJNA797778 & SRR17635679 & human\\_vagina\\\\\n",
+       "\t UAB079\\_W7D6  & PRJNA797778 & SRR17858157 & PRJNA797778 & SRR17635680 & human\\_vagina\\\\\n",
+       "\t UAB079\\_W6D7  & PRJNA797778 & SRR17858158 & PRJNA797778 & SRR17635681 & human\\_vagina\\\\\n",
+       "\t UAB079\\_W3D7  & PRJNA797778 & SRR17858159 & PRJNA797778 & SRR17635682 & human\\_vagina\\\\\n",
+       "\t UAB079\\_W2D2  & PRJNA797778 & SRR17858160 & PRJNA797778 & SRR17635683 & human\\_vagina\\\\\n",
+       "\t UAB006\\_W2D2  & PRJNA797778 & SRR17858161 & PRJNA797778 & SRR17635801 & human\\_vagina\\\\\n",
+       "\t UAB077\\_W9D7  & PRJNA797778 & SRR17858162 & PRJNA797778 & SRR17635685 & human\\_vagina\\\\\n",
+       "\t UAB077\\_W8D2  & PRJNA797778 & SRR17858163 & PRJNA797778 & SRR17635686 & human\\_vagina\\\\\n",
+       "\t UAB077\\_W5D7  & PRJNA797778 & SRR17858164 & PRJNA797778 & SRR17635687 & human\\_vagina\\\\\n",
+       "\t UAB077\\_W3D1  & PRJNA797778 & SRR17858165 & PRJNA797778 & SRR17635688 & human\\_vagina\\\\\n",
+       "\t UAB077\\_W1D7  & PRJNA797778 & SRR17858166 & PRJNA797778 & SRR17635689 & human\\_vagina\\\\\n",
+       "\t UAB071\\_W10D2 & PRJNA797778 & SRR17858167 & PRJNA797778 & SRR17635690 & human\\_vagina\\\\\n",
+       "\t UAB071\\_W7D7  & PRJNA797778 & SRR17858168 & PRJNA797778 & SRR17635691 & human\\_vagina\\\\\n",
+       "\t UAB071\\_W5D7  & PRJNA797778 & SRR17858169 & PRJNA797778 & SRR17635692 & human\\_vagina\\\\\n",
+       "\t UAB071\\_W3D7  & PRJNA797778 & SRR17858170 & PRJNA797778 & SRR17635693 & human\\_vagina\\\\\n",
+       "\t UAB071\\_W1D7  & PRJNA797778 & SRR17858171 & PRJNA797778 & SRR17635694 & human\\_vagina\\\\\n",
+       "\t UAB002\\_W5D7  & PRJNA797778 & SRR17858172 & PRJNA797778 & SRR17635804 & human\\_vagina\\\\\n",
+       "\t AYAC02\\_W9D3  & PRJNA797778 & SRR17858173 & PRJNA797778 & SRR17635818 & human\\_vagina\\\\\n",
+       "\t UAB060\\_W10D2 & PRJNA797778 & SRR17858174 & PRJNA797778 & SRR17635696 & human\\_vagina\\\\\n",
+       "\t UAB060\\_W7D7  & PRJNA797778 & SRR17858175 & PRJNA797778 & SRR17635697 & human\\_vagina\\\\\n",
+       "\t UAB060\\_W5D7  & PRJNA797778 & SRR17858176 & PRJNA797778 & SRR17635698 & human\\_vagina\\\\\n",
+       "\t UAB060\\_W3D7  & PRJNA797778 & SRR17858177 & PRJNA797778 & SRR17635763 & human\\_vagina\\\\\n",
+       "\t UAB060\\_W1D6  & PRJNA797778 & SRR17858178 & PRJNA797778 & SRR17635764 & human\\_vagina\\\\\n",
+       "\t UAB052\\_W10D2 & PRJNA797778 & SRR17858179 & PRJNA797778 & SRR17635765 & human\\_vagina\\\\\n",
+       "\t UAB052\\_W8D3  & PRJNA797778 & SRR17858180 & PRJNA797778 & SRR17635766 & human\\_vagina\\\\\n",
+       "\t ⋮ & ⋮ & ⋮ & ⋮ & ⋮ & ⋮\\\\\n",
+       "\t UAB116\\_W1D7  & PRJNA797778 & SRR17858301 & PRJNA797778 & SRR17635741 & human\\_vagina\\\\\n",
+       "\t UAB110\\_W10D4 & PRJNA797778 & SRR17858302 & PRJNA797778 & SRR17635742 & human\\_vagina\\\\\n",
+       "\t UAB110\\_W7D7  & PRJNA797778 & SRR17858303 & PRJNA797778 & SRR17635743 & human\\_vagina\\\\\n",
+       "\t UAB110\\_W6D2  & PRJNA797778 & SRR17858304 & PRJNA797778 & SRR17635744 & human\\_vagina\\\\\n",
+       "\t UAB110\\_W3D7  & PRJNA797778 & SRR17858305 & PRJNA797778 & SRR17635745 & human\\_vagina\\\\\n",
+       "\t UAB010\\_W5D6  & PRJNA797778 & SRR17858306 & PRJNA797778 & SRR17635490 & human\\_vagina\\\\\n",
+       "\t UAB110\\_W1D7  & PRJNA797778 & SRR17858307 & PRJNA797778 & SRR17635746 & human\\_vagina\\\\\n",
+       "\t UAB106\\_W9D7  & PRJNA797778 & SRR17858308 & PRJNA797778 & SRR17635748 & human\\_vagina\\\\\n",
+       "\t UAB106\\_W7D7  & PRJNA797778 & SRR17858309 & PRJNA797778 & SRR17635749 & human\\_vagina\\\\\n",
+       "\t UAB106\\_W5D4  & PRJNA797778 & SRR17858310 & PRJNA797778 & SRR17635750 & human\\_vagina\\\\\n",
+       "\t UAB106\\_W3D7  & PRJNA797778 & SRR17858311 & PRJNA797778 & SRR17635751 & human\\_vagina\\\\\n",
+       "\t UAB106\\_W1D7  & PRJNA797778 & SRR17858312 & PRJNA797778 & SRR17635752 & human\\_vagina\\\\\n",
+       "\t UAB096\\_W9D7  & PRJNA797778 & SRR17858313 & PRJNA797778 & SRR17635753 & human\\_vagina\\\\\n",
+       "\t UAB096\\_W7D3  & PRJNA797778 & SRR17858314 & PRJNA797778 & SRR17635754 & human\\_vagina\\\\\n",
+       "\t UAB096\\_W5D3  & PRJNA797778 & SRR17858315 & PRJNA797778 & SRR17635755 & human\\_vagina\\\\\n",
+       "\t UAB096\\_W3D3  & PRJNA797778 & SRR17858316 & PRJNA797778 & SRR17635756 & human\\_vagina\\\\\n",
+       "\t UAB010\\_W3D1  & PRJNA797778 & SRR17858317 & PRJNA797778 & SRR17635491 & human\\_vagina\\\\\n",
+       "\t UAB096\\_W1D5  & PRJNA797778 & SRR17858318 & PRJNA797778 & SRR17635757 & human\\_vagina\\\\\n",
+       "\t UAB093\\_W9D6  & PRJNA797778 & SRR17858319 & PRJNA797778 & SRR17635759 & human\\_vagina\\\\\n",
+       "\t UAB093\\_W7D7  & PRJNA797778 & SRR17858320 & PRJNA797778 & SRR17635760 & human\\_vagina\\\\\n",
+       "\t UAB093\\_W5D7  & PRJNA797778 & SRR17858321 & PRJNA797778 & SRR17635761 & human\\_vagina\\\\\n",
+       "\t UAB093\\_W4D2  & PRJNA797778 & SRR17858322 & PRJNA797778 & SRR17635762 & human\\_vagina\\\\\n",
+       "\t UAB093\\_W1D7  & PRJNA797778 & SRR17858323 & PRJNA797778 & SRR17635667 & human\\_vagina\\\\\n",
+       "\t UAB088\\_W10D1 & PRJNA797778 & SRR17858324 & PRJNA797778 & SRR17635668 & human\\_vagina\\\\\n",
+       "\t UAB088\\_W7D6  & PRJNA797778 & SRR17858325 & PRJNA797778 & SRR17635669 & human\\_vagina\\\\\n",
+       "\t UAB088\\_W6D1  & PRJNA797778 & SRR17858326 & PRJNA797778 & SRR17635670 & human\\_vagina\\\\\n",
+       "\t UAB088\\_W4D1  & PRJNA797778 & SRR17858327 & PRJNA797778 & SRR17635671 & human\\_vagina\\\\\n",
+       "\t UAB007\\_W1D7  & PRJNA797778 & SRR17858328 & PRJNA797778 & SRR17635795 & human\\_vagina\\\\\n",
+       "\t AYAC02\\_W1D7  & PRJNA797778 & SRR17858329 & PRJNA797778 & SRR17635794 & human\\_vagina\\\\\n",
+       "\t EM04\\_W3D7    & PRJNA797778 & SRR17858330 & PRJNA797778 & SRR17635711 & human\\_vagina\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 180 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| UAB088_W2D1  | PRJNA797778 | SRR17858151 | PRJNA797778 | SRR17635672 | human_vagina |\n",
+       "| UAB082_W10D2 | PRJNA797778 | SRR17858152 | PRJNA797778 | SRR17635674 | human_vagina |\n",
+       "| UAB082_W5D7  | PRJNA797778 | SRR17858153 | PRJNA797778 | SRR17635676 | human_vagina |\n",
+       "| UAB082_W3D7  | PRJNA797778 | SRR17858154 | PRJNA797778 | SRR17635677 | human_vagina |\n",
+       "| UAB082_W2D5  | PRJNA797778 | SRR17858155 | PRJNA797778 | SRR17635678 | human_vagina |\n",
+       "| UAB079_W10D1 | PRJNA797778 | SRR17858156 | PRJNA797778 | SRR17635679 | human_vagina |\n",
+       "| UAB079_W7D6  | PRJNA797778 | SRR17858157 | PRJNA797778 | SRR17635680 | human_vagina |\n",
+       "| UAB079_W6D7  | PRJNA797778 | SRR17858158 | PRJNA797778 | SRR17635681 | human_vagina |\n",
+       "| UAB079_W3D7  | PRJNA797778 | SRR17858159 | PRJNA797778 | SRR17635682 | human_vagina |\n",
+       "| UAB079_W2D2  | PRJNA797778 | SRR17858160 | PRJNA797778 | SRR17635683 | human_vagina |\n",
+       "| UAB006_W2D2  | PRJNA797778 | SRR17858161 | PRJNA797778 | SRR17635801 | human_vagina |\n",
+       "| UAB077_W9D7  | PRJNA797778 | SRR17858162 | PRJNA797778 | SRR17635685 | human_vagina |\n",
+       "| UAB077_W8D2  | PRJNA797778 | SRR17858163 | PRJNA797778 | SRR17635686 | human_vagina |\n",
+       "| UAB077_W5D7  | PRJNA797778 | SRR17858164 | PRJNA797778 | SRR17635687 | human_vagina |\n",
+       "| UAB077_W3D1  | PRJNA797778 | SRR17858165 | PRJNA797778 | SRR17635688 | human_vagina |\n",
+       "| UAB077_W1D7  | PRJNA797778 | SRR17858166 | PRJNA797778 | SRR17635689 | human_vagina |\n",
+       "| UAB071_W10D2 | PRJNA797778 | SRR17858167 | PRJNA797778 | SRR17635690 | human_vagina |\n",
+       "| UAB071_W7D7  | PRJNA797778 | SRR17858168 | PRJNA797778 | SRR17635691 | human_vagina |\n",
+       "| UAB071_W5D7  | PRJNA797778 | SRR17858169 | PRJNA797778 | SRR17635692 | human_vagina |\n",
+       "| UAB071_W3D7  | PRJNA797778 | SRR17858170 | PRJNA797778 | SRR17635693 | human_vagina |\n",
+       "| UAB071_W1D7  | PRJNA797778 | SRR17858171 | PRJNA797778 | SRR17635694 | human_vagina |\n",
+       "| UAB002_W5D7  | PRJNA797778 | SRR17858172 | PRJNA797778 | SRR17635804 | human_vagina |\n",
+       "| AYAC02_W9D3  | PRJNA797778 | SRR17858173 | PRJNA797778 | SRR17635818 | human_vagina |\n",
+       "| UAB060_W10D2 | PRJNA797778 | SRR17858174 | PRJNA797778 | SRR17635696 | human_vagina |\n",
+       "| UAB060_W7D7  | PRJNA797778 | SRR17858175 | PRJNA797778 | SRR17635697 | human_vagina |\n",
+       "| UAB060_W5D7  | PRJNA797778 | SRR17858176 | PRJNA797778 | SRR17635698 | human_vagina |\n",
+       "| UAB060_W3D7  | PRJNA797778 | SRR17858177 | PRJNA797778 | SRR17635763 | human_vagina |\n",
+       "| UAB060_W1D6  | PRJNA797778 | SRR17858178 | PRJNA797778 | SRR17635764 | human_vagina |\n",
+       "| UAB052_W10D2 | PRJNA797778 | SRR17858179 | PRJNA797778 | SRR17635765 | human_vagina |\n",
+       "| UAB052_W8D3  | PRJNA797778 | SRR17858180 | PRJNA797778 | SRR17635766 | human_vagina |\n",
+       "| ⋮ | ⋮ | ⋮ | ⋮ | ⋮ | ⋮ |\n",
+       "| UAB116_W1D7  | PRJNA797778 | SRR17858301 | PRJNA797778 | SRR17635741 | human_vagina |\n",
+       "| UAB110_W10D4 | PRJNA797778 | SRR17858302 | PRJNA797778 | SRR17635742 | human_vagina |\n",
+       "| UAB110_W7D7  | PRJNA797778 | SRR17858303 | PRJNA797778 | SRR17635743 | human_vagina |\n",
+       "| UAB110_W6D2  | PRJNA797778 | SRR17858304 | PRJNA797778 | SRR17635744 | human_vagina |\n",
+       "| UAB110_W3D7  | PRJNA797778 | SRR17858305 | PRJNA797778 | SRR17635745 | human_vagina |\n",
+       "| UAB010_W5D6  | PRJNA797778 | SRR17858306 | PRJNA797778 | SRR17635490 | human_vagina |\n",
+       "| UAB110_W1D7  | PRJNA797778 | SRR17858307 | PRJNA797778 | SRR17635746 | human_vagina |\n",
+       "| UAB106_W9D7  | PRJNA797778 | SRR17858308 | PRJNA797778 | SRR17635748 | human_vagina |\n",
+       "| UAB106_W7D7  | PRJNA797778 | SRR17858309 | PRJNA797778 | SRR17635749 | human_vagina |\n",
+       "| UAB106_W5D4  | PRJNA797778 | SRR17858310 | PRJNA797778 | SRR17635750 | human_vagina |\n",
+       "| UAB106_W3D7  | PRJNA797778 | SRR17858311 | PRJNA797778 | SRR17635751 | human_vagina |\n",
+       "| UAB106_W1D7  | PRJNA797778 | SRR17858312 | PRJNA797778 | SRR17635752 | human_vagina |\n",
+       "| UAB096_W9D7  | PRJNA797778 | SRR17858313 | PRJNA797778 | SRR17635753 | human_vagina |\n",
+       "| UAB096_W7D3  | PRJNA797778 | SRR17858314 | PRJNA797778 | SRR17635754 | human_vagina |\n",
+       "| UAB096_W5D3  | PRJNA797778 | SRR17858315 | PRJNA797778 | SRR17635755 | human_vagina |\n",
+       "| UAB096_W3D3  | PRJNA797778 | SRR17858316 | PRJNA797778 | SRR17635756 | human_vagina |\n",
+       "| UAB010_W3D1  | PRJNA797778 | SRR17858317 | PRJNA797778 | SRR17635491 | human_vagina |\n",
+       "| UAB096_W1D5  | PRJNA797778 | SRR17858318 | PRJNA797778 | SRR17635757 | human_vagina |\n",
+       "| UAB093_W9D6  | PRJNA797778 | SRR17858319 | PRJNA797778 | SRR17635759 | human_vagina |\n",
+       "| UAB093_W7D7  | PRJNA797778 | SRR17858320 | PRJNA797778 | SRR17635760 | human_vagina |\n",
+       "| UAB093_W5D7  | PRJNA797778 | SRR17858321 | PRJNA797778 | SRR17635761 | human_vagina |\n",
+       "| UAB093_W4D2  | PRJNA797778 | SRR17858322 | PRJNA797778 | SRR17635762 | human_vagina |\n",
+       "| UAB093_W1D7  | PRJNA797778 | SRR17858323 | PRJNA797778 | SRR17635667 | human_vagina |\n",
+       "| UAB088_W10D1 | PRJNA797778 | SRR17858324 | PRJNA797778 | SRR17635668 | human_vagina |\n",
+       "| UAB088_W7D6  | PRJNA797778 | SRR17858325 | PRJNA797778 | SRR17635669 | human_vagina |\n",
+       "| UAB088_W6D1  | PRJNA797778 | SRR17858326 | PRJNA797778 | SRR17635670 | human_vagina |\n",
+       "| UAB088_W4D1  | PRJNA797778 | SRR17858327 | PRJNA797778 | SRR17635671 | human_vagina |\n",
+       "| UAB007_W1D7  | PRJNA797778 | SRR17858328 | PRJNA797778 | SRR17635795 | human_vagina |\n",
+       "| AYAC02_W1D7  | PRJNA797778 | SRR17858329 | PRJNA797778 | SRR17635794 | human_vagina |\n",
+       "| EM04_W3D7    | PRJNA797778 | SRR17858330 | PRJNA797778 | SRR17635711 | human_vagina |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "    sample_name  mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1   UAB088_W2D1  PRJNA797778         SRR17858151       PRJNA797778        \n",
+       "2   UAB082_W10D2 PRJNA797778         SRR17858152       PRJNA797778        \n",
+       "3   UAB082_W5D7  PRJNA797778         SRR17858153       PRJNA797778        \n",
+       "4   UAB082_W3D7  PRJNA797778         SRR17858154       PRJNA797778        \n",
+       "5   UAB082_W2D5  PRJNA797778         SRR17858155       PRJNA797778        \n",
+       "6   UAB079_W10D1 PRJNA797778         SRR17858156       PRJNA797778        \n",
+       "7   UAB079_W7D6  PRJNA797778         SRR17858157       PRJNA797778        \n",
+       "8   UAB079_W6D7  PRJNA797778         SRR17858158       PRJNA797778        \n",
+       "9   UAB079_W3D7  PRJNA797778         SRR17858159       PRJNA797778        \n",
+       "10  UAB079_W2D2  PRJNA797778         SRR17858160       PRJNA797778        \n",
+       "11  UAB006_W2D2  PRJNA797778         SRR17858161       PRJNA797778        \n",
+       "12  UAB077_W9D7  PRJNA797778         SRR17858162       PRJNA797778        \n",
+       "13  UAB077_W8D2  PRJNA797778         SRR17858163       PRJNA797778        \n",
+       "14  UAB077_W5D7  PRJNA797778         SRR17858164       PRJNA797778        \n",
+       "15  UAB077_W3D1  PRJNA797778         SRR17858165       PRJNA797778        \n",
+       "16  UAB077_W1D7  PRJNA797778         SRR17858166       PRJNA797778        \n",
+       "17  UAB071_W10D2 PRJNA797778         SRR17858167       PRJNA797778        \n",
+       "18  UAB071_W7D7  PRJNA797778         SRR17858168       PRJNA797778        \n",
+       "19  UAB071_W5D7  PRJNA797778         SRR17858169       PRJNA797778        \n",
+       "20  UAB071_W3D7  PRJNA797778         SRR17858170       PRJNA797778        \n",
+       "21  UAB071_W1D7  PRJNA797778         SRR17858171       PRJNA797778        \n",
+       "22  UAB002_W5D7  PRJNA797778         SRR17858172       PRJNA797778        \n",
+       "23  AYAC02_W9D3  PRJNA797778         SRR17858173       PRJNA797778        \n",
+       "24  UAB060_W10D2 PRJNA797778         SRR17858174       PRJNA797778        \n",
+       "25  UAB060_W7D7  PRJNA797778         SRR17858175       PRJNA797778        \n",
+       "26  UAB060_W5D7  PRJNA797778         SRR17858176       PRJNA797778        \n",
+       "27  UAB060_W3D7  PRJNA797778         SRR17858177       PRJNA797778        \n",
+       "28  UAB060_W1D6  PRJNA797778         SRR17858178       PRJNA797778        \n",
+       "29  UAB052_W10D2 PRJNA797778         SRR17858179       PRJNA797778        \n",
+       "30  UAB052_W8D3  PRJNA797778         SRR17858180       PRJNA797778        \n",
+       "⋮   ⋮            ⋮                   ⋮                 ⋮                  \n",
+       "151 UAB116_W1D7  PRJNA797778         SRR17858301       PRJNA797778        \n",
+       "152 UAB110_W10D4 PRJNA797778         SRR17858302       PRJNA797778        \n",
+       "153 UAB110_W7D7  PRJNA797778         SRR17858303       PRJNA797778        \n",
+       "154 UAB110_W6D2  PRJNA797778         SRR17858304       PRJNA797778        \n",
+       "155 UAB110_W3D7  PRJNA797778         SRR17858305       PRJNA797778        \n",
+       "156 UAB010_W5D6  PRJNA797778         SRR17858306       PRJNA797778        \n",
+       "157 UAB110_W1D7  PRJNA797778         SRR17858307       PRJNA797778        \n",
+       "158 UAB106_W9D7  PRJNA797778         SRR17858308       PRJNA797778        \n",
+       "159 UAB106_W7D7  PRJNA797778         SRR17858309       PRJNA797778        \n",
+       "160 UAB106_W5D4  PRJNA797778         SRR17858310       PRJNA797778        \n",
+       "161 UAB106_W3D7  PRJNA797778         SRR17858311       PRJNA797778        \n",
+       "162 UAB106_W1D7  PRJNA797778         SRR17858312       PRJNA797778        \n",
+       "163 UAB096_W9D7  PRJNA797778         SRR17858313       PRJNA797778        \n",
+       "164 UAB096_W7D3  PRJNA797778         SRR17858314       PRJNA797778        \n",
+       "165 UAB096_W5D3  PRJNA797778         SRR17858315       PRJNA797778        \n",
+       "166 UAB096_W3D3  PRJNA797778         SRR17858316       PRJNA797778        \n",
+       "167 UAB010_W3D1  PRJNA797778         SRR17858317       PRJNA797778        \n",
+       "168 UAB096_W1D5  PRJNA797778         SRR17858318       PRJNA797778        \n",
+       "169 UAB093_W9D6  PRJNA797778         SRR17858319       PRJNA797778        \n",
+       "170 UAB093_W7D7  PRJNA797778         SRR17858320       PRJNA797778        \n",
+       "171 UAB093_W5D7  PRJNA797778         SRR17858321       PRJNA797778        \n",
+       "172 UAB093_W4D2  PRJNA797778         SRR17858322       PRJNA797778        \n",
+       "173 UAB093_W1D7  PRJNA797778         SRR17858323       PRJNA797778        \n",
+       "174 UAB088_W10D1 PRJNA797778         SRR17858324       PRJNA797778        \n",
+       "175 UAB088_W7D6  PRJNA797778         SRR17858325       PRJNA797778        \n",
+       "176 UAB088_W6D1  PRJNA797778         SRR17858326       PRJNA797778        \n",
+       "177 UAB088_W4D1  PRJNA797778         SRR17858327       PRJNA797778        \n",
+       "178 UAB007_W1D7  PRJNA797778         SRR17858328       PRJNA797778        \n",
+       "179 AYAC02_W1D7  PRJNA797778         SRR17858329       PRJNA797778        \n",
+       "180 EM04_W3D7    PRJNA797778         SRR17858330       PRJNA797778        \n",
+       "    mgx_run_accession sample_type \n",
+       "1   SRR17635672       human_vagina\n",
+       "2   SRR17635674       human_vagina\n",
+       "3   SRR17635676       human_vagina\n",
+       "4   SRR17635677       human_vagina\n",
+       "5   SRR17635678       human_vagina\n",
+       "6   SRR17635679       human_vagina\n",
+       "7   SRR17635680       human_vagina\n",
+       "8   SRR17635681       human_vagina\n",
+       "9   SRR17635682       human_vagina\n",
+       "10  SRR17635683       human_vagina\n",
+       "11  SRR17635801       human_vagina\n",
+       "12  SRR17635685       human_vagina\n",
+       "13  SRR17635686       human_vagina\n",
+       "14  SRR17635687       human_vagina\n",
+       "15  SRR17635688       human_vagina\n",
+       "16  SRR17635689       human_vagina\n",
+       "17  SRR17635690       human_vagina\n",
+       "18  SRR17635691       human_vagina\n",
+       "19  SRR17635692       human_vagina\n",
+       "20  SRR17635693       human_vagina\n",
+       "21  SRR17635694       human_vagina\n",
+       "22  SRR17635804       human_vagina\n",
+       "23  SRR17635818       human_vagina\n",
+       "24  SRR17635696       human_vagina\n",
+       "25  SRR17635697       human_vagina\n",
+       "26  SRR17635698       human_vagina\n",
+       "27  SRR17635763       human_vagina\n",
+       "28  SRR17635764       human_vagina\n",
+       "29  SRR17635765       human_vagina\n",
+       "30  SRR17635766       human_vagina\n",
+       "⋮   ⋮                 ⋮           \n",
+       "151 SRR17635741       human_vagina\n",
+       "152 SRR17635742       human_vagina\n",
+       "153 SRR17635743       human_vagina\n",
+       "154 SRR17635744       human_vagina\n",
+       "155 SRR17635745       human_vagina\n",
