@prefix LoadListingRequirement: . @prefix CommandLineBinding: . @prefix xsd: . @prefix DockerRequirement: . @prefix Workflow: . @prefix sld: . @prefix rdfs: . @prefix CommandOutputBinding: . @prefix ns1: . @prefix NetworkAccess: . @prefix rdf: . @prefix ScatterMethod: . @prefix cwl: . @prefix CommandLineTool: . @prefix ExpressionTool: . cwl:source . rdfs:comment "Peaks in bigBed format using each paired mate independently" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . rdfs:comment "\nRemoves the specified number of bases, regardless of quality, from the beginning of the read.\n: The number of bases to keep, from the start of the read.\n" ; cwl:inputBinding [ CommandLineBinding:position 13 ; CommandLineBinding:prefix "HEADCROP:" ; CommandLineBinding:separate false ] ; sld:type xsd:int , sld:null . rdfs:comment "Peak counts within replicate" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . cwl:valueFrom "${return true}" . cwl:source . cwl:source . rdfs:comment "-x=:, strand shifts to exclude (This is mainly to avoid region around phantom peak) default=10:(readlen+10)" ; cwl:inputBinding [ CommandLineBinding:prefix "-x=" ; CommandLineBinding:separate false ] ; sld:type xsd:string , sld:null . rdfs:comment "maximum insert size for paired-end alignment (default: 2000)" ; cwl:default 2000 ; cwl:inputBinding [ CommandLineBinding:position 4 ; CommandLineBinding:prefix "-X" ] ; sld:type xsd:int , sld:null . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . rdfs:comment "Raw read counts of fastq files for paired_read1 after QC" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . rdfs:comment "Raw reads bigWig (signal) files" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "FASTQ file for read R2 in Paired End mode" ; cwl:inputBinding [ CommandLineBinding:position 6 ] ; sld:type cwl:File , sld:null . rdfs:comment "CHR:START:END\nRegion of the genome to limit the operation to - this\nis useful when testing parameters to reduce the\ncomputing time. The format is chr:start:end, for\nexample --region chr10 or --region\nchr10:456700:891000. (default: None)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--region" ] ; sld:type xsd:string , sld:null . rdfs:comment "-savn= OR -savn NarrowPeak file name (fixed width peaks)" ; cwl:inputBinding [ cwl:valueFrom "${ if (self) return \"-savn=\" + inputs.input_bam.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, \"\") + \".spp.narrowPeak\"; return null}" ] ; sld:type xsd:boolean , sld:null . cwl:source . rdfs:comment "-tab - If set, expect fields to be tab separated, normally expects white space separator.\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type xsd:boolean , sld:null . rdfs:comment "\tCalculate coverage of 5\" positions (instead of entire interval).\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-5" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-5" ] ; sld:type xsd:boolean , sld:null . cwl:source . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.ibam.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '.bdg')" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.ibam.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '.bdg')" ] ; sld:type cwl:File . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . rdfs:comment "Peaks information/report file." ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.treatment[0].path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '_peaks.xls')" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.treatment[0].path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '_peaks.xls')" ] ; sld:type cwl:File . rdfs:comment "Preseq c_curve output files" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "\t Whether or not to build the shifting model. If True, MACS will not build model. by default it means shifting size = 100, try to set extsize to change it. DEFAULT: False" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--nomodel" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--nomodel" ] ; sld:type xsd:boolean , sld:null . cwl:outputBinding [ CommandOutputBinding:outputEval "$(inputs.input_file.path.substr(inputs.input_file.path.lastIndexOf('/') + 1, inputs.input_file.path.lastIndexOf('.') - (inputs.input_file.path.lastIndexOf('/') + 1)))" ] ; cwl:outputBinding [ CommandOutputBinding:outputEval "$(inputs.input_file.path.substr(inputs.input_file.path.lastIndexOf('/') + 1, inputs.input_file.path.lastIndexOf('.') - (inputs.input_file.path.lastIndexOf('/') + 1)))" ] ; cwl:outputBinding [ CommandOutputBinding:outputEval "$(inputs.input_file.path.substr(inputs.input_file.path.lastIndexOf('/') + 1, inputs.input_file.path.lastIndexOf('.') - (inputs.input_file.path.lastIndexOf('/') + 1)))" ] ; cwl:outputBinding [ CommandOutputBinding:outputEval "$(inputs.input_file.path.substr(inputs.input_file.path.lastIndexOf('/') + 1, inputs.input_file.path.lastIndexOf('.') - (inputs.input_file.path.lastIndexOf('/') + 1)))" ] ; cwl:outputBinding [ CommandOutputBinding:outputEval "$(inputs.input_file.path.substr(inputs.input_file.path.lastIndexOf('/') + 1, inputs.input_file.path.lastIndexOf('.') - (inputs.input_file.path.lastIndexOf('/') + 1)))" ] ; sld:type xsd:string . cwl:valueFrom "RPKM" . rdfs:comment "Number of threads used" ; cwl:default 1 ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-@" ] ; sld:type xsd:int . cwl:source . rdfs:comment "-s=:: , strand shifts at which cross-correlation is evaluated, default=-500:5:1500" ; cwl:inputBinding [ CommandLineBinding:prefix "-s=" ; CommandLineBinding:separate false ] ; sld:type xsd:string , sld:null . rdfs:comment "Peak calling output file in narrowPeak|broadPeak format." ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.treatment[0].path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '_peaks.*Peak')" ; CommandOutputBinding:outputEval "$(self[0])" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.treatment[0].path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '_peaks.*Peak')" ; CommandOutputBinding:outputEval "$(self[0])" ] ; sld:type cwl:File . rdfs:comment "The number of megabytes of memory a given thread is given to store path descriptors in --best mode. (Default: 256)" ; cwl:inputBinding [ CommandLineBinding:position 5 ; CommandLineBinding:prefix "--chunkmbs" ] ; sld:type xsd:int , sld:null . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.peak_xls_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\_peaks\\.xls$/, '_read_count.txt'))" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.peak_xls_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\_peaks\\.xls$/, '_read_count.txt'))" ] ; sld:type cwl:File . rdfs:comment "Percentage of mitochondrial reads." ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . sld:type xsd:string . cwl:in , , , , ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:in , , , , , ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "File containing peak summits" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "SE|PE\nSingle End (SE) or Paired End (PE) mode\n" ; cwl:inputBinding [ CommandLineBinding:position 3 ] ; sld:type xsd:string . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:source . rdfs:comment "Number of threads" ; cwl:default 1 ; sld:type xsd:int . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "KEEPDUPLICATES\nIt controls the MACS behavior towards duplicate tags\nat the exact same location -- the same coordination\nand the same strand. The 'auto' option makes MACS\ncalculate the maximum tags at the exact same location\nbased on binomal distribution using 1e-5 as pvalue\ncutoff; and the 'all' option keeps every tags. If an\ninteger is given, at most this number of tags will be\nkept at the same location. The default is to keep one\ntag at the same location. Default: 1\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--keep-dup" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--keep-dup" ] ; sld:type xsd:string , sld:null . rdfs:comment "File containing peak summits using each paired mate independently" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . a cwl:CommandLineTool ; rdfs:comment "Un-pack a BEDPE concatenating both mates so that they are treated independently" ; ns1:original_cwlVersion "v1.0" ; cwl:baseCommand ( "bedpe-to-bed.sh" ) ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:stdout "$(inputs.bedpe.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '').replace(/([_\\.]?sorted)*$/, '.unpaired.bed'))" . cwl:valueFrom ".peak_count.within_replicate.txt" . cwl:source . rdfs:comment "only include reads with all bits set in INT set in FLAG [0]" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-f" ] ; sld:type xsd:int , sld:null . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "Treatment sample file(s). If multiple files are given as -t A B C, then they will all be read and pooled together. IMPORTANT: the first sample will be used as the outputs basename." ; cwl:inputBinding [ CommandLineBinding:position 2 ; CommandLineBinding:prefix "--treatment" ] ; cwl:inputBinding [ CommandLineBinding:position 2 ; CommandLineBinding:prefix "--treatment" ] ; sld:type [ sld:items cwl:File ; sld:type sld:array ] ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Aligned file to be sorted with samtools" ; cwl:inputBinding [ CommandLineBinding:position 1000 ] ; sld:type cwl:File . rdfs:comment "Save the percentage in a file of the given name" ; sld:type xsd:string , sld:null . cwl:valueFrom "33" . rdfs:comment "FASTQ files for paired_read1 after trimming" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . cwl:in , , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:valueFrom "${return true}" . cwl:default 1 ; sld:type xsd:int . a cwl:CommandLineTool ; ns1:original_cwlVersion "v1.0" ; cwl:arguments ( [ cwl:valueFrom "$(\"-out=\" + inputs.input_bam.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, \"\") + \".spp_cross_corr.txt\")" ] [ CommandLineBinding:shellQuote false ; cwl:valueFrom "$(\"-tmpdir=\"+runtime.tmpdir)" ] ) ; cwl:baseCommand ( "run_spp.R" ) ; cwl:cwlVersion ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/spp" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:inputs , , , , , , , , , , , , , ; cwl:outputs , , , , ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:ShellCommandRequirement ] . rdfs:comment "\tReport the depth at each genome position (with zero-based coordinates).\nReports only non-zero positions.\nDefault behavior is to report a histogram.\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-dz" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-dz" ] ; sld:type xsd:boolean , sld:null . cwl:source . rdfs:comment "(NOT the legacy --shiftsize option!) The arbitrary shift in bp. Use discretion while setting it other than default value. When NOMODEL is set, MACS will use this value to move cutting ends (5') towards 5'->3' direction then apply EXTSIZE to extend them to fragments. When this value is negative, ends will be moved toward 3'->5' direction. Recommended to keep it as default 0 for ChIP-Seq datasets, or -1 * half of EXTSIZE together with EXTSIZE option for detecting enriched cutting loci such as certain DNAseI-Seq datasets. Note, you can't set values other than 0 if format is BAMPE for paired-end data. DEFAULT: 0." ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--shift" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--shift" ] ; sld:type xsd:int , sld:null . cwl:valueFrom "bed6+4" . cwl:valueFrom "BAMPE" . rdfs:comment "Writes additional track line definition parameters in the first line.\n- Example:\n-trackopts 'name=\"My Track\" visibility=2 color=255,30,30'\nNote the use of single-quotes if you have spaces in your parameters.\n- (TEXT)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-trackopts" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-trackopts" ] ; sld:type xsd:string , sld:null . cwl:source . sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "-savd= OR -savd, save Rdata file" ; cwl:inputBinding [ cwl:valueFrom "${ if (self) return \"-savd=\" + inputs.input_bam.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, \"\") + \".spp.Rdata\"; return null}" ] ; sld:type xsd:boolean , sld:null . a cwl:CommandLineTool ; rdfs:comment "bedSort - Sort a .bed file by chrom,chromStart\nusage:\n bedSort in.bed out.bed\nin.bed and out.bed may be the same.\n" ; ns1:original_cwlVersion "v1.0" ; cwl:arguments ( [ CommandLineBinding:position 2 ; cwl:valueFrom "$(inputs.bed_file.path.replace(/^.*[\\\\\\/]/, '') + \"_sorted\")" ] ) ; cwl:baseCommand ( "bedSort" ) ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dleehr/docker-hubutils" ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . rdfs:comment "Aligned file to be sorted with samtools" ; cwl:inputBinding [ CommandLineBinding:position 1000 ] ; cwl:inputBinding [ CommandLineBinding:position 1000 ] ; cwl:inputBinding [ CommandLineBinding:position 1000 ] ; cwl:inputBinding [ CommandLineBinding:position 1000 ] ; cwl:inputBinding [ CommandLineBinding:position 1000 ] ; sld:type cwl:File . rdfs:comment "This (re)encodes the quality part of the FASTQ file to base 33." ; cwl:inputBinding [ CommandLineBinding:position 12 ; CommandLineBinding:prefix "TOPHRED33" ; CommandLineBinding:separate false ] ; sld:type xsd:boolean , sld:null . rdfs:comment "VERBOSE_LEVEL Set verbose level of runtime message. 0: only show\ncritical message, 1: show additional warning message,\n2: show process information, 3: show debug messages.\nDEFAULT:2\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--verbose" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--verbose" ] ; sld:type xsd:int , sld:null . rdfs:comment "If true do not write duplicates to the output file instead of writing them with appropriate flags set. (Default false)." ; cwl:inputBinding [ CommandLineBinding:position 5 ; CommandLineBinding:prefix "BARCODE_TAG=" ; CommandLineBinding:separate false ] ; sld:type xsd:string , sld:null . rdfs:comment "Split alignments based on N and D CIGAR operators.\nForces -split.\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-splitD" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "\nRemove low quality bases from the end. As long as a base has a value below this threshold\nthe base is removed and the next base (which as trimmomatic is starting from the 3\" prime end\nwould be base preceding the just removed base) will be investigated. This approach can be\nused removing the special illumina \"low quality segment\" regions (which are marked with\nquality score of 2), but we recommend Sliding Window or MaxInfo instead\n: Specifies the minimum quality required to keep a base.\n" ; cwl:inputBinding [ CommandLineBinding:position 14 ; CommandLineBinding:prefix "TRAILING:" ; CommandLineBinding:separate false ] ; sld:type xsd:int , sld:null . a cwl:CommandLineTool ; ns1:original_cwlVersion "v1.0" ; cwl:arguments ( [ CommandLineBinding:position 3 ; cwl:valueFrom "MarkDuplicates" ] [ CommandLineBinding:position 5 ; CommandLineBinding:shellQuote false ; cwl:valueFrom "$('OUTPUT=' + inputs.output_filename + '.' + inputs.output_suffix)" ] [ CommandLineBinding:position 5 ; CommandLineBinding:shellQuote false ; cwl:valueFrom "$('METRICS_FILE='+inputs.output_filename + '.' + inputs.metrics_suffix)" ] [ CommandLineBinding:position 5 ; CommandLineBinding:shellQuote false ; cwl:valueFrom "$('TMP_DIR='+runtime.tmpdir)" ] ) ; cwl:baseCommand ( "java" ) ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/picard" ] ; cwl:inputs , , , , , , , ; cwl:outputs , ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:ShellCommandRequirement ] . rdfs:comment "BED file\nA BED file containing regions that should be excluded\nfrom all analyses. Currently this works by rejecting\ngenomic chunks that happen to overlap an entry.\nConsequently, for BAM files, if a read partially\noverlaps a blacklisted region or a fragment spans over\nit, then the read/fragment might still be considered.