From 1f04c9fcad217fa6e605101b76b83e2fee2b5e63 Mon Sep 17 00:00:00 2001 From: RoanKanninga Date: Fri, 1 Nov 2019 07:35:48 +0100 Subject: [PATCH 1/6] fixing >200 lines in samplesheet issue --- protocols/CreateInhouseProjects.sh | 3 ++- protocols/VariantGenotyping.sh | 6 +++--- templates/generate_template.sh | 1 + 3 files changed, 6 insertions(+), 4 deletions(-) diff --git a/protocols/CreateInhouseProjects.sh b/protocols/CreateInhouseProjects.sh index 41594a81..1fda1a8f 100755 --- a/protocols/CreateInhouseProjects.sh +++ b/protocols/CreateInhouseProjects.sh @@ -28,7 +28,7 @@ #string environment_parameters #string ngsversion #string ngsUtilsVersion - +#string sampleSize #string dataDir #string coveragePerBaseDir @@ -258,6 +258,7 @@ sh "${EBROOTMOLGENISMINCOMPUTE}/molgenis_compute.sh" \ -runid "${runid}" \ -o "ngsversion=${ngsversion};\ batchIDList=${EBROOTNGS_DNA}/batchIDList${batching}.csv;\ +sampleSize=${sampleSize};\ groupname=${groupname};\ runid=${runid}" diff --git a/protocols/VariantGenotyping.sh b/protocols/VariantGenotyping.sh index 44604191..23c68d09 100755 --- a/protocols/VariantGenotyping.sh +++ b/protocols/VariantGenotyping.sh @@ -17,6 +17,7 @@ #string projectJobsDir #string logsDir #string groupname +#string sampleSize #Function to check if array contains value array_contains () { @@ -39,11 +40,10 @@ tmpProjectBatchGenotypedVariantCalls="${MC_tmpFile}" module load "${gatkVersion}" module list -SAMPLESIZE=$(cat "${projectJobsDir}/${project}.csv" | wc -l) -numberofbatches=$(("${SAMPLESIZE}" / 200)) +numberofbatches=$(("${sampleSize}" / 200)) ALLGVCFs=() -if [ "${SAMPLESIZE}" -gt 200 ] +if [ "${sampleSize}" -gt 200 ] then for b in $(seq 0 "${numberofbatches}") do diff --git a/templates/generate_template.sh b/templates/generate_template.sh index 43705e70..dff8a984 100755 --- a/templates/generate_template.sh +++ b/templates/generate_template.sh @@ -102,6 +102,7 @@ groupname=${group};\ ngsversion=$(module list | grep -o -P 'NGS_DNA(.+)');\ environment_parameters=${genScripts}/parameters_environment_converted.csv;\ tmpdir_parameters=${genScripts}/parameters_tmpdir_converted.csv;\ +sampleSize=${sampleSize};\ worksheet=${genScripts}/${filePrefix}.csv;\ runid=${runID}" \ -weave \ From 9f5c21bb35fb36e82dc5e4bcdb1bdf9300b6d9a9 Mon Sep 17 00:00:00 2001 From: RoanKanninga Date: Fri, 31 Jan 2020 08:18:08 +0100 Subject: [PATCH 2/6] updated prm cluster --- parameters_zinc-finger.csv | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/parameters_zinc-finger.csv b/parameters_zinc-finger.csv index 5c16ec8b..9dbe5fe7 100644 --- a/parameters_zinc-finger.csv +++ b/parameters_zinc-finger.csv @@ -1,6 +1,6 @@ queue,ll -prmName,prm03 -prmHost,boxy.hpc.rug.nl +prmName,prm05 +prmHost,coenzyme.umcg.nl root,/ appsDir,${root}/apps/ toolChain,foss-2015b From 55ac585a7801d355cf01def757615b0f11e6d96b Mon Sep 17 00:00:00 2001 From: RoanKanninga Date: Fri, 31 Jan 2020 11:05:55 +0100 Subject: [PATCH 3/6] removed arrayFile dependency --- parameters.csv | 1 - 1 file changed, 1 deletion(-) diff --git a/parameters.csv b/parameters.csv index e2eda6c6..f6cd98bd 100644 --- a/parameters.csv +++ b/parameters.csv @@ -381,7 +381,6 @@ sampleConcordanceFile,${intermediateDir}/${externalSampleID}.ConcordanceFile.txt arrayTmpMap,${intermediateDir}/${externalSampleID}.concordance.tmp.map arrayMapFile,${intermediateDir}/${externalSampleID}.concordance.map familyList,${intermediateDir}/${externalSampleID}.familyList.txt -arrayFileLocation,${inputData}/${arrayFile} mergedBamRecalibratedTable,${projectResultsDir}/alignment/${externalSampleID}.recalibrated.table From 790395103e34448bf8fe449105b05540d123fb80 Mon Sep 17 00:00:00 2001 From: RoanKanninga Date: Thu, 13 Feb 2020 08:42:52 +0100 Subject: [PATCH 4/6] fix --- workflow.csv | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/workflow.csv b/workflow.csv index b7c22b7c..27a6697f 100644 --- a/workflow.csv +++ b/workflow.csv @@ -31,12 +31,10 @@ s22a_MergeIndelsAndSnpsSample,protocols/MergeIndelsAndSnpsSample.sh,s21b_IndelFi s22b_MergeIndelsAndSnpsProject,protocols/MergeIndelsAndSnpsProject.sh,s22a_MergeIndelsAndSnpsSample s23_DetermineTrio,protocols/DetermineTrio.sh,s22a_MergeIndelsAndSnpsSample;s22b_MergeIndelsAndSnpsProject s24a_Gavin,protocols/Gavin.sh,s22a_MergeIndelsAndSnpsSample;s22b_MergeIndelsAndSnpsProject -s24b_CartegeniaTree,protocols/CartegeniaTree.sh,s24a_Gavin -s24c_CartegeniaFiltering,protocols/CartegeniaFiltering.sh,s24b_CartegeniaTree s25a_CompressingSampleVcf,protocols/CompressingFinalVcf.sh,s22a_MergeIndelsAndSnpsSample;s22b_MergeIndelsAndSnpsProject;finalVcf=sampleFinalVcf s25b_CompressingProjectVcf,protocols/CompressingFinalVcf.sh,s22a_MergeIndelsAndSnpsSample;s22b_MergeIndelsAndSnpsProject;finalVcf=projectFinalVcf s26_VcfToTable,protocols/VcfToTable.sh,s22a_MergeIndelsAndSnpsSample;s22b_MergeIndelsAndSnpsProject s27_InSilicoConcordance,protocols/InSilicoConcordance.sh,s26_VcfToTable s28_MultiQC,protocols/MultiQC.sh,s08a_CollectMultipleMetrics;s08b_CollectHSMetrics;s08d_CollectGCBiasMetrics;s08c_CollectBamIndexMetrics;s10_Flagstat;s27_InSilicoConcordance -s29_CountAllFinishedFiles,protocols/CountAllFinishedFiles.sh,s11_Manta;s12c_DecisionTree;s13_CramConversion;s14_MakeDedupBamMd5;s23_DetermineTrio;s24c_CartegeniaFiltering;s25a_CompressingSampleVcf;s25b_CompressingProjectVcf;s15_CoverageCalculations;s28_MultiQC +s29_CountAllFinishedFiles,protocols/CountAllFinishedFiles.sh,s11_Manta;s12c_DecisionTree;s13_CramConversion;s14_MakeDedupBamMd5;s23_DetermineTrio;s24a_Gavin;s25a_CompressingSampleVcf;s25b_CompressingProjectVcf;s15_CoverageCalculations;s28_MultiQC s30_CopyToResultsDir,protocols/CopyToResultsDir.sh,s29_CountAllFinishedFiles From 7409480fed43b080a97815eb93a72da4f2148e34 Mon Sep 17 00:00:00 2001 From: RoanKanninga Date: Thu, 13 Feb 2020 09:38:21 +0100 Subject: [PATCH 5/6] bugfix for XTHS bedfile --- protocols/CoverageCalculations.sh | 3 +++ templates/generate_template.sh | 8 ++++++++ 2 files changed, 11 insertions(+) diff --git a/protocols/CoverageCalculations.sh b/protocols/CoverageCalculations.sh index cadc808a..a9ce63a2 100755 --- a/protocols/CoverageCalculations.sh +++ b/protocols/CoverageCalculations.sh @@ -25,6 +25,9 @@ bedfileRaw=$(basename "${capturingKit}") if [[ "${bedfileRaw}" =~ "QXT" ]] then bedfile=$(echo "${bedfileRaw}" | awk '{print substr($0,4)}') +elif [[ "${bedfileRaw}" =~ "XT-HS" ]] +then + bedfile=$(echo "${bedfileRaw}" | awk '{print substr($0,6)}') elif [[ "${bedfileRaw}" =~ "XT" ]] then bedfile=$(echo "${bedfileRaw}" | awk '{print substr($0,3)}') diff --git a/templates/generate_template.sh b/templates/generate_template.sh index dff8a984..9c4b71d6 100755 --- a/templates/generate_template.sh +++ b/templates/generate_template.sh @@ -1,5 +1,13 @@ #!/bin/bash +if module list | grep -o -P 'NGS_DNA(.+)' +then + echo "DNA pipeline loaded, proceding" +else + echo "No DNA Pipeline loaded, exiting" + exit 1 +fi + module list host=$(hostname -s) From fc11bb2343df5a0d43d7a91613e5985b82a10dac Mon Sep 17 00:00:00 2001 From: RoanKanninga Date: Thu, 13 Feb 2020 11:19:11 +0100 Subject: [PATCH 6/6] added sampleSize parameter to externalsamples --- protocols/CreateExternSamplesProjects.sh | 2 ++ 1 file changed, 2 insertions(+) diff --git a/protocols/CreateExternSamplesProjects.sh b/protocols/CreateExternSamplesProjects.sh index cb53842b..ae0e7aa4 100755 --- a/protocols/CreateExternSamplesProjects.sh +++ b/protocols/CreateExternSamplesProjects.sh @@ -19,6 +19,7 @@ #string group_parameters #string environment_parameters #string groupname +#string sampleSize #string mainParameters #string worksheet @@ -172,4 +173,5 @@ sh "${EBROOTMOLGENISMINCOMPUTE}/molgenis_compute.sh" -p "${mainParameters}" \ -runid "${runid}" \ -o "ngsversion=${ngsversion};\ batchIDList=${EBROOTNGS_DNA}/batchIDList${batching}.csv;\ +sampleSize=${sampleSize};\ groupname=${groupname}"