@prefix LoadListingRequirement: .
@prefix CommandLineBinding: .
@prefix xsd: .
@prefix DockerRequirement: .
@prefix Workflow: .
@prefix InlineJavascriptRequirement: .
@prefix sld: .
@prefix rdfs: .
@prefix CommandOutputBinding: .
@prefix ns2: .
@prefix ns1: .
@prefix NetworkAccess: .
@prefix rdf: .
@prefix cwl: .
rdfs:comment "Optional parameter to calculate scale as 1000000/mapped_reads_number if inputs.scale is not provided\n" ;
cwl:inputBinding [ CommandLineBinding:position 7 ;
CommandLineBinding:prefix "-scale" ;
cwl:valueFrom "${\n if (inputs.scale){\n return null;\n } else if (inputs.mapped_reads_number) {\n return 1000000/inputs.mapped_reads_number;\n } else {\n return null;\n }\n}\n"
] ;
sld:type xsd:int , sld:null .
rdfs:comment "Bash function to run samtools index with all input parameters or skip it if trigger is false\n" ;
cwl:default "#!/bin/bash\nif [ \"$0\" = \"true\" ]\nthen\n echo \"Run: samtools index \" ${@:1}\n samtools index \"${@:1}\"\nelse\n echo \"Skip samtools index \" ${@:1}\nfi\n" ;
cwl:inputBinding [ CommandLineBinding:position
20 ] ;
sld:type xsd:string , sld:null .
cwl:outputBinding [ CommandOutputBinding:glob
"*" ] ;
cwl:outputBinding [ CommandOutputBinding:glob
"*" ] ;
sld:type cwl:File .
a cwl:CommandLineTool ;
rdfs:comment "Tool sorts data from `unsorted_file` by key\n\n`default_output_filename` function returns file name identical to `unsorted_file`, if `output_filename` is not provided.\n" ;
ns2:original_cwlVersion "v1.0" ;
ns1:codeRepository "https://github.com/Barski-lab/workflows" ;
ns1:creator [ a ns1:Organization ;
ns1:department [ a ns1:Organization ;
ns1:department [ a ns1:Organization ;
ns1:legalName "Barski Research Lab" ;
ns1:member [ a ns1:Person ;
ns1:email "mailto:misha.kotliar@gmail.com" ;
ns1:name "Michael Kotliar" ;
ns1:sameAs
] ;
ns1:member [ a ns1:Person ;
ns1:email "mailto:Andrey.Kartashov@cchmc.org" ;
ns1:name "Andrey Kartashov" ;
ns1:sameAs
]
] ;
ns1:legalName "Allergy and Immunology"
] ;
ns1:legalName "Cincinnati Children's Hospital Medical Center" ;
ns1:location [ a ns1:PostalAddress ;
ns1:addressCountry "USA" ;
ns1:addressLocality "Cincinnati" ;
ns1:addressRegion "OH" ;
ns1:postalCode "45229" ;
ns1:streetAddress "3333 Burnet Ave" ;
ns1:telephone "+1(513)636-4200"
] ;
ns1:logo "https://www.cincinnatichildrens.org/-/media/cincinnati%20childrens/global%20shared/childrens-logo-new.png"
] ;
ns1:downloadUrl "https://raw.githubusercontent.com/Barski-lab/workflows/master/tools/linux-sort.cwl" ;
ns1:isPartOf [ a ns1:CreativeWork ;
ns1:name "Common Workflow Language" ;
ns1:url "http://commonwl.org/"
] ;
ns1:license "http://www.apache.org/licenses/LICENSE-2.0" ;
ns1:name "linux-sort" ;
cwl:baseCommand ( "sort" ) ;
cwl:cwlVersion ;
cwl:hints [ a ;
NetworkAccess:networkAccess true
] ;
cwl:hints [ a ;
LoadListingRequirement:loadListing
"deep_listing"
] ;
cwl:hints [ a cwl:DockerRequirement ;
DockerRequirement:dockerPull "biowardrobe2/scidap:v0.0.2"
] ;
cwl:inputs , , ;
cwl:outputs ;
cwl:requirements [ a cwl:InlineJavascriptRequirement ;
InlineJavascriptRequirement:expressionLib
"var get_output_filename = function() { if (inputs.output_filename) { return inputs.output_filename; } return inputs.unsorted_file.location.split('/').slice(-1)[0]; };"
] ;
cwl:stdout "$(get_output_filename())" .
