c6b00020d3775552377ee3fda1a77d9cb39c453d hiram Fri Apr 17 15:16:44 2026 -0700 correct specification for the linearGap and scoreMatrix inputs refs #31811 diff --git src/hg/utils/automation/kegAlignLastz.sh src/hg/utils/automation/kegAlignLastz.sh index fa7af802c7e..28875950c8b 100755 --- src/hg/utils/automation/kegAlignLastz.sh +++ src/hg/utils/automation/kegAlignLastz.sh @@ -366,52 +366,70 @@ "primate") ;; "mammal") ;; "other") minScore="5000" linearGap="loose" ;; esac ;; "other") minScore="5000" linearGap="loose" esac +########## primate <-> primate ######################################### if [ "$tClade" == "primate" -a "$qClade" == "primate" ]; then export yamlString="# ${tAccId}.${qAccId}.yaml TARGET_Sequence: class: File path: ${tFaGzUrl} QUERY_Sequence: class: File path: ${qFaGzUrl} # axtChain options axtChainMinScore: ${minScore} -linear_gap_options.linear_gap: ${linearGap} +axtChainLinearGap: + class: File + filetype: txt + path: https://genome-test.gi.ucsc.edu/~hiram/galaxy/kegAlign/axtChain.medium.txt +axtChainScoreScheme: + class: File + filetype: txt + path: https://genome-test.gi.ucsc.edu/~hiram/galaxy/kegAlign/primate-primate.lastz.score.txt +# A C G T +# 90 -330 -236 -356 +# -330 100 -318 -236 +# -236 -318 100 -330 +# -356 -236 -330 90 +# O=600 E=150 # lastz options xdropX: 910 ydropY: 15000 stepZ: 1 noTransitionT: false strand_selectorB: both -seeding_options.seed_selector: 12of19 +# seeding_options.seed.seed_selector: 12of19 does not get into the process hspthreshK: 4500 gappedthreshL: 4500 innerH: 2000 +scoringMatrix: + class: File + filetype: txt + path: https://genome-test.gi.ucsc.edu/~hiram/galaxy/kegAlign/primate-primate.lastz.score.txt " export defString="# ${qOrgName} ${Query} vs. ${tOrgName} ${Target} BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz BLASTZ_T=2 BLASTZ_O=600 BLASTZ_E=150 BLASTZ_M=254 BLASTZ_K=4500 BLASTZ_Y=15000 BLASTZ_Q=/hive/data/staging/data/blastz/human_chimp.v2.q # A C G T # A 90 -330 -236 -356 # C -330 100 -318 -236 # G -236 -318 100 -330 @@ -433,69 +451,72 @@ BASE=${buildDir} TMPDIR=/dev/shm " else export yamlString="# ${target}.${query}.yaml TARGET_Sequence: class: File path: ${tFaGzUrl} QUERY_Sequence: class: File path: ${qFaGzUrl} # axtChain options axtChainMinScore: ${minScore} -linear_gap_options.linear_gap: ${linearGap} +axtChainLinearGap: + class: File + filetype: txt + path: https://genome-test.gi.ucsc.edu/~hiram/galaxy/kegAlign/axtChain.loose.txt # lastz options xdropX: 910 ydropY: 9400 stepZ: 1 noTransitionT: true strand_selectorB: both -seeding_options.seed_selector: 12of19 +# seeding_options.seed.seed_selector: 12of19 does not get into the process hspthreshK: 3000 gappedthreshL: 3000 innerH: 2000 " export defString="# ${qOrgName} ${Query} vs. ${tOrgName} ${Target} BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz # TARGET: ${tOrgName} ${tOrgDate} ${target} SEQ1_DIR=${target2bit} SEQ1_LEN=${targetSizes} SEQ1_CHUNK=20000000 SEQ1_LAP=10000 SEQ1_LIMIT=${seq1Limit} # QUERY: ${qOrgName} ${qOrgDate} ${query} SEQ2_DIR=${query2bit} SEQ2_LEN=${querySizes} SEQ2_CHUNK=20000000 SEQ2_LAP=0 SEQ2_LIMIT=${seq2Limit} BASE=${buildDir} TMPDIR=/dev/shm " fi ### skip primary alignment if it is already done ### primaryDone == 0 means NOT done yet if [ $primaryDone -eq 0 ]; then - mkdir "${buildDir}" + mkdir -p "${buildDir}" ### setup the DEF file printf "%s" "${defString}" > ${buildDir}/DEF ### and the yaml file printf "%s" "${yamlString}" > ${buildDir}/${tAccId}.${qAccId}.yaml ### setup the buildDir/lastzRun.sh script printf "#!/bin/bash set -beEu -o pipefail export targetDb=\"${tAccId}\" export queryDb=\"${qAccId}\" export QueryDb=\"${Query}\"