\n(default: None)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--blackListFileName" ] ; sld:type cwl:File , sld:null . rdfs:comment "BAM file to process " ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--bam" ] ; cwl:secondaryFiles [] ; sld:type cwl:File . sld:type cwl:File , xsd:string . sld:type xsd:string . rdfs:comment "\nRemove low quality bases from the beginning. As long as a base has a value below this\nthreshold the base is removed and the next base will be investigated.\n: Specifies the minimum quality required to keep a base.\n" ; cwl:inputBinding [ CommandLineBinding:position 14 ; CommandLineBinding:prefix "LEADING:" ; CommandLineBinding:separate false ] ; sld:type xsd:int , sld:null . rdfs:comment "Input fastq paired-end read 1 files" ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "peakshift/phantomPeak extended fragment results file using each paired mate independently" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_fastq_file.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, '') + \"_fastqc.zip\")" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_fastq_file.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, '') + \"_fastqc.zip\")" ] ; sld:type cwl:File . cwl:source . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:valueFrom ".rpkm.bw" . cwl:source . cwl:source . rdfs:comment "suffix of the transformed SAM/BAM file (including extension, e.g. .filtered.sam)" ; cwl:default ".sorted.bam" ; sld:type xsd:string . rdfs:comment " number of alignment threads to launch (default: 1)" ; cwl:default 1 ; cwl:inputBinding [ CommandLineBinding:position 8 ; CommandLineBinding:prefix "--threads" ] ; sld:type xsd:int . cwl:source . cwl:valueFrom "${return true}" . rdfs:comment "Peak calling report file (*_peaks.xls file produced by MACS2)" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:in , , ; cwl:out ; cwl:run ; cwl:scatter ( ) . sld:type xsd:string . rdfs:comment "Peak counts within replicate using each paired mate independently" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "INT\nNumber of processors to use. Type \"max/2\" to use half\nthe maximum number of processors or \"max\" to use all\navailable processors. (default: max/2)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--numberOfProcessors" ] ; sld:type xsd:int , sld:null . rdfs:comment "Input adapters files for paired_read2" ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . cwl:valueFrom "${return 200}" . cwl:source . a cwl:Workflow ; rdfs:comment "ATAC-seq 01 QC - reads: PE" ; ns1:original_cwlVersion "v1.0" ; Workflow:steps , , , , , , , , , , , , , ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:inputs , , , ; cwl:outputs , , , , , , , , , ; cwl:requirements [ a cwl:StepInputExpressionRequirement ] ; cwl:requirements [ a cwl:ScatterFeatureRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . cwl:inputBinding [ CommandLineBinding:position 2 ] ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; sld:type cwl:File . rdfs:comment "Effective genome size used by MACS2. It can be numeric or a shortcuts:'hs' for human (2.7e9), 'mm' for mouse (1.87e9), 'ce' for C. elegans (9e7) and 'dm' for fruitfly (1.2e8), Default:hs" ; cwl:default "hs" ; sld:type xsd:string . cwl:in , , ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:source . rdfs:comment "By adding this option, reads are centered with respect\nto the fragment length. For paired-end data, the read\nis centered at the fragment length defined by the two\nends of the fragment. For single-end data, the given\nfragment length is used. This option is useful to get\na sharper signal around enriched regions. (default:\nFalse)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--centerReads" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "Include header in output" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-h" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "Suffix used to create the metrics output file (Default: dedup_metrics.txt)" ; cwl:default "dedup_metrics.txt" ; sld:type xsd:string . cwl:source . cwl:source . rdfs:comment "TSIZE, --tsize TSIZE\nTag size. This will overide the auto detected tag\nsize. DEFAULT: Not set\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-s" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-s" ] ; sld:type xsd:int , sld:null . cwl:source . rdfs:comment "\tgenome_sizes is two column: .\n" ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; sld:type cwl:File . cwl:default true . rdfs:comment "-unc - If set, do not use compression.\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type xsd:boolean , sld:null . rdfs:comment "Percentage of uniq reads from preseq c_curve output" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:valueFrom "4:20" . rdfs:comment "trim bases from 3' (right) end of reads" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--trim3" ] ; sld:type xsd:int , sld:null . rdfs:comment "Report \"split\" BAM alignments as separate BED entries.\nSplits only on N CIGAR operations.\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-split" ] ; sld:type xsd:boolean , sld:null . cwl:valueFrom "${return inputs.idxstats.basename.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '').replace(/\\.[^/.]+$/, '').replace(/\\.[^/.]+$/, '.mitochondrial_percentage.txt')}" . a cwl:CommandLineTool ; rdfs:comment "Extracts the base name of a file" ; ns1:original_cwlVersion "v1.0" ; cwl:baseCommand ( "echo" ) ; cwl:cwlVersion ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs ; cwl:outputs . cwl:source . cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:inputBinding [ CommandLineBinding:position 2 ] ; sld:type cwl:File . rdfs:comment "INT \nExclude reads based on the SAM flag. For example, to\nget only reads that map to the forward strand, use\n--samFlagExclude 16, where 16 is the SAM flag for\nreads that map to the reverse strand. (default: None)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--samFlagExclude" ] ; sld:type xsd:int , sld:null . cwl:source . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "Filter unmapped reads in aligned file" ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.output_filename + '.accepted_hits.bam')" ] ; sld:type cwl:File . cwl:source . cwl:source . cwl:source . cwl:outputBinding [ CommandOutputBinding:glob "${ if (inputs.outFileName) return inputs.outFileName; if (inputs.output_suffix) return inputs.bam.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, \"\") + inputs.output_suffix; if (inputs.outFileFormat == \"bedgraph\") return inputs.bam.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, \"\") + \".bdg\"; return inputs.bam.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, \"\") + \".bw\"; }" ] ; sld:type cwl:File . cwl:source . cwl:valueFrom "${return 3}" . a cwl:CommandLineTool ; rdfs:comment "Count number of dedup-ed reads used in peak calling" ; ns1:original_cwlVersion "v1.2" ; cwl:baseCommand ( "count-filtered-reads-macs2.sh" ) ; cwl:baseCommand ( "count-filtered-reads-macs2.sh" ) ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:stdout "$(inputs.peak_xls_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\_peaks\\.xls$/, '_read_count.txt'))" . rdfs:comment "Preseq c_curve output files." ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Peak calling report file (*_peaks.xls file produced by MACS2) using each paired mate independently" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . rdfs:comment "If True, MACS will save signal per million reads for fragment pileup profiles. Require --bdg to be set. Default: False " ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--SPMR" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--SPMR" ] ; sld:type xsd:boolean , sld:null . cwl:in , , , , , , ; cwl:out , , , , , , , , ; cwl:run . rdfs:comment "Aligned BAM file to filter" ; cwl:inputBinding [ CommandLineBinding:position 3 ] ; cwl:inputBinding [ CommandLineBinding:position 3 ] ; sld:type cwl:File . cwl:valueFrom "chrM" . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.bowtie_log.path.replace(/^.*[\\\\\\/]/, '') + '.read_count.mapped')" ] ; sld:type cwl:File . rdfs:comment "PCR Bottleneck Coeficient files." ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . sld:type xsd:string . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:source . rdfs:comment "-savr= OR -savr RegionPeak file name (variable width peaks with regions of enrichment)" ; cwl:inputBinding [ cwl:valueFrom "${ if (self) return \"-savr=\" + inputs.input_bam.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, \"\") + \".spp.regionPeak\"; return null}" ] ; sld:type xsd:boolean , sld:null . cwl:in , , , , , , ; cwl:out , , , ; cwl:run . rdfs:comment "-extraIndex=fieldList - If set, make an index on each field in a comma separated list\n extraIndex=name and extraIndex=name,id are commonly used.\n" ; cwl:inputBinding [ CommandLineBinding:itemSeparator "," ; CommandLineBinding:position 1 ; CommandLineBinding:prefix "-extraIndex=" ] ; cwl:inputBinding [ CommandLineBinding:itemSeparator "," ; CommandLineBinding:position 1 ; CommandLineBinding:prefix "-extraIndex=" ] ; sld:type sld:null ; sld:type [ sld:items xsd:string ; sld:type sld:array ] ; sld:type [ sld:items xsd:string ; sld:type sld:array ] . cwl:inputBinding [ CommandLineBinding:position 10000 ] ; cwl:inputBinding [ CommandLineBinding:position 10000 ] ; sld:type cwl:File . cwl:in , , ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "BAM files with marked duplicate reads." ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . a cwl:CommandLineTool ; rdfs:comment "Counts lines in a file and returns a suffixed file with that number" ; ns1:original_cwlVersion "v1.2" ; CommandLineTool:stdin "$(inputs.input_file.path)" ; cwl:baseCommand ( "wc" "-l" ) ; cwl:baseCommand ( "wc" "-l" ) ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs , ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:stdout "$(inputs.input_file.path.replace(/^.*[\\\\\\/]/, '') + inputs.output_suffix)" . rdfs:comment "Peak counts within replicate" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:valueFrom "${return -100}" . cwl:source . rdfs:comment "Tells MACS to include trackline with bedGraph files. To include this trackline while displaying bedGraph at UCSC genome browser, can show name and description of the file as well. However my suggestion is to convert bedGraph to bigWig, then show the smaller and faster binary bigWig file at UCSC genome browser, as well as downstream analysis. Require --bdg to be set. Default: Not include trackline. " ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--trackline" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--trackline" ] ; sld:type xsd:boolean , sld:null . cwl:source . rdfs:comment "SEED Set the random seed while down sampling data. Must be\na non-negative integer in order to be effective.\nDEFAULT: not set\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--seed" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--seed" ] ; sld:type xsd:int , sld:null . rdfs:comment "Rdata file from the run_spp.R run" ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_bam.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, \"\") + \".spp.Rdata\")" ] ; sld:type cwl:File , sld:null . rdfs:comment ", full path and name (or URL) of tagAlign/BAM file (can be gzipped) (FILE EXTENSION MUST BE tagAlign.gz, tagAlign, bam or bam.gz)" ; cwl:inputBinding [ CommandLineBinding:prefix "-i=" ; CommandLineBinding:separate false ] ; sld:type cwl:File , sld:null . cwl:source . cwl:valueFrom "${return 2}" . cwl:inputBinding [ CommandLineBinding:position 2 ; CommandLineBinding:prefix "-jar" ] ; sld:type xsd:string . cwl:source . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_basename + '.read_count.txt')" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_basename + '.read_count.txt')" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_basename + '.read_count.txt')" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_basename + '.read_count.txt')" ] ; sld:type cwl:File . cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . rdfs:comment "Write \"blocked\" BED format (aka \"BED12\"). Forces -split.\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-bed12" ] ; sld:type xsd:boolean , sld:null . cwl:source . rdfs:comment "SMALLLOCAL The small nearby region in basepairs to calculate\ndynamic lambda. This is used to capture the bias near\nthe peak summit region. Invalid if there is no control\ndata. If you set this to 0, MACS will skip slocal\nlambda calculation. *Note* that MACS will always\nperform a d-size local lambda calculation. The final\nlocal bias should be the maximum of the lambda value\nfrom d, slocal, and llocal size windows. DEFAULT: 1000\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--slocal" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--slocal" ] ; sld:type xsd:int , sld:null . rdfs:comment "Bowtie log file." ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . a cwl:CommandLineTool ; rdfs:comment "Get number of processed reads from Bowtie log." ; ns1:original_cwlVersion "v1.0" ; cwl:baseCommand ( "read-count-from-bowtie-log.sh" ) ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:ShellCommandRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:stdout "$(inputs.bowtie_log.path.replace(/^.*[\\\\\\/]/, '') + '.read_count.mapped')" . cwl:source . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.bed_file.path.replace(/^.*[\\\\\\/]/, '') + \"_sorted\")" ] ; sld:type cwl:File . cwl:valueFrom ".dedup.bam" . cwl:source . rdfs:comment "Print wall-clock time taken by search phases" ; cwl:default true ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-t" ] ; sld:type xsd:boolean . rdfs:comment "Effective genome size used by MACS2. It can be numeric or a shortcuts:'hs' for human (2.7e9), 'mm' for mouse (1.87e9), 'ce' for C. elegans (9e7) and 'dm' for fruitfly (1.2e8), Default:hs" ; cwl:default "hs" ; sld:type xsd:string . cwl:source . cwl:source . rdfs:comment "-pe input is paired end read file \n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-P" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "Peak calling report file (*_peaks.xls file produced by MACS2) using each paired mate independently" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:in , , , ; cwl:out , , , , , , , , , ; cwl:run . cwl:source . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "{forward,reverse}\nSelects RNA-seq reads (single-end or paired-end) in\nthe given strand. (default: None)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--filterRNAstrand" ] ; sld:type xsd:string , sld:null . cwl:default ".count" ; sld:type xsd:string . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "Genome sizes tab-delimited file (used in samtools)" ; sld:type cwl:File . rdfs:comment "Peaks in bigBed format" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Number of threads required for the 01-qc step" ; sld:type xsd:int . cwl:in , , , , , ; cwl:out , , , , , , , , , , , , , , , , ; cwl:run . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_basename + '.fastqc-read_count.txt')" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_basename + '.fastqc-read_count.txt')" ] ; sld:type cwl:File . a cwl:CommandLineTool ; rdfs:comment "usage: An example usage is:$ bamCoverage -b reads.bam -o coverage.bw\n\nThis tool takes an alignment of reads or fragments as input (BAM file) and\ngenerates a coverage track (bigWig or bedGraph) as output. The coverage is\ncalculated as the number of reads per bin, where bins are short consecutive\ncounting windows of a defined size. It is possible to extended the length of\nthe reads to better reflect the actual fragment length. *bamCoverage* offers\nnormalization by scaling factor, Reads Per Kilobase per Million mapped reads\n(RPKM), and 1x depth (reads per genome coverage, RPGC).\nRequired arguments:\n --bam BAM file, -b BAM file\n BAM file to process (default: None)\nOutput:\n --outFileName FILENAME, -o FILENAME\n Output file name. (default: None)\n --outFileFormat {bigwig,bedgraph}, -of {bigwig,bedgraph}\n Output file type. Either \"bigwig\" or \"bedgraph\".