188f092007924642ae2e37ea29492d88dc4a52b1 angie Wed Apr 15 10:23:30 2020 -0700 Nextstrain changed the live-data URL; http://data.nextstrain.org/ncov.json has had the same data since April 8, now there's a dynamic query. refs #25188 diff --git src/hg/utils/otto/nextstrainNcov/doUpdate.sh src/hg/utils/otto/nextstrainNcov/doUpdate.sh index 3e4b23a..1e19ac2 100755 --- src/hg/utils/otto/nextstrainNcov/doUpdate.sh +++ src/hg/utils/otto/nextstrainNcov/doUpdate.sh @@ -1,67 +1,70 @@ #!/bin/bash set -beEu -o pipefail # Do not modify this script, modify the source tree copy: # kent/src/hg/utils/nextstrainNcov/doUpdate.sh ottoDir=/hive/data/outside/otto/nextstrainNcov chromSizes=/hive/data/genomes/wuhCor1/chrom.sizes gbdbDir=/gbdb/wuhCor1/nextstrain +ncovJsonUrl='https://nextstrain.org/charon/getDataset?prefix=/ncov/global' + cd $ottoDir # The file is named .json, but is actually gzipped, so gunzip it. -curl -s http://data.nextstrain.org/ncov.json | gunzip -c > ncov.json -curl -s -I http://data.nextstrain.org/ncov.json \ +curl -s "$ncovJsonUrl" \ +| gunzip -c > ncov.json +curl -s -I "$ncovJsonUrl" \ | grep Last-Mod | sed -re 's/Last-Modified: //; s/\r//;' \ > ncov.json.date latestDate=$(cat ncov.json.date) oldDate=$(cat old.ncov.json.date) if [ $(date -d "$latestDate" +%s) -le $(date -d "$oldDate" +%s) ]; then exit 0 fi today=`date +%F` mkdir -p $today cp -p ncov.json $today mv ncov.json old.ncov.json mv ncov.json.date old.ncov.json.date runDir=$ottoDir/$today cd $runDir #Generate bed and VCF files $ottoDir/nextstrain.py # bgzip & tabix the VCF files bgzip -f nextstrainSamples.vcf tabix -p vcf nextstrainSamples.vcf.gz for clade in A1a A2 A2a A3 A6 A7 B B1 B2 B4; do bgzip -f nextstrainSamples$clade.vcf tabix -p vcf nextstrainSamples$clade.vcf.gz done # bigBed-ify the gene names and "clades" bedToBigBed -type=bed4 -tab -verbose=0 nextstrainGene.bed $chromSizes \ nextstrainGene.bb sort -k2n,2n nextstrainClade.bed > nextstrainClade.sorted.bed bedToBigBed -as=$ottoDir/nextstrainClade.as -type=bed12+7 -tab -verbose=0 \ nextstrainClade.sorted.bed $chromSizes \ nextstrainClade.bb # Archive mkdir -p $ottoDir/archive/$today cp -p $runDir/nextstrainGene.bb $runDir/nextstrainClade.bb \ $runDir/nextstrainSamples*.vcf.gz{,.tbi} \ $runDir/nextstrain*.nh \ $runDir/ncov.json \ $ottoDir/archive/$today # Install ln -sf $runDir/nextstrainGene.bb $runDir/nextstrainClade.bb \ $runDir/nextstrainSamples*.vcf.gz{,.tbi} \ $runDir/nextstrain*.nh \ $gbdbDir/ echo "Updated nextstrain/ncov `date` (ncov.json date $latestDate)"