+       "156 SRR17635490       human_vagina\n",
+       "157 SRR17635746       human_vagina\n",
+       "158 SRR17635748       human_vagina\n",
+       "159 SRR17635749       human_vagina\n",
+       "160 SRR17635750       human_vagina\n",
+       "161 SRR17635751       human_vagina\n",
+       "162 SRR17635752       human_vagina\n",
+       "163 SRR17635753       human_vagina\n",
+       "164 SRR17635754       human_vagina\n",
+       "165 SRR17635755       human_vagina\n",
+       "166 SRR17635756       human_vagina\n",
+       "167 SRR17635491       human_vagina\n",
+       "168 SRR17635757       human_vagina\n",
+       "169 SRR17635759       human_vagina\n",
+       "170 SRR17635760       human_vagina\n",
+       "171 SRR17635761       human_vagina\n",
+       "172 SRR17635762       human_vagina\n",
+       "173 SRR17635667       human_vagina\n",
+       "174 SRR17635668       human_vagina\n",
+       "175 SRR17635669       human_vagina\n",
+       "176 SRR17635670       human_vagina\n",
+       "177 SRR17635671       human_vagina\n",
+       "178 SRR17635795       human_vagina\n",
+       "179 SRR17635794       human_vagina\n",
+       "180 SRR17635711       human_vagina"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna797778_mtx <- prjna797778 %>% \n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna797778_mgx <- prjna797778 %>% \n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjna797778_mtx_vs_mgx <- left_join(prjna797778_mtx, prjna797778_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"human_vagina\")\n",
+    "\n",
+    "prjna797778_mtx_vs_mgx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e19c96ba",
+   "metadata": {},
+   "source": [
+    "## PRJNA339914"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "id": "bb6f3136",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna339914 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA339914&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "id": "3c6e9e34",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 4 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>MV_FEI4_t2Q15</td><td>PRJNA339914</td><td>SRR4100706</td><td>PRJNA339914</td><td>SRR4052039</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MV_FEI5_t3Q15</td><td>PRJNA339914</td><td>SRR4100707</td><td>PRJNA339914</td><td>SRR4052042</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MV_FEM4_t2Q15</td><td>PRJNA339914</td><td>SRR4100708</td><td>PRJNA339914</td><td>SRR4052025</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MV_FEM5_t3Q15</td><td>PRJNA339914</td><td>SRR4100709</td><td>PRJNA339914</td><td>SRR4052028</td><td>human_gut</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 4 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t MV\\_FEI4\\_t2Q15 & PRJNA339914 & SRR4100706 & PRJNA339914 & SRR4052039 & human\\_gut\\\\\n",
+       "\t MV\\_FEI5\\_t3Q15 & PRJNA339914 & SRR4100707 & PRJNA339914 & SRR4052042 & human\\_gut\\\\\n",
+       "\t MV\\_FEM4\\_t2Q15 & PRJNA339914 & SRR4100708 & PRJNA339914 & SRR4052025 & human\\_gut\\\\\n",
+       "\t MV\\_FEM5\\_t3Q15 & PRJNA339914 & SRR4100709 & PRJNA339914 & SRR4052028 & human\\_gut\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 4 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| MV_FEI4_t2Q15 | PRJNA339914 | SRR4100706 | PRJNA339914 | SRR4052039 | human_gut |\n",
+       "| MV_FEI5_t3Q15 | PRJNA339914 | SRR4100707 | PRJNA339914 | SRR4052042 | human_gut |\n",
+       "| MV_FEM4_t2Q15 | PRJNA339914 | SRR4100708 | PRJNA339914 | SRR4052025 | human_gut |\n",
+       "| MV_FEM5_t3Q15 | PRJNA339914 | SRR4100709 | PRJNA339914 | SRR4052028 | human_gut |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  sample_name   mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1 MV_FEI4_t2Q15 PRJNA339914         SRR4100706        PRJNA339914        \n",
+       "2 MV_FEI5_t3Q15 PRJNA339914         SRR4100707        PRJNA339914        \n",
+       "3 MV_FEM4_t2Q15 PRJNA339914         SRR4100708        PRJNA339914        \n",
+       "4 MV_FEM5_t3Q15 PRJNA339914         SRR4100709        PRJNA339914        \n",
+       "  mgx_run_accession sample_type\n",
+       "1 SRR4052039        human_gut  \n",
+       "2 SRR4052042        human_gut  \n",
+       "3 SRR4052025        human_gut  \n",
+       "4 SRR4052028        human_gut  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna339914_mtx <- prjna339914 %>% \n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  mutate(sample_name = gsub(\"RNA\", \"\", sample_alias)) %>%\n",
+    "  select(sample_name,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna339914_mgx <- prjna339914 %>% \n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjna339914_mtx_vs_mgx <- left_join(prjna339914_mtx, prjna339914_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"human_gut\")\n",
+    "\n",
+    "prjna339914_mtx_vs_mgx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a6999921",
+   "metadata": {},
+   "source": [
+    "## PRJEB33889"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "id": "8d446ea8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjeb33889 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJEB33889&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "id": "a4d19362",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 8 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>M1</td><td>PRJEB33889</td><td>ERR3473664</td><td>PRJEB33889</td><td>ERR3473656</td><td>mouse_cecum</td></tr>\n",
+       "\t<tr><td>M2</td><td>PRJEB33889</td><td>ERR3473665</td><td>PRJEB33889</td><td>ERR3473657</td><td>mouse_cecum</td></tr>\n",
+       "\t<tr><td>M3</td><td>PRJEB33889</td><td>ERR3473666</td><td>PRJEB33889</td><td>ERR3473658</td><td>mouse_cecum</td></tr>\n",
+       "\t<tr><td>M4</td><td>PRJEB33889</td><td>ERR3473667</td><td>PRJEB33889</td><td>ERR3473659</td><td>mouse_cecum</td></tr>\n",
+       "\t<tr><td>M5</td><td>PRJEB33889</td><td>ERR3473668</td><td>PRJEB33889</td><td>ERR3473660</td><td>mouse_cecum</td></tr>\n",
+       "\t<tr><td>M6</td><td>PRJEB33889</td><td>ERR3473669</td><td>PRJEB33889</td><td>ERR3473661</td><td>mouse_cecum</td></tr>\n",
+       "\t<tr><td>M7</td><td>PRJEB33889</td><td>ERR3473670</td><td>PRJEB33889</td><td>ERR3473662</td><td>mouse_cecum</td></tr>\n",
+       "\t<tr><td>M8</td><td>PRJEB33889</td><td>ERR3473671</td><td>PRJEB33889</td><td>ERR3473663</td><td>mouse_cecum</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 8 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t M1 & PRJEB33889 & ERR3473664 & PRJEB33889 & ERR3473656 & mouse\\_cecum\\\\\n",
+       "\t M2 & PRJEB33889 & ERR3473665 & PRJEB33889 & ERR3473657 & mouse\\_cecum\\\\\n",
+       "\t M3 & PRJEB33889 & ERR3473666 & PRJEB33889 & ERR3473658 & mouse\\_cecum\\\\\n",
+       "\t M4 & PRJEB33889 & ERR3473667 & PRJEB33889 & ERR3473659 & mouse\\_cecum\\\\\n",
+       "\t M5 & PRJEB33889 & ERR3473668 & PRJEB33889 & ERR3473660 & mouse\\_cecum\\\\\n",
+       "\t M6 & PRJEB33889 & ERR3473669 & PRJEB33889 & ERR3473661 & mouse\\_cecum\\\\\n",
+       "\t M7 & PRJEB33889 & ERR3473670 & PRJEB33889 & ERR3473662 & mouse\\_cecum\\\\\n",
+       "\t M8 & PRJEB33889 & ERR3473671 & PRJEB33889 & ERR3473663 & mouse\\_cecum\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 8 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| M1 | PRJEB33889 | ERR3473664 | PRJEB33889 | ERR3473656 | mouse_cecum |\n",
+       "| M2 | PRJEB33889 | ERR3473665 | PRJEB33889 | ERR3473657 | mouse_cecum |\n",
+       "| M3 | PRJEB33889 | ERR3473666 | PRJEB33889 | ERR3473658 | mouse_cecum |\n",
+       "| M4 | PRJEB33889 | ERR3473667 | PRJEB33889 | ERR3473659 | mouse_cecum |\n",
+       "| M5 | PRJEB33889 | ERR3473668 | PRJEB33889 | ERR3473660 | mouse_cecum |\n",
+       "| M6 | PRJEB33889 | ERR3473669 | PRJEB33889 | ERR3473661 | mouse_cecum |\n",
+       "| M7 | PRJEB33889 | ERR3473670 | PRJEB33889 | ERR3473662 | mouse_cecum |\n",
+       "| M8 | PRJEB33889 | ERR3473671 | PRJEB33889 | ERR3473663 | mouse_cecum |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  sample_name mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1 M1          PRJEB33889          ERR3473664        PRJEB33889         \n",
+       "2 M2          PRJEB33889          ERR3473665        PRJEB33889         \n",
+       "3 M3          PRJEB33889          ERR3473666        PRJEB33889         \n",
+       "4 M4          PRJEB33889          ERR3473667        PRJEB33889         \n",
+       "5 M5          PRJEB33889          ERR3473668        PRJEB33889         \n",
+       "6 M6          PRJEB33889          ERR3473669        PRJEB33889         \n",
+       "7 M7          PRJEB33889          ERR3473670        PRJEB33889         \n",
+       "8 M8          PRJEB33889          ERR3473671        PRJEB33889         \n",
+       "  mgx_run_accession sample_type\n",
+       "1 ERR3473656        mouse_cecum\n",
+       "2 ERR3473657        mouse_cecum\n",
+       "3 ERR3473658        mouse_cecum\n",
+       "4 ERR3473659        mouse_cecum\n",
+       "5 ERR3473660        mouse_cecum\n",
+       "6 ERR3473661        mouse_cecum\n",
+       "7 ERR3473662        mouse_cecum\n",
+       "8 ERR3473663        mouse_cecum"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjeb33889_mtx <- prjeb33889 %>% \n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  mutate(sample_name = gsub(\"T\", \"\", sample_alias)) %>%\n",
+    "  select(sample_name,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjeb33889_mgx <- prjeb33889 %>% \n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  filter(!grepl(\"16S\", sample_alias)) %>%\n",
+    "  mutate(sample_name = gsub(\"G\", \"\", sample_alias)) %>%\n",
+    "  select(sample_name,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjeb33889_mtx_vs_mgx <- left_join(prjeb33889_mtx, prjeb33889_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"mouse_cecum\")\n",
+    "\n",
+    "prjeb33889_mtx_vs_mgx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f04c78a3",
+   "metadata": {},
+   "source": [
+    "## PRJNA698464"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "7fcee7aa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna698464 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA698464&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "ccada9e6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 4 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>ad_supplemented_with_nitrogen_data_2</td><td>PRJNA698464</td><td>SRR13618127</td><td>PRJNA698464</td><td>SRR13618123</td><td>bioreactor</td></tr>\n",
+       "\t<tr><td>ad_supplemented_with_nitrogen_data_1</td><td>PRJNA698464</td><td>SRR13618128</td><td>PRJNA698464</td><td>SRR13618124</td><td>bioreactor</td></tr>\n",
+       "\t<tr><td>ad_supplemented_with_hydrogen_data_2</td><td>PRJNA698464</td><td>SRR13618129</td><td>PRJNA698464</td><td>SRR13618125</td><td>bioreactor</td></tr>\n",
+       "\t<tr><td>ad_supplemented_with_hydrogen_data_1</td><td>PRJNA698464</td><td>SRR13618130</td><td>PRJNA698464</td><td>SRR13618126</td><td>bioreactor</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 4 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t ad\\_supplemented\\_with\\_nitrogen\\_data\\_2 & PRJNA698464 & SRR13618127 & PRJNA698464 & SRR13618123 & bioreactor\\\\\n",
+       "\t ad\\_supplemented\\_with\\_nitrogen\\_data\\_1 & PRJNA698464 & SRR13618128 & PRJNA698464 & SRR13618124 & bioreactor\\\\\n",
+       "\t ad\\_supplemented\\_with\\_hydrogen\\_data\\_2 & PRJNA698464 & SRR13618129 & PRJNA698464 & SRR13618125 & bioreactor\\\\\n",
+       "\t ad\\_supplemented\\_with\\_hydrogen\\_data\\_1 & PRJNA698464 & SRR13618130 & PRJNA698464 & SRR13618126 & bioreactor\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 4 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| ad_supplemented_with_nitrogen_data_2 | PRJNA698464 | SRR13618127 | PRJNA698464 | SRR13618123 | bioreactor |\n",
+       "| ad_supplemented_with_nitrogen_data_1 | PRJNA698464 | SRR13618128 | PRJNA698464 | SRR13618124 | bioreactor |\n",
+       "| ad_supplemented_with_hydrogen_data_2 | PRJNA698464 | SRR13618129 | PRJNA698464 | SRR13618125 | bioreactor |\n",
+       "| ad_supplemented_with_hydrogen_data_1 | PRJNA698464 | SRR13618130 | PRJNA698464 | SRR13618126 | bioreactor |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  sample_name                          mtx_study_accession mtx_run_accession\n",
+       "1 ad_supplemented_with_nitrogen_data_2 PRJNA698464         SRR13618127      \n",
+       "2 ad_supplemented_with_nitrogen_data_1 PRJNA698464         SRR13618128      \n",
+       "3 ad_supplemented_with_hydrogen_data_2 PRJNA698464         SRR13618129      \n",
+       "4 ad_supplemented_with_hydrogen_data_1 PRJNA698464         SRR13618130      \n",
+       "  mgx_study_accession mgx_run_accession sample_type\n",
+       "1 PRJNA698464         SRR13618123       bioreactor \n",
+       "2 PRJNA698464         SRR13618124       bioreactor \n",
+       "3 PRJNA698464         SRR13618125       bioreactor \n",
+       "4 PRJNA698464         SRR13618126       bioreactor "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna698464_mtx <- prjna698464 %>% \n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  mutate(sample_name = gsub(\"Illumina MiSeq sequencing; \", \"\", experiment_title),\n",
+    "         sample_name = gsub(\"RNA\", \"\", sample_name),\n",
+    "         sample_name = make_clean_names(sample_name)) %>%\n",
+    "  select(sample_name,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna698464_mgx <- prjna698464 %>% \n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  mutate(sample_name = gsub(\"Illumina MiSeq sequencing; \", \"\", experiment_title),\n",
+    "         sample_name = gsub(\"DNA\", \"\", sample_name),\n",
+    "         sample_name = make_clean_names(sample_name)) %>%\n",
+    "  select(sample_name,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjna698464_mtx_vs_mgx <- left_join(prjna698464_mtx, prjna698464_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"bioreactor\")\n",
+    "\n",
+    "prjna698464_mtx_vs_mgx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e51f3b6d",
+   "metadata": {},
+   "source": [
+    "## PRJNA396840"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "d841dd17",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna396840 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA396840&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "id": "a6864499",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 30 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>X4074</td><td>PRJNA396840</td><td>SRR5892181</td><td>PRJNA396840</td><td>SRR5892217</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4080</td><td>PRJNA396840</td><td>SRR5892182</td><td>PRJNA396840</td><td>SRR5892216</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4068</td><td>PRJNA396840</td><td>SRR5892183</td><td>PRJNA396840</td><td>SRR5892215</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4072</td><td>PRJNA396840</td><td>SRR5892184</td><td>PRJNA396840</td><td>SRR5892214</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4060</td><td>PRJNA396840</td><td>SRR5892185</td><td>PRJNA396840</td><td>SRR5892213</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4064</td><td>PRJNA396840</td><td>SRR5892186</td><td>PRJNA396840</td><td>SRR5892212</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4050</td><td>PRJNA396840</td><td>SRR5892187</td><td>PRJNA396840</td><td>SRR5892211</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4056</td><td>PRJNA396840</td><td>SRR5892188</td><td>PRJNA396840</td><td>SRR5892210</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4108</td><td>PRJNA396840</td><td>SRR5892189</td><td>PRJNA396840</td><td>SRR5892233</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4082</td><td>PRJNA396840</td><td>SRR5892190</td><td>PRJNA396840</td><td>SRR5892209</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4088</td><td>PRJNA396840</td><td>SRR5892191</td><td>PRJNA396840</td><td>SRR5892208</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4124</td><td>PRJNA396840</td><td>SRR5892192</td><td>PRJNA396840</td><td>SRR5892236</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4120</td><td>PRJNA396840</td><td>SRR5892195</td><td>PRJNA396840</td><td>SRR5892235</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4096</td><td>PRJNA396840</td><td>SRR5892200</td><td>PRJNA396840</td><td>SRR5892238</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4092</td><td>PRJNA396840</td><td>SRR5892204</td><td>PRJNA396840</td><td>SRR5892237</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4104</td><td>PRJNA396840</td><td>SRR5892205</td><td>PRJNA396840</td><td>SRR5892240</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4100</td><td>PRJNA396840</td><td>SRR5892207</td><td>PRJNA396840</td><td>SRR5892239</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4024</td><td>PRJNA396840</td><td>SRR5892218</td><td>PRJNA396840</td><td>SRR5892196</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4020</td><td>PRJNA396840</td><td>SRR5892219</td><td>PRJNA396840</td><td>SRR5892197</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4014</td><td>PRJNA396840</td><td>SRR5892220</td><td>PRJNA396840</td><td>SRR5892198</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4012</td><td>PRJNA396840</td><td>SRR5892221</td><td>PRJNA396840</td><td>SRR5892199</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4040</td><td>PRJNA396840</td><td>SRR5892222</td><td>PRJNA396840</td><td>SRR5892206</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4036</td><td>PRJNA396840</td><td>SRR5892223</td><td>PRJNA396840</td><td>SRR5892201</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4032</td><td>PRJNA396840</td><td>SRR5892224</td><td>PRJNA396840</td><td>SRR5892202</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4028</td><td>PRJNA396840</td><td>SRR5892225</td><td>PRJNA396840</td><td>SRR5892203</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4048</td><td>PRJNA396840</td><td>SRR5892226</td><td>PRJNA396840</td><td>SRR5892193</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4044</td><td>PRJNA396840</td><td>SRR5892227</td><td>PRJNA396840</td><td>SRR5892194</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4132</td><td>PRJNA396840</td><td>SRR5892228</td><td>PRJNA396840</td><td>SRR5892232</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4128</td><td>PRJNA396840</td><td>SRR5892229</td><td>PRJNA396840</td><td>SRR5892231</td><td>human_oral</td></tr>\n",
+       "\t<tr><td>X4116</td><td>PRJNA396840</td><td>SRR5892230</td><td>PRJNA396840</td><td>SRR5892234</td><td>human_oral</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 30 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t X4074 & PRJNA396840 & SRR5892181 & PRJNA396840 & SRR5892217 & human\\_oral\\\\\n",
+       "\t X4080 & PRJNA396840 & SRR5892182 & PRJNA396840 & SRR5892216 & human\\_oral\\\\\n",
+       "\t X4068 & PRJNA396840 & SRR5892183 & PRJNA396840 & SRR5892215 & human\\_oral\\\\\n",
+       "\t X4072 & PRJNA396840 & SRR5892184 & PRJNA396840 & SRR5892214 & human\\_oral\\\\\n",
+       "\t X4060 & PRJNA396840 & SRR5892185 & PRJNA396840 & SRR5892213 & human\\_oral\\\\\n",
+       "\t X4064 & PRJNA396840 & SRR5892186 & PRJNA396840 & SRR5892212 & human\\_oral\\\\\n",
+       "\t X4050 & PRJNA396840 & SRR5892187 & PRJNA396840 & SRR5892211 & human\\_oral\\\\\n",