a ns1:ScholarlyArticle ;
ns1:name "(Li, 2011) A statistical framework for SNP calling, mutation discovery, association mapping and population genetical parameter estimation from sequencing data. Bioinformatics." ;
ns1:url "http://www.ncbi.nlm.nih.gov/pubmed/21903627" .
cwl:source .
cwl:source .
rdfs:comment "Set minimum interval size for CSI indices to 2^INT [14]\n" ;
cwl:inputBinding [ CommandLineBinding:position 24 ;
CommandLineBinding:prefix "-m"
] ;
sld:type xsd:int , sld:null .
rdfs:comment "Set number of sorting and compression threads [1] (Only for sorting)\n" ;
sld:type xsd:int , sld:null .
cwl:default "cat \"$0\" | grep \"$1\" > `basename $0`" .
cwl:source .
rdfs:comment "Source genome name\n" ;
cwl:inputBinding [ CommandLineBinding:position
5 ] ;
sld:type xsd:string .
cwl:default true .
cwl:source , ;
cwl:valueFrom "$(self.join(\"_\")+\".bam\")" .
rdfs:comment "treat \"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 8 ;
CommandLineBinding:prefix "-split"
] ;
sld:type xsd:boolean , sld:null .
rdfs:comment "Calculate coverage of 3\" positions (instead of entire interval)\n" ;
cwl:inputBinding [ CommandLineBinding:position 15 ;
CommandLineBinding:prefix "-3"
] ;
sld:type xsd:boolean , sld:null .
a cwl:CommandLineTool ;
rdfs:comment "Tool to sort and index input BAM/SAM/CRAM.\nIf input `trigger` is set to `true` or isn't set at all (`true` is used by default), run `samtools sort` and\n`samtools index`, return sorted BAM and BAI/CSI index file.\nIf input `trigger` is set to `false`, return unchanged `sort_input` (BAM/SAM/CRAM) and index (BAI/CSI, if provided in\n`secondaryFiles`) files, previously staged into output directory.\n\nBefore execution `baseCommand`, `sort_input` and `secondaryFiles` (if provided) are staged into directory\nset as docker parameter `--workdir` (tool's output directory), using `InitialWorkDirRequirement`. Setting\n`writable: true` makes cwl-runner to make copies of the `sort_input` and `secondaryFiles` (if provided) and mount\nthem to docker container with `rw` mode as part of `--workdir` (if set to false, the files staged into output\ndirectory will be mounted to docker container separately with `ro` mode). Because both `samtools sort` and\n`samtools index` can overwrite files with the same names (and in case of `samtools sort` even the input file can be\noverwritten), we don't need to rename any of the staged files.\n\nTrigger logic is implemented in two bash scripts set by default as `bash_script_sort` and `bash_script_index` inputs.\nFor both of then, if the first argument $0 (which is `trigger` input) is true, run `samtools sort/index` with the rest\nof the arguments. If $0 is not true, skip `samtools sort/index` and return `sort_input` and `secondaryFiles`\n(if provided) staged into output directory.\n\nInput `trigger` is Boolean, but returns String, because of `valueFrom` field. The `valueFrom` is used, because if `trigger`\nis false, cwl-runner doesn't append this argument at all to the the `baseCommand` - new feature of CWL v1.0.2. Alternatively,\n`prefix` field could be used, but it causes changing in script logic.\n\nIf using `sort_output_filename`, the output file extension should be `*.bam`, because `samtools sort` defines the output\nfile format on the base of the file extension. If `*.sam` is sed as output filename, it cannot be usefully indexed\nby `samtools index`.