71a5bf4d42948792ba96729c01bec373eed86918
angie
  Sun Feb 4 09:16:38 2024 -0800
Use nextclade v3 output column indices.

diff --git src/hg/utils/otto/sarscov2phylo/getCncb.sh src/hg/utils/otto/sarscov2phylo/getCncb.sh
index c06af03..44976b8 100755
--- src/hg/utils/otto/sarscov2phylo/getCncb.sh
+++ src/hg/utils/otto/sarscov2phylo/getCncb.sh
@@ -93,31 +93,31 @@
 
 xzcat cncb.nonGenBank.acc.fasta.xz \
 | faSomeRecords stdin <(cut -f 1 accToNameBarAcc.tsv) stdout \
 | faRenameRecords stdin accToNameBarAcc.tsv stdout \
 | xz -T 20 > cncb.nonGenBank.fasta.xz
 
 # Run nextclade
 cp ../cncb.latest/nextclade.full.tsv.gz .
 cp ../cncb.latest/nextclade.tsv .
 if [ -s new.accs.fa ]; then
     nDataDir=~angie/github/nextclade/data/sars-cov-2
     time nextclade run -j 20 new.accs.fa \
         --input-dataset $nDataDir \
         --output-fasta nextalign.new.fa.xz \
         --output-tsv nextclade.new.full.tsv.gz  >& nextclade.log
-    zcat nextclade.new.full.tsv.gz | cut -f 1,7 | tail -n+2 >> nextclade.tsv
+    zcat nextclade.new.full.tsv.gz | cut -f 2,8 | tail -n+2 >> nextclade.tsv
     sort -u nextclade.tsv > tmp
     mv tmp nextclade.tsv
     cat nextclade.new.full.tsv.gz >> nextclade.full.tsv.gz
 fi
 
 # Run pangolin
 cp ../cncb.latest/pangolin.tsv .
 if [ -s new.accs.fa ]; then
     set +x
     . ~/.bashrc
     conda activate pangolin
     set -x
     set -e
     time pangolin -t 20 new.accs.fa --skip-scorpio --outfile lineages.csv \
         >& pangolin.log