+       "\t X4056 & PRJNA396840 & SRR5892188 & PRJNA396840 & SRR5892210 & human\\_oral\\\\\n",
+       "\t X4108 & PRJNA396840 & SRR5892189 & PRJNA396840 & SRR5892233 & human\\_oral\\\\\n",
+       "\t X4082 & PRJNA396840 & SRR5892190 & PRJNA396840 & SRR5892209 & human\\_oral\\\\\n",
+       "\t X4088 & PRJNA396840 & SRR5892191 & PRJNA396840 & SRR5892208 & human\\_oral\\\\\n",
+       "\t X4124 & PRJNA396840 & SRR5892192 & PRJNA396840 & SRR5892236 & human\\_oral\\\\\n",
+       "\t X4120 & PRJNA396840 & SRR5892195 & PRJNA396840 & SRR5892235 & human\\_oral\\\\\n",
+       "\t X4096 & PRJNA396840 & SRR5892200 & PRJNA396840 & SRR5892238 & human\\_oral\\\\\n",
+       "\t X4092 & PRJNA396840 & SRR5892204 & PRJNA396840 & SRR5892237 & human\\_oral\\\\\n",
+       "\t X4104 & PRJNA396840 & SRR5892205 & PRJNA396840 & SRR5892240 & human\\_oral\\\\\n",
+       "\t X4100 & PRJNA396840 & SRR5892207 & PRJNA396840 & SRR5892239 & human\\_oral\\\\\n",
+       "\t X4024 & PRJNA396840 & SRR5892218 & PRJNA396840 & SRR5892196 & human\\_oral\\\\\n",
+       "\t X4020 & PRJNA396840 & SRR5892219 & PRJNA396840 & SRR5892197 & human\\_oral\\\\\n",
+       "\t X4014 & PRJNA396840 & SRR5892220 & PRJNA396840 & SRR5892198 & human\\_oral\\\\\n",
+       "\t X4012 & PRJNA396840 & SRR5892221 & PRJNA396840 & SRR5892199 & human\\_oral\\\\\n",
+       "\t X4040 & PRJNA396840 & SRR5892222 & PRJNA396840 & SRR5892206 & human\\_oral\\\\\n",
+       "\t X4036 & PRJNA396840 & SRR5892223 & PRJNA396840 & SRR5892201 & human\\_oral\\\\\n",
+       "\t X4032 & PRJNA396840 & SRR5892224 & PRJNA396840 & SRR5892202 & human\\_oral\\\\\n",
+       "\t X4028 & PRJNA396840 & SRR5892225 & PRJNA396840 & SRR5892203 & human\\_oral\\\\\n",
+       "\t X4048 & PRJNA396840 & SRR5892226 & PRJNA396840 & SRR5892193 & human\\_oral\\\\\n",
+       "\t X4044 & PRJNA396840 & SRR5892227 & PRJNA396840 & SRR5892194 & human\\_oral\\\\\n",
+       "\t X4132 & PRJNA396840 & SRR5892228 & PRJNA396840 & SRR5892232 & human\\_oral\\\\\n",
+       "\t X4128 & PRJNA396840 & SRR5892229 & PRJNA396840 & SRR5892231 & human\\_oral\\\\\n",
+       "\t X4116 & PRJNA396840 & SRR5892230 & PRJNA396840 & SRR5892234 & human\\_oral\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 30 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| X4074 | PRJNA396840 | SRR5892181 | PRJNA396840 | SRR5892217 | human_oral |\n",
+       "| X4080 | PRJNA396840 | SRR5892182 | PRJNA396840 | SRR5892216 | human_oral |\n",
+       "| X4068 | PRJNA396840 | SRR5892183 | PRJNA396840 | SRR5892215 | human_oral |\n",
+       "| X4072 | PRJNA396840 | SRR5892184 | PRJNA396840 | SRR5892214 | human_oral |\n",
+       "| X4060 | PRJNA396840 | SRR5892185 | PRJNA396840 | SRR5892213 | human_oral |\n",
+       "| X4064 | PRJNA396840 | SRR5892186 | PRJNA396840 | SRR5892212 | human_oral |\n",
+       "| X4050 | PRJNA396840 | SRR5892187 | PRJNA396840 | SRR5892211 | human_oral |\n",
+       "| X4056 | PRJNA396840 | SRR5892188 | PRJNA396840 | SRR5892210 | human_oral |\n",
+       "| X4108 | PRJNA396840 | SRR5892189 | PRJNA396840 | SRR5892233 | human_oral |\n",
+       "| X4082 | PRJNA396840 | SRR5892190 | PRJNA396840 | SRR5892209 | human_oral |\n",
+       "| X4088 | PRJNA396840 | SRR5892191 | PRJNA396840 | SRR5892208 | human_oral |\n",
+       "| X4124 | PRJNA396840 | SRR5892192 | PRJNA396840 | SRR5892236 | human_oral |\n",
+       "| X4120 | PRJNA396840 | SRR5892195 | PRJNA396840 | SRR5892235 | human_oral |\n",
+       "| X4096 | PRJNA396840 | SRR5892200 | PRJNA396840 | SRR5892238 | human_oral |\n",
+       "| X4092 | PRJNA396840 | SRR5892204 | PRJNA396840 | SRR5892237 | human_oral |\n",
+       "| X4104 | PRJNA396840 | SRR5892205 | PRJNA396840 | SRR5892240 | human_oral |\n",
+       "| X4100 | PRJNA396840 | SRR5892207 | PRJNA396840 | SRR5892239 | human_oral |\n",
+       "| X4024 | PRJNA396840 | SRR5892218 | PRJNA396840 | SRR5892196 | human_oral |\n",
+       "| X4020 | PRJNA396840 | SRR5892219 | PRJNA396840 | SRR5892197 | human_oral |\n",
+       "| X4014 | PRJNA396840 | SRR5892220 | PRJNA396840 | SRR5892198 | human_oral |\n",
+       "| X4012 | PRJNA396840 | SRR5892221 | PRJNA396840 | SRR5892199 | human_oral |\n",
+       "| X4040 | PRJNA396840 | SRR5892222 | PRJNA396840 | SRR5892206 | human_oral |\n",
+       "| X4036 | PRJNA396840 | SRR5892223 | PRJNA396840 | SRR5892201 | human_oral |\n",
+       "| X4032 | PRJNA396840 | SRR5892224 | PRJNA396840 | SRR5892202 | human_oral |\n",
+       "| X4028 | PRJNA396840 | SRR5892225 | PRJNA396840 | SRR5892203 | human_oral |\n",
+       "| X4048 | PRJNA396840 | SRR5892226 | PRJNA396840 | SRR5892193 | human_oral |\n",
+       "| X4044 | PRJNA396840 | SRR5892227 | PRJNA396840 | SRR5892194 | human_oral |\n",
+       "| X4132 | PRJNA396840 | SRR5892228 | PRJNA396840 | SRR5892232 | human_oral |\n",
+       "| X4128 | PRJNA396840 | SRR5892229 | PRJNA396840 | SRR5892231 | human_oral |\n",
+       "| X4116 | PRJNA396840 | SRR5892230 | PRJNA396840 | SRR5892234 | human_oral |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "   sample_name mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1  X4074       PRJNA396840         SRR5892181        PRJNA396840        \n",
+       "2  X4080       PRJNA396840         SRR5892182        PRJNA396840        \n",
+       "3  X4068       PRJNA396840         SRR5892183        PRJNA396840        \n",
+       "4  X4072       PRJNA396840         SRR5892184        PRJNA396840        \n",
+       "5  X4060       PRJNA396840         SRR5892185        PRJNA396840        \n",
+       "6  X4064       PRJNA396840         SRR5892186        PRJNA396840        \n",
+       "7  X4050       PRJNA396840         SRR5892187        PRJNA396840        \n",
+       "8  X4056       PRJNA396840         SRR5892188        PRJNA396840        \n",
+       "9  X4108       PRJNA396840         SRR5892189        PRJNA396840        \n",
+       "10 X4082       PRJNA396840         SRR5892190        PRJNA396840        \n",
+       "11 X4088       PRJNA396840         SRR5892191        PRJNA396840        \n",
+       "12 X4124       PRJNA396840         SRR5892192        PRJNA396840        \n",
+       "13 X4120       PRJNA396840         SRR5892195        PRJNA396840        \n",
+       "14 X4096       PRJNA396840         SRR5892200        PRJNA396840        \n",
+       "15 X4092       PRJNA396840         SRR5892204        PRJNA396840        \n",
+       "16 X4104       PRJNA396840         SRR5892205        PRJNA396840        \n",
+       "17 X4100       PRJNA396840         SRR5892207        PRJNA396840        \n",
+       "18 X4024       PRJNA396840         SRR5892218        PRJNA396840        \n",
+       "19 X4020       PRJNA396840         SRR5892219        PRJNA396840        \n",
+       "20 X4014       PRJNA396840         SRR5892220        PRJNA396840        \n",
+       "21 X4012       PRJNA396840         SRR5892221        PRJNA396840        \n",
+       "22 X4040       PRJNA396840         SRR5892222        PRJNA396840        \n",
+       "23 X4036       PRJNA396840         SRR5892223        PRJNA396840        \n",
+       "24 X4032       PRJNA396840         SRR5892224        PRJNA396840        \n",
+       "25 X4028       PRJNA396840         SRR5892225        PRJNA396840        \n",
+       "26 X4048       PRJNA396840         SRR5892226        PRJNA396840        \n",
+       "27 X4044       PRJNA396840         SRR5892227        PRJNA396840        \n",
+       "28 X4132       PRJNA396840         SRR5892228        PRJNA396840        \n",
+       "29 X4128       PRJNA396840         SRR5892229        PRJNA396840        \n",
+       "30 X4116       PRJNA396840         SRR5892230        PRJNA396840        \n",
+       "   mgx_run_accession sample_type\n",
+       "1  SRR5892217        human_oral \n",
+       "2  SRR5892216        human_oral \n",
+       "3  SRR5892215        human_oral \n",
+       "4  SRR5892214        human_oral \n",
+       "5  SRR5892213        human_oral \n",
+       "6  SRR5892212        human_oral \n",
+       "7  SRR5892211        human_oral \n",
+       "8  SRR5892210        human_oral \n",
+       "9  SRR5892233        human_oral \n",
+       "10 SRR5892209        human_oral \n",
+       "11 SRR5892208        human_oral \n",
+       "12 SRR5892236        human_oral \n",
+       "13 SRR5892235        human_oral \n",
+       "14 SRR5892238        human_oral \n",
+       "15 SRR5892237        human_oral \n",
+       "16 SRR5892240        human_oral \n",
+       "17 SRR5892239        human_oral \n",
+       "18 SRR5892196        human_oral \n",
+       "19 SRR5892197        human_oral \n",
+       "20 SRR5892198        human_oral \n",
+       "21 SRR5892199        human_oral \n",
+       "22 SRR5892206        human_oral \n",
+       "23 SRR5892201        human_oral \n",
+       "24 SRR5892202        human_oral \n",
+       "25 SRR5892203        human_oral \n",
+       "26 SRR5892193        human_oral \n",
+       "27 SRR5892194        human_oral \n",
+       "28 SRR5892232        human_oral \n",
+       "29 SRR5892231        human_oral \n",
+       "30 SRR5892234        human_oral "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna396840_mtx <- prjna396840 %>% \n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  mutate(sample_name = gsub(\"RNA\", \"\", sample_alias)) %>%\n",
+    "  select(sample_name,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna396840_mgx <- prjna396840 %>% \n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  mutate(sample_name = gsub(\"DNA\", \"\", sample_alias)) %>%\n",
+    "  select(sample_name,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjna396840_mtx_vs_mgx <- left_join(prjna396840_mtx, prjna396840_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"human_oral\")\n",
+    "\n",
+    "prjna396840_mtx_vs_mgx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "52d148ea",
+   "metadata": {},
+   "source": [
+    "## PRJNA492158"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "id": "f946d7cd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna492158 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA492158&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "id": "c5490b6a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 26 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>L2 </td><td>PRJNA492158</td><td>SRR7880350</td><td>PRJNA492158</td><td>SRR7880198</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>L3 </td><td>PRJNA492158</td><td>SRR7880351</td><td>PRJNA492158</td><td>SRR7880201</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>L5 </td><td>PRJNA492158</td><td>SRR7880352</td><td>PRJNA492158</td><td>SRR7880203</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>L6 </td><td>PRJNA492158</td><td>SRR7880353</td><td>PRJNA492158</td><td>SRR7880202</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>L7 </td><td>PRJNA492158</td><td>SRR7880354</td><td>PRJNA492158</td><td>SRR7880205</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>L8 </td><td>PRJNA492158</td><td>SRR7880355</td><td>PRJNA492158</td><td>SRR7880204</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>L9 </td><td>PRJNA492158</td><td>SRR7880356</td><td>PRJNA492158</td><td>SRR7880207</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>L11</td><td>PRJNA492158</td><td>SRR7880357</td><td>PRJNA492158</td><td>SRR7880227</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>L12</td><td>PRJNA492158</td><td>SRR7880358</td><td>PRJNA492158</td><td>SRR7880226</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>O1 </td><td>PRJNA492158</td><td>SRR7880359</td><td>PRJNA492158</td><td>SRR7880225</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>V6 </td><td>PRJNA492158</td><td>SRR7880360</td><td>PRJNA492158</td><td>SRR7880217</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>V5 </td><td>PRJNA492158</td><td>SRR7880361</td><td>PRJNA492158</td><td>SRR7880216</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>V8 </td><td>PRJNA492158</td><td>SRR7880362</td><td>PRJNA492158</td><td>SRR7880218</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>V7 </td><td>PRJNA492158</td><td>SRR7880363</td><td>PRJNA492158</td><td>SRR7880219</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>V11</td><td>PRJNA492158</td><td>SRR7880364</td><td>PRJNA492158</td><td>SRR7880223</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>V9 </td><td>PRJNA492158</td><td>SRR7880365</td><td>PRJNA492158</td><td>SRR7880197</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>O6 </td><td>PRJNA492158</td><td>SRR7880366</td><td>PRJNA492158</td><td>SRR7880228</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>O8 </td><td>PRJNA492158</td><td>SRR7880367</td><td>PRJNA492158</td><td>SRR7880220</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>O9 </td><td>PRJNA492158</td><td>SRR7880368</td><td>PRJNA492158</td><td>SRR7880210</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>O10</td><td>PRJNA492158</td><td>SRR7880369</td><td>PRJNA492158</td><td>SRR7880211</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>O2 </td><td>PRJNA492158</td><td>SRR7880370</td><td>PRJNA492158</td><td>SRR7880224</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>O3 </td><td>PRJNA492158</td><td>SRR7880371</td><td>PRJNA492158</td><td>SRR7880231</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>O4 </td><td>PRJNA492158</td><td>SRR7880372</td><td>PRJNA492158</td><td>SRR7880230</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>O5 </td><td>PRJNA492158</td><td>SRR7880373</td><td>PRJNA492158</td><td>SRR7880229</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>O11</td><td>PRJNA492158</td><td>SRR7880374</td><td>PRJNA492158</td><td>SRR7880208</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>O12</td><td>PRJNA492158</td><td>SRR7880375</td><td>PRJNA492158</td><td>SRR7880209</td><td>human_gut</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 26 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t L2  & PRJNA492158 & SRR7880350 & PRJNA492158 & SRR7880198 & human\\_gut\\\\\n",
+       "\t L3  & PRJNA492158 & SRR7880351 & PRJNA492158 & SRR7880201 & human\\_gut\\\\\n",
+       "\t L5  & PRJNA492158 & SRR7880352 & PRJNA492158 & SRR7880203 & human\\_gut\\\\\n",
+       "\t L6  & PRJNA492158 & SRR7880353 & PRJNA492158 & SRR7880202 & human\\_gut\\\\\n",
+       "\t L7  & PRJNA492158 & SRR7880354 & PRJNA492158 & SRR7880205 & human\\_gut\\\\\n",
+       "\t L8  & PRJNA492158 & SRR7880355 & PRJNA492158 & SRR7880204 & human\\_gut\\\\\n",
+       "\t L9  & PRJNA492158 & SRR7880356 & PRJNA492158 & SRR7880207 & human\\_gut\\\\\n",
+       "\t L11 & PRJNA492158 & SRR7880357 & PRJNA492158 & SRR7880227 & human\\_gut\\\\\n",
+       "\t L12 & PRJNA492158 & SRR7880358 & PRJNA492158 & SRR7880226 & human\\_gut\\\\\n",
+       "\t O1  & PRJNA492158 & SRR7880359 & PRJNA492158 & SRR7880225 & human\\_gut\\\\\n",
+       "\t V6  & PRJNA492158 & SRR7880360 & PRJNA492158 & SRR7880217 & human\\_gut\\\\\n",
+       "\t V5  & PRJNA492158 & SRR7880361 & PRJNA492158 & SRR7880216 & human\\_gut\\\\\n",
+       "\t V8  & PRJNA492158 & SRR7880362 & PRJNA492158 & SRR7880218 & human\\_gut\\\\\n",
+       "\t V7  & PRJNA492158 & SRR7880363 & PRJNA492158 & SRR7880219 & human\\_gut\\\\\n",
+       "\t V11 & PRJNA492158 & SRR7880364 & PRJNA492158 & SRR7880223 & human\\_gut\\\\\n",
+       "\t V9  & PRJNA492158 & SRR7880365 & PRJNA492158 & SRR7880197 & human\\_gut\\\\\n",
+       "\t O6  & PRJNA492158 & SRR7880366 & PRJNA492158 & SRR7880228 & human\\_gut\\\\\n",
+       "\t O8  & PRJNA492158 & SRR7880367 & PRJNA492158 & SRR7880220 & human\\_gut\\\\\n",
+       "\t O9  & PRJNA492158 & SRR7880368 & PRJNA492158 & SRR7880210 & human\\_gut\\\\\n",
+       "\t O10 & PRJNA492158 & SRR7880369 & PRJNA492158 & SRR7880211 & human\\_gut\\\\\n",
+       "\t O2  & PRJNA492158 & SRR7880370 & PRJNA492158 & SRR7880224 & human\\_gut\\\\\n",
+       "\t O3  & PRJNA492158 & SRR7880371 & PRJNA492158 & SRR7880231 & human\\_gut\\\\\n",
+       "\t O4  & PRJNA492158 & SRR7880372 & PRJNA492158 & SRR7880230 & human\\_gut\\\\\n",
+       "\t O5  & PRJNA492158 & SRR7880373 & PRJNA492158 & SRR7880229 & human\\_gut\\\\\n",
+       "\t O11 & PRJNA492158 & SRR7880374 & PRJNA492158 & SRR7880208 & human\\_gut\\\\\n",
+       "\t O12 & PRJNA492158 & SRR7880375 & PRJNA492158 & SRR7880209 & human\\_gut\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 26 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| L2  | PRJNA492158 | SRR7880350 | PRJNA492158 | SRR7880198 | human_gut |\n",
+       "| L3  | PRJNA492158 | SRR7880351 | PRJNA492158 | SRR7880201 | human_gut |\n",
+       "| L5  | PRJNA492158 | SRR7880352 | PRJNA492158 | SRR7880203 | human_gut |\n",
+       "| L6  | PRJNA492158 | SRR7880353 | PRJNA492158 | SRR7880202 | human_gut |\n",
+       "| L7  | PRJNA492158 | SRR7880354 | PRJNA492158 | SRR7880205 | human_gut |\n",
+       "| L8  | PRJNA492158 | SRR7880355 | PRJNA492158 | SRR7880204 | human_gut |\n",
+       "| L9  | PRJNA492158 | SRR7880356 | PRJNA492158 | SRR7880207 | human_gut |\n",
+       "| L11 | PRJNA492158 | SRR7880357 | PRJNA492158 | SRR7880227 | human_gut |\n",
+       "| L12 | PRJNA492158 | SRR7880358 | PRJNA492158 | SRR7880226 | human_gut |\n",
+       "| O1  | PRJNA492158 | SRR7880359 | PRJNA492158 | SRR7880225 | human_gut |\n",
+       "| V6  | PRJNA492158 | SRR7880360 | PRJNA492158 | SRR7880217 | human_gut |\n",
+       "| V5  | PRJNA492158 | SRR7880361 | PRJNA492158 | SRR7880216 | human_gut |\n",
+       "| V8  | PRJNA492158 | SRR7880362 | PRJNA492158 | SRR7880218 | human_gut |\n",
+       "| V7  | PRJNA492158 | SRR7880363 | PRJNA492158 | SRR7880219 | human_gut |\n",
+       "| V11 | PRJNA492158 | SRR7880364 | PRJNA492158 | SRR7880223 | human_gut |\n",
+       "| V9  | PRJNA492158 | SRR7880365 | PRJNA492158 | SRR7880197 | human_gut |\n",
+       "| O6  | PRJNA492158 | SRR7880366 | PRJNA492158 | SRR7880228 | human_gut |\n",
+       "| O8  | PRJNA492158 | SRR7880367 | PRJNA492158 | SRR7880220 | human_gut |\n",
+       "| O9  | PRJNA492158 | SRR7880368 | PRJNA492158 | SRR7880210 | human_gut |\n",
+       "| O10 | PRJNA492158 | SRR7880369 | PRJNA492158 | SRR7880211 | human_gut |\n",
+       "| O2  | PRJNA492158 | SRR7880370 | PRJNA492158 | SRR7880224 | human_gut |\n",
+       "| O3  | PRJNA492158 | SRR7880371 | PRJNA492158 | SRR7880231 | human_gut |\n",
+       "| O4  | PRJNA492158 | SRR7880372 | PRJNA492158 | SRR7880230 | human_gut |\n",
+       "| O5  | PRJNA492158 | SRR7880373 | PRJNA492158 | SRR7880229 | human_gut |\n",
+       "| O11 | PRJNA492158 | SRR7880374 | PRJNA492158 | SRR7880208 | human_gut |\n",
+       "| O12 | PRJNA492158 | SRR7880375 | PRJNA492158 | SRR7880209 | human_gut |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "   sample_name mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1  L2          PRJNA492158         SRR7880350        PRJNA492158        \n",
+       "2  L3          PRJNA492158         SRR7880351        PRJNA492158        \n",
+       "3  L5          PRJNA492158         SRR7880352        PRJNA492158        \n",
+       "4  L6          PRJNA492158         SRR7880353        PRJNA492158        \n",
+       "5  L7          PRJNA492158         SRR7880354        PRJNA492158        \n",
+       "6  L8          PRJNA492158         SRR7880355        PRJNA492158        \n",
+       "7  L9          PRJNA492158         SRR7880356        PRJNA492158        \n",