\n\n`default_bam` function is used to generate output filename for `samtools sort` if input `sort_output_filename` is not\nset or when `trigger` is false and we need to return `sort_input` and `secondaryFiles` (if provided) files staged into\noutput directory. Output filename is generated on the base of `sort_input` basename with `.bam` extension by default.\n\n`ext` function is used to return the index file extension (BAI/CSI) based on `csi` and `bai` inputs according to the\nfollowing logic\n `csi` && `bai` => BAI\n !`csi` && !`bai ` => BAI\n `csi` && !`bai ` => CSI\n" ;
ns2:original_cwlVersion "v1.0" ;
ns1:about "Usage: samtools sort [options...] [in.bam]\nOptions:\n -l INT Set compression level, from 0 (uncompressed) to 9 (best)\n -m INT Set maximum memory per thread; suffix K/M/G recognized [768M]\n -n Sort by read name\n -o FILE Write final output to FILE rather than standard output\n -T PREFIX Write temporary files to PREFIX.nnnn.bam\n --input-fmt-option OPT[=VAL]\n Specify a single input file format option in the form\n of OPTION or OPTION=VALUE\n -O, --output-fmt FORMAT[,OPT[=VAL]]...\n Specify output format (SAM, BAM, CRAM)\n --output-fmt-option OPT[=VAL]\n Specify a single output file format option in the form\n of OPTION or OPTION=VALUE\n --reference FILE\n Reference sequence FASTA FILE [null]\n -@, --threads INT\n Number of additional threads to use [0]\n\nUsage: samtools index [-bc] [-m INT] [out.index]\nOptions:\n -b Generate BAI-format index for BAM files [default]\n -c Generate CSI-format index for BAM files\n -m INT Set minimum interval size for CSI indices to 2^INT [14]\n -@ INT Sets the number of threads [none]\n" ;
ns1:codeRepository "https://github.com/Barski-lab/workflows" ;
ns1:creator [ a ns1:Organization ;
ns1:department [ a ns1:Organization ;
ns1:department [ a ns1:Organization ;
ns1:legalName "Barski Research Lab" ;
ns1:member [ a ns1:Person ;
ns1:email "mailto:misha.kotliar@gmail.com" ;
ns1:name "Michael Kotliar" ;
ns1:sameAs
]
] ;
ns1:legalName "Allergy and Immunology"
] ;
ns1:legalName "Cincinnati Children's Hospital Medical Center" ;
ns1:location [ a ns1:PostalAddress ;
ns1:addressCountry "USA" ;
ns1:addressLocality "Cincinnati" ;
ns1:addressRegion "OH" ;
ns1:postalCode "45229" ;
ns1:streetAddress "3333 Burnet Ave" ;
ns1:telephone "+1(513)636-4200"
] ;
ns1:logo "https://www.cincinnatichildrens.org/-/media/cincinnati%20childrens/global%20shared/childrens-logo-new.png"
] ;
ns1:downloadUrl "https://raw.githubusercontent.com/Barski-lab/workflows/master/tools/samtools-sort-index.cwl" ;
ns1:isPartOf [ a ns1:CreativeWork ;
ns1:name "Common Workflow Language" ;
ns1:url "http://commonwl.org/"
] ;
ns1:license "http://www.apache.org/licenses/LICENSE-2.0" ;
ns1:mainEntity ;
ns1:name "samtools-sort-index" ;
cwl:arguments ( [ CommandLineBinding:position 6 ;
cwl:valueFrom "${ return inputs.trigger ? \"true\" : \"false\" }\n"
]
[ CommandLineBinding:position 13 ;
CommandLineBinding:prefix "-O" ;
cwl:valueFrom "bam"
]
[ CommandLineBinding:position 15 ;
CommandLineBinding:prefix "-@" ;
cwl:valueFrom "$(inputs.threads?inputs.threads:1)"
]
[ CommandLineBinding:position 17 ;
CommandLineBinding:shellQuote false ;
cwl:valueFrom ";"
]
[ CommandLineBinding:position 18 ;
cwl:valueFrom "bash"
]
[ CommandLineBinding:position 19 ;
cwl:valueFrom "-c"
]
[ CommandLineBinding:position 21 ;
cwl:valueFrom "${ return inputs.trigger ? \"true\" : \"false\" }\n"