\n (default: bigwig)\nOptional arguments:\n --help, -h show this help message and exit\n --scaleFactor SCALEFACTOR\n The smooth length defines a window, larger than the\n binSize, to average the number of reads. For example,\n if the –binSize is set to 20 and the –smoothLength is\n set to 60, then, for each bin, the average of the bin\n and its left and right neighbors is considered.\n Any value smaller than –binSize will be ignored and\n no smoothing will be applied. (default: 1.0)\n --MNase Determine nucleosome positions from MNase-seq data.\n Only 3 nucleotides at the center of each fragment are\n counted. The fragment ends are defined by the two mate\n reads. Only fragment lengthsbetween 130 - 200 bp are\n considered to avoid dinucleosomes or other\n artifacts.*NOTE*: Requires paired-end data. A bin size\n of 1 is recommended. (default: False)\n --filterRNAstrand {forward,reverse}\n Selects RNA-seq reads (single-end or paired-end) in\n the given strand. (default: None)\n --version show program's version number and exit\n --binSize INT bp, -bs INT bp\n Size of the bins, in bases, for the output of the\n bigwig/bedgraph file. (default: 50)\n --region CHR:START:END, -r CHR:START:END\n Region of the genome to limit the operation to - this\n is useful when testing parameters to reduce the\n computing time. The format is chr:start:end, for\n example --region chr10 or --region\n chr10:456700:891000. (default: None)\n --blackListFileName BED file, -bl BED file\n A BED file containing regions that should be excluded\n from all analyses. Currently this works by rejecting\n genomic chunks that happen to overlap an entry.\n Consequently, for BAM files, if a read partially\n overlaps a blacklisted region or a fragment spans over\n it, then the read/fragment might still be considered.\n (default: None)\n --numberOfProcessors INT, -p INT\n Number of processors to use. Type \"max/2\" to use half\n the maximum number of processors or \"max\" to use all\n available processors. (default: max/2)\n --verbose, -v Set to see processing messages. (default: False)\nRead coverage normalization options:\n --normalizeTo1x EFFECTIVE GENOME SIZE LENGTH\n Report read coverage normalized to 1x sequencing depth\n (also known as Reads Per Genomic Content (RPGC)).\n Sequencing depth is defined as: (total number of\n mapped reads * fragment length) / effective genome\n size. The scaling factor used is the inverse of the\n sequencing depth computed for the sample to match the\n 1x coverage. To use this option, the effective genome\n size has to be indicated after the option. The\n effective genome size is the portion of the genome\n that is mappable. Large fractions of the genome are\n stretches of NNNN that should be discarded. Also, if\n repetitive regions were not included in the mapping of\n reads, the effective genome size needs to be adjusted\n accordingly. Common values are: mm9: 2,150,570,000;\n hg19:2,451,960,000; dm3:121,400,000 and\n ce10:93,260,000. See Table 2 of http://www.plosone.org\n /article/info:doi/10.1371/journal.pone.0030377 or http\n ://www.nature.com/nbt/journal/v27/n1/fig_tab/nbt.1518_\n T1.html for several effective genome sizes. (default:\n None)\n--ignoreForNormalization IGNOREFORNORMALIZATION [IGNOREFORNORMALIZATION ...]\n A list of space-delimited chromosome names containing\n those chromosomes that should be excluded for\n computing the normalization. This is useful when\n considering samples with unequal coverage across\n chromosomes, like male samples. An usage examples is\n --ignoreForNormalization chrX chrM. (default: None)\n --skipNonCoveredRegions, --skipNAs\n This parameter determines if non-covered regions\n (regions without overlapping reads) in a BAM file\n should be skipped. The default is to treat those\n regions as having a value of zero. The decision to\n skip non-covered regions depends on the interpretation\n of the data. Non-covered regions may represent, for\n example, repetitive regions that should be skipped.\n (default: False)\n --smoothLength INT bp\n The smooth length defines a window, larger than the\n binSize, to average the number of reads. For example,\n if the --binSize is set to 20 and the --smoothLength\n is set to 60, then, for each bin, the average of the\n bin and its left and right neighbors is considered.\n Any value smaller than --binSize will be ignored and\n no smoothing will be applied. (default: None)\nRead processing options:\n --extendReads [INT bp], -e [INT bp]\n This parameter allows the extension of reads to\n fragment size. If set, each read is extended, without\n exception. *NOTE*: This feature is generally NOT\n recommended for spliced-read data, such as RNA-seq, as\n it would extend reads over skipped regions. *Single-\n end*: Requires a user specified value for the final\n fragment length. Reads that already exceed this\n fragment length will not be extended. *Paired-end*:\n Reads with mates are always extended to match the\n fragment size defined by the two read mates. Unmated\n reads, mate reads that map too far apart (>4x fragment\n length) or even map to different chromosomes are\n treated like single-end reads. The input of a fragment\n length value is optional. If no value is specified, it\n is estimated from the data (mean of the fragment size\n of all mate reads). (default: False)\n --ignoreDuplicates If set, reads that have the same orientation and start\n position will be considered only once. If reads are\n paired, the mate's position also has to coincide to\n ignore a read. (default: False)\n --minMappingQuality INT\n If set, only reads that have a mapping quality score\n of at least this are considered. (default: None)\n --centerReads By adding this option, reads are centered with respect\n to the fragment length. For paired-end data, the read\n is centered at the fragment length defined by the two\n ends of the fragment. For single-end data, the given\n fragment length is used. This option is useful to get\n a sharper signal around enriched regions. (default:\n False)\n --samFlagInclude INT Include reads based on the SAM flag. For example, to\n get only reads that are the first mate, use a flag of\n 64. This is useful to count properly paired reads only\n once, as otherwise the second mate will be also\n considered for the coverage. (default: None)\n --samFlagExclude INT Exclude reads based on the SAM flag. For example, to\n get only reads that map to the forward strand, use\n --samFlagExclude 16, where 16 is the SAM flag for\n reads that map to the reverse strand. (default: None)\n" ; ns1:original_cwlVersion "v1.0" ; cwl:arguments ( [ CommandLineBinding:position 3 ; CommandLineBinding:prefix "--outFileName" ; cwl:valueFrom "${ if (inputs.outFileName) return inputs.outFileName; if (inputs.output_suffix) return inputs.bam.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, \"\") + inputs.output_suffix; if (inputs.outFileFormat == \"bedgraph\") return inputs.bam.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, \"\") + \".bdg\"; return inputs.bam.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, \"\") + \".bw\"; }" ] ) ; cwl:baseCommand ( "bamCoverage" ) ; cwl:cwlVersion ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/deeptools:3.0.1" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs , , , , , , , , , , , , , , , , , , , , , , ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . rdfs:comment "JVM arguments should be a quoted, space separated list (e.g. \"-Xms128m -Xmx512m\")" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:shellQuote false ] ; sld:type xsd:string , sld:null . rdfs:comment "FASTA file containing adapters, PCR sequences, etc. It is used to search for and remove these sequences in the input FASTQ file(s)" ; sld:type cwl:File . rdfs:comment "-hist input is a text file containing the observed histogram \n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-H" ] ; sld:type cwl:File , sld:null . cwl:source . cwl:source . cwl:source . cwl:source . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:default true ; cwl:inputBinding [ CommandLineBinding:position 2 ; CommandLineBinding:prefix "--noextract" ] ; cwl:inputBinding [ CommandLineBinding:position 2 ; CommandLineBinding:prefix "--noextract" ] ; sld:type xsd:boolean . rdfs:comment "BROADCUTOFF\nCutoff for broad region. This option is not available\nunless --broad is set. If -p is set, this is a pvalue\ncutoff, otherwise, it's a qvalue cutoff. DEFAULT: 0.1\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--broad-cutoff" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--broad-cutoff" ] ; sld:type xsd:float , sld:null . rdfs:comment "Input fastq files for paired_read2" ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "-itemsPerSlot=N - Number of data points bundled at lowest level. Default 512\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-itemsPerSlot=" ; CommandLineBinding:separate false ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-itemsPerSlot=" ; CommandLineBinding:separate false ] ; sld:type xsd:int , sld:null . rdfs:comment "Trimmed fastq files for paired_read1" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "regionPeak output file" ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_bam.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, \"\") + \".spp.regionPeak\")" ] ; sld:type cwl:File , sld:null . cwl:source . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.bed_graph.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, \"\") + inputs.output_suffix)" ] ; sld:type cwl:File . rdfs:comment "Raw read counts for paired_read2 of fastq files after trimming" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . cwl:source . cwl:default "-phred33" ; sld:type xsd:string . cwl:source . cwl:source . cwl:outputBinding [ CommandOutputBinding:outputEval "$(inputs.file_path.replace(/\\.[^/.]+$/, \"\"))" ] ; sld:type xsd:string . rdfs:comment "Control sample file." ; cwl:inputBinding [ CommandLineBinding:position 2 ; CommandLineBinding:prefix "--control" ] ; cwl:inputBinding [ CommandLineBinding:position 2 ; CommandLineBinding:prefix "--control" ] ; sld:type cwl:File , sld:null . rdfs:comment "First file (extension .1.ebwt) of the Bowtie index files generated for the reference genome (see http://bowtie-bio.sourceforge.net/tutorial.shtml#newi)" ; cwl:inputBinding [ CommandLineBinding:position 9 ; cwl:valueFrom "$(self.path.split('.').splice(0,self.path.split('.').length-2).join(\".\"))" ] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; sld:type cwl:File . cwl:valueFrom "${return true}" . cwl:source . rdfs:comment "Sort by read name" ; cwl:default false ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-n" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-n" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-n" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-n" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-n" ] ; sld:type xsd:boolean . cwl:source . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.output_filename + '.' + inputs.output_suffix)" ] ; sld:type cwl:File . cwl:source . rdfs:comment "Aligned file to be sorted with samtools" ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . a cwl:CommandLineTool ; ns1:original_cwlVersion "v1.2" ; cwl:baseCommand ( "samtools" "sort" ) ; cwl:baseCommand ( "samtools" "sort" ) ; cwl:baseCommand ( "samtools" "sort" ) ; cwl:baseCommand ( "samtools" "sort" ) ; cwl:baseCommand ( "samtools" "sort" ) ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools:1.3" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools:1.3" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools:1.3" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools:1.3" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools:1.3" ] ; cwl:inputs , , , ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:stdout "$(inputs.input_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + inputs.suffix)" . rdfs:comment "JVM arguments should be a quoted, space separated list (e.g. \"-Xms128m -Xmx512m\")" ; sld:type xsd:string , sld:null . rdfs:comment "signal files of pileup reads in RPKM" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . a cwl:CommandLineTool ; rdfs:comment "Usage: c_curve [OPTIONS] \n\nOptions:\n -o, -output yield output file (default: stdout) \n -s, -step step size in extrapolations (default: 1e+06) \n -v, -verbose print more information \n -P, -pe input is paired end read file \n -H, -hist input is a text file containing the observed histogram \n -V, -vals input is a text file containing only the observed counts \n -B, -bam input is in BAM format \n -l, -seg_len maximum segment length when merging paired end bam reads \n (default: 5000) \n\nHelp options:\n -?, -help print this help message \n -about print about message" ; ns1:original_cwlVersion "v1.0" ; cwl:baseCommand ( "preseq" "c_curve" ) ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/preseq:2.0" ] ; cwl:inputs , , , , , , , , ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:stdout "$(inputs.output_file_basename + '.preseq_c_curve.txt')" . cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:default "fastq" ; cwl:inputBinding [ CommandLineBinding:position 3 ; CommandLineBinding:prefix "--format" ] ; cwl:inputBinding [ CommandLineBinding:position 3 ; CommandLineBinding:prefix "--format" ] ; sld:type xsd:string . rdfs:comment "\nRemoves bases regardless of quality from the end of the read, so that the read has maximally\nthe specified length after this step has been performed. Steps performed after CROP might of\ncourse further shorten the read.\n: The number of bases to keep, from the start of the read.\n" ; cwl:inputBinding [ CommandLineBinding:position 13 ; CommandLineBinding:prefix "CROP:" ; CommandLineBinding:separate false ] ; sld:type xsd:int , sld:null . rdfs:comment "INT bp\nSize of the bins, in bases, for the output of the\nbigwig/bedgraph file. (default: 50)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--binSize" ] ; sld:type xsd:int , sld:null . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_file1.path.replace(/.*\\/|\\.[^.]*$/g, \"\") + \"_\" + inputs.input_file2.path.replace(/.*\\/|\\.[^.]*$/g, \"\") + \".joined\")" ] ; sld:type cwl:File . rdfs:comment "suffix of the transformed SAM/BAM file (including extension, e.g. .filtered.sam)" ; sld:type xsd:string , sld:null . cwl:source . cwl:source . cwl:source . rdfs:comment "An R,G,B string for the color used with BED12 format.\nDefault is (255,0,0).\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-color" ] ; sld:type xsd:string , sld:null . cwl:source . a cwl:CommandLineTool ; rdfs:comment "Extracts best fragment length from SPP output text file" ; ns1:original_cwlVersion "v1.0" ; cwl:baseCommand ( "extract-best-frag-length.sh" ) ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs ; cwl:outputs ; cwl:stdout "best_frag_length" . rdfs:comment "A list of space-delimited chromosome names containing those chromosomes\nthat should be excluded for computing the normalization. This is useful\nwhen considering samples with unequal coverage across chromosomes, like\nmale samples. An usage examples is –ignoreForNormalization chrX chrM.\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--ignoreForNormalization" ] ; sld:type sld:null ; sld:type [ sld:items xsd:string ; sld:type sld:array ] . rdfs:comment "\tReport the depth at each genome position (with one-based coordinates).\nDefault behavior is to report a histogram.\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-d" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-d" ] ; sld:type xsd:boolean , sld:null . cwl:in , , ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:source . rdfs:comment "\tReport depth in BedGraph format, as above (-bg).\nHowever with this option, regions with zero\ncoverage are also reported. This allows one to\nquickly extract all regions of a genome with 0\ncoverage by applying: \"grep -w 0$\" to the output.