+       "8  L11         PRJNA492158         SRR7880357        PRJNA492158        \n",
+       "9  L12         PRJNA492158         SRR7880358        PRJNA492158        \n",
+       "10 O1          PRJNA492158         SRR7880359        PRJNA492158        \n",
+       "11 V6          PRJNA492158         SRR7880360        PRJNA492158        \n",
+       "12 V5          PRJNA492158         SRR7880361        PRJNA492158        \n",
+       "13 V8          PRJNA492158         SRR7880362        PRJNA492158        \n",
+       "14 V7          PRJNA492158         SRR7880363        PRJNA492158        \n",
+       "15 V11         PRJNA492158         SRR7880364        PRJNA492158        \n",
+       "16 V9          PRJNA492158         SRR7880365        PRJNA492158        \n",
+       "17 O6          PRJNA492158         SRR7880366        PRJNA492158        \n",
+       "18 O8          PRJNA492158         SRR7880367        PRJNA492158        \n",
+       "19 O9          PRJNA492158         SRR7880368        PRJNA492158        \n",
+       "20 O10         PRJNA492158         SRR7880369        PRJNA492158        \n",
+       "21 O2          PRJNA492158         SRR7880370        PRJNA492158        \n",
+       "22 O3          PRJNA492158         SRR7880371        PRJNA492158        \n",
+       "23 O4          PRJNA492158         SRR7880372        PRJNA492158        \n",
+       "24 O5          PRJNA492158         SRR7880373        PRJNA492158        \n",
+       "25 O11         PRJNA492158         SRR7880374        PRJNA492158        \n",
+       "26 O12         PRJNA492158         SRR7880375        PRJNA492158        \n",
+       "   mgx_run_accession sample_type\n",
+       "1  SRR7880198        human_gut  \n",
+       "2  SRR7880201        human_gut  \n",
+       "3  SRR7880203        human_gut  \n",
+       "4  SRR7880202        human_gut  \n",
+       "5  SRR7880205        human_gut  \n",
+       "6  SRR7880204        human_gut  \n",
+       "7  SRR7880207        human_gut  \n",
+       "8  SRR7880227        human_gut  \n",
+       "9  SRR7880226        human_gut  \n",
+       "10 SRR7880225        human_gut  \n",
+       "11 SRR7880217        human_gut  \n",
+       "12 SRR7880216        human_gut  \n",
+       "13 SRR7880218        human_gut  \n",
+       "14 SRR7880219        human_gut  \n",
+       "15 SRR7880223        human_gut  \n",
+       "16 SRR7880197        human_gut  \n",
+       "17 SRR7880228        human_gut  \n",
+       "18 SRR7880220        human_gut  \n",
+       "19 SRR7880210        human_gut  \n",
+       "20 SRR7880211        human_gut  \n",
+       "21 SRR7880224        human_gut  \n",
+       "22 SRR7880231        human_gut  \n",
+       "23 SRR7880230        human_gut  \n",
+       "24 SRR7880229        human_gut  \n",
+       "25 SRR7880208        human_gut  \n",
+       "26 SRR7880209        human_gut  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna492158_mtx <- prjna492158 %>% \n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna492158_mgx <- prjna492158 %>% \n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjna492158_mtx_vs_mgx <- left_join(prjna492158_mtx, prjna492158_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"human_gut\")\n",
+    "\n",
+    "prjna492158_mtx_vs_mgx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c6297be8",
+   "metadata": {},
+   "source": [
+    "## PRJNA278075"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "e2bbc1d3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna278075 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA278075&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "c04f4678",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 1 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>3m_Station6_GOM</td><td>PRJNA278075</td><td>SRR1918203</td><td>PRJNA278075</td><td>SRR2001210</td><td>ocean</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 1 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t 3m\\_Station6\\_GOM & PRJNA278075 & SRR1918203 & PRJNA278075 & SRR2001210 & ocean\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 1 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| 3m_Station6_GOM | PRJNA278075 | SRR1918203 | PRJNA278075 | SRR2001210 | ocean |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  sample_name     mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1 3m_Station6_GOM PRJNA278075         SRR1918203        PRJNA278075        \n",
+       "  mgx_run_accession sample_type\n",
+       "1 SRR2001210        ocean      "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna278075_mtx <- prjna278075 %>% \n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  mutate(sample_name = gsub(\"_Metatranscriptome\", \"\", sample_alias)) %>%\n",
+    "  select(sample_name,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna278075_mgx <- prjna278075 %>% \n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  mutate(sample_name = gsub(\"_Metagenome\", \"\", sample_alias)) %>%\n",
+    "  select(sample_name,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjna278075_mtx_vs_mgx <- left_join(prjna278075_mtx, prjna278075_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"ocean\")\n",
+    "\n",
+    "prjna278075_mtx_vs_mgx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "47b51151",
+   "metadata": {},
+   "source": [
+    "## PRJEB38017"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "id": "2ffa1577",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjeb38017 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJEB38017&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "id": "de8f831d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 3 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>CRF2_7 </td><td>PRJEB38017</td><td>ERR4077213</td><td>PRJEB38017</td><td>ERR4073751</td><td>cocoa_box_fermentation</td></tr>\n",
+       "\t<tr><td>CRF2_20</td><td>PRJEB38017</td><td>ERR4077214</td><td>PRJEB38017</td><td>ERR4073752</td><td>cocoa_box_fermentation</td></tr>\n",
+       "\t<tr><td>CRF2_68</td><td>PRJEB38017</td><td>ERR4077215</td><td>PRJEB38017</td><td>ERR4073754</td><td>cocoa_box_fermentation</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 3 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t CRF2\\_7  & PRJEB38017 & ERR4077213 & PRJEB38017 & ERR4073751 & cocoa\\_box\\_fermentation\\\\\n",
+       "\t CRF2\\_20 & PRJEB38017 & ERR4077214 & PRJEB38017 & ERR4073752 & cocoa\\_box\\_fermentation\\\\\n",
+       "\t CRF2\\_68 & PRJEB38017 & ERR4077215 & PRJEB38017 & ERR4073754 & cocoa\\_box\\_fermentation\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 3 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| CRF2_7  | PRJEB38017 | ERR4077213 | PRJEB38017 | ERR4073751 | cocoa_box_fermentation |\n",
+       "| CRF2_20 | PRJEB38017 | ERR4077214 | PRJEB38017 | ERR4073752 | cocoa_box_fermentation |\n",
+       "| CRF2_68 | PRJEB38017 | ERR4077215 | PRJEB38017 | ERR4073754 | cocoa_box_fermentation |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  sample_name mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1 CRF2_7      PRJEB38017          ERR4077213        PRJEB38017         \n",
+       "2 CRF2_20     PRJEB38017          ERR4077214        PRJEB38017         \n",
+       "3 CRF2_68     PRJEB38017          ERR4077215        PRJEB38017         \n",
+       "  mgx_run_accession sample_type           \n",
+       "1 ERR4073751        cocoa_box_fermentation\n",
+       "2 ERR4073752        cocoa_box_fermentation\n",
+       "3 ERR4073754        cocoa_box_fermentation"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjeb38017_mtx <- prjeb38017 %>% \n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  mutate(sample_name = gsub(\"CRF\", \"\", sample_alias),\n",
+    "         sample_name = gsub(\"R\", \"_\", sample_name),\n",
+    "         sample_name = paste0(\"CRF\", sample_name)) %>%\n",
+    "  select(sample_name,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjeb38017_mgx <- prjeb38017 %>% \n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  mutate(sample_name = gsub(\"D\", \"_\", sample_alias)) %>%\n",
+    "  select(sample_name,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjeb38017_mtx_vs_mgx <- left_join(prjeb38017_mtx, prjeb38017_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"cocoa_box_fermentation\")\n",
+    "\n",
+    "prjeb38017_mtx_vs_mgx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f35357e1",
+   "metadata": {},
+   "source": [
+    "## PRJNA616041"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "3fe05289",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna616041 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA616041&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "id": "35e3b96e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 6 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>HP_AsLow </td><td>PRJNA616041</td><td>SRR11450577</td><td>PRJNA616041</td><td>SRR11450583</td><td>paddy_soil</td></tr>\n",
+       "\t<tr><td>SKS_AsHig</td><td>PRJNA616041</td><td>SRR11450578</td><td>PRJNA616041</td><td>SRR11450584</td><td>paddy_soil</td></tr>\n",
+       "\t<tr><td>CZ_AsHig </td><td>PRJNA616041</td><td>SRR11450579</td><td>PRJNA616041</td><td>SRR11450587</td><td>paddy_soil</td></tr>\n",
+       "\t<tr><td>CL_AsHig </td><td>PRJNA616041</td><td>SRR11450580</td><td>PRJNA616041</td><td>SRR11450588</td><td>paddy_soil</td></tr>\n",
+       "\t<tr><td>YCP_AsLow</td><td>PRJNA616041</td><td>SRR11450585</td><td>PRJNA616041</td><td>SRR11450581</td><td>paddy_soil</td></tr>\n",
+       "\t<tr><td>LH_AsLow </td><td>PRJNA616041</td><td>SRR11450586</td><td>PRJNA616041</td><td>SRR11450582</td><td>paddy_soil</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 6 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t HP\\_AsLow  & PRJNA616041 & SRR11450577 & PRJNA616041 & SRR11450583 & paddy\\_soil\\\\\n",
+       "\t SKS\\_AsHig & PRJNA616041 & SRR11450578 & PRJNA616041 & SRR11450584 & paddy\\_soil\\\\\n",
+       "\t CZ\\_AsHig  & PRJNA616041 & SRR11450579 & PRJNA616041 & SRR11450587 & paddy\\_soil\\\\\n",
+       "\t CL\\_AsHig  & PRJNA616041 & SRR11450580 & PRJNA616041 & SRR11450588 & paddy\\_soil\\\\\n",
+       "\t YCP\\_AsLow & PRJNA616041 & SRR11450585 & PRJNA616041 & SRR11450581 & paddy\\_soil\\\\\n",
+       "\t LH\\_AsLow  & PRJNA616041 & SRR11450586 & PRJNA616041 & SRR11450582 & paddy\\_soil\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 6 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| HP_AsLow  | PRJNA616041 | SRR11450577 | PRJNA616041 | SRR11450583 | paddy_soil |\n",
+       "| SKS_AsHig | PRJNA616041 | SRR11450578 | PRJNA616041 | SRR11450584 | paddy_soil |\n",
+       "| CZ_AsHig  | PRJNA616041 | SRR11450579 | PRJNA616041 | SRR11450587 | paddy_soil |\n",
+       "| CL_AsHig  | PRJNA616041 | SRR11450580 | PRJNA616041 | SRR11450588 | paddy_soil |\n",
+       "| YCP_AsLow | PRJNA616041 | SRR11450585 | PRJNA616041 | SRR11450581 | paddy_soil |\n",
+       "| LH_AsLow  | PRJNA616041 | SRR11450586 | PRJNA616041 | SRR11450582 | paddy_soil |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  sample_name mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1 HP_AsLow    PRJNA616041         SRR11450577       PRJNA616041        \n",
+       "2 SKS_AsHig   PRJNA616041         SRR11450578       PRJNA616041        \n",
+       "3 CZ_AsHig    PRJNA616041         SRR11450579       PRJNA616041        \n",
+       "4 CL_AsHig    PRJNA616041         SRR11450580       PRJNA616041        \n",
+       "5 YCP_AsLow   PRJNA616041         SRR11450585       PRJNA616041        \n",
+       "6 LH_AsLow    PRJNA616041         SRR11450586       PRJNA616041        \n",
+       "  mgx_run_accession sample_type\n",
+       "1 SRR11450583       paddy_soil \n",
+       "2 SRR11450584       paddy_soil \n",
+       "3 SRR11450587       paddy_soil \n",
+       "4 SRR11450588       paddy_soil \n",
+       "5 SRR11450581       paddy_soil \n",
+       "6 SRR11450582       paddy_soil "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna616041_mtx <- prjna616041 %>% \n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna616041_mgx <- prjna616041 %>% \n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjna616041_mtx_vs_mgx <- left_join(prjna616041_mtx, prjna616041_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"paddy_soil\")\n",
+    "\n",
+    "prjna616041_mtx_vs_mgx"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d3351487",
+   "metadata": {},
+   "source": [
+    "## PRJNA393770 (mgx) & PRJNA395125 (mtx)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "id": "5b193bc9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna393770 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA393770&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)\n",
+    "\n",
+    "prjna395125 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA395125&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "id": "b7dfdb12",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna393770_mgx <- prjna393770 %>%\n",
+    "  filter(library_source %in% c(\"METAGENOMIC\")) %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjna395125_mtx <- prjna395125 %>%\n",
+    "  filter(library_source %in% c(\"METATRANSCRIPTOMIC\")) %>%\n",
+    "  mutate(sample_name = gsub(\"_MT\", \"\", sample_alias)) %>%\n",
+    "  select(sample_name,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna395125_vs_prjna393770 <- inner_join(prjna395125_mtx, prjna393770_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"bioreactor\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "718078bd",
+   "metadata": {},
+   "source": [
+    "## PRJEB12284 (mtx) & PRJEB12083 (mgx)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "id": "3c808614",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjeb12284 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJEB12284&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)\n",
+    "\n",
+    "prjeb12083 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJEB12083&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "id": "2dfe7df8",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 8 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>AH1</td><td>PRJEB12284</td><td>ERR1198915</td><td>PRJEB12083</td><td>ERR1191817</td><td>wastewater</td></tr>\n",
+       "\t<tr><td>AH4</td><td>PRJEB12284</td><td>ERR1198916</td><td>PRJEB12083</td><td>ERR1191820</td><td>wastewater</td></tr>\n",
+       "\t<tr><td>AH5</td><td>PRJEB12284</td><td>ERR1198917</td><td>PRJEB12083</td><td>ERR1191821</td><td>wastewater</td></tr>\n",
+       "\t<tr><td>AH6</td><td>PRJEB12284</td><td>ERR1198918</td><td>PRJEB12083</td><td>ERR1191822</td><td>wastewater</td></tr>\n",
+       "\t<tr><td>DF1</td><td>PRJEB12284</td><td>ERR1198919</td><td>PRJEB12083</td><td>ERR1193331</td><td>wastewater</td></tr>\n",
+       "\t<tr><td>DF4</td><td>PRJEB12284</td><td>ERR1198920</td><td>PRJEB12083</td><td>ERR1193299</td><td>wastewater</td></tr>\n",
+       "\t<tr><td>DF5</td><td>PRJEB12284</td><td>ERR1198921</td><td>PRJEB12083</td><td>ERR1193300</td><td>wastewater</td></tr>\n",
+       "\t<tr><td>DF6</td><td>PRJEB12284</td><td>ERR1198922</td><td>PRJEB12083</td><td>ERR1193301</td><td>wastewater</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 8 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t AH1 & PRJEB12284 & ERR1198915 & PRJEB12083 & ERR1191817 & wastewater\\\\\n",
+       "\t AH4 & PRJEB12284 & ERR1198916 & PRJEB12083 & ERR1191820 & wastewater\\\\\n",
+       "\t AH5 & PRJEB12284 & ERR1198917 & PRJEB12083 & ERR1191821 & wastewater\\\\\n",
+       "\t AH6 & PRJEB12284 & ERR1198918 & PRJEB12083 & ERR1191822 & wastewater\\\\\n",
+       "\t DF1 & PRJEB12284 & ERR1198919 & PRJEB12083 & ERR1193331 & wastewater\\\\\n",
+       "\t DF4 & PRJEB12284 & ERR1198920 & PRJEB12083 & ERR1193299 & wastewater\\\\\n",
+       "\t DF5 & PRJEB12284 & ERR1198921 & PRJEB12083 & ERR1193300 & wastewater\\\\\n",
+       "\t DF6 & PRJEB12284 & ERR1198922 & PRJEB12083 & ERR1193301 & wastewater\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 8 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| AH1 | PRJEB12284 | ERR1198915 | PRJEB12083 | ERR1191817 | wastewater |\n",
+       "| AH4 | PRJEB12284 | ERR1198916 | PRJEB12083 | ERR1191820 | wastewater |\n",
+       "| AH5 | PRJEB12284 | ERR1198917 | PRJEB12083 | ERR1191821 | wastewater |\n",
+       "| AH6 | PRJEB12284 | ERR1198918 | PRJEB12083 | ERR1191822 | wastewater |\n",
+       "| DF1 | PRJEB12284 | ERR1198919 | PRJEB12083 | ERR1193331 | wastewater |\n",
+       "| DF4 | PRJEB12284 | ERR1198920 | PRJEB12083 | ERR1193299 | wastewater |\n",
+       "| DF5 | PRJEB12284 | ERR1198921 | PRJEB12083 | ERR1193300 | wastewater |\n",
+       "| DF6 | PRJEB12284 | ERR1198922 | PRJEB12083 | ERR1193301 | wastewater |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  sample_name mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1 AH1         PRJEB12284          ERR1198915        PRJEB12083         \n",
+       "2 AH4         PRJEB12284          ERR1198916        PRJEB12083         \n",
+       "3 AH5         PRJEB12284          ERR1198917        PRJEB12083         \n",
+       "4 AH6         PRJEB12284          ERR1198918        PRJEB12083         \n",
+       "5 DF1         PRJEB12284          ERR1198919        PRJEB12083         \n",
+       "6 DF4         PRJEB12284          ERR1198920        PRJEB12083         \n",
+       "7 DF5         PRJEB12284          ERR1198921        PRJEB12083         \n",
+       "8 DF6         PRJEB12284          ERR1198922        PRJEB12083         \n",
+       "  mgx_run_accession sample_type\n",
+       "1 ERR1191817        wastewater \n",
+       "2 ERR1191820        wastewater \n",
+       "3 ERR1191821        wastewater \n",
+       "4 ERR1191822        wastewater \n",
+       "5 ERR1193331        wastewater \n",
+       "6 ERR1193299        wastewater \n",
+       "7 ERR1193300        wastewater \n",
+       "8 ERR1193301        wastewater "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjeb12284_mtx <- prjeb12284 %>%\n",
+    "  mutate(sample_name = gsub(\"\\\\.\", \"\", sample_alias)) %>%\n",
+    "  select(sample_name,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjeb12083_mgx <- prjeb12083 %>%\n",
+    "  select(sample_name = sample_alias,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjeb12284_vs_prjeb12083 <- inner_join(prjeb12284_mtx, prjeb12083_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"wastewater\")\n",
+    "\n",
+    "prjeb12284_vs_prjeb12083"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "256aec2e",
+   "metadata": {},
+   "source": [
+    "## PRJEB32787 (mgx) & PRJEB32788 (mtx)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "id": "6041c9ec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjeb32787 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJEB32787&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)\n",
+    "\n",
+    "prjeb32788 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJEB32788&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "id": "c46f0f14",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 17 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>BazoSym_LS-ET_5</td><td>PRJEB32788</td><td>ERR3342479</td><td>PRJEB32787</td><td>ERR3342499</td><td>mussel_gill</td></tr>\n",
