be4311c07e14feb728abc6425ee606ffaa611a58
markd
  Fri Jan 22 06:46:58 2021 -0800
merge with master

diff --git src/hg/utils/otto/sarscov2phylo/publicCredits.sh src/hg/utils/otto/sarscov2phylo/publicCredits.sh
index 1c464ff..e50d582 100755
--- src/hg/utils/otto/sarscov2phylo/publicCredits.sh
+++ src/hg/utils/otto/sarscov2phylo/publicCredits.sh
@@ -1,45 +1,48 @@
 #!/bin/bash
 set -beEu -x -o pipefail
 
 #	Do not modify this script, modify the source tree copy:
-#	kent/src/hg/utils/otto/sarscov2phylo/mapPublic.sh
+#	kent/src/hg/utils/otto/sarscov2phylo/publicCredits.sh
 
 usage() {
     echo "usage: $0"
 }
 
 if [ $# != 0 ]; then
   usage
   exit 1
 fi
 
 cncbMetadata=/hive/data/outside/otto/sarscov2phylo/cncb.latest/cncb.metadata.tsv
 ncbiMetadata=ncbi.authors.20-11-13.csv
 #*** TODO AUTOMATE ME
 #   * https://www.ncbi.nlm.nih.gov/labs/virus/vssi/#/virus?SeqType_s=Nucleotide&VirusLineage_ss=SARS-CoV-2,%20taxid:2697049
 #   * Download button
 #   * Current table view result --> CSV format, Next button
 #   * Download all records, Next button
 #   * Select Accession and Authors [no labs options unfortunately]
 #   * Download button, save as ncbi.authors.date.csv
 
 #*** TODO AUTOMATE ME
 #   * https://www.ebi.ac.uk/ena/browser/view/PRJEB37886
 #   * select columns center_name, sample_accession, sample_alias
 #   * Download report: TSV
 #   * file saved to filereport_read_run_PRJEB37886_tsv.2020-11-3.txt (extra first column, run_accession)
+# 2021-01-08: the project seems to have 133312 sequences, but the download file is cut off
+# after 100,000.  It would probably be more efficient to just identify all of the country/center
+# strings in strain names, and ask COG-UK how to attribute sequences from each one.
 cogUkMetadata=filereport_read_run_PRJEB37886_tsv.2020-11-13.txt
 
 
 # Author credits file... strip GenBank version numbers because NCBI metadata doesn't have those
 cut -f 2 treeToPublic \
 | cut -d \| -f 2 \
 | sed -re 's/^([A-Z][A-Z][0-9]{6})\.[0-9]/\1/;' \
 | sort > publicIdsInTree
 tail -n+2 $cncbMetadata \
 | cut -f 2,12,14 \
 | grep -v ^EPI_ISL_ \
 | egrep -v '^[A-Z][A-Z][0-9]{6}' \
 | sed -e 's/"//g; s/$/\tn\/a/;' \
   > cncb.credits
 tail -n+2 $ncbiMetadata \