large update and script bugfix

docs/exhibit/exhibit_main.rst

@@ -139,21 +139,14 @@ Assembly Pipeline
 SRA Pipeline
 ^^^^^^^^^^^^^^^^^
 
-Black Death 8291 SRA Accession
-
-::
-
-  SRR341961
-
-Prep tsv input from pipeline.nf
+Prep tsv input from pipeline.nf, select only EAGER Ancient samples
 
 ::
 
   nextflow run pipeline.nf \
     --sqlite results/ncbimeta_db/update/latest/output/database/yersinia_pestis_db.sqlite \
-    --outdir test \
-    --sqlite_select_command_sra "\"SELECT BioSampleAccession,SRARunAccession,SRALibraryLayout,SRAFileURL FROM Master WHERE (SRARunAccession = 'SRR341961')\"" \
-    --max_datasets_assembly 2000 \
+    --outdir EAGER_Ancient \
+    --sqlite_select_command_sra "\"SELECT BioSampleAccession,SRARunAccession,SRALibraryLayout,SRAFileURL FROM Master WHERE (BioSampleComment LIKE '%KEEP: EAGER Ancient%')\"" \
     --max_datasets_sra 2000  \
     --skip_assembly_download \
     --skip_sra_download \
@@ -164,11 +157,12 @@ Make directories for SRA data
 
 ::
 
-  mkdir test/sra_download;
-  mkdir test/sra_download/fastq;
-  mkdir test/sra_download/fastq/single;
-  mkdir test/sra_download/fastq/paired;
-  mkdir test/sra_download/info
+  outdir="EAGER_Ancient";
+  mkdir ${outdir}/sra_download;
+  mkdir ${outdir}/sra_download/fastq;
+  mkdir ${outdir}/sra_download/fastq/single;
+  mkdir ${outdir}/sra_download/fastq/paired;
+  mkdir ${outdir}/sra_download/info
 
 Download single-end fastq files from the SRA
 
@@ -275,18 +269,21 @@ Repeat but include Barcelona3031 (SRARunAccession = 'ERR1368878')
     --skip_reference_detect_low_complexity \
     -resume ab34c580-164d-4420-9e6f-a5aa7aa1dd05
 
-Repeat but include everything marked for EAGER
+Repeat but include everything marked for EAGER Ancient
 
 ::
 
   nextflow run pipeline.nf \
     --sqlite results/ncbimeta_db/update/latest/output/database/yersinia_pestis_db.sqlite \
-    --outdir test \
-    --sqlite_select_command_sra "\"SELECT BioSampleAccession,SRARunAccession,SRALibraryLayout,SRAFileURL FROM Master WHERE (BioSampleComment LIKE '%EAGER%')\"" \
+    --outdir EAGER_Ancient \
+    --sqlite_select_command_sra "\"SELECT BioSampleAccession,SRARunAccession,SRALibraryLayout,SRAFileURL FROM Master WHERE (BioSampleComment LIKE '%KEEP: EAGER Ancient%')\"" \
     --max_datasets_assembly 2000 \
     --max_datasets_sra 2000  \
     --skip_assembly_download \
     --skip_sra_download \
     --skip_reference_detect_repeats \
     --skip_reference_detect_low_complexity \
     -resume ab34c580-164d-4420-9e6f-a5aa7aa1dd05
+
+| Notes:
+| SAMN00715800: Split after base 75 into two separate files to maintain proper paired-end format.

pipeline.nf

@@ -58,9 +58,9 @@ def helpMessage() {
 
     DATABASE:
 
-    --ncbimeta_create         Path to yaml config file to create NCBImeta DB (ncbimeta.yaml).
-    --ncbimeta_update         Path to yaml config file to update NCBImeta DB (ncbimeta.yaml).
-    --ncbimeta_annot          Path to text annotation file for NCBImeta DB (annot.txt).
+    --ncbimeta_create         Path to config file to create NCBImeta DB (ncbimeta.yaml).
+    --ncbimeta_update         Path to config file to update NCBImeta DB (ncbimeta.yaml).
+    --ncbimeta_annot          Path to optional annotation file for NCBImeta DB (annot.txt).
     --sqlite                  Path to sqlite database file from NCBImeta (my_db.sqlite).
 
 
@@ -348,7 +348,6 @@ if (!params.skip_assembly_download && (params.sqlite || ( params.ncbimeta_update
 
 if (!params.skip_sra_download && (params.sqlite || ( params.ncbimeta_update) ) && !params.skip_sqlite_import){
 
-
   process sra_download{
     /*
 
@@ -380,11 +379,12 @@ if (!params.skip_sra_download && (params.sqlite || ( params.ncbimeta_update) ) &
     // Shell script to execute
     script:
     """
+    echo "TEST"
     sraAcc=`cat ${sra_acc_file}`
     # Disable local caching to save disk space
     # vdb-config -s cache-enabled=false
     # Download fastq files from the SRA
-    fastq-dump --outdir fastq/ --skip-technical --gzip --split-files \$sraAcc
+    echo "fastq-dump --outdir fastq/ --skip-technical --gzip --split-files \$sraAcc"
     """
   }
 
@@ -653,7 +653,12 @@ if (!params.skip_eager && (!params.skip_sra_download) && (params.sqlite || ( par
 
 // --------------------------------Pairwise Alignment-------------------------//
 
-if(!params.skip_snippy_pairwise && (!params.skip_assembly_download || (!params.skip_eager && !params.skip_sra_download)) && (params.sqlite || params.ncbimeta_update) && !params.skip_sqlite_import){
+if(!params.skip_snippy_pairwise &&
+  (!params.skip_assembly_download ||
+    (!params.skip_eager && !params.skip_sra_download)
+  ) &&
+  (params.sqlite || params.ncbimeta_update) &&
+  !params.skip_sqlite_import){
 
   process snippy_pairwise{
     /*

results/ncbimeta_db/update/latest/ncbimeta.yaml

@@ -18,7 +18,7 @@ TABLES :
 SEARCH_TERMS :
   - Assembly : (plague OR pestis OR Yersinia pestis)  AND (1900[Date - Sequences Release]:2019[Date - Sequences Release])
   - BioProject : (plague OR pestis OR Yersinia pestis) AND (bioproject assembly[Filter] OR bioproject sra[Filter]) AND (1900[Registration Date]:2019[Registration Date])
-  - BioSample: (plague OR pestis OR Yersinia pestis) AND (biosample assembly[Filter] OR biosample sra[Filter]) AND (1900[Publication Date]:2019[Publication Date]) OR ("project_name=Rise of the Bronze Age"[attr])
+  - BioSample: (plague OR pestis OR Yersinia pestis) AND (biosample assembly[Filter] OR biosample sra[Filter]) AND (1900[Publication Date]:2019[Publication Date]) OR ("project_name=Rise of the Bronze Age"[attr]) OR ("Title=DA101"[attr])
   - SRA : ((plague OR pestis OR Yersinia pestis) AND (genome OR genomes OR genomic OR genomics) NOT transcriptomic[Source]) AND (1900[Publication Date]:2019[Publication Date])
   - Nucleotide : (plague OR pestis OR Yersinia pestis) AND WGS_MASTER[KYWD] AND nucleotide assembly[Filter]) AND (1900[Publication Date]:2019[Publication Date])
   - Pubmed : (Yersinia pestis) AND (pubmed assembly[Filter] OR pubmed sra[Filter]) AND (1900[Date - Create]:2019[Date - Create])