+       "\t<tr><td>BazoSym_LS-ET_4</td><td>PRJEB32788</td><td>ERR3342480</td><td>PRJEB32787</td><td>ERR3342500</td><td>mussel_gill</td></tr>\n",
+       "\t<tr><td>BazoSym_LS-MS_3</td><td>PRJEB32788</td><td>ERR3342481</td><td>PRJEB32787</td><td>ERR3342501</td><td>mussel_gill</td></tr>\n",
+       "\t<tr><td>BazoSym_LS-MS_2</td><td>PRJEB32788</td><td>ERR3342482</td><td>PRJEB32787</td><td>ERR3342502</td><td>mussel_gill</td></tr>\n",
+       "\t<tr><td>BazoSym_LS-MS_1</td><td>PRJEB32788</td><td>ERR3342483</td><td>PRJEB32787</td><td>ERR3342503</td><td>mussel_gill</td></tr>\n",
+       "\t<tr><td>BspSym_Li_5    </td><td>PRJEB32788</td><td>ERR3342467</td><td>PRJEB32787</td><td>ERR3342486</td><td>mussel_gill</td></tr>\n",
+       "\t<tr><td>BspSym_Li_4    </td><td>PRJEB32788</td><td>ERR3342468</td><td>PRJEB32787</td><td>ERR3342487</td><td>mussel_gill</td></tr>\n",
+       "\t<tr><td>BspSym_Li_3    </td><td>PRJEB32788</td><td>ERR3342469</td><td>PRJEB32787</td><td>ERR3342488</td><td>mussel_gill</td></tr>\n",
+       "\t<tr><td>BspSym_Li_2    </td><td>PRJEB32788</td><td>ERR3342470</td><td>PRJEB32787</td><td>ERR3342489</td><td>mussel_gill</td></tr>\n",
+       "\t<tr><td>BspSym_Li_1    </td><td>PRJEB32788</td><td>ERR3342471</td><td>PRJEB32787</td><td>ERR3342490</td><td>mussel_gill</td></tr>\n",
+       "\t<tr><td>BspSym_Cl_4    </td><td>PRJEB32788</td><td>ERR3342472</td><td>PRJEB32787</td><td>ERR3342492</td><td>mussel_gill</td></tr>\n",
+       "\t<tr><td>BspSym_Cl_3    </td><td>PRJEB32788</td><td>ERR3342473</td><td>PRJEB32787</td><td>ERR3342493</td><td>mussel_gill</td></tr>\n",
+       "\t<tr><td>BspSym_Cl_2    </td><td>PRJEB32788</td><td>ERR3342474</td><td>PRJEB32787</td><td>ERR3342494</td><td>mussel_gill</td></tr>\n",
+       "\t<tr><td>BspSym_Cl_1    </td><td>PRJEB32788</td><td>ERR3342475</td><td>PRJEB32787</td><td>ERR3342495</td><td>mussel_gill</td></tr>\n",
+       "\t<tr><td>BputSym_Se-AL_3</td><td>PRJEB32788</td><td>ERR3342476</td><td>PRJEB32787</td><td>ERR3342496</td><td>mussel_gill</td></tr>\n",
+       "\t<tr><td>BputSym_Se-AL_2</td><td>PRJEB32788</td><td>ERR3342477</td><td>PRJEB32787</td><td>ERR3342497</td><td>mussel_gill</td></tr>\n",
+       "\t<tr><td>BputSym_Se-AL_1</td><td>PRJEB32788</td><td>ERR3342478</td><td>PRJEB32787</td><td>ERR3342498</td><td>mussel_gill</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 17 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t BazoSym\\_LS-ET\\_5 & PRJEB32788 & ERR3342479 & PRJEB32787 & ERR3342499 & mussel\\_gill\\\\\n",
+       "\t BazoSym\\_LS-ET\\_4 & PRJEB32788 & ERR3342480 & PRJEB32787 & ERR3342500 & mussel\\_gill\\\\\n",
+       "\t BazoSym\\_LS-MS\\_3 & PRJEB32788 & ERR3342481 & PRJEB32787 & ERR3342501 & mussel\\_gill\\\\\n",
+       "\t BazoSym\\_LS-MS\\_2 & PRJEB32788 & ERR3342482 & PRJEB32787 & ERR3342502 & mussel\\_gill\\\\\n",
+       "\t BazoSym\\_LS-MS\\_1 & PRJEB32788 & ERR3342483 & PRJEB32787 & ERR3342503 & mussel\\_gill\\\\\n",
+       "\t BspSym\\_Li\\_5     & PRJEB32788 & ERR3342467 & PRJEB32787 & ERR3342486 & mussel\\_gill\\\\\n",
+       "\t BspSym\\_Li\\_4     & PRJEB32788 & ERR3342468 & PRJEB32787 & ERR3342487 & mussel\\_gill\\\\\n",
+       "\t BspSym\\_Li\\_3     & PRJEB32788 & ERR3342469 & PRJEB32787 & ERR3342488 & mussel\\_gill\\\\\n",
+       "\t BspSym\\_Li\\_2     & PRJEB32788 & ERR3342470 & PRJEB32787 & ERR3342489 & mussel\\_gill\\\\\n",
+       "\t BspSym\\_Li\\_1     & PRJEB32788 & ERR3342471 & PRJEB32787 & ERR3342490 & mussel\\_gill\\\\\n",
+       "\t BspSym\\_Cl\\_4     & PRJEB32788 & ERR3342472 & PRJEB32787 & ERR3342492 & mussel\\_gill\\\\\n",
+       "\t BspSym\\_Cl\\_3     & PRJEB32788 & ERR3342473 & PRJEB32787 & ERR3342493 & mussel\\_gill\\\\\n",
+       "\t BspSym\\_Cl\\_2     & PRJEB32788 & ERR3342474 & PRJEB32787 & ERR3342494 & mussel\\_gill\\\\\n",
+       "\t BspSym\\_Cl\\_1     & PRJEB32788 & ERR3342475 & PRJEB32787 & ERR3342495 & mussel\\_gill\\\\\n",
+       "\t BputSym\\_Se-AL\\_3 & PRJEB32788 & ERR3342476 & PRJEB32787 & ERR3342496 & mussel\\_gill\\\\\n",
+       "\t BputSym\\_Se-AL\\_2 & PRJEB32788 & ERR3342477 & PRJEB32787 & ERR3342497 & mussel\\_gill\\\\\n",
+       "\t BputSym\\_Se-AL\\_1 & PRJEB32788 & ERR3342478 & PRJEB32787 & ERR3342498 & mussel\\_gill\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 17 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| BazoSym_LS-ET_5 | PRJEB32788 | ERR3342479 | PRJEB32787 | ERR3342499 | mussel_gill |\n",
+       "| BazoSym_LS-ET_4 | PRJEB32788 | ERR3342480 | PRJEB32787 | ERR3342500 | mussel_gill |\n",
+       "| BazoSym_LS-MS_3 | PRJEB32788 | ERR3342481 | PRJEB32787 | ERR3342501 | mussel_gill |\n",
+       "| BazoSym_LS-MS_2 | PRJEB32788 | ERR3342482 | PRJEB32787 | ERR3342502 | mussel_gill |\n",
+       "| BazoSym_LS-MS_1 | PRJEB32788 | ERR3342483 | PRJEB32787 | ERR3342503 | mussel_gill |\n",
+       "| BspSym_Li_5     | PRJEB32788 | ERR3342467 | PRJEB32787 | ERR3342486 | mussel_gill |\n",
+       "| BspSym_Li_4     | PRJEB32788 | ERR3342468 | PRJEB32787 | ERR3342487 | mussel_gill |\n",
+       "| BspSym_Li_3     | PRJEB32788 | ERR3342469 | PRJEB32787 | ERR3342488 | mussel_gill |\n",
+       "| BspSym_Li_2     | PRJEB32788 | ERR3342470 | PRJEB32787 | ERR3342489 | mussel_gill |\n",
+       "| BspSym_Li_1     | PRJEB32788 | ERR3342471 | PRJEB32787 | ERR3342490 | mussel_gill |\n",
+       "| BspSym_Cl_4     | PRJEB32788 | ERR3342472 | PRJEB32787 | ERR3342492 | mussel_gill |\n",
+       "| BspSym_Cl_3     | PRJEB32788 | ERR3342473 | PRJEB32787 | ERR3342493 | mussel_gill |\n",
+       "| BspSym_Cl_2     | PRJEB32788 | ERR3342474 | PRJEB32787 | ERR3342494 | mussel_gill |\n",
+       "| BspSym_Cl_1     | PRJEB32788 | ERR3342475 | PRJEB32787 | ERR3342495 | mussel_gill |\n",
+       "| BputSym_Se-AL_3 | PRJEB32788 | ERR3342476 | PRJEB32787 | ERR3342496 | mussel_gill |\n",
+       "| BputSym_Se-AL_2 | PRJEB32788 | ERR3342477 | PRJEB32787 | ERR3342497 | mussel_gill |\n",
+       "| BputSym_Se-AL_1 | PRJEB32788 | ERR3342478 | PRJEB32787 | ERR3342498 | mussel_gill |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "   sample_name     mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1  BazoSym_LS-ET_5 PRJEB32788          ERR3342479        PRJEB32787         \n",
+       "2  BazoSym_LS-ET_4 PRJEB32788          ERR3342480        PRJEB32787         \n",
+       "3  BazoSym_LS-MS_3 PRJEB32788          ERR3342481        PRJEB32787         \n",
+       "4  BazoSym_LS-MS_2 PRJEB32788          ERR3342482        PRJEB32787         \n",
+       "5  BazoSym_LS-MS_1 PRJEB32788          ERR3342483        PRJEB32787         \n",
+       "6  BspSym_Li_5     PRJEB32788          ERR3342467        PRJEB32787         \n",
+       "7  BspSym_Li_4     PRJEB32788          ERR3342468        PRJEB32787         \n",
+       "8  BspSym_Li_3     PRJEB32788          ERR3342469        PRJEB32787         \n",
+       "9  BspSym_Li_2     PRJEB32788          ERR3342470        PRJEB32787         \n",
+       "10 BspSym_Li_1     PRJEB32788          ERR3342471        PRJEB32787         \n",
+       "11 BspSym_Cl_4     PRJEB32788          ERR3342472        PRJEB32787         \n",
+       "12 BspSym_Cl_3     PRJEB32788          ERR3342473        PRJEB32787         \n",
+       "13 BspSym_Cl_2     PRJEB32788          ERR3342474        PRJEB32787         \n",
+       "14 BspSym_Cl_1     PRJEB32788          ERR3342475        PRJEB32787         \n",
+       "15 BputSym_Se-AL_3 PRJEB32788          ERR3342476        PRJEB32787         \n",
+       "16 BputSym_Se-AL_2 PRJEB32788          ERR3342477        PRJEB32787         \n",
+       "17 BputSym_Se-AL_1 PRJEB32788          ERR3342478        PRJEB32787         \n",
+       "   mgx_run_accession sample_type\n",
+       "1  ERR3342499        mussel_gill\n",
+       "2  ERR3342500        mussel_gill\n",
+       "3  ERR3342501        mussel_gill\n",
+       "4  ERR3342502        mussel_gill\n",
+       "5  ERR3342503        mussel_gill\n",
+       "6  ERR3342486        mussel_gill\n",
+       "7  ERR3342487        mussel_gill\n",
+       "8  ERR3342488        mussel_gill\n",
+       "9  ERR3342489        mussel_gill\n",
+       "10 ERR3342490        mussel_gill\n",
+       "11 ERR3342492        mussel_gill\n",
+       "12 ERR3342493        mussel_gill\n",
+       "13 ERR3342494        mussel_gill\n",
+       "14 ERR3342495        mussel_gill\n",
+       "15 ERR3342496        mussel_gill\n",
+       "16 ERR3342497        mussel_gill\n",
+       "17 ERR3342498        mussel_gill"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjeb32787_mgx <- prjeb32787 %>%\n",
+    "  mutate(sample_name = gsub(\"_[^_]*$\", \"\", sample_title)) %>%\n",
+    "  select(sample_name,\n",
+    "         mgx_study_accession = study_accession,\n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjeb32788_mtx <- prjeb32788 %>%\n",
+    "  mutate(sample_name = gsub(\"_[^_]*$\", \"\", sample_title)) %>%\n",
+    "  select(sample_name,\n",
+    "         mtx_study_accession = study_accession,\n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjeb32788_vs_prjeb32781_1 <- left_join(prjeb32788_mtx, prjeb32787_mgx, by = \"sample_name\") %>%\n",
+    "  filter(!is.na(mgx_study_accession))\n",
+    "\n",
+    "prjeb32788_mtx_2 <- prjeb32788_mtx %>%\n",
+    "  mutate(sample_name = gsub(\"_[^_]*$\", \"\", sample_name)) \n",
+    "\n",
+    "prjeb32788_vs_prjeb32781_2 <- left_join(prjeb32788_mtx_2, prjeb32787_mgx, by = \"sample_name\") %>%\n",
+    "  filter(!is.na(mgx_study_accession))\n",
+    "\n",
+    "prjeb32788_vs_prjeb32781 <- bind_rows(prjeb32788_vs_prjeb32781_1, prjeb32788_vs_prjeb32781_2) %>%\n",
+    "  mutate(sample_type = \"mussel_gill\")\n",
+    "\n",
+    "prjeb32788_vs_prjeb32781 "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cd95fc8c",
+   "metadata": {},
+   "source": [
+    "## iHMP (PRJNA398089)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "id": "1f0ccf12",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna398089 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA398089&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "id": "dd826c94",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 761 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>CSM67UC6</td><td>PRJNA398089</td><td>SRR5949109</td><td>PRJNA398089</td><td>SRR5936217</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>CSM67UDY</td><td>PRJNA398089</td><td>SRR5949110</td><td>PRJNA398089</td><td>SRR5936216</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>HSM67VI9</td><td>PRJNA398089</td><td>SRR5949111</td><td>PRJNA398089</td><td>SRR5936212</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>HSM6XRTQ</td><td>PRJNA398089</td><td>SRR5949112</td><td>PRJNA398089</td><td>SRR5936211</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>CSM79HHM</td><td>PRJNA398089</td><td>SRR5949113</td><td>PRJNA398089</td><td>SRR5946811</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>CSM79HIR</td><td>PRJNA398089</td><td>SRR5949114</td><td>PRJNA398089</td><td>SRR5936215</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>CSM79HJO</td><td>PRJNA398089</td><td>SRR5949115</td><td>PRJNA398089</td><td>SRR5947089</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>HSM67VEI</td><td>PRJNA398089</td><td>SRR5949116</td><td>PRJNA398089</td><td>SRR5936210</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM79H9K</td><td>PRJNA398089</td><td>SRR5949117</td><td>PRJNA398089</td><td>SRR5935975</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM79HAH</td><td>PRJNA398089</td><td>SRR5949118</td><td>PRJNA398089</td><td>SRR5935976</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>HSM7J4L5</td><td>PRJNA398089</td><td>SRR5949119</td><td>PRJNA398089</td><td>SRR5935953</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM79H7E</td><td>PRJNA398089</td><td>SRR5949120</td><td>PRJNA398089</td><td>SRR5935950</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>PSM7J17Z</td><td>PRJNA398089</td><td>SRR5949121</td><td>PRJNA398089</td><td>SRR5935951</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>PSM7J18G</td><td>PRJNA398089</td><td>SRR5949122</td><td>PRJNA398089</td><td>SRR5935952</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM79HDI</td><td>PRJNA398089</td><td>SRR5949123</td><td>PRJNA398089</td><td>SRR5935954</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>HSM7J4JH</td><td>PRJNA398089</td><td>SRR5949124</td><td>PRJNA398089</td><td>SRR5935955</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>HSM7J4HU</td><td>PRJNA398089</td><td>SRR5949125</td><td>PRJNA398089</td><td>SRR5935956</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>PSM7J1CI</td><td>PRJNA398089</td><td>SRR5949126</td><td>PRJNA398089</td><td>SRR5935957</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>HSM7CZ36</td><td>PRJNA398089</td><td>SRR5949127</td><td>PRJNA398089</td><td>SRR5936016</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>CSM7KOJW</td><td>PRJNA398089</td><td>SRR5949128</td><td>PRJNA398089</td><td>SRR5947102</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM79HDM</td><td>PRJNA398089</td><td>SRR5949129</td><td>PRJNA398089</td><td>SRR5936018</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>PSM6XBTP</td><td>PRJNA398089</td><td>SRR5949130</td><td>PRJNA398089</td><td>SRR5936066</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM79HF9</td><td>PRJNA398089</td><td>SRR5949131</td><td>PRJNA398089</td><td>SRR5936064</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>CSM79HQF</td><td>PRJNA398089</td><td>SRR5949132</td><td>PRJNA398089</td><td>SRR5936119</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM79H9A</td><td>PRJNA398089</td><td>SRR5949133</td><td>PRJNA398089</td><td>SRR5936118</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>HSM7CZ3E</td><td>PRJNA398089</td><td>SRR5949134</td><td>PRJNA398089</td><td>SRR5936121</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>CSM79HP4</td><td>PRJNA398089</td><td>SRR5949135</td><td>PRJNA398089</td><td>SRR5946645</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>HSM7CYY7</td><td>PRJNA398089</td><td>SRR5949136</td><td>PRJNA398089</td><td>SRR5936117</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>CSM79HLC</td><td>PRJNA398089</td><td>SRR5949137</td><td>PRJNA398089</td><td>SRR5936176</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM79H5K</td><td>PRJNA398089</td><td>SRR5949138</td><td>PRJNA398089</td><td>SRR5936132</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>⋮</td><td>⋮</td><td>⋮</td><td>⋮</td><td>⋮</td><td>⋮</td></tr>\n",
+       "\t<tr><td>PSM6XBSM   </td><td>PRJNA398089</td><td>SRR5963918</td><td>PRJNA398089</td><td>SRR5950713</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM79HDQ_TR</td><td>PRJNA398089</td><td>SRR5963920</td><td>PRJNA398089</td><td>SRR5962901</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM79HDG_TR</td><td>PRJNA398089</td><td>SRR5963921</td><td>PRJNA398089</td><td>SRR5962900</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM9VZEK_TR</td><td>PRJNA398089</td><td>SRR5963922</td><td>PRJNA398089</td><td>SRR5962903</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM9VZMA_TR</td><td>PRJNA398089</td><td>SRR5963923</td><td>PRJNA398089</td><td>SRR5962902</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>PSMA265J_TR</td><td>PRJNA398089</td><td>SRR5963924</td><td>PRJNA398089</td><td>SRR5962904</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSMA26AZ_TR</td><td>PRJNA398089</td><td>SRR5963925</td><td>PRJNA398089</td><td>SRR5962908</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>HSMA33LH_TR</td><td>PRJNA398089</td><td>SRR5963926</td><td>PRJNA398089</td><td>SRR5962907</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM9VZNH_TR</td><td>PRJNA398089</td><td>SRR5963927</td><td>PRJNA398089</td><td>SRR5962906</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>HSMA33RX_TR</td><td>PRJNA398089</td><td>SRR5963928</td><td>PRJNA398089</td><td>SRR5962885</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>PSM6XBQY_TR</td><td>PRJNA398089</td><td>SRR5963929</td><td>PRJNA398089</td><td>SRR5962895</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>CSM79HLA_TR</td><td>PRJNA398089</td><td>SRR5963930</td><td>PRJNA398089</td><td>SRR5962894</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>HSM6XRVC_TR</td><td>PRJNA398089</td><td>SRR5963931</td><td>PRJNA398089</td><td>SRR5962893</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>HSM5MD6A_TR</td><td>PRJNA398089</td><td>SRR5963932</td><td>PRJNA398089</td><td>SRR5962891</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>PSM6XBRK_TR</td><td>PRJNA398089</td><td>SRR5963933</td><td>PRJNA398089</td><td>SRR5962890</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>CSM67UEW_TR</td><td>PRJNA398089</td><td>SRR5963934</td><td>PRJNA398089</td><td>SRR5962889</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>HSM67VEM_TR</td><td>PRJNA398089</td><td>SRR5963935</td><td>PRJNA398089</td><td>SRR5962892</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>CSM67UDR_TR</td><td>PRJNA398089</td><td>SRR5963936</td><td>PRJNA398089</td><td>SRR5962888</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>PSM6XBSU_TR</td><td>PRJNA398089</td><td>SRR5963937</td><td>PRJNA398089</td><td>SRR5962897</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM79HF9_TR</td><td>PRJNA398089</td><td>SRR5963938</td><td>PRJNA398089</td><td>SRR5962898</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>PSM6XBRK   </td><td>PRJNA398089</td><td>SRR5963939</td><td>PRJNA398089</td><td>SRR5935960</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>PSM6XBQY   </td><td>PRJNA398089</td><td>SRR5963940</td><td>PRJNA398089</td><td>SRR5935809</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSMA26EP   </td><td>PRJNA398089</td><td>SRR5963941</td><td>PRJNA398089</td><td>SRR5946720</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM9VZOW   </td><td>PRJNA398089</td><td>SRR5963942</td><td>PRJNA398089</td><td>SRR5946733</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>PSM6XBQU   </td><td>PRJNA398089</td><td>SRR5963943</td><td>PRJNA398089</td><td>SRR5936007</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSMAPC5Z   </td><td>PRJNA398089</td><td>SRR5963944</td><td>PRJNA398089</td><td>SRR5946832</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM6J2M3   </td><td>PRJNA398089</td><td>SRR5963945</td><td>PRJNA398089</td><td>SRR5935963</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM6J2K6   </td><td>PRJNA398089</td><td>SRR5963946</td><td>PRJNA398089</td><td>SRR5935938</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM6J2Q1   </td><td>PRJNA398089</td><td>SRR5963947</td><td>PRJNA398089</td><td>SRR5936013</td><td>human_gut</td></tr>\n",
+       "\t<tr><td>MSM6J2PS   </td><td>PRJNA398089</td><td>SRR5963948</td><td>PRJNA398089</td><td>SRR5936231</td><td>human_gut</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 761 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t CSM67UC6 & PRJNA398089 & SRR5949109 & PRJNA398089 & SRR5936217 & human\\_gut\\\\\n",
+       "\t CSM67UDY & PRJNA398089 & SRR5949110 & PRJNA398089 & SRR5936216 & human\\_gut\\\\\n",
+       "\t HSM67VI9 & PRJNA398089 & SRR5949111 & PRJNA398089 & SRR5936212 & human\\_gut\\\\\n",
+       "\t HSM6XRTQ & PRJNA398089 & SRR5949112 & PRJNA398089 & SRR5936211 & human\\_gut\\\\\n",
+       "\t CSM79HHM & PRJNA398089 & SRR5949113 & PRJNA398089 & SRR5946811 & human\\_gut\\\\\n",
