update metadata formatting

ktmeaton · May 15, 2020 · 4f056f5 · 4f056f5
1 parent a73d376
commit 4f056f5
Showing 1 changed file with 35 additions and 0 deletions.
diff --git a/docs/exhibit/exhibit_dhsi2020.rst b/docs/exhibit/exhibit_dhsi2020.rst
@@ -46,3 +46,38 @@ Run the full pipeline, including sample download, aligning to a reference genome
         --skip_sra_download \
         --sqlite_select_command_asm "\"SELECT AssemblyFTPGenbank FROM Master WHERE BioSampleComment LIKE '%Morelli%'\"" \
         -resume
+
+Prepare a metadata file for NextStrain. Afterwards, manually clean up dates to remove uncertainty characters and change to the format 2000-XX-XX. Also separate out columns that have multiple entries (ex. AssemblyTotalLength) by retaining the first semi-colon separated value.
+
+**Shell script**::
+
+      mkdir -p morelli2010/nextstrain/
+
+      scripts/sqlite_NextStrain_tsv.py \
+        --database results/ncbimeta_db/update/latest/output/database/yersinia_pestis_db.sqlite \
+        --query "SELECT BioSampleAccession,AssemblyFTPGenbank,SRARunAccession,BioSampleStrain,BioSampleCollectionDate,BioSampleHost,BioSampleGeographicLocation,BioSampleBiovar,PubmedArticleTitle,PubmedAuthorsLastName,AssemblyContigCount,AssemblyTotalLength,NucleotideGenes,NucleotideGenesTotal,NucleotidePseudoGenes,NucleotidePseudoGenesTotal,NucleotiderRNAs,AssemblySubmissionDate,SRARunPublishDate,BioSampleComment FROM Master WHERE (BioSampleComment LIKE '%Morelli%' AND TRIM(AssemblyFTPGenbank) > '')" \
+        --no-data-char ? \
+        --output morelli2010/nextstrain/metadata_nextstrain.tsv
+
+        head -n 1 morelli2010/nextstrain/metadata_nextstrain.tsv | \
+          awk -F "\t" '{print "name\t"$0}' \
+          > morelli2010/nextstrain/metadata_nextstrain_edit.tsv
+
+        tail -n +2 morelli2010/nextstrain/metadata_nextstrain.tsv  | \
+          awk -F "\t" '{split($2,ftpSplit,"/"); name=ftpSplit[10]"_genomic"; print name"\t"$0}' \
+          >> morelli2010/nextstrain/metadata_nextstrain_edit.tsv
+
+Estimate a time-scaled phylogeny.
+
+**Shell script**::
+
+      augur refine \
+          --tree morelli2010/iqtree/iqtree.core-filter0_bootstrap.treefile \
+          --alignment morelli2010/snippy_multi/snippy-core.full_CHROM.fasta \
+          --vcf-reference morelli2010/reference_genome/GCF_000009065.1_ASM906v1_genomic.fna \
+          --metadata morelli2010/nextstrain/metadata_nextstrain_edit.tsv \
+          --timetree \
+          --root residual \
+          --coalescent opt \
+          --output-tree morelli2010/nextstrain/tree.nwk \
+          --output-node-data morelli2010/nextstrain/branch_lengths.json;