]
[ CommandLineBinding:position 23 ;
cwl:valueFrom "$(inputs.bai?'-b':inputs.csi?'-c':[])"
]
[ CommandLineBinding:position 25 ;
CommandLineBinding:prefix "-@" ;
cwl:valueFrom "$(inputs.threads?inputs.threads:1)"
]
[ CommandLineBinding:position 26 ;
cwl:valueFrom "${\n if (inputs.sort_output_filename == \"\" || inputs.trigger == false){\n return default_bam();\n } else {\n return inputs.sort_output_filename;\n }\n}\n"
]
[ CommandLineBinding:position 27 ;
cwl:valueFrom "${\n if (inputs.sort_output_filename == \"\" || inputs.trigger == false){\n return default_bam() + ext();\n } else {\n return inputs.sort_output_filename + ext();\n }\n}\n"
]
) ;
cwl:baseCommand ( "bash" "-c" ) ;
cwl:cwlVersion ;
cwl:hints [ a ;
NetworkAccess:networkAccess true
] ;
cwl:hints [ a cwl:DockerRequirement ;
DockerRequirement:dockerPull "biowardrobe2/samtools:v1.4"
] ;
cwl:hints [ a ;
LoadListingRequirement:loadListing
"deep_listing"
] ;
cwl:inputs , , , , , , , , , ;
cwl:outputs ;
cwl:requirements [ a cwl:InitialWorkDirRequirement ;
cwl:listing "${\n return [\n {\n \"entry\": inputs.sort_input,\n \"entryname\": inputs.sort_input.basename,\n \"writable\": true\n }\n ]\n}\n"
] ;
cwl:requirements [ a cwl:ShellCommandRequirement ] ;
cwl:requirements [ a cwl:InlineJavascriptRequirement ;
InlineJavascriptRequirement:expressionLib
"var default_bam = function() { if (inputs.trigger == true){ return inputs.sort_input.location.split('/').slice(-1)[0].split('.').slice(0,-1).join('.')+\".bam\"; } else { return inputs.sort_input.location.split('/').slice(-1)[0]; } };" , "var ext = function() { if (inputs.csi && !inputs.bai){ return '.csi'; } else { return '.bai'; } };"
] .
rdfs:comment "Four column bedGraph file: \n" ;
cwl:inputBinding [ CommandLineBinding:position
10 ] ;
sld:type cwl:File .
rdfs:comment "Input BED file\n" ;
cwl:inputBinding [ CommandLineBinding:position
6 ] ;
sld:type cwl:File .
rdfs:comment "Name for generated output file\n" ;
sld:type xsd:string , sld:null .
rdfs:comment "Scale 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 6 ;
CommandLineBinding:prefix "-scale"
] ;
sld:type xsd:float , sld:null .
cwl:in , , ;
cwl:out ;
cwl:run .
rdfs:comment "keep extra columns. these are columns in the input\nbeyond the specified or detected bed version, and which\nare cut by default\n" ;
cwl:inputBinding [ CommandLineBinding:position 1 ;
CommandLineBinding:prefix "--keepExtra"
] ;
sld:type xsd:boolean , sld:null .
rdfs:comment "SORT: desired compression level for the final output file, ranging from 0 (uncompressed)\nor 1 (fastest but minimal compression) to 9 (best compression but slowest to write),\nsimilarly to gzip(1)'s compression level setting.\nIf -l is not used, the default compression level will apply.\n" ;
cwl:inputBinding [ CommandLineBinding:position 11 ;
CommandLineBinding:prefix "-l"
] ;
sld:type xsd:int , sld:null .
cwl:inputBinding [ CommandLineBinding:position
4 ] ;
sld:type cwl:File .
sld:symbols , , , ;
sld:type sld:enum .
cwl:source .
rdfs:comment "Change strand af the mate read (so both reads from the same strand) useful for strand specific.\nWorks for BAM files only\n" ;
cwl:inputBinding [ CommandLineBinding:position 11 ;
CommandLineBinding:prefix "-du"
] ;
sld:type xsd:boolean , sld:null .
cwl:in , ;
cwl:out ;
cwl:run .
cwl:outputBinding [ CommandOutputBinding:glob
"$(get_output_filename())" ] ;
sld:type cwl:File .