+       "\t CSM79HIR & PRJNA398089 & SRR5949114 & PRJNA398089 & SRR5936215 & human\\_gut\\\\\n",
+       "\t CSM79HJO & PRJNA398089 & SRR5949115 & PRJNA398089 & SRR5947089 & human\\_gut\\\\\n",
+       "\t HSM67VEI & PRJNA398089 & SRR5949116 & PRJNA398089 & SRR5936210 & human\\_gut\\\\\n",
+       "\t MSM79H9K & PRJNA398089 & SRR5949117 & PRJNA398089 & SRR5935975 & human\\_gut\\\\\n",
+       "\t MSM79HAH & PRJNA398089 & SRR5949118 & PRJNA398089 & SRR5935976 & human\\_gut\\\\\n",
+       "\t HSM7J4L5 & PRJNA398089 & SRR5949119 & PRJNA398089 & SRR5935953 & human\\_gut\\\\\n",
+       "\t MSM79H7E & PRJNA398089 & SRR5949120 & PRJNA398089 & SRR5935950 & human\\_gut\\\\\n",
+       "\t PSM7J17Z & PRJNA398089 & SRR5949121 & PRJNA398089 & SRR5935951 & human\\_gut\\\\\n",
+       "\t PSM7J18G & PRJNA398089 & SRR5949122 & PRJNA398089 & SRR5935952 & human\\_gut\\\\\n",
+       "\t MSM79HDI & PRJNA398089 & SRR5949123 & PRJNA398089 & SRR5935954 & human\\_gut\\\\\n",
+       "\t HSM7J4JH & PRJNA398089 & SRR5949124 & PRJNA398089 & SRR5935955 & human\\_gut\\\\\n",
+       "\t HSM7J4HU & PRJNA398089 & SRR5949125 & PRJNA398089 & SRR5935956 & human\\_gut\\\\\n",
+       "\t PSM7J1CI & PRJNA398089 & SRR5949126 & PRJNA398089 & SRR5935957 & human\\_gut\\\\\n",
+       "\t HSM7CZ36 & PRJNA398089 & SRR5949127 & PRJNA398089 & SRR5936016 & human\\_gut\\\\\n",
+       "\t CSM7KOJW & PRJNA398089 & SRR5949128 & PRJNA398089 & SRR5947102 & human\\_gut\\\\\n",
+       "\t MSM79HDM & PRJNA398089 & SRR5949129 & PRJNA398089 & SRR5936018 & human\\_gut\\\\\n",
+       "\t PSM6XBTP & PRJNA398089 & SRR5949130 & PRJNA398089 & SRR5936066 & human\\_gut\\\\\n",
+       "\t MSM79HF9 & PRJNA398089 & SRR5949131 & PRJNA398089 & SRR5936064 & human\\_gut\\\\\n",
+       "\t CSM79HQF & PRJNA398089 & SRR5949132 & PRJNA398089 & SRR5936119 & human\\_gut\\\\\n",
+       "\t MSM79H9A & PRJNA398089 & SRR5949133 & PRJNA398089 & SRR5936118 & human\\_gut\\\\\n",
+       "\t HSM7CZ3E & PRJNA398089 & SRR5949134 & PRJNA398089 & SRR5936121 & human\\_gut\\\\\n",
+       "\t CSM79HP4 & PRJNA398089 & SRR5949135 & PRJNA398089 & SRR5946645 & human\\_gut\\\\\n",
+       "\t HSM7CYY7 & PRJNA398089 & SRR5949136 & PRJNA398089 & SRR5936117 & human\\_gut\\\\\n",
+       "\t CSM79HLC & PRJNA398089 & SRR5949137 & PRJNA398089 & SRR5936176 & human\\_gut\\\\\n",
+       "\t MSM79H5K & PRJNA398089 & SRR5949138 & PRJNA398089 & SRR5936132 & human\\_gut\\\\\n",
+       "\t ⋮ & ⋮ & ⋮ & ⋮ & ⋮ & ⋮\\\\\n",
+       "\t PSM6XBSM    & PRJNA398089 & SRR5963918 & PRJNA398089 & SRR5950713 & human\\_gut\\\\\n",
+       "\t MSM79HDQ\\_TR & PRJNA398089 & SRR5963920 & PRJNA398089 & SRR5962901 & human\\_gut\\\\\n",
+       "\t MSM79HDG\\_TR & PRJNA398089 & SRR5963921 & PRJNA398089 & SRR5962900 & human\\_gut\\\\\n",
+       "\t MSM9VZEK\\_TR & PRJNA398089 & SRR5963922 & PRJNA398089 & SRR5962903 & human\\_gut\\\\\n",
+       "\t MSM9VZMA\\_TR & PRJNA398089 & SRR5963923 & PRJNA398089 & SRR5962902 & human\\_gut\\\\\n",
+       "\t PSMA265J\\_TR & PRJNA398089 & SRR5963924 & PRJNA398089 & SRR5962904 & human\\_gut\\\\\n",
+       "\t MSMA26AZ\\_TR & PRJNA398089 & SRR5963925 & PRJNA398089 & SRR5962908 & human\\_gut\\\\\n",
+       "\t HSMA33LH\\_TR & PRJNA398089 & SRR5963926 & PRJNA398089 & SRR5962907 & human\\_gut\\\\\n",
+       "\t MSM9VZNH\\_TR & PRJNA398089 & SRR5963927 & PRJNA398089 & SRR5962906 & human\\_gut\\\\\n",
+       "\t HSMA33RX\\_TR & PRJNA398089 & SRR5963928 & PRJNA398089 & SRR5962885 & human\\_gut\\\\\n",
+       "\t PSM6XBQY\\_TR & PRJNA398089 & SRR5963929 & PRJNA398089 & SRR5962895 & human\\_gut\\\\\n",
+       "\t CSM79HLA\\_TR & PRJNA398089 & SRR5963930 & PRJNA398089 & SRR5962894 & human\\_gut\\\\\n",
+       "\t HSM6XRVC\\_TR & PRJNA398089 & SRR5963931 & PRJNA398089 & SRR5962893 & human\\_gut\\\\\n",
+       "\t HSM5MD6A\\_TR & PRJNA398089 & SRR5963932 & PRJNA398089 & SRR5962891 & human\\_gut\\\\\n",
+       "\t PSM6XBRK\\_TR & PRJNA398089 & SRR5963933 & PRJNA398089 & SRR5962890 & human\\_gut\\\\\n",
+       "\t CSM67UEW\\_TR & PRJNA398089 & SRR5963934 & PRJNA398089 & SRR5962889 & human\\_gut\\\\\n",
+       "\t HSM67VEM\\_TR & PRJNA398089 & SRR5963935 & PRJNA398089 & SRR5962892 & human\\_gut\\\\\n",
+       "\t CSM67UDR\\_TR & PRJNA398089 & SRR5963936 & PRJNA398089 & SRR5962888 & human\\_gut\\\\\n",
+       "\t PSM6XBSU\\_TR & PRJNA398089 & SRR5963937 & PRJNA398089 & SRR5962897 & human\\_gut\\\\\n",
+       "\t MSM79HF9\\_TR & PRJNA398089 & SRR5963938 & PRJNA398089 & SRR5962898 & human\\_gut\\\\\n",
+       "\t PSM6XBRK    & PRJNA398089 & SRR5963939 & PRJNA398089 & SRR5935960 & human\\_gut\\\\\n",
+       "\t PSM6XBQY    & PRJNA398089 & SRR5963940 & PRJNA398089 & SRR5935809 & human\\_gut\\\\\n",
+       "\t MSMA26EP    & PRJNA398089 & SRR5963941 & PRJNA398089 & SRR5946720 & human\\_gut\\\\\n",
+       "\t MSM9VZOW    & PRJNA398089 & SRR5963942 & PRJNA398089 & SRR5946733 & human\\_gut\\\\\n",
+       "\t PSM6XBQU    & PRJNA398089 & SRR5963943 & PRJNA398089 & SRR5936007 & human\\_gut\\\\\n",
+       "\t MSMAPC5Z    & PRJNA398089 & SRR5963944 & PRJNA398089 & SRR5946832 & human\\_gut\\\\\n",
+       "\t MSM6J2M3    & PRJNA398089 & SRR5963945 & PRJNA398089 & SRR5935963 & human\\_gut\\\\\n",
+       "\t MSM6J2K6    & PRJNA398089 & SRR5963946 & PRJNA398089 & SRR5935938 & human\\_gut\\\\\n",
+       "\t MSM6J2Q1    & PRJNA398089 & SRR5963947 & PRJNA398089 & SRR5936013 & human\\_gut\\\\\n",
+       "\t MSM6J2PS    & PRJNA398089 & SRR5963948 & PRJNA398089 & SRR5936231 & human\\_gut\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 761 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| CSM67UC6 | PRJNA398089 | SRR5949109 | PRJNA398089 | SRR5936217 | human_gut |\n",
+       "| CSM67UDY | PRJNA398089 | SRR5949110 | PRJNA398089 | SRR5936216 | human_gut |\n",
+       "| HSM67VI9 | PRJNA398089 | SRR5949111 | PRJNA398089 | SRR5936212 | human_gut |\n",
+       "| HSM6XRTQ | PRJNA398089 | SRR5949112 | PRJNA398089 | SRR5936211 | human_gut |\n",
+       "| CSM79HHM | PRJNA398089 | SRR5949113 | PRJNA398089 | SRR5946811 | human_gut |\n",
+       "| CSM79HIR | PRJNA398089 | SRR5949114 | PRJNA398089 | SRR5936215 | human_gut |\n",
+       "| CSM79HJO | PRJNA398089 | SRR5949115 | PRJNA398089 | SRR5947089 | human_gut |\n",
+       "| HSM67VEI | PRJNA398089 | SRR5949116 | PRJNA398089 | SRR5936210 | human_gut |\n",
+       "| MSM79H9K | PRJNA398089 | SRR5949117 | PRJNA398089 | SRR5935975 | human_gut |\n",
+       "| MSM79HAH | PRJNA398089 | SRR5949118 | PRJNA398089 | SRR5935976 | human_gut |\n",
+       "| HSM7J4L5 | PRJNA398089 | SRR5949119 | PRJNA398089 | SRR5935953 | human_gut |\n",
+       "| MSM79H7E | PRJNA398089 | SRR5949120 | PRJNA398089 | SRR5935950 | human_gut |\n",
+       "| PSM7J17Z | PRJNA398089 | SRR5949121 | PRJNA398089 | SRR5935951 | human_gut |\n",
+       "| PSM7J18G | PRJNA398089 | SRR5949122 | PRJNA398089 | SRR5935952 | human_gut |\n",
+       "| MSM79HDI | PRJNA398089 | SRR5949123 | PRJNA398089 | SRR5935954 | human_gut |\n",
+       "| HSM7J4JH | PRJNA398089 | SRR5949124 | PRJNA398089 | SRR5935955 | human_gut |\n",
+       "| HSM7J4HU | PRJNA398089 | SRR5949125 | PRJNA398089 | SRR5935956 | human_gut |\n",
+       "| PSM7J1CI | PRJNA398089 | SRR5949126 | PRJNA398089 | SRR5935957 | human_gut |\n",
+       "| HSM7CZ36 | PRJNA398089 | SRR5949127 | PRJNA398089 | SRR5936016 | human_gut |\n",
+       "| CSM7KOJW | PRJNA398089 | SRR5949128 | PRJNA398089 | SRR5947102 | human_gut |\n",
+       "| MSM79HDM | PRJNA398089 | SRR5949129 | PRJNA398089 | SRR5936018 | human_gut |\n",
+       "| PSM6XBTP | PRJNA398089 | SRR5949130 | PRJNA398089 | SRR5936066 | human_gut |\n",
+       "| MSM79HF9 | PRJNA398089 | SRR5949131 | PRJNA398089 | SRR5936064 | human_gut |\n",
+       "| CSM79HQF | PRJNA398089 | SRR5949132 | PRJNA398089 | SRR5936119 | human_gut |\n",
+       "| MSM79H9A | PRJNA398089 | SRR5949133 | PRJNA398089 | SRR5936118 | human_gut |\n",
+       "| HSM7CZ3E | PRJNA398089 | SRR5949134 | PRJNA398089 | SRR5936121 | human_gut |\n",
+       "| CSM79HP4 | PRJNA398089 | SRR5949135 | PRJNA398089 | SRR5946645 | human_gut |\n",
+       "| HSM7CYY7 | PRJNA398089 | SRR5949136 | PRJNA398089 | SRR5936117 | human_gut |\n",
+       "| CSM79HLC | PRJNA398089 | SRR5949137 | PRJNA398089 | SRR5936176 | human_gut |\n",
+       "| MSM79H5K | PRJNA398089 | SRR5949138 | PRJNA398089 | SRR5936132 | human_gut |\n",
+       "| ⋮ | ⋮ | ⋮ | ⋮ | ⋮ | ⋮ |\n",
+       "| PSM6XBSM    | PRJNA398089 | SRR5963918 | PRJNA398089 | SRR5950713 | human_gut |\n",
+       "| MSM79HDQ_TR | PRJNA398089 | SRR5963920 | PRJNA398089 | SRR5962901 | human_gut |\n",
+       "| MSM79HDG_TR | PRJNA398089 | SRR5963921 | PRJNA398089 | SRR5962900 | human_gut |\n",
+       "| MSM9VZEK_TR | PRJNA398089 | SRR5963922 | PRJNA398089 | SRR5962903 | human_gut |\n",
+       "| MSM9VZMA_TR | PRJNA398089 | SRR5963923 | PRJNA398089 | SRR5962902 | human_gut |\n",
+       "| PSMA265J_TR | PRJNA398089 | SRR5963924 | PRJNA398089 | SRR5962904 | human_gut |\n",
+       "| MSMA26AZ_TR | PRJNA398089 | SRR5963925 | PRJNA398089 | SRR5962908 | human_gut |\n",
+       "| HSMA33LH_TR | PRJNA398089 | SRR5963926 | PRJNA398089 | SRR5962907 | human_gut |\n",
+       "| MSM9VZNH_TR | PRJNA398089 | SRR5963927 | PRJNA398089 | SRR5962906 | human_gut |\n",
+       "| HSMA33RX_TR | PRJNA398089 | SRR5963928 | PRJNA398089 | SRR5962885 | human_gut |\n",
+       "| PSM6XBQY_TR | PRJNA398089 | SRR5963929 | PRJNA398089 | SRR5962895 | human_gut |\n",
+       "| CSM79HLA_TR | PRJNA398089 | SRR5963930 | PRJNA398089 | SRR5962894 | human_gut |\n",
+       "| HSM6XRVC_TR | PRJNA398089 | SRR5963931 | PRJNA398089 | SRR5962893 | human_gut |\n",
+       "| HSM5MD6A_TR | PRJNA398089 | SRR5963932 | PRJNA398089 | SRR5962891 | human_gut |\n",
+       "| PSM6XBRK_TR | PRJNA398089 | SRR5963933 | PRJNA398089 | SRR5962890 | human_gut |\n",
+       "| CSM67UEW_TR | PRJNA398089 | SRR5963934 | PRJNA398089 | SRR5962889 | human_gut |\n",
+       "| HSM67VEM_TR | PRJNA398089 | SRR5963935 | PRJNA398089 | SRR5962892 | human_gut |\n",
+       "| CSM67UDR_TR | PRJNA398089 | SRR5963936 | PRJNA398089 | SRR5962888 | human_gut |\n",
+       "| PSM6XBSU_TR | PRJNA398089 | SRR5963937 | PRJNA398089 | SRR5962897 | human_gut |\n",
+       "| MSM79HF9_TR | PRJNA398089 | SRR5963938 | PRJNA398089 | SRR5962898 | human_gut |\n",
+       "| PSM6XBRK    | PRJNA398089 | SRR5963939 | PRJNA398089 | SRR5935960 | human_gut |\n",
+       "| PSM6XBQY    | PRJNA398089 | SRR5963940 | PRJNA398089 | SRR5935809 | human_gut |\n",
+       "| MSMA26EP    | PRJNA398089 | SRR5963941 | PRJNA398089 | SRR5946720 | human_gut |\n",
+       "| MSM9VZOW    | PRJNA398089 | SRR5963942 | PRJNA398089 | SRR5946733 | human_gut |\n",
+       "| PSM6XBQU    | PRJNA398089 | SRR5963943 | PRJNA398089 | SRR5936007 | human_gut |\n",
+       "| MSMAPC5Z    | PRJNA398089 | SRR5963944 | PRJNA398089 | SRR5946832 | human_gut |\n",
+       "| MSM6J2M3    | PRJNA398089 | SRR5963945 | PRJNA398089 | SRR5935963 | human_gut |\n",
+       "| MSM6J2K6    | PRJNA398089 | SRR5963946 | PRJNA398089 | SRR5935938 | human_gut |\n",
+       "| MSM6J2Q1    | PRJNA398089 | SRR5963947 | PRJNA398089 | SRR5936013 | human_gut |\n",
+       "| MSM6J2PS    | PRJNA398089 | SRR5963948 | PRJNA398089 | SRR5936231 | human_gut |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "    sample_name mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1   CSM67UC6    PRJNA398089         SRR5949109        PRJNA398089        \n",
+       "2   CSM67UDY    PRJNA398089         SRR5949110        PRJNA398089        \n",
+       "3   HSM67VI9    PRJNA398089         SRR5949111        PRJNA398089        \n",
+       "4   HSM6XRTQ    PRJNA398089         SRR5949112        PRJNA398089        \n",
+       "5   CSM79HHM    PRJNA398089         SRR5949113        PRJNA398089        \n",
+       "6   CSM79HIR    PRJNA398089         SRR5949114        PRJNA398089        \n",
+       "7   CSM79HJO    PRJNA398089         SRR5949115        PRJNA398089        \n",
+       "8   HSM67VEI    PRJNA398089         SRR5949116        PRJNA398089        \n",
+       "9   MSM79H9K    PRJNA398089         SRR5949117        PRJNA398089        \n",
+       "10  MSM79HAH    PRJNA398089         SRR5949118        PRJNA398089        \n",
+       "11  HSM7J4L5    PRJNA398089         SRR5949119        PRJNA398089        \n",
+       "12  MSM79H7E    PRJNA398089         SRR5949120        PRJNA398089        \n",
+       "13  PSM7J17Z    PRJNA398089         SRR5949121        PRJNA398089        \n",
+       "14  PSM7J18G    PRJNA398089         SRR5949122        PRJNA398089        \n",
+       "15  MSM79HDI    PRJNA398089         SRR5949123        PRJNA398089        \n",
+       "16  HSM7J4JH    PRJNA398089         SRR5949124        PRJNA398089        \n",
+       "17  HSM7J4HU    PRJNA398089         SRR5949125        PRJNA398089        \n",
+       "18  PSM7J1CI    PRJNA398089         SRR5949126        PRJNA398089        \n",
+       "19  HSM7CZ36    PRJNA398089         SRR5949127        PRJNA398089        \n",
+       "20  CSM7KOJW    PRJNA398089         SRR5949128        PRJNA398089        \n",
+       "21  MSM79HDM    PRJNA398089         SRR5949129        PRJNA398089        \n",
+       "22  PSM6XBTP    PRJNA398089         SRR5949130        PRJNA398089        \n",
+       "23  MSM79HF9    PRJNA398089         SRR5949131        PRJNA398089        \n",
+       "24  CSM79HQF    PRJNA398089         SRR5949132        PRJNA398089        \n",
+       "25  MSM79H9A    PRJNA398089         SRR5949133        PRJNA398089        \n",
+       "26  HSM7CZ3E    PRJNA398089         SRR5949134        PRJNA398089        \n",
+       "27  CSM79HP4    PRJNA398089         SRR5949135        PRJNA398089        \n",
+       "28  HSM7CYY7    PRJNA398089         SRR5949136        PRJNA398089        \n",
+       "29  CSM79HLC    PRJNA398089         SRR5949137        PRJNA398089        \n",
+       "30  MSM79H5K    PRJNA398089         SRR5949138        PRJNA398089        \n",
+       "⋮   ⋮           ⋮                   ⋮                 ⋮                  \n",
+       "732 PSM6XBSM    PRJNA398089         SRR5963918        PRJNA398089        \n",
+       "733 MSM79HDQ_TR PRJNA398089         SRR5963920        PRJNA398089        \n",
+       "734 MSM79HDG_TR PRJNA398089         SRR5963921        PRJNA398089        \n",
+       "735 MSM9VZEK_TR PRJNA398089         SRR5963922        PRJNA398089        \n",
+       "736 MSM9VZMA_TR PRJNA398089         SRR5963923        PRJNA398089        \n",
+       "737 PSMA265J_TR PRJNA398089         SRR5963924        PRJNA398089        \n",
+       "738 MSMA26AZ_TR PRJNA398089         SRR5963925        PRJNA398089        \n",
+       "739 HSMA33LH_TR PRJNA398089         SRR5963926        PRJNA398089        \n",
+       "740 MSM9VZNH_TR PRJNA398089         SRR5963927        PRJNA398089        \n",
+       "741 HSMA33RX_TR PRJNA398089         SRR5963928        PRJNA398089        \n",
+       "742 PSM6XBQY_TR PRJNA398089         SRR5963929        PRJNA398089        \n",
+       "743 CSM79HLA_TR PRJNA398089         SRR5963930        PRJNA398089        \n",
+       "744 HSM6XRVC_TR PRJNA398089         SRR5963931        PRJNA398089        \n",
+       "745 HSM5MD6A_TR PRJNA398089         SRR5963932        PRJNA398089        \n",
+       "746 PSM6XBRK_TR PRJNA398089         SRR5963933        PRJNA398089        \n",
+       "747 CSM67UEW_TR PRJNA398089         SRR5963934        PRJNA398089        \n",
+       "748 HSM67VEM_TR PRJNA398089         SRR5963935        PRJNA398089        \n",
+       "749 CSM67UDR_TR PRJNA398089         SRR5963936        PRJNA398089        \n",
+       "750 PSM6XBSU_TR PRJNA398089         SRR5963937        PRJNA398089        \n",
+       "751 MSM79HF9_TR PRJNA398089         SRR5963938        PRJNA398089        \n",
+       "752 PSM6XBRK    PRJNA398089         SRR5963939        PRJNA398089        \n",
+       "753 PSM6XBQY    PRJNA398089         SRR5963940        PRJNA398089        \n",
+       "754 MSMA26EP    PRJNA398089         SRR5963941        PRJNA398089        \n",
+       "755 MSM9VZOW    PRJNA398089         SRR5963942        PRJNA398089        \n",
+       "756 PSM6XBQU    PRJNA398089         SRR5963943        PRJNA398089        \n",
+       "757 MSMAPC5Z    PRJNA398089         SRR5963944        PRJNA398089        \n",
+       "758 MSM6J2M3    PRJNA398089         SRR5963945        PRJNA398089        \n",
+       "759 MSM6J2K6    PRJNA398089         SRR5963946        PRJNA398089        \n",
+       "760 MSM6J2Q1    PRJNA398089         SRR5963947        PRJNA398089        \n",
+       "761 MSM6J2PS    PRJNA398089         SRR5963948        PRJNA398089        \n",
+       "    mgx_run_accession sample_type\n",
+       "1   SRR5936217        human_gut  \n",
+       "2   SRR5936216        human_gut  \n",
+       "3   SRR5936212        human_gut  \n",
+       "4   SRR5936211        human_gut  \n",
+       "5   SRR5946811        human_gut  \n",
+       "6   SRR5936215        human_gut  \n",
+       "7   SRR5947089        human_gut  \n",
+       "8   SRR5936210        human_gut  \n",
+       "9   SRR5935975        human_gut  \n",
+       "10  SRR5935976        human_gut  \n",
+       "11  SRR5935953        human_gut  \n",
+       "12  SRR5935950        human_gut  \n",
+       "13  SRR5935951        human_gut  \n",
+       "14  SRR5935952        human_gut  \n",
+       "15  SRR5935954        human_gut  \n",
+       "16  SRR5935955        human_gut  \n",
+       "17  SRR5935956        human_gut  \n",
+       "18  SRR5935957        human_gut  \n",
+       "19  SRR5936016        human_gut  \n",
+       "20  SRR5947102        human_gut  \n",
+       "21  SRR5936018        human_gut  \n",
+       "22  SRR5936066        human_gut  \n",
+       "23  SRR5936064        human_gut  \n",
+       "24  SRR5936119        human_gut  \n",
+       "25  SRR5936118        human_gut  \n",
+       "26  SRR5936121        human_gut  \n",
+       "27  SRR5946645        human_gut  \n",
+       "28  SRR5936117        human_gut  \n",
+       "29  SRR5936176        human_gut  \n",
+       "30  SRR5936132        human_gut  \n",
+       "⋮   ⋮                 ⋮          \n",
+       "732 SRR5950713        human_gut  \n",
+       "733 SRR5962901        human_gut  \n",
+       "734 SRR5962900        human_gut  \n",
+       "735 SRR5962903        human_gut  \n",
+       "736 SRR5962902        human_gut  \n",
+       "737 SRR5962904        human_gut  \n",
+       "738 SRR5962908        human_gut  \n",
+       "739 SRR5962907        human_gut  \n",
+       "740 SRR5962906        human_gut  \n",
+       "741 SRR5962885        human_gut  \n",
+       "742 SRR5962895        human_gut  \n",
+       "743 SRR5962894        human_gut  \n",
+       "744 SRR5962893        human_gut  \n",
+       "745 SRR5962891        human_gut  \n",
+       "746 SRR5962890        human_gut  \n",
+       "747 SRR5962889        human_gut  \n",
+       "748 SRR5962892        human_gut  \n",
+       "749 SRR5962888        human_gut  \n",
+       "750 SRR5962897        human_gut  \n",
+       "751 SRR5962898        human_gut  \n",
+       "752 SRR5935960        human_gut  \n",
+       "753 SRR5935809        human_gut  \n",
+       "754 SRR5946720        human_gut  \n",
+       "755 SRR5946733        human_gut  \n",
+       "756 SRR5936007        human_gut  \n",
