diff --git a/workflow/rna-seq.nf b/workflow/rna-seq.nf index 615c68e9e902ffa3ebb9c6d934168050058aa56c..3c67be3cba6ca815814a56b81ec5f268093982bc 100644 --- a/workflow/rna-seq.nf +++ b/workflow/rna-seq.nf @@ -44,6 +44,28 @@ script_parseMeta = Channel.fromPath("${baseDir}/scripts/parseMeta.py") script_calculateTPM = Channel.fromPath("${baseDir}/scripts/calculateTPM.R") script_inferMeta = Channel.fromPath("${baseDir}/scripts/inferMeta.sh") +/* + * trackStart: track start of pipeline + */ +process trackStart { + script: + """ + hostname + ulimit -a + export https_proxy=\${http_proxy} + + aws dynamodb put-item \ + --table-name pipeline.tracking \ + --item '{ \ + "sessionId": {"S": "${workflow.sessionId}"}, \ + "pipeline": {"S": "cellranger_count"}, \ + "start": {"S": "${workflow.start}"}, \ + "astrocyte": {"BOOL": ${params.astrocyte}}, \ + "status": {"S": "started"}, \ + "nextflowVersion": {"S": "${workflow.nextflow.version}"}}' + """ + } + /* * splitData: split bdbag files by replicate so fetch can occure in parallel, and rename files to replicate rid */ @@ -828,4 +850,4 @@ process dataQC { echo "echo \"LOG: running tin.py on \${i}\" >> ${repRID}.rseqc.err; tin.py -i ${repRID}.sorted.deduped.\${i}.bam -r ./bed/genome.bed 1>>${repRID}.rseqc.log 2>>${repRID}.rseqc.err; cat ${repRID}.sorted.deduped.\${i}.tin.xls | tr -s \"\\w\" \"\\t\" | grep -P \\\"\\\\t\${i}\\\\t\\\";"; done | parallel -j `nproc` -k 1>> ${repRID}.sorted.deduped.tin.xls 2>>${repRID}.rseqc.err """ -} \ No newline at end of file +}