\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-bga" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-bga" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "FastQC data files for paired_read2" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . a cwl:Workflow ; rdfs:comment "ATAC-seq 03 mapping - reads: PE" ; ns1:original_cwlVersion "v1.0" ; Workflow:steps , , , , , , , , , , , , , , , , , , , , , ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs , , , , , , ; cwl:outputs , , , , , , , , , ; cwl:requirements [ a cwl:SubworkflowFeatureRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:ScatterFeatureRequirement ] ; cwl:requirements [ a cwl:StepInputExpressionRequirement ] . rdfs:comment "Number of threads required for the 05-quantification step" ; sld:type xsd:int . cwl:in , , , , ; cwl:out , , , ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . rdfs:comment "MFOLD MFOLD, --mfold MFOLD MFOLD\nSelect the regions within MFOLD range of high-\nconfidence enrichment ratio against background to\nbuild model. Fold-enrichment in regions must be lower\nthan upper limit, and higher than the lower limit. Use\nas \"-m 10 30\". DEFAULT:5 50\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-m" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-m" ] ; sld:type xsd:string , sld:null . rdfs:comment "peakshift/phantomPeak results file" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . rdfs:comment "Samtools idxstats file" ; cwl:inputBinding [ cwl:loadContents true ] ; sld:type cwl:File . rdfs:comment "Definition narrowPeak file in AutoSql format (used in bedToBigBed)" ; sld:type cwl:File . rdfs:comment ":\nPerforms an adaptive quality trim, balancing the benefits of retaining longer reads against the\ncosts of retaining bases with errors.\n: This specifies the read length which is likely to allow the\nlocation of the read within the target sequence to be determined.\n: This value, which should be set between 0 and 1, specifies the\nbalance between preserving as much read length as possible vs. removal of incorrect\nbases. A low value of this parameter (<0.2) favours longer reads, while a high value\n(>0.8) favours read correctness.\n" ; cwl:inputBinding [ CommandLineBinding:position 15 ; CommandLineBinding:prefix "MAXINFO:" ; CommandLineBinding:separate false ] ; sld:type xsd:string , sld:null . cwl:in , , ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . rdfs:comment "If set, MACS will try to call broad peaks by linking nearby highly enriched regions. The linking region is controlled by another cutoff through --linking-cutoff. The maximum linking region length is 4 times of d from MACS. DEFAULT: False " ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--broad" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--broad" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "Possible choices: RPKM, CPM, BPM, RPGC\n\nUse one of the entered methods to normalize the number of reads per bin.\nBy default, no normalization is performed. RPKM = Reads Per Kilobase per\nMillion mapped reads; CPM = Counts Per Million mapped reads, same as\nCPM in RNA-seq; BPM = Bins Per Million mapped reads, same as TPM in\nRNA-seq; RPGC = reads per genomic content (1x normalization);\nMapped reads are considered after blacklist filtering (if applied).\nRPKM (per bin) = number of reads per bin / (number of mapped reads (in millions) * bin length (kb)).\nCPM (per bin) = number of reads per bin / number of mapped reads (in millions).\nBPM (per bin) = number of reads per bin / sum of all reads per bin (in millions).\nRPGC (per bin) = number of reads per bin / scaling factor for 1x average coverage.\nThis scaling factor, in turn, is determined from the sequencing depth:\n(total number of mapped reads * fragment length) / effective genome size.\nThe scaling factor used is the inverse of the sequencing depth\ncomputed for the sample to match the 1x coverage.\nThis option requires –effectiveGenomeSize.\nEach read is considered independently, if you want to only count one\nmate from a pair in paired-end data, then use\nthe –samFlagInclude/–samFlagExclude options.\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--normalizeUsing" ] ; sld:type xsd:string , sld:null . rdfs:comment "Bam file (it should be indexed)" ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:secondaryFiles [] ; sld:type cwl:File . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.output_filename + '.' + inputs.metrics_suffix)" ] ; sld:type cwl:File . cwl:outputBinding [ CommandOutputBinding:glob "${\n if (inputs.end_mode == \"PE\")\n return inputs.input_read1_fastq_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '.unpaired.trimmed.fastq';\n return null;\n}\n" ] ; sld:type cwl:File , sld:null . a cwl:CommandLineTool ; ns1:original_cwlVersion "v1.0" ; cwl:baseCommand ( "samtools" "view" "-F" "4" "-b" "-h" ) ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools:1.3" ] ; cwl:inputs , , ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:stdout "$(inputs.output_filename + '.accepted_hits.bam')" . cwl:valueFrom "${return 2000}" . a cwl:CommandLineTool ; rdfs:comment "Filter BAM file to only include reads overlapping with a BED file" ; ns1:original_cwlVersion "v1.2" ; cwl:baseCommand ( "samtools" "view" "-b" "-h" ) ; cwl:baseCommand ( "samtools" "view" "-b" "-h" ) ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools:1.3" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools:1.3" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:inputs , ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:stdout "$(inputs.input_bam_file.path.replace(/^.*[\\\\\\/]/, '') + '.in_peaks.bam')" . cwl:source . rdfs:comment "-vals input is a text file containing only the observed counts \n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-V" ] ; sld:type cwl:File , sld:null . cwl:in , , ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "Peaks in bigBed format" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . cwl:source . rdfs:comment "FILE only include reads overlapping this BED FILE [null]" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-L" ] ; sld:type cwl:File , sld:null . cwl:source . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "FastQC data files for paired_read2" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "fastqc_data.txt file from a fastqc report" ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:source . rdfs:comment "Peaks in ENCODE Peak file format" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . rdfs:comment "{bigwig,bedgraph}, -of {bigwig,bedgraph}\nOutput file type. Either \"bigwig\" or \"bedgraph\".\n(default: bigwig)\n" ; cwl:default "bigwig" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--outFileFormat" ] ; sld:type xsd:string . rdfs:comment "Trimmed read counts of fastq files for paired_read2" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "peakshift/phantomPeak results file" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . rdfs:comment "Trimmed read counts of fastq files for paired_read1" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "-speak=, user-defined cross-correlation peak strandshift" ; cwl:inputBinding [ CommandLineBinding:prefix "-speak=" ; CommandLineBinding:separate false ] ; sld:type xsd:string , sld:null . rdfs:comment "Sorted aligned file" ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + inputs.suffix)" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + inputs.suffix)" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + inputs.suffix)" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + inputs.suffix)" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + inputs.suffix)" ] ; sld:type cwl:File . cwl:default ".bw" ; sld:type xsd:string . a cwl:Workflow ; rdfs:comment "ATAC-seq 02 trimming - reads: PE" ; ns1:original_cwlVersion "v1.0" ; Workflow:steps , , , , , ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs , , , , , , , ; cwl:outputs , , , ; cwl:requirements [ a cwl:ScatterFeatureRequirement ] ; cwl:requirements [ a cwl:StepInputExpressionRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . cwl:source . cwl:source . cwl:in , , ; cwl:out ; cwl:run . a cwl:CommandLineTool ; ns1:original_cwlVersion "v1.0" ; cwl:baseCommand ( "samtools" "idxstats" ) ; cwl:cwlVersion ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools:1.3" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:InitialWorkDirRequirement ; cwl:listing "$(inputs.bam)" ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:stdout "$(inputs.bam.basename + \".idxstats\")" . cwl:source . rdfs:comment "Path to the picard.jar file" ; cwl:inputBinding [ CommandLineBinding:position 2 ; CommandLineBinding:prefix "-jar" ] ; sld:type xsd:string . cwl:source . rdfs:comment "-step step size in extrapolations (default: 1e+06) \n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-s" ] ; sld:type xsd:float , sld:null . rdfs:comment "Peaks summits in bedfile format" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . cwl:valueFrom "2:30:15" . cwl:valueFrom ".mapped_and_filtered.read_count.txt" . cwl:source . rdfs:comment "Number of threads required for the 04-peakcall step" ; sld:type xsd:int . cwl:source . cwl:source . rdfs:comment "\tCalculate coverage of 3\" positions (instead of entire interval).\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-3" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-3" ] ; sld:type xsd:boolean , sld:null . cwl:source . cwl:valueFrom "${return 1024}" . cwl:source . cwl:source . rdfs:comment "--verbose \nSet to see processing messages. (default: False)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--verbose" ] ; sld:type xsd:boolean , sld:null . cwl:outputBinding [ CommandOutputBinding:glob "best_frag_length" ; CommandOutputBinding:outputEval "$(Number(self[0].contents.replace('\\n', '')))" ; cwl:loadContents true ] ; sld:type xsd:float . cwl:inputBinding [] ; sld:type cwl:File . cwl:source . rdfs:comment "FILENAME\nOutput file name. (default: input BAM filename with bigwig [*.bw] or bedgraph [*.bdg] extension.)\n" ; sld:type xsd:string , sld:null . cwl:valueFrom "${return 200}" . rdfs:comment "Input fastq files for paired_read1" ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Input format autodetected" ; cwl:default true ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-S" ] ; sld:type xsd:boolean . rdfs:comment "JVM arguments should be a quoted, space separated list" ; sld:type xsd:string , sld:null . cwl:source . cwl:source . a cwl:CommandLineTool ; rdfs:comment "Counts reads in a fastq file" ; ns1:original_cwlVersion "v1.2" ; cwl:baseCommand ( "count-fastq-reads.sh" ) ; cwl:baseCommand ( "count-fastq-reads.sh" ) ; cwl:baseCommand ( "count-fastq-reads.sh" ) ; cwl:baseCommand ( "count-fastq-reads.sh" ) ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs , ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:stdout "$(inputs.input_basename + '.read_count.txt')" . cwl:source . rdfs:comment "Aligned bowtie file in [SAM|BAM] format." ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.output_filename + '.sam')" ] ; sld:type cwl:File . rdfs:comment "The arbitrary extension size in bp. When nomodel is true, MACS will use this value as fragment size to extend each read towards 3' end, then pile them up. It's exactly twice the number of obsolete SHIFTSIZE. In previous language, each read is moved 5'->3' direction to middle of fragment by 1/2 d, then extended to both direction with 1/2 d. This is equivalent to say each read is extended towards 5'->3' into a d size fragment. DEFAULT: 200. EXTSIZE and SHIFT can be combined when necessary. Check SHIFT option." ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--extsize" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--extsize" ] ; sld:type xsd:float , sld:null . rdfs:comment "\tScale the coverage by a constant factor.\nEach coverage value is multiplied by this factor before being reported.\nUseful for normalizing coverage by, e.g., reads per million (RPM).\n- Default is 1.0; i.e., unscaled.\n- (FLOAT)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-scale" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-scale" ] ; sld:type xsd:float , sld:null . cwl:source . rdfs:comment "Percentage of mitochondrial reads" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "JVM arguments should be a quoted, space separated list (e.g. \"-Xms128m -Xmx512m\")" ; sld:type xsd:string , sld:null . rdfs:comment "\tThe input file is in BAM format.\nNote: BAM _must_ be sorted by position\n" ; cwl:inputBinding [ CommandLineBinding:position 2 ; CommandLineBinding:prefix "-ibam" ] ; cwl:inputBinding [ CommandLineBinding:position 2 ; CommandLineBinding:prefix "-ibam" ] ; sld:type cwl:File . sld:type cwl:File . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.output_filename + '.bowtie.log')" ] ; sld:type cwl:File . cwl:source . rdfs:comment "Picard Java jar file" ; cwl:default "/usr/picard/picard.jar" ; sld:type xsd:string . rdfs:comment "Determine nucleosome positions from MNase-seq data.\nOnly 3 nucleotides at the center of each fragment are\ncounted. The fragment ends are defined by the two mate\nreads. Only fragment lengthsbetween 130 - 200 bp are\nconsidered to avoid dinucleosomes or other\nartifacts.*NOTE*: Requires paired-end data. A bin size\nof 1 is recommended. (default: False)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--MNase" ] ; sld:type xsd:boolean , sld:null . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "FastQC reports in zip format for paired_read2" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:in , , , ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "Adapters file" ; sld:type cwl:File . cwl:source . rdfs:comment "Input bed file" ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; sld:type cwl:File . rdfs:comment "Use BAM edit distance (NM tag) for BED score.\n- Default for BED is to use mapping quality.\n- Default for BEDPE is to use the minimum of\nthe two mapping qualities for the pair.\n- When -ed is used with -bedpe, the total edit\ndistance from the two mates is reported.\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-ed" ] ; sld:type xsd:boolean , sld:null . a cwl:CommandLineTool ; rdfs:comment "Compute PCR Bottleneck Coeficient from BedGraph file." ; ns1:original_cwlVersion "v1.0" ; cwl:baseCommand ( "awk" "$4==1 {N1 += $3 - $2}; $4>=1 {Nd += $3 - $2} END {print N1/Nd}" ) ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:inputs , ; cwl:outputs ; cwl:stdout "$(inputs.output_filename + '.PBC.txt')" . cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:default 1 ; sld:type xsd:int . cwl:source . rdfs:comment "Raw read counts for paired_read1 of fastq files after trimming" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "-fdr= , false discovery rate threshold for peak calling" ; cwl:inputBinding [ CommandLineBinding:prefix "-fdr=" ; CommandLineBinding:separate false ] ; sld:type xsd:float , sld:null . rdfs:comment "-bam input is in BAM format \n" ; cwl:default true ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-B" ] ; sld:type xsd:boolean . cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "INT bp\nThe smooth length defines a window, larger than the\nbinSize, to average the number of reads. For example,\nif the --binSize is set to 20 and the --smoothLength\nis set to 60, then, for each bin, the average of the\nbin and its left and right neighbors is considered.\nAny value smaller than --binSize will be ignored and\nno smoothing will be applied. (default: None)\nRead processing options:\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--smoothLength" ] ; sld:type xsd:int , sld:null . rdfs:comment "LARGELOCAL The large nearby region in basepairs to calculate\ndynamic lambda. This is used to capture the surround\nbias. If you set this to 0, MACS will skip llocal\nlambda calculation. *Note* that MACS will always\nperform a d-size local lambda calculation. The final\nlocal bias should be the maximum of the lambda value\nfrom d, slocal, and llocal size windows. DEFAULT:\n10000.