a cwl:CommandLineTool ;
rdfs:comment "Tool converts bedGraph to bigWig file.\n\n`default_output_filename` function returns filename for generated bigWig if `output_filename` is not provided.\nDefault filename is generated on the base of `bedgraph_file` basename with the updated to `*.bigWig` extension.\n" ;
ns2:original_cwlVersion "v1.0" ;
ns1:about "usage:\n bedGraphToBigWig in.bedGraph chrom.sizes out.bw\nwhere in.bedGraph is a four column file in the format:\n \nand chrom.sizes is a two-column file/URL: \nand out.bw is the output indexed big wig file.\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.\nThe input bedGraph file must be sorted, use the unix sort command:\n sort -k1,1 -k2,2n unsorted.bedGraph > sorted.bedGraph\noptions:\n -blockSize=N - Number of items to bundle in r-tree. Default 256\n -itemsPerSlot=N - Number of data points bundled at lowest level. Default 1024\n -unc - If set, do not use compression.\n" ;
ns1:codeRepository "https://github.com/Barski-lab/workflows" ;
ns1:creator [ a ns1:Organization ;
ns1:department [ a ns1:Organization ;
ns1:department [ a ns1:Organization ;
ns1:legalName "Barski Research Lab" ;
ns1:member [ a ns1:Person ;
ns1:email "mailto:Andrey.Kartashov@cchmc.org" ;
ns1:name "Andrey Kartashov" ;
ns1:sameAs
] ;
ns1:member [ a ns1:Person ;
ns1:email "mailto:misha.kotliar@gmail.com" ;
ns1:name "Michael Kotliar" ;
ns1:sameAs
]
] ;
ns1:legalName "Allergy and Immunology"
] ;
ns1:legalName "Cincinnati Children's Hospital Medical Center" ;
ns1:location [ a ns1:PostalAddress ;
ns1:addressCountry "USA" ;
ns1:addressLocality "Cincinnati" ;
ns1:addressRegion "OH" ;
ns1:postalCode "45229" ;
ns1:streetAddress "3333 Burnet Ave" ;
ns1:telephone "+1(513)636-4200"
] ;
ns1:logo "https://www.cincinnatichildrens.org/-/media/cincinnati%20childrens/global%20shared/childrens-logo-new.png"
] ;
ns1:downloadUrl "https://raw.githubusercontent.com/Barski-lab/workflows/master/tools/ucsc-bedgraphtobigwig.cwl" ;
ns1:isPartOf [ a ns1:CreativeWork ;
ns1:name "Common Workflow Language" ;
ns1:url "http://commonwl.org/"
] ;
ns1:license "http://www.apache.org/licenses/LICENSE-2.0" ;
ns1:mainEntity ;
ns1:name "ucsc-bedgraphtobigwig" ;
cwl:baseCommand ( "bedGraphToBigWig" ) ;
cwl:cwlVersion ;
cwl:hints [ a cwl:DockerRequirement ;
DockerRequirement:dockerPull "biowardrobe2/ucscuserapps:v358"
] ;
cwl:hints [ a ;
LoadListingRequirement:loadListing
"deep_listing"
] ;
cwl:hints [ a ;
NetworkAccess:networkAccess true
] ;
cwl:inputs , , , , , ;
cwl:outputs ;
cwl:requirements [ a cwl:InlineJavascriptRequirement ;
InlineJavascriptRequirement:expressionLib
"var default_output_filename = function() { let basename = inputs.bedgraph_file.location.split('/').slice(-1)[0]; let root = basename.split('.').slice(0,-1).join('.'); let ext = \".bigWig\"; return (root == \"\")?basename+ext:root+ext; };"
] .
