95c23a8a25292bec7fd5c853412f0d04d2d44145 angie Mon May 24 10:03:07 2021 -0700 Preserve older mappings in the case of duplicates -- but allow GenBank dot-version updates. Also, subColumn is way faster than sed. diff --git src/hg/utils/otto/sarscov2phylo/updateIdMapping.sh src/hg/utils/otto/sarscov2phylo/updateIdMapping.sh index 710e664..e2c8d2b 100755 --- src/hg/utils/otto/sarscov2phylo/updateIdMapping.sh +++ src/hg/utils/otto/sarscov2phylo/updateIdMapping.sh @@ -52,41 +52,42 @@ join -t$'\t' -a 1 -1 2 -o 1.1,1.2,1.3,2.2 \ <(sort -k2,2 ~/chris_ncov/epiToPublicIdName.$today.txt) \ <(sort $gbToDate $cncbToDate $cogUkToDate) \ | sort -u adders - \ > epiToPublicAndDate.$today # Look for duplicate ID swizzles relative to existing ncov-ingest mappings cut -f 1,2 epiToPublicAndDate.$today \ | egrep $'\t''[A-Z][A-Z][0-9]+\.[0-9]+' \ | sort > latestEpiToGb tail -n+2 ~/github/ncov-ingest/source-data/accessions.tsv \ | tawk '{print $2, $1;}' \ | sort > ncovEpiToGb wc -l latestEpiToGb ncovEpiToGb -# Replace disagreeing IDs with ncov-ingest IDs. +# But allow version updates (e.g. .1 --> .2) join -t$'\t' ncovEpiToGb latestEpiToGb \ -| tawk '$2 != $3 {print "s/"$3"/"$2"/;";}' \ -| sed -re 's/\./\\./;' \ - > fix.sed -sed -f fix.sed epiToPublicAndDate.$today > tmp +| tawk '{ ncovNoDot = substr($2, 0, index($2, ".")-1); + latestNoDot = substr($3, 0, index($3, ".")-1); + if (ncovNoDot != latestNoDot) {print $3, $2;} }' \ + > latestToNcov.sub +subColumn -miss=/dev/null 2 epiToPublicAndDate.$today latestToNcov.sub tmp mv tmp epiToPublicAndDate.$today ln -sf epiToPublicAndDate.$today epiToPublicAndDate.latest # Now that mapping is updated, add GenBank accessions to 4th column of metadata zcat $nextmeta | cut -f 4 | grep ... | wc -l set +o pipefail zcat $nextmeta | head -1 > tmp set -o pipefail zcat $nextmeta \ | tail -n+2 \ | sort -t $'\t' -k3,3 \ | join -t$'\t' -a 1 -1 3 - <(tawk '$2 ~ /^[A-Z][A-Z][0-9]+/' epiToPublicAndDate.latest) \ -o 1.1,1.2,1.3,2.2,1.5,1.6,1.7,1.8,1.9,1.10,1.11,1.12,1.13,1.14,1.15,1.16,1.17,1.18,1.19,1.20,1.21,1.22,1.23,1.24,1.25,1.26,1.27 \ | sort \ >> tmp wc -l tmp -gzip -c tmp > $nextmeta -rm tmp +gzip tmp +mv tmp.gz $nextmeta zcat $nextmeta | cut -f 4 | grep ... | wc -l