\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--llocal" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--llocal" ] ; sld:type xsd:int , sld:null . rdfs:comment "-p= , number of parallel processing nodes, default=0" ; cwl:inputBinding [ CommandLineBinding:prefix "-p=" ; CommandLineBinding:separate false ] ; sld:type xsd:int , sld:null . rdfs:comment "Number of threads used" ; cwl:default 1 ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-@" ] ; sld:type xsd:int . cwl:source . a cwl:CommandLineTool ; rdfs:comment "Tool: bedGraphToBigWig v 4 - Convert a bedGraph file to bigWig format." ; ns1:original_cwlVersion "v1.0" ; cwl:arguments ( [ CommandLineBinding:position 3 ; cwl:valueFrom "$(inputs.bed_graph.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, \"\") + inputs.output_suffix)" ] ) ; cwl:baseCommand ( "bedGraphToBigWig" ) ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/bedgraphtobigwig" ] ; cwl:inputs , , ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:source . rdfs:comment "Normalized reads bigWig (signal) files" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Summary of duplicates removed with Picard tool MarkDuplicates (for multiple reads aligned to the same positions" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "narrowPeak output file" ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_bam.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, \"\") + \".spp.narrowPeak\")" ] ; sld:type cwl:File , sld:null . rdfs:comment "File to be converted to BAM with samtools" ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; sld:type cwl:File . cwl:source . cwl:outputBinding [ CommandOutputBinding:glob "${\n if (inputs.end_mode == \"PE\" && inputs.input_read2_fastq_file)\n return inputs.input_read2_fastq_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '.trimmed.fastq';\n return null;\n}\n" ] ; sld:type cwl:File , sld:null . cwl:source . rdfs:comment "Read counts of the mapped and filtered BAM files" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:default 1 ; cwl:inputBinding [ CommandLineBinding:position 5 ; CommandLineBinding:prefix "--threads" ] ; cwl:inputBinding [ CommandLineBinding:position 5 ; CommandLineBinding:prefix "--threads" ] ; sld:type xsd:int . rdfs:comment "peakshift/phantomPeak results bigbed file using each paired mate independently" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:default true ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-p" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-p" ] ; sld:type xsd:boolean . rdfs:comment "If set, reads that have the same orientation and start\nposition will be considered only once. If reads are\npaired, the mate's position also has to coincide to\nignore a read. (default: False)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--ignoreDuplicates" ] ; sld:type xsd:boolean , sld:null . sld:type xsd:string . rdfs:comment "Filtered read count after peak calling" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . rdfs:comment "Genome sizes tab-delimited file (used in samtools)" ; sld:type cwl:File . rdfs:comment "SPP strand cross correlation summary" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . rdfs:comment "Picard MarkDuplicates metrics files." ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "FECUTOFF When set, the value will be used to filter out peaks\nwith low fold-enrichment. Note, MACS2 use 1.0 as\npseudocount while calculating fold-enrichment.\nDEFAULT: 1.0\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--fe-cutoff" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--fe-cutoff" ] ; sld:type xsd:float , sld:null . rdfs:comment "Minimum FDR (q-value) cutoff for peak detection. DEFAULT: 0.05. -q, and -p are mutually exclusive." ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-q" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-q" ] ; sld:type xsd:float , sld:null . cwl:valueFrom "${return 15}" . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_basename + '.fastqc_data.txt')" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_basename + '.fastqc_data.txt')" ] ; sld:type cwl:File . cwl:default "*/fastqc_data.txt" ; cwl:inputBinding [ CommandLineBinding:position 3 ] ; cwl:inputBinding [ CommandLineBinding:position 3 ] ; sld:type xsd:string . rdfs:comment "Write hits in SAM format (default: BAM)" ; cwl:default true ; cwl:inputBinding [ CommandLineBinding:position 2 ; CommandLineBinding:prefix "--sam" ] ; sld:type xsd:boolean . a cwl:ExpressionTool ; ns1:original_cwlVersion "v1.0" ; ExpressionTool:expression "${\n var regExp = new RegExp(inputs.chrom + \"\\\\s\\\\d+\\\\s(\\\\d+)\\\\s(\\\\d+)\");\n var match = inputs.idxstats.contents.match(regExp);\n if (match){\n var chrom_mapped_reads = match[1];\n var total_reads = inputs.idxstats.contents.split(\"\\n\")\n .map(function(x){\n var rr = x.match(/.*\\s\\d+\\s(\\d+)\\s\\d+/);\n return (rr ? rr[1] : 0);\n })\n .reduce(function(a, b) { return Number(a) + Number(b); });\n\n var output = (100*chrom_mapped_reads/total_reads).toFixed(4) + \"%\" + \"\\n\";\n\n if (inputs.output_filename){\n return {\n percent_map : {\n \"class\": \"File\",\n \"basename\" : inputs.output_filename,\n \"contents\" : output,\n }\n }\n }\n return output;\n }\n}\n" ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs , , ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . rdfs:comment "Whether turn on the auto pair model process. If set, when MACS failed to build paired model, it will use the nomodel settings, the --exsize parameter to extend each tags towards 3' direction. Not to use this automate fixation is a default behavior now. DEFAULT: False " ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--fix-bimodal" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--fix-bimodal" ] ; sld:type xsd:boolean , sld:null . cwl:valueFrom ".dups_marked.bam" . rdfs:comment "Hits in sub-optimal strata aren't reported (requires --best)" ; cwl:default true ; cwl:inputBinding [ CommandLineBinding:position 6 ; CommandLineBinding:prefix "--strata" ] ; sld:type xsd:boolean . rdfs:comment "FastQC data files for paired_read1" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . rdfs:comment "genome_sizes is two column: .\n" ; cwl:inputBinding [ CommandLineBinding:position 3 ] ; cwl:inputBinding [ CommandLineBinding:position 3 ] ; sld:type cwl:File . rdfs:comment "Trimmomatic Java jar file" ; sld:type xsd:string . rdfs:comment "Number of threads required for the 02-trim step" ; sld:type xsd:int . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:source . cwl:source . rdfs:comment "\nDrop the read if the average quality is below the specified level\n: Specifies the minimum average quality required to keep a read.\n" ; cwl:inputBinding [ CommandLineBinding:position 101 ; CommandLineBinding:prefix "AVGQUAL:" ; CommandLineBinding:separate false ] ; sld:type xsd:int , sld:null . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "Filtered read count reported by MACS2 using each paired mate independently" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . cwl:in , , , ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:source . cwl:valueFrom "${return 1}" . rdfs:comment "\"First index file of Bowtie reference genome with extension 1.ebwt. \\ (Note: the rest of the index files MUST be in the same folder)\" " ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; sld:type cwl:File . cwl:source . cwl:source . cwl:source . rdfs:comment "BUFFER_SIZE\nBuffer size for incrementally increasing internal\narray size to store reads alignment information. In\nmost cases, you don't have to change this parameter.\nHowever, if there are large number of\nchromosomes/contigs/scaffolds in your alignment, it's\nrecommended to specify a smaller buffer size in order\nto decrease memory usage (but it will take longer time\nto read alignment files). Minimum memory requested for\nreading an alignment file is about # of CHROMOSOME *\nBUFFER_SIZE * 2 Bytes. DEFAULT: 100000\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--buffer-size" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--buffer-size" ] ; sld:type xsd:int , sld:null . rdfs:comment ", full path and name (or URL) of tagAlign/BAM file (can be gzipped)(FILE EXTENSION MUST BE tagAlign.gz, tagAlign, bam or bam.gz)" ; cwl:inputBinding [ CommandLineBinding:prefix "-c=" ; CommandLineBinding:separate false ] ; sld:type cwl:File . rdfs:comment "BAM files without duplicate reads." ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Aligned file in BAM format" ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '.bam')" ] ; sld:type cwl:File . cwl:in , , ; cwl:out , ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . rdfs:comment "SPP strand cross correlation plot" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Peak counts within replicate" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "-f {AUTO,BAM,SAM,BED,ELAND,ELANDMULTI,ELANDEXPORT,BOWTIE,BAMPE}, --format {AUTO,BAM,SAM,BED,ELAND,ELANDMULTI,ELANDEXPORT,BOWTIE,BAMPE} Format of tag file, \"AUTO\", \"BED\" or \"ELAND\" or \"ELANDMULTI\" or \"ELANDEXPORT\" or \"SAM\" or \"BAM\" or \"BOWTIE\" or \"BAMPE\". The default AUTO option will let MACS decide which format the file is. Note that MACS can't detect \"BAMPE\" or \"BEDPE\" format with \"AUTO\", and you have to implicitly specify the format for \"BAMPE\" and \"BEDPE\". DEFAULT: \"AUTO\"." ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-f" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-f" ] ; sld:type xsd:string , sld:null . rdfs:comment "Effective genome size. It can be 1.0e+9 or 1000000000, or shortcuts:'hs' for human (2.7e9), 'mm' for mouse (1.87e9), 'ce' for C. elegans (9e7) and 'dm' for fruitfly (1.2e8), Default:hs." ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-g" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-g" ] ; sld:type xsd:string , sld:null . cwl:valueFrom "${return true}" . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "save cross-correlation plot" ; cwl:inputBinding [ cwl:valueFrom "${ if (self) return \"-savp=\" + inputs.input_bam.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, \"\") + \".spp_cross_corr.pdf\"; return null}" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "FastQC data files for paired_read1" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "JVM arguments should be a quoted, space separated list (e.g. \"-Xms128m -Xmx512m\")" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:shellQuote false ] ; sld:type xsd:string , sld:null . cwl:valueFrom ".read_count.within_replicate.txt" . rdfs:comment "Read counts of the mapped BAM files" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "JVM arguments should be a quoted, space separated list (e.g. \"-Xms128m -Xmx512m\")" ; sld:type xsd:string , sld:null . rdfs:comment "Diff file between number of raw reads and number of reads counted by FASTQC, for paired_read2" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . a cwl:CommandLineTool ; ns1:original_cwlVersion "v1.2" ; cwl:arguments ( [ CommandLineBinding:position 3 ; cwl:valueFrom "$(inputs.input_basename + '.custom_adapters.fasta')" ] ) ; cwl:arguments ( [ CommandLineBinding:position 3 ; cwl:valueFrom "$(inputs.input_basename + '.custom_adapters.fasta')" ] ) ; cwl:baseCommand ( "overrepresented_sequence_extract.py" ) ; cwl:baseCommand ( "overrepresented_sequence_extract.py" ) ; cwl:cwlVersion ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/overrepresented_sequence_extract:1.0" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/overrepresented_sequence_extract:1.0" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:inputs , , ; cwl:outputs . cwl:source . cwl:outputBinding [ CommandOutputBinding:glob "stdout.txt" ] ; cwl:outputBinding [ CommandOutputBinding:glob "stdout.txt" ] ; sld:type cwl:File . rdfs:comment "Number of threads" ; cwl:default 1 ; cwl:inputBinding [ CommandLineBinding:position 4 ; CommandLineBinding:prefix "-threads" ] ; sld:type xsd:int . a cwl:CommandLineTool ; rdfs:comment "Extract mapped reads from BAM file using Samtools flagstat command" ; ns1:original_cwlVersion "v1.2" ; cwl:arguments ( [ CommandLineBinding:position 10000 ; CommandLineBinding:shellQuote false ; cwl:valueFrom " | head -n1 | cut -f 1 -d ' '" ] ) ; cwl:arguments ( [ CommandLineBinding:position 10000 ; CommandLineBinding:shellQuote false ; cwl:valueFrom " | head -n1 | cut -f 1 -d ' '" ] ) ; cwl:baseCommand ( "samtools" "flagstat" ) ; cwl:baseCommand ( "samtools" "flagstat" ) ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:inputs , ; cwl:outputs ; cwl:requirements [ a cwl:ShellCommandRequirement ] ; cwl:requirements [ a cwl:ShellCommandRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:stdout "$(inputs.input_bam_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, \"\") + inputs.output_suffix)" . cwl:source . cwl:in , , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . a cwl:CommandLineTool ; ns1:original_cwlVersion "v1.0" ; cwl:arguments ( [ CommandLineBinding:position 12 ; cwl:valueFrom "$(inputs.output_filename + '.sam')" ] ) ; cwl:baseCommand ( "bowtie" ) ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/bowtie" ] ; cwl:inputs , , , , , , , , , , , , , , , , ; cwl:outputs , ; cwl:requirements [ a cwl:ShellCommandRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:stderr "$(inputs.output_filename + '.bowtie.log')" . cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type xsd:string . rdfs:comment "peakshift/phantomPeak extended fragment results file using each paired mate independently" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . sld:type cwl:File . cwl:valueFrom "${return true}" . rdfs:comment "Indexed BAM file" ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_file.basename)" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_file.basename)" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_file.basename)" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_file.basename)" ] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; sld:type cwl:File . cwl:source . rdfs:comment "only include reads with none of the bits set in INT set in FLAG [0]" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-F" ] ; sld:type xsd:int , sld:null . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.bam.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, \"\") + '.bed')" ] ; sld:type cwl:File . cwl:in , , , , ; cwl:out , ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . rdfs:comment "Peak calling report file" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . a cwl:CommandLineTool ; rdfs:comment "Get number of processed reads from Bowtie log." ; ns1:original_cwlVersion "v1.0" ; cwl:baseCommand ( "percent-uniq-reads-from-preseq.sh" ) ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:ShellCommandRequirement ] ; cwl:stdout "$(inputs.preseq_c_curve_outfile.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, \"\") + '.percentage_unique_reads.txt')" . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.output_file_basename + '.preseq_c_curve.txt')" ] ; sld:type cwl:File . a cwl:CommandLineTool ; rdfs:comment "Tool: bedtools genomecov (aka genomeCoverageBed)\nVersion: v2.25.0\nSummary: Compute the coverage of a feature file among a genome.\n\nUsage: bedtools genomecov [OPTIONS] -i -g \n\nOptions: \n\t-ibam\t\tThe input file is in BAM format.\n\t\t\tNote: BAM _must_ be sorted by position\n\n\t-d\t\tReport the depth at each genome position (with one-based coordinates).\n\t\t\tDefault behavior is to report a histogram.\n\n\t-dz\t\tReport the depth at each genome position (with zero-based coordinates).\n\t\t\tReports only non-zero positions.\n\t\t\tDefault behavior is to report a histogram.\n\n\t-bg\t\tReport depth in BedGraph format. For details, see:\n\t\t\tgenome.ucsc.edu/goldenPath/help/bedgraph.html\n\n\t-bga\t\tReport depth in BedGraph format, as above (-bg).\n\t\t\tHowever with this option, regions with zero \n\t\t\tcoverage are also reported. This allows one to\n\t\t\tquickly extract all regions of a genome with 0 \n\t\t\tcoverage by applying: \"grep -w 0$\" to the output.\n\n\t-split\t\tTreat \"split\" BAM or BED12 entries as distinct BED intervals.\n\t\t\twhen computing coverage.