+       "757 SRR5946832        human_gut  \n",
+       "758 SRR5935963        human_gut  \n",
+       "759 SRR5935938        human_gut  \n",
+       "760 SRR5936013        human_gut  \n",
+       "761 SRR5936231        human_gut  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna398089_mtx <- prjna398089 %>%\n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  filter(library_strategy == \"RNA-Seq\") %>%\n",
+    "  mutate(sample_name = gsub(\"_MTX\", \"\", experiment_alias)) %>%\n",
+    "  select(sample_name, \n",
+    "         mtx_study_accession = study_accession, \n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna398089_mgx <- prjna398089 %>%\n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  filter(library_strategy == \"WGS\") %>%\n",
+    "  mutate(sample_name = gsub(\"_MGX\", \"\", experiment_alias)) %>%\n",
+    "  select(sample_name, \n",
+    "         mgx_study_accession = study_accession, \n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjna398089_mtx_vs_mgx <- inner_join(prjna398089_mtx, prjna398089_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"human_gut\")\n",
+    "\n",
+    "prjna398089_mtx_vs_mgx "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f12fe413",
+   "metadata": {},
+   "source": [
+    "## PRJNA632343"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "id": "ce6d4776",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna632343 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA632343&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "id": "acd04061",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 4 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>Amar_Carlsberg-38I-DV129-2-N2        </td><td>PRJNA632343</td><td>SRR11781625</td><td>PRJNA632343</td><td>SRR11781636</td><td>snail_gut</td></tr>\n",
+       "\t<tr><td>Amar_Carlsberg-38I-DV131-6-Intestine </td><td>PRJNA632343</td><td>SRR11781640</td><td>PRJNA632343</td><td>SRR11781639</td><td>snail_gut</td></tr>\n",
+       "\t<tr><td>Amar_Carlsberg-38I-DV129-15-Intestine</td><td>PRJNA632343</td><td>SRR11781643</td><td>PRJNA632343</td><td>SRR11781642</td><td>snail_gut</td></tr>\n",
+       "\t<tr><td>Amar_Carlsberg-38I-DV129-5-Intestine </td><td>PRJNA632343</td><td>SRR11781646</td><td>PRJNA632343</td><td>SRR11781645</td><td>snail_gut</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 4 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t Amar\\_Carlsberg-38I-DV129-2-N2         & PRJNA632343 & SRR11781625 & PRJNA632343 & SRR11781636 & snail\\_gut\\\\\n",
+       "\t Amar\\_Carlsberg-38I-DV131-6-Intestine  & PRJNA632343 & SRR11781640 & PRJNA632343 & SRR11781639 & snail\\_gut\\\\\n",
+       "\t Amar\\_Carlsberg-38I-DV129-15-Intestine & PRJNA632343 & SRR11781643 & PRJNA632343 & SRR11781642 & snail\\_gut\\\\\n",
+       "\t Amar\\_Carlsberg-38I-DV129-5-Intestine  & PRJNA632343 & SRR11781646 & PRJNA632343 & SRR11781645 & snail\\_gut\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 4 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| Amar_Carlsberg-38I-DV129-2-N2         | PRJNA632343 | SRR11781625 | PRJNA632343 | SRR11781636 | snail_gut |\n",
+       "| Amar_Carlsberg-38I-DV131-6-Intestine  | PRJNA632343 | SRR11781640 | PRJNA632343 | SRR11781639 | snail_gut |\n",
+       "| Amar_Carlsberg-38I-DV129-15-Intestine | PRJNA632343 | SRR11781643 | PRJNA632343 | SRR11781642 | snail_gut |\n",
+       "| Amar_Carlsberg-38I-DV129-5-Intestine  | PRJNA632343 | SRR11781646 | PRJNA632343 | SRR11781645 | snail_gut |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  sample_name                           mtx_study_accession mtx_run_accession\n",
+       "1 Amar_Carlsberg-38I-DV129-2-N2         PRJNA632343         SRR11781625      \n",
+       "2 Amar_Carlsberg-38I-DV131-6-Intestine  PRJNA632343         SRR11781640      \n",
+       "3 Amar_Carlsberg-38I-DV129-15-Intestine PRJNA632343         SRR11781643      \n",
+       "4 Amar_Carlsberg-38I-DV129-5-Intestine  PRJNA632343         SRR11781646      \n",
+       "  mgx_study_accession mgx_run_accession sample_type\n",
+       "1 PRJNA632343         SRR11781636       snail_gut  \n",
+       "2 PRJNA632343         SRR11781639       snail_gut  \n",
+       "3 PRJNA632343         SRR11781642       snail_gut  \n",
+       "4 PRJNA632343         SRR11781645       snail_gut  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna632343_mtx <- prjna632343 %>%\n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  filter(library_strategy == \"RNA-Seq\") %>%\n",
+    "  mutate(sample_name = gsub(\"-Illumina-metaRNA\", \"\", experiment_alias),\n",
+    "         sample_name = gsub(\"-Illumina-meta-RNA\", \"\", sample_name)) %>%\n",
+    "  select(sample_name, \n",
+    "         mtx_study_accession = study_accession, \n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna632343_mgx <- prjna632343 %>%\n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  filter(library_strategy == \"WGS\") %>%\n",
+    "  filter(instrument_platform == \"ILLUMINA\") %>%\n",
+    "  mutate(sample_name = gsub(\"-Illumina-metaDNA\", \"\", experiment_alias),\n",
+    "         sample_name = gsub(\"-Illumina-meta-DNA\", \"\", sample_name)) %>%\n",
+    "  select(sample_name, \n",
+    "         mgx_study_accession = study_accession, \n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjna632343_mtx_vs_mgx <- inner_join(prjna632343_mtx, prjna632343_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"snail_gut\")\n",
+    "\n",
+    "prjna632343_mtx_vs_mgx "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "941acc7a",
+   "metadata": {},
+   "source": [
+    "##  PRJNA242360"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "id": "5ce910c4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna242360 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA242360&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "id": "d231a938",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 4 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>BATS_256_C3_1B </td><td>PRJNA242360</td><td>SRR1230757</td><td>PRJNA242360</td><td>SRR1230754</td><td>ocean</td></tr>\n",
+       "\t<tr><td>BATS_261_C2_B2 </td><td>PRJNA242360</td><td>SRR1230758</td><td>PRJNA242360</td><td>SRR1230755</td><td>ocean</td></tr>\n",
+       "\t<tr><td>BATS_261_C8_F2 </td><td>PRJNA242360</td><td>SRR1230759</td><td>PRJNA242360</td><td>SRR1230756</td><td>ocean</td></tr>\n",
+       "\t<tr><td>BATS_256_C10_5A</td><td>PRJNA242360</td><td>SRR1238005</td><td>PRJNA242360</td><td>SRR1230729</td><td>ocean</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 4 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t BATS\\_256\\_C3\\_1B  & PRJNA242360 & SRR1230757 & PRJNA242360 & SRR1230754 & ocean\\\\\n",
+       "\t BATS\\_261\\_C2\\_B2  & PRJNA242360 & SRR1230758 & PRJNA242360 & SRR1230755 & ocean\\\\\n",
+       "\t BATS\\_261\\_C8\\_F2  & PRJNA242360 & SRR1230759 & PRJNA242360 & SRR1230756 & ocean\\\\\n",
+       "\t BATS\\_256\\_C10\\_5A & PRJNA242360 & SRR1238005 & PRJNA242360 & SRR1230729 & ocean\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 4 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| BATS_256_C3_1B  | PRJNA242360 | SRR1230757 | PRJNA242360 | SRR1230754 | ocean |\n",
+       "| BATS_261_C2_B2  | PRJNA242360 | SRR1230758 | PRJNA242360 | SRR1230755 | ocean |\n",
+       "| BATS_261_C8_F2  | PRJNA242360 | SRR1230759 | PRJNA242360 | SRR1230756 | ocean |\n",
+       "| BATS_256_C10_5A | PRJNA242360 | SRR1238005 | PRJNA242360 | SRR1230729 | ocean |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  sample_name     mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1 BATS_256_C3_1B  PRJNA242360         SRR1230757        PRJNA242360        \n",
+       "2 BATS_261_C2_B2  PRJNA242360         SRR1230758        PRJNA242360        \n",
+       "3 BATS_261_C8_F2  PRJNA242360         SRR1230759        PRJNA242360        \n",
+       "4 BATS_256_C10_5A PRJNA242360         SRR1238005        PRJNA242360        \n",
+       "  mgx_run_accession sample_type\n",
+       "1 SRR1230754        ocean      \n",
+       "2 SRR1230755        ocean      \n",
+       "3 SRR1230756        ocean      \n",
+       "4 SRR1230729        ocean      "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna242360_mtx <- prjna242360 %>%\n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  filter(instrument_platform == \"ILLUMINA\") %>%\n",
+    "  mutate(sample_name = gsub(\"Illumina HiSeq 2500 sequencing; \", \"\", experiment_title),\n",
+    "         sample_name = gsub(\"_M[GT]\", \"\", sample_name),\n",
+    "         sample_name = gsub(\"_R1R2\", \"\", sample_name),\n",
+    "         sample_name = gsub(\"C2_2\", \"C2_B2\", sample_name),\n",
+    "         sample_name = gsub(\"C8_2\", \"C8_F2\", sample_name)) %>%\n",
+    "  select(sample_name, \n",
+    "         mtx_study_accession = study_accession, \n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna242360_mgx <- prjna242360 %>%\n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  filter(library_strategy == \"WGS\") %>%\n",
+    "  filter(instrument_platform == \"ILLUMINA\") %>%\n",
+    "  mutate(sample_name = gsub(\"Illumina HiSeq 2500 sequencing; \", \"\", experiment_title),\n",
+    "         sample_name = gsub(\"_M[GT]\", \"\", sample_name),\n",
+    "         sample_name = gsub(\"_R1R2\", \"\", sample_name),\n",
+    "         sample_name = gsub(\"C2_2\", \"C2_B2\", sample_name),\n",
+    "         sample_name = gsub(\"C8_2\", \"C8_F2\", sample_name)) %>%\n",
+    "  select(sample_name, \n",
+    "         mgx_study_accession = study_accession, \n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjna242360_mtx_vs_mgx <- inner_join(prjna242360_mtx, prjna242360_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"ocean\")\n",
+    "\n",
+    "prjna242360_mtx_vs_mgx "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0f3958d4",
+   "metadata": {},
+   "source": [
+    "## PRJEB12234"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "id": "7b4cd065",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjeb12234 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJEB12234&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                      show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "id": "a965057c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 13 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>ES_08072017_CAT2012July    </td><td>PRJEB12234</td><td>ERR2088997</td><td>PRJEB12234</td><td>ERR2094669</td><td>ocean</td></tr>\n",
+       "\t<tr><td>ES_08072017_CAT2012October </td><td>PRJEB12234</td><td>ERR2088998</td><td>PRJEB12234</td><td>ERR2094670</td><td>ocean</td></tr>\n",
+       "\t<tr><td>ES_08072017_CAT2013January </td><td>PRJEB12234</td><td>ERR2088999</td><td>PRJEB12234</td><td>ERR2094671</td><td>ocean</td></tr>\n",
+       "\t<tr><td>ES_08072017_CAT2013April   </td><td>PRJEB12234</td><td>ERR2089000</td><td>PRJEB12234</td><td>ERR2094672</td><td>ocean</td></tr>\n",
+       "\t<tr><td>ES_08072017_POLA2012July   </td><td>PRJEB12234</td><td>ERR2089001</td><td>PRJEB12234</td><td>ERR2094673</td><td>ocean</td></tr>\n",
+       "\t<tr><td>ES_08072017_POLA2012October</td><td>PRJEB12234</td><td>ERR2089002</td><td>PRJEB12234</td><td>ERR2094674</td><td>ocean</td></tr>\n",
+       "\t<tr><td>ES_08072017_POLA2013January</td><td>PRJEB12234</td><td>ERR2089003</td><td>PRJEB12234</td><td>ERR2094675</td><td>ocean</td></tr>\n",
+       "\t<tr><td>ES_08072017_POLA2013April  </td><td>PRJEB12234</td><td>ERR2089004</td><td>PRJEB12234</td><td>ERR2094676</td><td>ocean</td></tr>\n",
+       "\t<tr><td>ES_08072017_SPOT2012July   </td><td>PRJEB12234</td><td>ERR2089005</td><td>PRJEB12234</td><td>ERR2094677</td><td>ocean</td></tr>\n",
+       "\t<tr><td>ES_08072017_SPOT2012October</td><td>PRJEB12234</td><td>ERR2089006</td><td>PRJEB12234</td><td>ERR2094678</td><td>ocean</td></tr>\n",
+       "\t<tr><td>ES_08072017_SPOT2013January</td><td>PRJEB12234</td><td>ERR2089007</td><td>PRJEB12234</td><td>ERR2094679</td><td>ocean</td></tr>\n",
+       "\t<tr><td>ES_08072017_SPOT2013April  </td><td>PRJEB12234</td><td>ERR2089008</td><td>PRJEB12234</td><td>ERR2094680</td><td>ocean</td></tr>\n",
+       "\t<tr><td>ES_08072017_neg_reads      </td><td>PRJEB12234</td><td>ERR2089009</td><td>PRJEB12234</td><td>ERR2097133</td><td>ocean</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 13 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t ES\\_08072017\\_CAT2012July     & PRJEB12234 & ERR2088997 & PRJEB12234 & ERR2094669 & ocean\\\\\n",
+       "\t ES\\_08072017\\_CAT2012October  & PRJEB12234 & ERR2088998 & PRJEB12234 & ERR2094670 & ocean\\\\\n",
+       "\t ES\\_08072017\\_CAT2013January  & PRJEB12234 & ERR2088999 & PRJEB12234 & ERR2094671 & ocean\\\\\n",
+       "\t ES\\_08072017\\_CAT2013April    & PRJEB12234 & ERR2089000 & PRJEB12234 & ERR2094672 & ocean\\\\\n",
+       "\t ES\\_08072017\\_POLA2012July    & PRJEB12234 & ERR2089001 & PRJEB12234 & ERR2094673 & ocean\\\\\n",
+       "\t ES\\_08072017\\_POLA2012October & PRJEB12234 & ERR2089002 & PRJEB12234 & ERR2094674 & ocean\\\\\n",
+       "\t ES\\_08072017\\_POLA2013January & PRJEB12234 & ERR2089003 & PRJEB12234 & ERR2094675 & ocean\\\\\n",
+       "\t ES\\_08072017\\_POLA2013April   & PRJEB12234 & ERR2089004 & PRJEB12234 & ERR2094676 & ocean\\\\\n",
+       "\t ES\\_08072017\\_SPOT2012July    & PRJEB12234 & ERR2089005 & PRJEB12234 & ERR2094677 & ocean\\\\\n",
+       "\t ES\\_08072017\\_SPOT2012October & PRJEB12234 & ERR2089006 & PRJEB12234 & ERR2094678 & ocean\\\\\n",
+       "\t ES\\_08072017\\_SPOT2013January & PRJEB12234 & ERR2089007 & PRJEB12234 & ERR2094679 & ocean\\\\\n",
+       "\t ES\\_08072017\\_SPOT2013April   & PRJEB12234 & ERR2089008 & PRJEB12234 & ERR2094680 & ocean\\\\\n",
+       "\t ES\\_08072017\\_neg\\_reads       & PRJEB12234 & ERR2089009 & PRJEB12234 & ERR2097133 & ocean\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 13 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| ES_08072017_CAT2012July     | PRJEB12234 | ERR2088997 | PRJEB12234 | ERR2094669 | ocean |\n",
+       "| ES_08072017_CAT2012October  | PRJEB12234 | ERR2088998 | PRJEB12234 | ERR2094670 | ocean |\n",
+       "| ES_08072017_CAT2013January  | PRJEB12234 | ERR2088999 | PRJEB12234 | ERR2094671 | ocean |\n",
+       "| ES_08072017_CAT2013April    | PRJEB12234 | ERR2089000 | PRJEB12234 | ERR2094672 | ocean |\n",
+       "| ES_08072017_POLA2012July    | PRJEB12234 | ERR2089001 | PRJEB12234 | ERR2094673 | ocean |\n",
+       "| ES_08072017_POLA2012October | PRJEB12234 | ERR2089002 | PRJEB12234 | ERR2094674 | ocean |\n",
+       "| ES_08072017_POLA2013January | PRJEB12234 | ERR2089003 | PRJEB12234 | ERR2094675 | ocean |\n",
+       "| ES_08072017_POLA2013April   | PRJEB12234 | ERR2089004 | PRJEB12234 | ERR2094676 | ocean |\n",
+       "| ES_08072017_SPOT2012July    | PRJEB12234 | ERR2089005 | PRJEB12234 | ERR2094677 | ocean |\n",
+       "| ES_08072017_SPOT2012October | PRJEB12234 | ERR2089006 | PRJEB12234 | ERR2094678 | ocean |\n",
+       "| ES_08072017_SPOT2013January | PRJEB12234 | ERR2089007 | PRJEB12234 | ERR2094679 | ocean |\n",
+       "| ES_08072017_SPOT2013April   | PRJEB12234 | ERR2089008 | PRJEB12234 | ERR2094680 | ocean |\n",
+       "| ES_08072017_neg_reads       | PRJEB12234 | ERR2089009 | PRJEB12234 | ERR2097133 | ocean |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "   sample_name                 mtx_study_accession mtx_run_accession\n",
+       "1  ES_08072017_CAT2012July     PRJEB12234          ERR2088997       \n",
+       "2  ES_08072017_CAT2012October  PRJEB12234          ERR2088998       \n",
+       "3  ES_08072017_CAT2013January  PRJEB12234          ERR2088999       \n",
+       "4  ES_08072017_CAT2013April    PRJEB12234          ERR2089000       \n",
+       "5  ES_08072017_POLA2012July    PRJEB12234          ERR2089001       \n",
+       "6  ES_08072017_POLA2012October PRJEB12234          ERR2089002       \n",
+       "7  ES_08072017_POLA2013January PRJEB12234          ERR2089003       \n",
+       "8  ES_08072017_POLA2013April   PRJEB12234          ERR2089004       \n",
+       "9  ES_08072017_SPOT2012July    PRJEB12234          ERR2089005       \n",
+       "10 ES_08072017_SPOT2012October PRJEB12234          ERR2089006       \n",
+       "11 ES_08072017_SPOT2013January PRJEB12234          ERR2089007       \n",
+       "12 ES_08072017_SPOT2013April   PRJEB12234          ERR2089008       \n",
+       "13 ES_08072017_neg_reads       PRJEB12234          ERR2089009       \n",
+       "   mgx_study_accession mgx_run_accession sample_type\n",
+       "1  PRJEB12234          ERR2094669        ocean      \n",
+       "2  PRJEB12234          ERR2094670        ocean      \n",
+       "3  PRJEB12234          ERR2094671        ocean      \n",
+       "4  PRJEB12234          ERR2094672        ocean      \n",
+       "5  PRJEB12234          ERR2094673        ocean      \n",
+       "6  PRJEB12234          ERR2094674        ocean      \n",
+       "7  PRJEB12234          ERR2094675        ocean      \n",
+       "8  PRJEB12234          ERR2094676        ocean      \n",
+       "9  PRJEB12234          ERR2094677        ocean      \n",
+       "10 PRJEB12234          ERR2094678        ocean      \n",
+       "11 PRJEB12234          ERR2094679        ocean      \n",
+       "12 PRJEB12234          ERR2094680        ocean      \n",
+       "13 PRJEB12234          ERR2097133        ocean      "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjeb12234_mtx <- prjeb12234 %>%\n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  filter(library_strategy == \"WGS\") %>%\n",
+    "  mutate(sample_name = gsub(\"_MT\", \"\", sample_alias)) %>%\n",
+    "  select(sample_name, \n",
+    "         mtx_study_accession = study_accession, \n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjeb12234_mgx <- prjeb12234 %>%\n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  filter(library_strategy == \"WGS\") %>%\n",
+    "  mutate(sample_name = gsub(\"_MG\", \"\", sample_alias)) %>%\n",
+    "  select(sample_name, \n",
+    "         mgx_study_accession = study_accession, \n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjeb12234_mtx_vs_mgx <- inner_join(prjeb12234_mtx, prjeb12234_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"ocean\")\n",
+    "\n",
+    "prjeb12234_mtx_vs_mgx "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "419d1e0e",
+   "metadata": {},
+   "source": [
+    "## PRJNA340003"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "id": "308ec27f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prjna340003 <- read_tsv(\"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA340003&result=read_run&fields=study_accession,secondary_study_accession,sample_accession,secondary_sample_accession,experiment_accession,run_accession,submission_accession,tax_id,scientific_name,instrument_platform,instrument_model,library_name,nominal_length,library_layout,library_strategy,library_source,library_selection,read_count,base_count,center_name,first_public,last_updated,experiment_title,study_title,study_alias,experiment_alias,run_alias,fastq_bytes,fastq_md5,fastq_ftp,fastq_aspera,fastq_galaxy,submitted_bytes,submitted_md5,submitted_ftp,submitted_aspera,submitted_galaxy,submitted_format,sra_bytes,sra_md5,sra_ftp,sra_aspera,sra_galaxy,cram_index_ftp,cram_index_aspera,cram_index_galaxy,sample_alias,broker_name,sample_title,nominal_sdev,first_created&format=tsv&download=true&limit=0\",\n",
