diff --git a/CHANGELOG.md b/CHANGELOG.md index 9112c77d790e87aa7b10a337e1688c327ad8339b..83da5399be8b18ad4cd42bfd755c400b431a98cf 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -10,6 +10,7 @@ that users understand how the changes affect the new version. version 5.0.0-dev --------------------------- ++ Fix output files in ccs.wdl. + Update biowdl-input-converter to version 0.3. + Update minimap2 to version 2.20. + Update lima to version 2.2.0. diff --git a/ccs.wdl b/ccs.wdl index 69095f4d099ac41d29052cdc9e888b0587780b29..29f1a7f9468cdb72da35b168d4821d430536a319 100644 --- a/ccs.wdl +++ b/ccs.wdl @@ -24,12 +24,19 @@ task CCS { input { File subreadsFile String outputPrefix + String logLevel = "WARN" Int minPasses = 3 + Int topPasses = 60 Int minLength = 10 Int maxLength = 50000 Boolean byStrand = false + Boolean skipPolish = false + Boolean all = false + Boolean subreadFallback = false + Boolean allKinetics = false + Boolean hifiKinetics = false + Float minSnr = 2.5 Float minReadQuality = 0.99 - String logLevel = "WARN" File? subreadsIndexFile String? chunkString @@ -45,15 +52,24 @@ task CCS { mkdir -p "$(dirname ~{outputPrefix})" ccs \ --min-passes ~{minPasses} \ + --min-snr ~{minSnr} \ + --top-passes ~{topPasses} \ --min-length ~{minLength} \ --max-length ~{maxLength} \ ~{true="--by-strand" false="" byStrand} \ + ~{true="--skip-polish" false="" skipPolish} \ + ~{true="--all" false="" all} \ + ~{true="--subread-fallback" false="" subreadFallback} \ + ~{true="--all-kinetics" false="" allKinetics} \ + ~{true="--hifi-kinetics" false="" hifiKinetics} \ --min-rq ~{minReadQuality} \ --log-level ~{logLevel} \ --num-threads ~{threads} \ ~{"--chunk " + chunkString} \ + ~{"--report-file " + outputPrefix + ".ccs_report.txt"} \ ~{"--report-json " + outputPrefix + ".ccs.report.json"} \ ~{"--log-file " + outputPrefix + ".ccs.stderr.log"} \ + ~{"--metrics-json " + outputPrefix + ".zmw_metrics.json.gz"} \ ~{subreadsFile} \ ~{outputPrefix + ".ccs.bam"} } @@ -61,8 +77,10 @@ task CCS { output { File ccsBam = outputPrefix + ".ccs.bam" File ccsBamIndex = outputPrefix + ".ccs.bam.pbi" - File ccsReport = outputPrefix + ".ccs.report.json" + File ccsReport = outputPrefix + ".ccs_report.txt" + File ccsJsonReport = outputPrefix + ".ccs.report.json" File ccsStderr = outputPrefix + ".ccs.stderr.log" + File zmwMetrics = outputPrefix + ".zmw_metrics.json.gz" } runtime { @@ -76,12 +94,19 @@ task CCS { # inputs subreadsFile: {description: "Subreads input file.", category: "required"} outputPrefix: {description: "Output directory path + output file prefix.", category: "required"} + logLevel: {description: "Set log level. Valid choices: (TRACE, DEBUG, INFO, WARN, FATAL).", category: "advanced"} minPasses: {description: "Minimum number of full-length subreads required to generate ccs for a ZMW.", category: "advanced"} + topPasses: {description: "Pick at maximum the top N passes for each ZMW.", category: "advanced"} minLength: {description: "Minimum draft length before polishing.", category: "advanced"} maxLength: {description: "Maximum draft length before polishing.", category: "advanced"} byStrand: {description: "Generate a consensus for each strand.", category: "advanced"} + skipPolish: {description: "Only output the initial draft template (faster, less accurate).", category: "advanced"} + all: {description: "Emit all ZMWs.", category: "advanced"} + subreadFallback: {description: "Emit a representative subread, instead of the draft consensus, if polishing failed.", category: "advanced"} + allKinetics: {description: "Calculate mean pulse widths (PW) and interpulse durations (IPD) for every ZMW.", category: "advanced"} + hifiKinetics: {description: "Calculate mean pulse widths (PW) and interpulse durations (IPD) for every HiFi read.", category: "advanced"} + minSnr: {description: "Minimum SNR of subreads to use for generating CCS.", category: "advanced"} minReadQuality: {description: "Minimum predicted accuracy in [0, 1].", category: "common"} - logLevel: {description: "Set log level. Valid choices: (TRACE, DEBUG, INFO, WARN, FATAL).", category: "advanced"} subreadsIndexFile: {description: "Index for the subreads input file, required when using chunkString.", category: "advanced"} chunkString: {descpription: "Chunk string (e.g. 1/4, 5/5) for CCS.", category: "advanced"} threads: {description: "The number of threads to be used.", category: "advanced"} @@ -92,7 +117,9 @@ task CCS { # outputs ccsBam: {description: "Consensus reads output file."} ccsBamIndex: {description: "Index of consensus reads output file."} - ccsReport: {description: "Ccs results report file."} + ccsReport: {description: "Ccs report file."} + ccsJsonReport: {description: "Ccs results json report file."} ccsStderr: {description: "Ccs STDERR log file."} + zmwMetrics: {description: "ZMW metrics json file."} } } diff --git a/cutadapt.wdl b/cutadapt.wdl index b2dbdec0c58c9d9aa5fbd464b0efff3793211dc8..b49a95d46dc64be3abe018fc0157fa250eaeba08 100644 --- a/cutadapt.wdl +++ b/cutadapt.wdl @@ -83,7 +83,7 @@ task Cutadapt { Boolean? noZeroCap Int cores = 4 - String memory = "~{300 + 100 * cores}M" + String memory = "5G" Int timeMinutes = 1 + ceil(size([read1, read2], "G") * 12.0 / cores) String dockerImage = "quay.io/biocontainers/cutadapt:2.10--py37hf01694f_1" } diff --git a/multiqc.wdl b/multiqc.wdl index 2571463a1a9fa42bcd87db1b5edfb5a279060ea8..a166293799d75a24f8aa7f14d3ade49d5fcfdf07 100644 --- a/multiqc.wdl +++ b/multiqc.wdl @@ -57,7 +57,7 @@ task MultiQC { String? clConfig String? memory - Int timeMinutes = 2 + ceil(size(reports, "G") * 8) + Int timeMinutes = 10 + ceil(size(reports, "G") * 8) String dockerImage = "quay.io/biocontainers/multiqc:1.9--py_1" }