\n\t\t\tFor BAM files, this uses the CIGAR \"N\" and \"D\" operations \n\t\t\tto infer the blocks for computing coverage.\n\t\t\tFor BED12 files, this uses the BlockCount, BlockStarts, and BlockEnds\n\t\t\tfields (i.e., columns 10,11,12).\n\n\t-strand\t\tCalculate coverage of intervals from a specific strand.\n\t\t\tWith BED files, requires at least 6 columns (strand is column 6). \n\t\t\t- (STRING): can be + or -\n\n\t-5\t\tCalculate coverage of 5\" positions (instead of entire interval).\n\n\t-3\t\tCalculate coverage of 3\" positions (instead of entire interval).\n\n\t-max\t\tCombine all positions with a depth >= max into\n\t\t\ta single bin in the histogram. Irrelevant\n\t\t\tfor -d and -bedGraph\n\t\t\t- (INTEGER)\n\n\t-scale\t\tScale the coverage by a constant factor.\n\t\t\tEach coverage value is multiplied by this factor before being reported.\n\t\t\tUseful for normalizing coverage by, e.g., reads per million (RPM).\n\t\t\t- Default is 1.0; i.e., unscaled.\n\t\t\t- (FLOAT)\n\n\t-trackline\tAdds a UCSC/Genome-Browser track line definition in the first line of the output.\n\t\t\t- See here for more details about track line definition:\n\t\t\t http://genome.ucsc.edu/goldenPath/help/bedgraph.html\n\t\t\t- NOTE: When adding a trackline definition, the output BedGraph can be easily\n\t\t\t uploaded to the Genome Browser as a custom track,\n\t\t\t BUT CAN NOT be converted into a BigWig file (w/o removing the first line).\n\n\t-trackopts\tWrites additional track line definition parameters in the first line.\n\t\t\t- Example:\n\t\t\t -trackopts 'name=\"My Track\" visibility=2 color=255,30,30'\n\t\t\t Note the use of single-quotes if you have spaces in your parameters.\n\t\t\t- (TEXT)\n\nNotes: \n\t(1) The genome file should tab delimited and structured as follows:\n\t \n\n\tFor example, Human (hg19):\n\tchr1\t249250621\n\tchr2\t243199373\n\t...\n\tchr18_gl000207_random\t4262\n\n\t(2) The input BED (-i) file must be grouped by chromosome.\n\t A simple \"sort -k 1,1 > .sorted\" will suffice.\n\n\t(3) The input BAM (-ibam) file must be sorted by position.\n\t A \"samtools sort \" should suffice.\n\nTips: \n\tOne can use the UCSC Genome Browser's MySQL database to extract\n\tchromosome sizes. For example, H. sapiens:\n\n\tmysql --user=genome --host=genome-mysql.cse.ucsc.edu -A -e \\\n\t\"select chrom, size from hg19.chromInfo\" > hg19.genome" ; ns1:original_cwlVersion "v1.2" ; cwl:baseCommand ( "bedtools" "genomecov" ) ; cwl:baseCommand ( "bedtools" "genomecov" ) ; cwl:cwlVersion ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/bedtools" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/bedtools" ] ; cwl:inputs , , , , , , , , , , , , , ; cwl:outputs ; cwl:requirements [ a cwl:ShellCommandRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:ShellCommandRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:stdout "$(inputs.ibam.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '.bdg')" . rdfs:comment "Aligned BAM file to filter" ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . rdfs:comment "If set, MACS will use a more sophisticated signal processing approach to find subpeak summits in each enriched peak region. DEFAULT: False " ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--call-summits" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--call-summits" ] ; sld:type xsd:boolean , sld:null . cwl:source . a cwl:CommandLineTool ; ns1:original_cwlVersion "v1.2" ; cwl:arguments ( [ CommandLineBinding:position 5 ; CommandLineBinding:prefix "--dir" ; cwl:valueFrom "$(runtime.tmpdir)" ] [ CommandLineBinding:position 5 ; CommandLineBinding:prefix "-o" ; cwl:valueFrom "$(runtime.outdir)" ] ) ; cwl:arguments ( [ CommandLineBinding:position 5 ; CommandLineBinding:prefix "--dir" ; cwl:valueFrom "$(runtime.tmpdir)" ] [ CommandLineBinding:position 5 ; CommandLineBinding:prefix "-o" ; cwl:valueFrom "$(runtime.outdir)" ] ) ; cwl:baseCommand ( "fastqc" ) ; cwl:baseCommand ( "fastqc" ) ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/fastqc" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/fastqc" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs , , , ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . cwl:source ; cwl:valueFrom "$([self])" . rdfs:comment "Filtered read count reported by MACS2 using each paired mate independently" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:default ".bb" ; sld:type xsd:string . a cwl:CommandLineTool ; ns1:original_cwlVersion "v1.0" ; cwl:baseCommand ( "bedtools" "bamtobed" ) ; cwl:cwlVersion ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/bedtools" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs , , , , , , , , , ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:stdout "$(inputs.bam.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, \"\") + '.bed')" . cwl:in , , ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:default ".clip" ; sld:type xsd:string . cwl:source . cwl:source . cwl:valueFrom "bam" . cwl:valueFrom "${return true}" . cwl:valueFrom "${return inputs.input_file.basename.replace('dups_marked', 'dedup')}" . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "Number of threads required for the 03-map step" ; sld:type xsd:int . cwl:valueFrom "BAMPE" . cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . rdfs:comment "File containing peak summits using each paired mate independently" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Suppress all alignments if > exist (def: 1)" ; cwl:default 1 ; cwl:inputBinding [ CommandLineBinding:position 7 ; CommandLineBinding:prefix "-m" ] ; sld:type xsd:int . rdfs:comment "Adds a UCSC/Genome-Browser track line definition in the first line of the output.\n- See here for more details about track line definition:\nhttp://genome.ucsc.edu/goldenPath/help/bedgraph.html\n- NOTE: When adding a trackline definition, the output BedGraph can be easily\nuploaded to the Genome Browser as a custom track,\nBUT CAN NOT be converted into a BigWig file (w/o removing the first line).\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-trackline" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-trackline" ] ; sld:type xsd:boolean , sld:null . cwl:default "\\t" ; cwl:inputBinding [ CommandLineBinding:position 2 ; CommandLineBinding:prefix "-F" ] ; cwl:inputBinding [ CommandLineBinding:position 2 ; CommandLineBinding:prefix "-F" ] ; sld:type xsd:string . cwl:source . a cwl:CommandLineTool ; rdfs:comment "Trunk scores in ENCODE bed6+4 files" ; ns1:original_cwlVersion "v1.2" ; cwl:arguments ( [ CommandLineBinding:position 3 ; cwl:valueFrom "BEGIN{OFS=FS}$5>1000{$5=1000}{print}" ] ) ; cwl:arguments ( [ CommandLineBinding:position 3 ; cwl:valueFrom "BEGIN{OFS=FS}$5>1000{$5=1000}{print}" ] ) ; cwl:baseCommand ( "awk" ) ; cwl:baseCommand ( "awk" ) ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:inputs , ; cwl:outputs ; cwl:stdout "$(inputs.peaks.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.([^/.]+)$/, \"\\.trunked_scores\\.$1\"))" . cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Use other NUMERIC BAM alignment tag for BED score.\n- Default for BED is to use mapping quality.\nDisallowed with BEDPE output.\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-tag" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "Trimmomatic Log file." ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.log_filename)" ] ; sld:type cwl:File , sld:null . rdfs:comment "Bowtie first index files for reference genome (e.g. *1.ebwt). The rest of the files should be in the same folder." ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; sld:type cwl:File . rdfs:comment "FastQC reports in zip format for paired_read1" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "INT \nInclude reads based on the SAM flag. For example, to\nget only reads that are the first mate, use a flag of\n64. This is useful to count properly paired reads only\nonce, as otherwise the second mate will be also\nconsidered for the coverage. (default: None)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--samFlagInclude" ] ; sld:type xsd:int , sld:null . rdfs:comment "Reads peak counts within replicate" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "INT bp\nThis parameter allows the extension of reads to\nfragment size. If set, each read is extended, without\nexception. *NOTE*: This feature is generally NOT\nrecommended for spliced-read data, such as RNA-seq, as\nit would extend reads over skipped regions. *Single-\nend*: Requires a user specified value for the final\nfragment length. Reads that already exceed this\nfragment length will not be extended. *Paired-end*:\nReads with mates are always extended to match the\nfragment size defined by the two read mates. Unmated\nreads, mate reads that map too far apart (>4x fragment\nlength) or even map to different chromosomes are\ntreated like single-end reads. The input of a fragment\nlength value is optional. If no value is specified, it\nis estimated from the data (mean of the fragment size\nof all mate reads). (default: False)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--extendReads" ] ; sld:type xsd:int , sld:null . rdfs:comment "PCR Bottleneck Coefficient files (used to flag samples when pbc<0.5)" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "When set, random sampling method will scale down the bigger sample. By default, MACS uses linear scaling. Warning: This option will make your result unstable and irreproducible since each time, random reads would be selected. Consider to use 'randsample' script instead. If used together with --SPMR, 1 million unique reads will be randomly picked. Caution: due to the implementation, the final number of selected reads may not be as you expected! DEFAULT: False " ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--down-sample" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--down-sample" ] ; sld:type xsd:boolean , sld:null . cwl:source . cwl:outputBinding [ CommandOutputBinding:glob "${\n if (inputs.end_mode == \"PE\" && inputs.input_read2_fastq_file)\n return inputs.input_read2_fastq_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '.unpaired.trimmed.fastq';\n return null;\n}\n" ] ; sld:type cwl:File , sld:null . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . rdfs:comment "\tCombine all positions with a depth >= max into\na single bin in the histogram. Irrelevant\nfor -d and -bedGraph\n- (INTEGER)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-max" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-max" ] ; sld:type xsd:int , sld:null . rdfs:comment "\"33\"|\"64\"\n-phred33 (\"33\") or -phred64 (\"64\") specifies the base quality encoding. Default: -phred64\n" ; cwl:default "64" ; cwl:inputBinding [ CommandLineBinding:position 4 ; CommandLineBinding:prefix "-phred" ; CommandLineBinding:separate false ] ; sld:type xsd:string . a cwl:CommandLineTool ; rdfs:comment "Extracts the base name of a file" ; ns1:original_cwlVersion "v1.2" ; cwl:baseCommand ( "echo" ) ; cwl:baseCommand ( "echo" ) ; cwl:baseCommand ( "echo" ) ; cwl:baseCommand ( "echo" ) ; cwl:baseCommand ( "echo" ) ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . a cwl:Workflow ; rdfs:comment "ATAC-seq - Quantification" ; ns1:original_cwlVersion "v1.0" ; Workflow:steps , , , ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:inputs , , ; cwl:outputs , ; cwl:requirements [ a cwl:StepInputExpressionRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:ScatterFeatureRequirement ] . cwl:source . rdfs:comment "If True, MACS will use fixed background lambda as local lambda for every peak region. Normally, MACS calculates a dynamic local lambda to reflect the local bias due to potential chromatin structure. " ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--nolambda" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--nolambda" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "-type=bedN[+[P]] :\n N is between 3 and 15,\n optional (+) if extra \"bedPlus\" fields,\n optional P specifies the number of extra fields. Not required, but preferred.\n Examples: -type=bed6 or -type=bed6+ or -type=bed6+3\n (see http://genome.ucsc.edu/FAQ/FAQformat.html#format1)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-type=" ; CommandLineBinding:separate false ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-type=" ; CommandLineBinding:separate false ] ; sld:type xsd:string , sld:null . rdfs:comment "overwrite (force remove) output files in case they exist. Default: true" ; cwl:default true ; cwl:inputBinding [ CommandLineBinding:prefix "-rf" ] ; sld:type xsd:boolean . rdfs:comment "Hits guaranteed best stratum; ties broken by quality" ; cwl:default true ; cwl:inputBinding [ CommandLineBinding:position 5 ; CommandLineBinding:prefix "--best" ] ; sld:type xsd:boolean . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.preseq_c_curve_outfile.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, \"\") + '.percentage_unique_reads.txt')" ] ; sld:type cwl:File . rdfs:comment "One or more input SAM or BAM files to analyze. Must be coordinate sorted." ; cwl:inputBinding [ CommandLineBinding:position 4 ; CommandLineBinding:shellQuote false ; cwl:valueFrom "$('INPUT=' + self.path)" ] ; sld:type cwl:File . cwl:source . a cwl:CommandLineTool ; rdfs:comment "Concat file1 and file2 into output_file." ; ns1:original_cwlVersion "v1.0" ; cwl:baseCommand ( "cat" ) ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:inputs , ; cwl:outputs ; cwl:stdout "$(inputs.input_file1.path.replace(/.*\\/|\\.[^.]*$/g, \"\") + \"_\" + inputs.input_file2.path.replace(/.*\\/|\\.[^.]*$/g, \"\") + \".joined\")" . cwl:source . rdfs:comment "Query input FASTQ file." ; cwl:inputBinding [ CommandLineBinding:position 10 ; CommandLineBinding:prefix "-1" ] ; sld:type cwl:File . rdfs:comment "\tReport depth in BedGraph format. For details, see:\ngenome.ucsc.edu/goldenPath/help/bedgraph.html\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-bg" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-bg" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "" ; cwl:inputBinding [ CommandLineBinding:position 3 ; CommandLineBinding:prefix "-g" ] ; cwl:inputBinding [ CommandLineBinding:position 3 ; CommandLineBinding:prefix "-g" ] ; sld:type cwl:File . rdfs:comment "show program's version number and exit" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--version" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "trim bases from 5' (left) end of reads" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--trim5" ] ; sld:type xsd:int , sld:null . cwl:valueFrom "${return 0.1}" . rdfs:comment "seed length for -n (default: 28)" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--seedlen" ] ; sld:type xsd:int , sld:null . rdfs:comment "This (re)encodes the quality part of the FASTQ file to base 64." ; cwl:inputBinding [ CommandLineBinding:position 12 ; CommandLineBinding:prefix "TOPHRED64" ; CommandLineBinding:separate false ] ; sld:type xsd:boolean , sld:null . rdfs:comment "Sorted bed or BAM file" ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; sld:type cwl:File . rdfs:comment "Picard Java jar file" ; sld:type xsd:string . cwl:source . cwl:inputBinding [ CommandLineBinding:position 2 ] ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; sld:type cwl:File . cwl:source . rdfs:comment "FastQC reports in zip format for paired_read2" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Bedgraph with extended fragment pileup." ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.treatment[0].path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '_treat_pileup.bdg')" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.treatment[0].path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '_treat_pileup.bdg')" ] ; sld:type cwl:File , sld:null . cwl:source . cwl:source . cwl:source . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "Pvalue cutoff for peak detection. DEFAULT: not set. -q, and -p are mutually exclusive. If pvalue cutoff is set, qvalue will not be calculated and reported as -1 in the final .xls file.." ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-p" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-p" ] ; sld:type xsd:float , sld:null . rdfs:comment "Number of threads used in sorting" ; cwl:default 1 ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-@" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-@" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-@" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-@" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-@" ] ; sld:type xsd:int . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . rdfs:comment "peakshift/phantomPeak extended fragment results file" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Filtered BAM files (post-processing end point)" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . a cwl:CommandLineTool ; rdfs:comment "Extracts read count from fastqc_data.txt" ; ns1:original_cwlVersion "v1.2" ; cwl:baseCommand ( "count-fastqc_data-reads.sh" ) ; cwl:baseCommand ( "count-fastqc_data-reads.sh" ) ; cwl:cwlVersion ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs , ; cwl:outputs ; cwl:stdout "$(inputs.input_basename + '.fastqc-read_count.txt')" . a cwl:Workflow ; rdfs:comment "ChIP-seq - map - PCR Bottleneck Coefficients" ; ns1:original_cwlVersion "v1.0" ; Workflow:steps , ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:inputs , , ; cwl:outputs ; cwl:requirements [ a cwl:ScatterFeatureRequirement ] . rdfs:comment "Idxstats output file. TAB-delimited with each line consisting of reference\nsequence name, sequence length, # mapped reads and # unmapped reads\n" ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.bam.basename + \".idxstats\")" ] ; sld:type cwl:File . rdfs:comment "Suffix used to identify the output file (Default: dedup.bam)" ; cwl:default "dedup.bam" ; sld:type xsd:string . rdfs:comment "--skipNonCoveredRegions, --skipNAs\nThis parameter determines if non-covered regions\n(regions without overlapping reads) in a BAM file\nshould be skipped. The default is to treat those\nregions as having a value of zero. The decision to\nskip non-covered regions depends on the interpretation\nof the data. Non-covered regions may represent, for\nexample, repetitive regions that should be skipped.\n(default: False)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--skipNonCoveredRegions" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "peakshift/phantomPeak results summary file" ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_bam.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, \"\") + \".spp_cross_corr.txt\")" ] ; sld:type cwl:File . rdfs:comment "peakshift/phantomPeak results file using each paired mate independently" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Aligned file in SAM or BAM format" ; cwl:outputBinding [ CommandOutputBinding:glob "${\n if (inputs.outfile_name) return inputs.outfile_name;\n var suffix = inputs.b ? '.bam' : '.sam';\n suffix = inputs.suffix || suffix;\n return inputs.input_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + suffix\n}\n" ] ; sld:type cwl:File . a cwl:CommandLineTool ; rdfs:comment "\"Tool: bedClip - Remove lines from bed file that refer to off-chromosome places.\nusage:\n bedClip input.bed chrom.sizes output.bed\nchrom.sizes is a two-column file/URL: \nIf the assembly is hosted by UCSC, chrom.sizes can be a URL like\n http://hgdownload.cse.ucsc.edu/goldenPath//bigZips/.chrom.sizes\nor you may use the script fetchChromSizes to download the chrom.sizes file.\nIf not hosted by UCSC, a chrom.sizes file can be generated by running\ntwoBitInfo on the assembly .2bit file.\noptions:\n -verbose=2 - set to get list of lines clipped and why\"\n" ; ns1:original_cwlVersion "v1.0" ; cwl:arguments ( [ CommandLineBinding:position 3 ; cwl:valueFrom "$(inputs.bed_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, \"\") + inputs.output_suffix)" ] ) ; cwl:baseCommand ( "bedClip" ) ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dleehr/docker-hubutils" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs , , ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . rdfs:comment "-npeak=, threshold on number of peaks to call" ; cwl:inputBinding [ CommandLineBinding:prefix "-npeak=" ; CommandLineBinding:separate false ] ; sld:type xsd:int , sld:null . a cwl:CommandLineTool ; rdfs:comment "\"bedToBigBed v. 2.7 - Convert bed file to bigBed. (BigBed version: 4)\nusage:\n bedToBigBed in.bed chrom.sizes out.bb\nWhere in.bed is in one of the ascii bed formats, but not including track lines\nand chrom.sizes is two column: \nand out.bb is the output indexed big bed file.\nUse the script: fetchChromSizes to obtain the actual chrom.sizes information\nfrom UCSC, please do not make up a chrom sizes from your own information.\nThe in.bed file must be sorted by chromosome,start,\n to sort a bed file, use the unix sort command:\n sort -k1,1 -k2,2n unsorted.bed > sorted.bed\"\n" ; ns1:original_cwlVersion "v1.2" ; cwl:arguments ( [ CommandLineBinding:position 4 ; cwl:valueFrom "$(inputs.bed.path.replace(/^.*[\\\\\\/]/, '') + inputs.output_suffix)" ] ) ; cwl:arguments ( [ CommandLineBinding:position 4 ; cwl:valueFrom "$(inputs.bed.path.replace(/^.*[\\\\\\/]/, '') + inputs.output_suffix)" ] ) ; cwl:baseCommand ( "bedToBigBed" ) ; cwl:baseCommand ( "bedToBigBed" ) ; cwl:cwlVersion ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dleehr/docker-hubutils" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dleehr/docker-hubutils" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:inputs , , , , , , , , , ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . cwl:source . rdfs:comment "peakshift/phantomPeak results summary plot" ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_bam.path.replace(/^.*[\\\\\\/]/, \"\").replace(/\\.[^/.]+$/, \"\") + \".spp_cross_corr.pdf\")" ] ; sld:type cwl:File , sld:null . cwl:inputBinding [] ; sld:type cwl:File . rdfs:comment "Peaks summits bedfile." ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.treatment[0].path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '_summits.bed')" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.treatment[0].path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '_summits.bed')" ] ; sld:type cwl:File , sld:null . cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:valueFrom ".raw.bw" . cwl:valueFrom ".narrowPeak" . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . a cwl:Workflow ; rdfs:comment "ATAC-seq 04 quantification - PE" ; ns1:original_cwlVersion "v1.0" ; Workflow:steps , , , , , , , , , , , , , , , , , , ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs , , , , ; cwl:outputs , , , , , , , , , , , , , , , , ; cwl:requirements [ a cwl:ScatterFeatureRequirement ] ; cwl:requirements [ a cwl:StepInputExpressionRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . rdfs:comment "FASTQ file for input read (read R1 in Paired End mode)" ; cwl:inputBinding [ CommandLineBinding:position 5 ] ; sld:type cwl:File . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "only include reads with mapping quality >= INT [0]" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-q" ] ; sld:type xsd:int , sld:null . rdfs:comment "Query input FASTQ file." ; cwl:inputBinding [ CommandLineBinding:position 11 ; CommandLineBinding:prefix "-2" ] ; sld:type cwl:File . rdfs:comment "Adapters file" ; sld:type cwl:File . rdfs:comment "Definition narrowPeak file in AutoSql format (used in bedToBigBed)" ; sld:type cwl:File . rdfs:comment "Extended fragment peaks in ENCODE Peak file format" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Read counts of the mapped BAM files" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "\tgenome_sizes is two column: .\n" ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; sld:type cwl:File . cwl:inputBinding [ CommandLineBinding:position 4 ] ; cwl:inputBinding [ CommandLineBinding:position 4 ] ; sld:type cwl:File . rdfs:comment "Bed file to be clipped" ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:source . cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . rdfs:comment "RATIO When set, use a custom scaling ratio of ChIP/control\n(e.g. calculated using NCIS) for linear scaling.\nDEFAULT: ingore\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--ratio" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--ratio" ] ; sld:type xsd:float , sld:null . a cwl:CommandLineTool ; rdfs:comment "Compares 2 files" ; ns1:original_cwlVersion "v1.2" ; cwl:baseCommand ( "diff" ) ; cwl:baseCommand ( "diff" ) ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "reddylab/workflow-utils:ggr" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:inputs , , ; cwl:outputs ; cwl:stdout "stdout.txt" . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.bed.path.replace(/^.*[\\\\\\/]/, '')+ inputs.output_suffix)" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.bed.path.replace(/^.*[\\\\\\/]/, '')+ inputs.output_suffix)" ] ; sld:type cwl:File . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . rdfs:comment "Raw read counts of fastq files for paired_read2 after QC" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.bed_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, \"\") + inputs.output_suffix)" ] ; sld:type cwl:File . a cwl:CommandLineTool ; ns1:original_cwlVersion "v1.0" ; cwl:baseCommand ( "samtools" "view" "-b" ) ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools:1.3" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs , , ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:stdout "$(inputs.input_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '.bam')" . cwl:valueFrom "${return true}" . cwl:source . cwl:source . sld:type xsd:string . cwl:source . rdfs:comment "-verbose print more information \n" ; cwl:default false ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-v" ] ; sld:type xsd:boolean . rdfs:comment "Peak counts within replicate using each paired mate independently" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . rdfs:comment ":\nPerform a sliding window trimming, cutting once the average quality within the window falls\nbelow a threshold. By considering multiple bases, a single poor quality base will not cause the\nremoval of high quality data later in the read.\n: specifies the number of bases to average across\n: specifies the average quality required\n" ; cwl:inputBinding [ CommandLineBinding:position 15 ; CommandLineBinding:prefix "SLIDINGWINDOW:" ; CommandLineBinding:separate false ] ; sld:type xsd:string , sld:null . cwl:default true ; cwl:inputBinding [ CommandLineBinding:position 3 ; CommandLineBinding:prefix "--brief" ] ; cwl:inputBinding [ CommandLineBinding:position 3 ; CommandLineBinding:prefix "--brief" ] ; sld:type xsd:boolean . rdfs:comment "Diff file between number of raw reads and number of reads counted by FASTQC, for paired_read1" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "\tTreat \"split\" BAM or BED12 entries as distinct BED intervals.\nwhen computing coverage.\nFor BAM files, this uses the CIGAR \"N\" and \"D\" operations\nto infer the blocks for computing coverage.\nFor BED12 files, this uses the BlockCount, BlockStarts, and BlockEnds\nfields (i.e., columns 10,11,12).\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-split" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-split" ] ; sld:type xsd:boolean , sld:null . cwl:in , , , , , , , , , , , , ; cwl:out , ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . cwl:valueFrom ".peak_count.within_replicate.txt" . rdfs:comment ":::::\nFind and remove Illumina adapters.\nREQUIRED:\n: specifies the path to a fasta file containing all the adapters, PCR sequences etc.\nThe naming of the various sequences within this file determines how they are used. See below.\n: specifies the maximum mismatch count which will still allow a full match to be performed\n: specifies how accurate the match between the two 'adapter ligated' reads must be\nfor PE palindrome read alignment.\n: specifies how accurate the match between any adapter etc. sequence must be against a read\nOPTIONAL:\n: In addition to the alignment score, palindrome mode can verify\nthat a minimum length of adapter has been detected. If unspecified, this defaults to 8 bases,\nfor historical reasons. However, since palindrome mode has a very low false positive rate, this\ncan be safely reduced, even down to 1, to allow shorter adapter fragments to be removed.\n: After read-though has been detected by palindrome mode, and the\nadapter sequence removed, the reverse read contains the same sequence information as the\nforward read, albeit in reverse complement. For this reason, the default behaviour is to\nentirely drop the reverse read. By specifying \"true\" for this parameter, the reverse read will\nalso be retained, which may be useful e.g. if the downstream tools cannot handle a\ncombination of paired and unpaired reads.\n" ; sld:type xsd:string . rdfs:comment "Output filename used as basename" ; sld:type xsd:string . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "Report end-to-end hits w/ <=v mismatches; ignore qualities" ; cwl:default 2 ; cwl:inputBinding [ CommandLineBinding:position 3 ; CommandLineBinding:prefix "-v" ] ; sld:type xsd:int , sld:null . a cwl:CommandLineTool ; rdfs:comment "Unzips a zipped fastqc report and returns the fastqc_data.txt file. Unzips the file to pipe and uses redirection" ; ns1:original_cwlVersion "v1.2" ; cwl:baseCommand ( "unzip" ) ; cwl:baseCommand ( "unzip" ) ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/fastqc" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/fastqc" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs , , , ; cwl:outputs ; cwl:stdout "$(inputs.input_basename + '.fastqc_data.txt')" . a cwl:CommandLineTool ; ns1:original_cwlVersion "v1.0" ; cwl:baseCommand ( "samtools" "view" ) ; cwl:cwlVersion ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools:1.3" ] ; cwl:inputs , , , , , , , , , , , ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:stdout "${\n if (inputs.outfile_name) return inputs.outfile_name;\n var suffix = inputs.b ? '.bam' : '.sam';\n suffix = inputs.suffix || suffix;\n return inputs.input_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + suffix\n}\n" . cwl:source . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "Basename for the output file" ; sld:type xsd:string . rdfs:comment "Input read1 fastq files" ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:valueFrom "PE" . cwl:valueFrom "${return 0.1}" . rdfs:comment "Input read2 fastq files" ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "-as=fields.as - If you have non-standard \"bedPlus\" fields, it's great to put a definition\n of each field in a row in AutoSql format here.1)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-as=" ; CommandLineBinding:separate false ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-as=" ; CommandLineBinding:separate false ] ; sld:type cwl:File , sld:null . rdfs:comment "-blockSize=N - Number of items to bundle in r-tree. Default 256\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-blockSize=" ; CommandLineBinding:separate false ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-blockSize=" ; CommandLineBinding:separate false ] ; sld:type xsd:int , sld:null . cwl:source . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_file.path.replace(/^.*[\\\\\\/]/, '') + inputs.output_suffix)" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_file.path.replace(/^.*[\\\\\\/]/, '') + inputs.output_suffix)" ] ; sld:type cwl:File . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "FASTQ files for paired_read2 after trimming" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Two column tab-delimited file with chromosome size information" ; sld:type cwl:File . rdfs:comment "Adapters file in fasta format" ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; sld:type cwl:File . rdfs:comment "Suffix used for output file (input BAM filename + suffix)" ; sld:type xsd:string , sld:null . cwl:in , , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . cwl:source . cwl:source . rdfs:comment "Samtools Flagstat report file" ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_bam_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, \"\") + inputs.output_suffix)" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_bam_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, \"\") + inputs.output_suffix)" ] ; sld:type cwl:File . a cwl:CommandLineTool ; ns1:original_cwlVersion "v1.2" ; cwl:arguments ( [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-n" ; cwl:valueFrom "$(inputs.treatment[0].path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, ''))" ] ) ; cwl:arguments ( [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-n" ; cwl:valueFrom "$(inputs.treatment[0].path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, ''))" ] ) ; cwl:baseCommand ( "macs2" "callpeak" ) ; cwl:baseCommand ( "macs2" "callpeak" ) ; cwl:cwlVersion ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/macs2" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/macs2" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ; cwl:outputs , , , ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . rdfs:comment "Whether or not to save extended fragment pileup, and local lambda tracks (two files) at every bp into a bedGraph file. DEFAULT: True" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--bdg" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--bdg" ] ; sld:type xsd:boolean , sld:null . cwl:source . rdfs:comment "Input BAM file to be converted to BED format" ; cwl:inputBinding [ CommandLineBinding:position 3 ; CommandLineBinding:prefix "-i" ] ; sld:type cwl:File . sld:type xsd:string . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "While set, MACS2 will analyze number or total length of peaks that can be called by different p-value cutoff then output a summary table to help user decide a better cutoff. The table will be saved in NAME_cutoff_analysis.txt file. Note, minlen and maxgap may affect the results. WARNING: May take ~30 folds longer time to finish. DEFAULT: False Post-processing options: " ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--cutoff-analysis" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--cutoff-analysis" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "Trimmomatic Java jar file" ; cwl:default "/usr/share/java/trimmomatic.jar" ; sld:type xsd:string . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . rdfs:comment "Add the CIGAR string to the BED entry as a 7th column.\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-cigar" ] ; sld:type xsd:string , sld:null . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.output_filename + '.PBC.txt')" ] ; sld:type cwl:File . rdfs:comment "-seg_len maximum segment length when merging paired end bam reads \n(default: 5000)\nHelp options:\n-?, -help print this help message\n-about print about message\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-l" ] ; sld:type xsd:int , sld:null . cwl:source . rdfs:comment "Filtered aligned BAM file by BED coordinates file" ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_bam_file.path.replace(/^.*[\\\\\\/]/, '') + '.in_peaks.bam')" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_bam_file.path.replace(/^.*[\\\\\\/]/, '') + '.in_peaks.bam')" ] ; sld:type cwl:File . rdfs:comment "Bed or bedGraph file to be sorted" ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . rdfs:comment "Write BEDPE format.\n- Requires BAM to be grouped or sorted by query.\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-bedpe" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "Query chromosome used to calculate percentage" ; sld:type xsd:string . rdfs:comment "output BAM" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-b" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "Preseq percentage of uniq reads" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "\tCalculate coverage of intervals from a specific strand.\nWith BED files, requires at least 6 columns (strand is column 6).\n- (STRING): can be + or -\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-strand" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-strand" ] ; sld:type xsd:string , sld:null . cwl:in , , , , , , , ; cwl:out , , , ; cwl:run ; cwl:scatter ( ) . cwl:default 1 ; sld:type xsd:int . cwl:valueFrom "${return 3}" . cwl:source . rdfs:comment "Input adapters files for paired_read1" ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:valueFrom "BED" . cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "The smooth length defines a window, larger than the\nbinSize, to average the number of reads. For example,\nif the –binSize is set to 20 and the –smoothLength is\nset to 60, then, for each bin, the average of the bin\nand its left and right neighbors is considered.\nAny value smaller than –binSize will be ignored and\nno smoothing will be applied. (default: 1.0)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--scaleFactor" ] ; sld:type xsd:float , sld:null . cwl:source . cwl:valueFrom "bed6+4" . rdfs:comment "-filtchr= , Pattern to use to remove tags that map to specific chromosomes e.g. _ will remove all tags that map to chromosomes with _ in their name" ; cwl:inputBinding [ CommandLineBinding:prefix "-filtchr=" ; CommandLineBinding:separate false ] ; sld:type xsd:string , sld:null . rdfs:comment "peakshift/phantomPeak results file using each paired mate independently" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . cwl:source . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) . sld:type [ sld:items xsd:string ; sld:type sld:array ] . cwl:source . rdfs:comment "Output file name. If not specified, the basename of the input file with the suffix specified in the suffix argument will be used." ; sld:type xsd:string , sld:null . cwl:source . rdfs:comment "Input fastq paired-end read 2 files" ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Number of threads used in sorting" ; cwl:default 1 ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-@" ] ; sld:type xsd:int . cwl:source . sld:type [ sld:items cwl:File ; sld:type sld:array ] . a cwl:CommandLineTool ; ns1:original_cwlVersion "v1.2" ; cwl:arguments ( [ CommandLineBinding:position 2 ; cwl:valueFrom "$(inputs.input_file.basename + '.bai')" ] ) ; cwl:arguments ( [ CommandLineBinding:position 2 ; cwl:valueFrom "$(inputs.input_file.basename + '.bai')" ] ) ; cwl:arguments ( [ CommandLineBinding:position 2 ; cwl:valueFrom "$(inputs.input_file.basename + '.bai')" ] ) ; cwl:arguments ( [ CommandLineBinding:position 2 ; cwl:valueFrom "$(inputs.input_file.basename + '.bai')" ] ) ; cwl:baseCommand ( "samtools" "index" ) ; cwl:baseCommand ( "samtools" "index" ) ; cwl:baseCommand ( "samtools" "index" ) ; cwl:baseCommand ( "samtools" "index" ) ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools:1.3" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools:1.3" ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools:1.3" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/samtools:1.3" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InitialWorkDirRequirement ; cwl:listing "$(inputs.input_file)" ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InitialWorkDirRequirement ; cwl:listing "$(inputs.input_file)" ] ; cwl:requirements [ a cwl:InitialWorkDirRequirement ; cwl:listing "$(inputs.input_file)" ] ; cwl:requirements [ a cwl:InitialWorkDirRequirement ; cwl:listing "$(inputs.input_file)" ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_basename + '.custom_adapters.fasta')" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_basename + '.custom_adapters.fasta')" ] ; sld:type cwl:File . rdfs:comment "When set, scale the small sample up to the bigger sample. By default, the bigger dataset will be scaled down towards the smaller dataset, which will lead to smaller p/qvalues and more specific results. Keep in mind that scaling down will bring down background noise more. DEFAULT: False " ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--to-large" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--to-large" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "max mismatches in seed (between [0, 3], default: 2)" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--seedmms" ] ; sld:type xsd:int , sld:null . cwl:source . rdfs:comment "If true do not write duplicates to the output file instead of writing them with appropriate flags set. (Default false)." ; cwl:default false ; cwl:inputBinding [ CommandLineBinding:position 5 ; cwl:valueFrom "$('REMOVE_DUPLICATES=' + self)" ] ; sld:type xsd:boolean . cwl:source . a cwl:CommandLineTool ; rdfs:comment "Trimmomatic is a fast, multithreaded command line tool that can be used to trim and crop\nIllumina (FASTQ) data as well as to remove adapters. These adapters can pose a real problem\ndepending on the library preparation and downstream application.\nThere are two major modes of the program: Paired end mode and Single end mode. The\npaired end mode will maintain correspondence of read pairs and also use the additional\ninformation contained in paired reads to better find adapter or PCR primer fragments\nintroduced by the library preparation process.\nTrimmomatic works with FASTQ files (using phred + 33 or phred + 64 quality scores,\ndepending on the Illumina pipeline used).\n" ; ns1:original_cwlVersion "v1.0" ; cwl:arguments ( [ CommandLineBinding:position 1 ; CommandLineBinding:shellQuote false ; cwl:valueFrom "$(\"-Djava.io.tmpdir=\"+runtime.tmpdir)" ] [ CommandLineBinding:position 7 ; cwl:valueFrom "$(inputs.input_read1_fastq_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '.trimmed.fastq')" ] [ CommandLineBinding:position 8 ; cwl:valueFrom "${\n if (inputs.end_mode == \"PE\" && inputs.input_read2_fastq_file)\n return inputs.input_read1_fastq_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '.trimmed.unpaired.fastq';\n return null;\n}\n" ] [ CommandLineBinding:position 9 ; cwl:valueFrom "${\n if (inputs.end_mode == \"PE\" && inputs.input_read2_fastq_file)\n return inputs.input_read2_fastq_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '.trimmed.fastq';\n return null;\n}\n" ] [ CommandLineBinding:position 10 ; cwl:valueFrom "${\n if (inputs.end_mode == \"PE\" && inputs.input_read2_fastq_file)\n return inputs.input_read2_fastq_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '.trimmed.unpaired.fastq';\n return null;\n}\n" ] [ CommandLineBinding:position 11 ; cwl:valueFrom "$(\"ILLUMINACLIP:\" + inputs.input_adapters_file.path + \":\"+ inputs.illuminaclip)" ] ) ; cwl:baseCommand ( "java" ) ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:hints [ a cwl:DockerRequirement ; DockerRequirement:dockerPull "dukegcb/trimmomatic" ] ; cwl:inputs , , , , , , , , , , , , , , , , , , , ; cwl:outputs , , , , ; cwl:requirements [ a cwl:ShellCommandRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . rdfs:comment "File to be converted to BAM with samtools" ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; sld:type cwl:File . rdfs:comment "Bedfile used to only include reads overlapping this BED FILE" ; cwl:inputBinding [ CommandLineBinding:position 2 ; CommandLineBinding:prefix "-L" ] ; cwl:inputBinding [ CommandLineBinding:position 2 ; CommandLineBinding:prefix "-L" ] ; sld:type cwl:File . rdfs:comment "\nThis module removes reads that fall below the specified minimal length. If required, it should\nnormally be after all other processing steps. Reads removed by this step will be counted and\nincluded in the \"dropped reads\" count presented in the trimmomatic summary.\n: Specifies the minimum length of reads to be kept\n" ; cwl:inputBinding [ CommandLineBinding:position 100 ; CommandLineBinding:prefix "MINLEN:" ; CommandLineBinding:separate false ] ; sld:type xsd:int , sld:null . rdfs:comment "FastQC reports in zip format for paired_read1" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . cwl:source . rdfs:comment "BW Band width for picking regions to compute fragment\nsize. This value is only used while building the\nshifting model. DEFAULT: 300\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--bw" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--bw" ] ; sld:type xsd:int , sld:null . rdfs:comment "Input fastq files for paired_read1" ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:source ; cwl:valueFrom "$([self])" . a cwl:Workflow ; rdfs:comment "ATAC-seq pipeline - reads: PE" ; ns1:original_cwlVersion "v1.0" ; Workflow:steps , , , , ; cwl:cwlVersion ; cwl:hints [ a ; LoadListingRequirement:loadListing "deep_listing" ] ; cwl:hints [ a ; NetworkAccess:networkAccess true ] ; cwl:inputs , , , , , , , , , , , , , , , ; cwl:outputs , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ; cwl:requirements [ a cwl:ScatterFeatureRequirement ] ; cwl:requirements [ a cwl:StepInputExpressionRequirement ] ; cwl:requirements [ a cwl:SubworkflowFeatureRequirement ] . rdfs:comment "Input fastq files for paired_read2" ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Input format autodetected" ; cwl:default true ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-S" ] ; sld:type xsd:boolean . rdfs:comment "Name of the sample - used as a base name for generating output files" ; sld:type xsd:string . cwl:in , , , , , , ; cwl:out , ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . rdfs:comment "uncompressed BAM output (implies -b)" ; cwl:default true ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-u" ] ; sld:type xsd:boolean . rdfs:comment "INT\nIf set, only reads that have a mapping quality score\nof at least this are considered. (default: None)\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--minMappingQuality" ] ; sld:type xsd:int , sld:null . rdfs:comment "Bowtie log file with mapping stats" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.bedpe.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '').replace(/([_\\.]?sorted)*$/, '.unpaired.bed'))" ] ; sld:type cwl:File . sld:type cwl:File . rdfs:comment "\nSpecifying a trimlog file creates a log of all read trimmings, indicating the following details:\n the read name\n the surviving sequence length\n the location of the first surviving base, aka. the amount trimmed from the start\n the location of the last surviving base in the original read\n the amount trimmed from the end\n: filename for the generated output log file.\n" ; cwl:inputBinding [ CommandLineBinding:position 4 ; CommandLineBinding:prefix "-trimlog" ] ; sld:type xsd:string , sld:null . cwl:source . cwl:source . cwl:source . cwl:source . rdfs:comment "Raw reads bigWig (signal) files" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "Filtered read count reported by MACS2" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:valueFrom "${return true}" . rdfs:comment "peakshift/phantomPeak results file" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatterMethod ScatterMethod:dotproduct . rdfs:comment "Number of threads." ; sld:type xsd:int . sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "When writing BEDPE (-bedpe) format, \nalways report mate one as the first BEDPE \"block\".\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-mate1" ] ; sld:type xsd:boolean , sld:null . rdfs:comment "Trimmed fastq files for paired_read2" ; cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:comment "\tbed_graph is a four column file in the format: \n" ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:source . cwl:outputSource ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:source . cwl:source . cwl:in , , ; cwl:out , ; cwl:run . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.input_read1_fastq_file.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.[^/.]+$/, '') + '.trimmed.fastq')" ] ; sld:type cwl:File . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.peaks.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.([^/.]+)$/, \"\\.trunked_scores\\.$1\"))" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.peaks.path.replace(/^.*[\\\\\\/]/, '').replace(/\\.([^/.]+)$/, \"\\.trunked_scores\\.$1\"))" ] ; sld:type cwl:File .