+    "                        show_col_types = F)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "id": "b9428e0a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 6 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>E2A</td><td>PRJNA340003</td><td>SRR4342131</td><td>PRJNA340003</td><td>SRR4342135</td><td>ocean</td></tr>\n",
+       "\t<tr><td>E4 </td><td>PRJNA340003</td><td>SRR4342132</td><td>PRJNA340003</td><td>SRR4342136</td><td>ocean</td></tr>\n",
+       "\t<tr><td>D1 </td><td>PRJNA340003</td><td>SRR4342137</td><td>PRJNA340003</td><td>SRR4342129</td><td>ocean</td></tr>\n",
+       "\t<tr><td>D2 </td><td>PRJNA340003</td><td>SRR4342138</td><td>PRJNA340003</td><td>SRR4342130</td><td>ocean</td></tr>\n",
+       "\t<tr><td>D3 </td><td>PRJNA340003</td><td>SRR4342139</td><td>PRJNA340003</td><td>SRR4342133</td><td>ocean</td></tr>\n",
+       "\t<tr><td>E2 </td><td>PRJNA340003</td><td>SRR4342140</td><td>PRJNA340003</td><td>SRR4342134</td><td>ocean</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 6 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t E2A & PRJNA340003 & SRR4342131 & PRJNA340003 & SRR4342135 & ocean\\\\\n",
+       "\t E4  & PRJNA340003 & SRR4342132 & PRJNA340003 & SRR4342136 & ocean\\\\\n",
+       "\t D1  & PRJNA340003 & SRR4342137 & PRJNA340003 & SRR4342129 & ocean\\\\\n",
+       "\t D2  & PRJNA340003 & SRR4342138 & PRJNA340003 & SRR4342130 & ocean\\\\\n",
+       "\t D3  & PRJNA340003 & SRR4342139 & PRJNA340003 & SRR4342133 & ocean\\\\\n",
+       "\t E2  & PRJNA340003 & SRR4342140 & PRJNA340003 & SRR4342134 & ocean\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 6 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| E2A | PRJNA340003 | SRR4342131 | PRJNA340003 | SRR4342135 | ocean |\n",
+       "| E4  | PRJNA340003 | SRR4342132 | PRJNA340003 | SRR4342136 | ocean |\n",
+       "| D1  | PRJNA340003 | SRR4342137 | PRJNA340003 | SRR4342129 | ocean |\n",
+       "| D2  | PRJNA340003 | SRR4342138 | PRJNA340003 | SRR4342130 | ocean |\n",
+       "| D3  | PRJNA340003 | SRR4342139 | PRJNA340003 | SRR4342133 | ocean |\n",
+       "| E2  | PRJNA340003 | SRR4342140 | PRJNA340003 | SRR4342134 | ocean |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  sample_name mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1 E2A         PRJNA340003         SRR4342131        PRJNA340003        \n",
+       "2 E4          PRJNA340003         SRR4342132        PRJNA340003        \n",
+       "3 D1          PRJNA340003         SRR4342137        PRJNA340003        \n",
+       "4 D2          PRJNA340003         SRR4342138        PRJNA340003        \n",
+       "5 D3          PRJNA340003         SRR4342139        PRJNA340003        \n",
+       "6 E2          PRJNA340003         SRR4342140        PRJNA340003        \n",
+       "  mgx_run_accession sample_type\n",
+       "1 SRR4342135        ocean      \n",
+       "2 SRR4342136        ocean      \n",
+       "3 SRR4342129        ocean      \n",
+       "4 SRR4342130        ocean      \n",
+       "5 SRR4342133        ocean      \n",
+       "6 SRR4342134        ocean      "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "prjna340003_mtx <- prjna340003 %>%\n",
+    "  filter(library_source == \"METATRANSCRIPTOMIC\") %>%\n",
+    "  mutate(sample_name = gsub(\":RNA\", \"\", sample_alias)) %>%\n",
+    "  select(sample_name, \n",
+    "         mtx_study_accession = study_accession, \n",
+    "         mtx_run_accession = run_accession)\n",
+    "\n",
+    "prjna340003_mgx <- prjna340003 %>%\n",
+    "  filter(library_source == \"METAGENOMIC\") %>%\n",
+    "  mutate(sample_name = gsub(\":DNA\", \"\", sample_alias)) %>%\n",
+    "  select(sample_name, \n",
+    "         mgx_study_accession = study_accession, \n",
+    "         mgx_run_accession = run_accession)\n",
+    "\n",
+    "prjna340003_mtx_vs_mgx <- inner_join(prjna340003_mtx, prjna340003_mgx, by = \"sample_name\") %>%\n",
+    "  mutate(sample_type = \"ocean\")\n",
+    "\n",
+    "prjna340003_mtx_vs_mgx "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fc5a0dc6",
+   "metadata": {},
+   "source": [
+    "# Combine everything together"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "id": "0aace26d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 6 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>C_2_1                              </td><td>PRJNA406858</td><td>SRR6032600</td><td>PRJNA406858</td><td>SRR6032602</td><td>activated_sludge</td></tr>\n",
+       "\t<tr><td>B_2_1                              </td><td>PRJNA406858</td><td>SRR6032604</td><td>PRJNA406858</td><td>SRR6032601</td><td>activated_sludge</td></tr>\n",
+       "\t<tr><td>E_2_1                              </td><td>PRJNA406858</td><td>SRR6032605</td><td>PRJNA406858</td><td>SRR6032603</td><td>activated_sludge</td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_101</td><td>PRJNA448333</td><td>SRR8416057</td><td>PRJNA448333</td><td>SRR8397906</td><td>cattle_rumen    </td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_103</td><td>PRJNA448333</td><td>SRR8416058</td><td>PRJNA448333</td><td>SRR8404214</td><td>cattle_rumen    </td></tr>\n",
+       "\t<tr><td>rumen_microbiome_of_beef_cattle_104</td><td>PRJNA448333</td><td>SRR8416055</td><td>PRJNA448333</td><td>SRR8397905</td><td>cattle_rumen    </td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 6 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t C\\_2\\_1                               & PRJNA406858 & SRR6032600 & PRJNA406858 & SRR6032602 & activated\\_sludge\\\\\n",
+       "\t B\\_2\\_1                               & PRJNA406858 & SRR6032604 & PRJNA406858 & SRR6032601 & activated\\_sludge\\\\\n",
+       "\t E\\_2\\_1                               & PRJNA406858 & SRR6032605 & PRJNA406858 & SRR6032603 & activated\\_sludge\\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_101 & PRJNA448333 & SRR8416057 & PRJNA448333 & SRR8397906 & cattle\\_rumen    \\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_103 & PRJNA448333 & SRR8416058 & PRJNA448333 & SRR8404214 & cattle\\_rumen    \\\\\n",
+       "\t rumen\\_microbiome\\_of\\_beef\\_cattle\\_104 & PRJNA448333 & SRR8416055 & PRJNA448333 & SRR8397905 & cattle\\_rumen    \\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 6 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| C_2_1                               | PRJNA406858 | SRR6032600 | PRJNA406858 | SRR6032602 | activated_sludge |\n",
+       "| B_2_1                               | PRJNA406858 | SRR6032604 | PRJNA406858 | SRR6032601 | activated_sludge |\n",
+       "| E_2_1                               | PRJNA406858 | SRR6032605 | PRJNA406858 | SRR6032603 | activated_sludge |\n",
+       "| rumen_microbiome_of_beef_cattle_101 | PRJNA448333 | SRR8416057 | PRJNA448333 | SRR8397906 | cattle_rumen     |\n",
+       "| rumen_microbiome_of_beef_cattle_103 | PRJNA448333 | SRR8416058 | PRJNA448333 | SRR8404214 | cattle_rumen     |\n",
+       "| rumen_microbiome_of_beef_cattle_104 | PRJNA448333 | SRR8416055 | PRJNA448333 | SRR8397905 | cattle_rumen     |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  sample_name                         mtx_study_accession mtx_run_accession\n",
+       "1 C_2_1                               PRJNA406858         SRR6032600       \n",
+       "2 B_2_1                               PRJNA406858         SRR6032604       \n",
+       "3 E_2_1                               PRJNA406858         SRR6032605       \n",
+       "4 rumen_microbiome_of_beef_cattle_101 PRJNA448333         SRR8416057       \n",
+       "5 rumen_microbiome_of_beef_cattle_103 PRJNA448333         SRR8416058       \n",
+       "6 rumen_microbiome_of_beef_cattle_104 PRJNA448333         SRR8416055       \n",
+       "  mgx_study_accession mgx_run_accession sample_type     \n",
+       "1 PRJNA406858         SRR6032602        activated_sludge\n",
+       "2 PRJNA406858         SRR6032601        activated_sludge\n",
+       "3 PRJNA406858         SRR6032603        activated_sludge\n",
+       "4 PRJNA448333         SRR8397906        cattle_rumen    \n",
+       "5 PRJNA448333         SRR8404214        cattle_rumen    \n",
+       "6 PRJNA448333         SRR8397905        cattle_rumen    "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 6 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>E2A</td><td>PRJNA340003</td><td>SRR4342131</td><td>PRJNA340003</td><td>SRR4342135</td><td>ocean</td></tr>\n",
+       "\t<tr><td>E4 </td><td>PRJNA340003</td><td>SRR4342132</td><td>PRJNA340003</td><td>SRR4342136</td><td>ocean</td></tr>\n",
+       "\t<tr><td>D1 </td><td>PRJNA340003</td><td>SRR4342137</td><td>PRJNA340003</td><td>SRR4342129</td><td>ocean</td></tr>\n",
+       "\t<tr><td>D2 </td><td>PRJNA340003</td><td>SRR4342138</td><td>PRJNA340003</td><td>SRR4342130</td><td>ocean</td></tr>\n",
+       "\t<tr><td>D3 </td><td>PRJNA340003</td><td>SRR4342139</td><td>PRJNA340003</td><td>SRR4342133</td><td>ocean</td></tr>\n",
+       "\t<tr><td>E2 </td><td>PRJNA340003</td><td>SRR4342140</td><td>PRJNA340003</td><td>SRR4342134</td><td>ocean</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 6 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\t E2A & PRJNA340003 & SRR4342131 & PRJNA340003 & SRR4342135 & ocean\\\\\n",
+       "\t E4  & PRJNA340003 & SRR4342132 & PRJNA340003 & SRR4342136 & ocean\\\\\n",
+       "\t D1  & PRJNA340003 & SRR4342137 & PRJNA340003 & SRR4342129 & ocean\\\\\n",
+       "\t D2  & PRJNA340003 & SRR4342138 & PRJNA340003 & SRR4342130 & ocean\\\\\n",
+       "\t D3  & PRJNA340003 & SRR4342139 & PRJNA340003 & SRR4342133 & ocean\\\\\n",
+       "\t E2  & PRJNA340003 & SRR4342140 & PRJNA340003 & SRR4342134 & ocean\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 6 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "| E2A | PRJNA340003 | SRR4342131 | PRJNA340003 | SRR4342135 | ocean |\n",
+       "| E4  | PRJNA340003 | SRR4342132 | PRJNA340003 | SRR4342136 | ocean |\n",
+       "| D1  | PRJNA340003 | SRR4342137 | PRJNA340003 | SRR4342129 | ocean |\n",
+       "| D2  | PRJNA340003 | SRR4342138 | PRJNA340003 | SRR4342130 | ocean |\n",
+       "| D3  | PRJNA340003 | SRR4342139 | PRJNA340003 | SRR4342133 | ocean |\n",
+       "| E2  | PRJNA340003 | SRR4342140 | PRJNA340003 | SRR4342134 | ocean |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  sample_name mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "1 E2A         PRJNA340003         SRR4342131        PRJNA340003        \n",
+       "2 E4          PRJNA340003         SRR4342132        PRJNA340003        \n",
+       "3 D1          PRJNA340003         SRR4342137        PRJNA340003        \n",
+       "4 D2          PRJNA340003         SRR4342138        PRJNA340003        \n",
+       "5 D3          PRJNA340003         SRR4342139        PRJNA340003        \n",
+       "6 E2          PRJNA340003         SRR4342140        PRJNA340003        \n",
+       "  mgx_run_accession sample_type\n",
+       "1 SRR4342135        ocean      \n",
+       "2 SRR4342136        ocean      \n",
+       "3 SRR4342129        ocean      \n",
+       "4 SRR4342130        ocean      \n",
+       "5 SRR4342133        ocean      \n",
+       "6 SRR4342134        ocean      "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "1280"
+      ],
+      "text/latex": [
+       "1280"
+      ],
+      "text/markdown": [
+       "1280"
+      ],
+      "text/plain": [
+       "[1] 1280"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "all_paired_mtx_mgx <- bind_rows(prjna406858_mtx_vs_mgx,\n",
+    "                                prjna448333_mtx_vs_mgx,\n",
+    "                                prjna344005_mtx_vs_mgx,\n",
+    "                                prjna453733_mtx_vs_mgx,\n",
+    "                                prjna237345_vs_prjna237344,\n",
+    "                                moran010B_mtx_vs_mgx,\n",
+    "                                prjna603240_mtx_vs_mgx,\n",
+    "                                prjna202380_mtx_vs_mgx,\n",
+    "                                prjna541981_mtx_vs_mgx,\n",
+    "                                prjna797778_mtx_vs_mgx,\n",
+    "                                prjna339914_mtx_vs_mgx,\n",
+    "                                prjeb33889_mtx_vs_mgx,\n",
+    "                                prjna698464_mtx_vs_mgx,\n",
+    "                                prjna396840_mtx_vs_mgx,\n",
+    "                                prjna492158_mtx_vs_mgx,\n",
+    "                                prjna278075_mtx_vs_mgx,\n",
+    "                                prjeb38017_mtx_vs_mgx,\n",
+    "                                prjna616041_mtx_vs_mgx,\n",
+    "                                prjna395125_vs_prjna393770,\n",
+    "                                prjeb12284_vs_prjeb12083,\n",
+    "                                prjeb32788_vs_prjeb32781,\n",
+    "                                prjna398089_mtx_vs_mgx,\n",
+    "                                prjna632343_mtx_vs_mgx,\n",
+    "                                prjna242360_mtx_vs_mgx,\n",
+    "                                prjeb12234_mtx_vs_mgx,\n",
+    "                                prjna340003_mtx_vs_mgx)\n",
+    "head(all_paired_mtx_mgx)\n",
+    "tail(all_paired_mtx_mgx)\n",
+    "nrow(all_paired_mtx_mgx)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "id": "f6f62f8e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\n",
+       "      activated_sludge             bioreactor           cattle_rumen \n",
+       "                     3                     11                     48 \n",
+       "cocoa_box_fermentation               deadwood            groundwater \n",
+       "                     3                     10                      2 \n",
+       "             human_gut             human_oral             human_skin \n",
+       "                   791                     30                     17 \n",
+       "          human_vagina                   lake            mouse_cecum \n",
+       "                   180                      1                      8 \n",
+       "           mussel_gill                  ocean             paddy_soil \n",
+       "                    17                     98                      6 \n",
+       "                 river            sheep_rumen              snail_gut \n",
+       "                    23                     20                      4 \n",
+       "            wastewater \n",
+       "                     8 "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# look at the breakdown of sample types\n",
+    "table(all_paired_mtx_mgx$sample_type)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "id": "8d49c7ee",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "1280"
+      ],
+      "text/latex": [
+       "1280"
+      ],
+      "text/markdown": [
+       "1280"
+      ],
+      "text/plain": [
+       "[1] 1280"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 0 × 6</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>sample_name</th><th scope=col>mtx_study_accession</th><th scope=col>mtx_run_accession</th><th scope=col>mgx_study_accession</th><th scope=col>mgx_run_accession</th><th scope=col>sample_type</th></tr>\n",
+       "\t<tr><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;chr&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 0 × 6\n",
+       "\\begin{tabular}{llllll}\n",
+       " sample\\_name & mtx\\_study\\_accession & mtx\\_run\\_accession & mgx\\_study\\_accession & mgx\\_run\\_accession & sample\\_type\\\\\n",
+       " <chr> & <chr> & <chr> & <chr> & <chr> & <chr>\\\\\n",
+       "\\hline\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 0 × 6\n",
+       "\n",
+       "| sample_name &lt;chr&gt; | mtx_study_accession &lt;chr&gt; | mtx_run_accession &lt;chr&gt; | mgx_study_accession &lt;chr&gt; | mgx_run_accession &lt;chr&gt; | sample_type &lt;chr&gt; |\n",
+       "|---|---|---|---|---|---|\n",
+       "\n"
+      ],
+      "text/plain": [
+       "     sample_name mtx_study_accession mtx_run_accession mgx_study_accession\n",
+       "     mgx_run_accession sample_type"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# check and make sure there are no duplicated sample names, \n",
+    "# either from faulty joins for from x-study shared sample identifiers\n",
+    "length(unique(all_paired_mtx_mgx$sample_name))\n",
+    "\n",
+    "tmp <- all_paired_mtx_mgx %>% \n",
+    "  group_by(sample_name) %>%\n",
+    "  tally() %>%\n",
+    "  filter(n > 1)\n",
+    "\n",
+    "all_paired_mtx_mgx %>%\n",
+    "  filter(sample_name %in% tmp$sample_name)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cffc574e",
+   "metadata": {},
+   "source": [
+    "## Write out tsv with results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "id": "63466e52",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "write_tsv(all_paired_mtx_mgx, \"inputs/metadata-paired-mgx-mtx.tsv\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "56293500",
+   "metadata": {},
+   "source": [
+    "## Session Info"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "id": "c886393d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "R version 4.1.3 (2022-03-10)\n",
+       "Platform: x86_64-apple-darwin13.4.0 (64-bit)\n",
+       "Running under: macOS Big Sur/Monterey 10.16\n",
+       "\n",
+       "Matrix products: default\n",
+       "BLAS/LAPACK: /Users/taylorreiter/miniconda3/envs/tidyjupyter/lib/libopenblasp-r0.3.21.dylib\n",
+       "\n",
+       "locale:\n",
+       "[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8\n",
+       "\n",
+       "attached base packages:\n",
+       "[1] stats     graphics  grDevices utils     datasets  methods   base     \n",
+       "\n",
+       "other attached packages:\n",
+       "[1] janitor_2.1.0 readr_2.1.2   dplyr_1.0.9  \n",
+       "\n",
+       "loaded via a namespace (and not attached):\n",
+       " [1] pillar_1.8.1     compiler_4.1.3   base64enc_0.1-3  tools_4.1.3     \n",
+       " [5] bit_4.0.4        digest_0.6.29    uuid_1.1-0       jsonlite_1.8.0  \n",
+       " [9] lubridate_1.8.0  evaluate_0.16    lifecycle_1.0.1  tibble_3.1.8    \n",
+       "[13] pkgconfig_2.0.3  rlang_1.0.4      IRdisplay_1.1    cli_3.3.0       \n",
+       "[17] DBI_1.1.3        curl_4.3.2       parallel_4.1.3   IRkernel_1.3    \n",
+       "[21] fastmap_1.1.0    stringr_1.4.0    repr_1.1.4       generics_0.1.3  \n",
+       "[25] vctrs_0.4.1      hms_1.1.2        bit64_4.0.5      tidyselect_1.1.2\n",
+       "[29] glue_1.6.2       snakecase_0.11.0 R6_2.5.1         fansi_1.0.3     \n",
+       "[33] vroom_1.5.7      pbdZMQ_0.3-7     purrr_0.3.4      tzdb_0.3.0      \n",
+       "[37] magrittr_2.0.3   htmltools_0.5.3  ellipsis_0.3.2   assertthat_0.2.1\n",
+       "[41] utf8_1.2.2       stringi_1.7.8    crayon_1.5.1    "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sessionInfo()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "R",
+   "language": "R",
+   "name": "ir"
+  },
+  "language_info": {
+   "codemirror_mode": "r",
+   "file_extension": ".r",
+   "mimetype": "text/x-r-source",
+   "name": "R",
+   "pygments_lexer": "r",
+   "version": "4.1.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}