a cwl:CommandLineTool ;
rdfs:comment "Runs halliftover to project input BED file from source to target genome.\n`source_genome_name` and `target_genome_name` should correspond to the fields in `hal_file`.\n\nIf `output_filename` is not set, call `default_output_filename` function.\n\nThe following parameters are not yet supported:\n --outPSL\n --outPSLWithName\n\nhalLiftover manual doesn't say anything if `input_bed_file` should be sorted or not\n" ;
ns2:original_cwlVersion "v1.0" ;
ns1:about "\nUSAGE:\nhalLiftover [Options] \n\nARGUMENTS:\nhalFile: input hal file\nsrcGenome: source genome name\nsrcBed: path of input bed file. set as stdin to stream from standard input\ntgtGenome: target genome name\ntgtBed: path of output bed file. set as stdout to stream to standard output.\n\nOPTIONS:\n--append: append results to tgtBed [default = 0]\n--cacheBytes : maximum size in bytes of regular hdf5 cache [default =\n 15728640]\n--cacheMDC : number of metadata slots in hdf5 cache [default = 113]\n--cacheRDC : number of regular slots in hdf5 cache. should be a\n prime number ~= 10 * DefaultCacheRDCBytes / chunk\n [default = 599999]\n--cacheW0 : w0 parameter fro hdf5 cache [default = 0.75]\n--coalescenceLimit : coalescence limit genome: the genome at or above the\n MRCA of source and target at which we stop looking for\n homologies (default: MRCA) [default = ]\n--help: dsiplay this help page [default = 0]\n--inBedVersion : bed version of input file as integer between 3 and 9 or\n 12 reflecting the number of columns (see bed format\n specification for more details). Will be autodetected\n by default. [default = 0]\n--inMemory: load all data in memory (and disable hdf5 cache)\n [default = 0]\n--keepExtra: keep extra columns. these are columns in the input\n beyond the specified or detected bed version, and which\n are cut by default. [default = 0]\n--noDupes: do not map between duplications in graph. [default = 0]\n--outBedVersion : bed version of output file as integer between 3 and 9\n or 12 reflecting the number of columns (see bed format\n specification for more details). Will be same as input\n by default. [default = 0]\n--outPSL: write output in PSL instead of bed format. overrides\n --outBedVersion when specified. [default = 0]\n--outPSLWithName: write output as input BED name followed by PSL line\n instead of bed format. overrides --outBedVersion when\n specified. [default = 0]\n--tab: input is tab-separated. this allows column entries to\n contain spaces. if this flag is not set, both spaces\n and tabs are used to separate input columns. [default = 0]\n" ;
ns1:codeRepository "https://github.com/Barski-lab/workflows" ;
ns1:creator [ a ns1:Organization ;
ns1:department [ a ns1:Organization ;
ns1:department [ a ns1:Organization ;
ns1:legalName "Barski Research Lab" ;
ns1:member [ a ns1:Person ;
ns1:email "mailto:misha.kotliar@gmail.com" ;
ns1:name "Michael Kotliar" ;
ns1:sameAs
]
] ;
ns1:legalName "Allergy and Immunology"
] ;
ns1:legalName "Cincinnati Children's Hospital Medical Center" ;
ns1:location [ a ns1:PostalAddress ;
ns1:addressCountry "USA" ;
ns1:addressLocality "Cincinnati" ;
ns1:addressRegion "OH" ;
ns1:postalCode "45229" ;
ns1:streetAddress "3333 Burnet Ave" ;
ns1:telephone "+1(513)636-4200"
] ;
ns1:logo "https://www.cincinnatichildrens.org/-/media/cincinnati%20childrens/global%20shared/childrens-logo-new.png"
] ;
ns1:downloadUrl "https://raw.githubusercontent.com/Barski-lab/workflows/master/tools/halliftover.cwl" ;
ns1:isPartOf [ a ns1:CreativeWork ;
ns1:name "Common Workflow Language" ;
ns1:url "http://commonwl.org/"
] ;
ns1:license "http://www.apache.org/licenses/LICENSE-2.0" ;
ns1:mainEntity ;
ns1:name "halliftover" ;
cwl:baseCommand ( "halLiftover" ) ;
cwl:cwlVersion ;
cwl:hints [ a ;
NetworkAccess:networkAccess true
] ;
cwl:hints [ a ;
LoadListingRequirement:loadListing
"deep_listing"
] ;
cwl:hints [ a cwl:DockerRequirement ;
DockerRequirement:dockerPull "biowardrobe2/hal:v0.0.1"
] ;
cwl:inputs , , , , , , , ;
cwl:outputs ;
cwl:requirements [ a cwl:InlineJavascriptRequirement ;
InlineJavascriptRequirement:expressionLib
"var default_output_filename = function() { var ext = \".bed\"; if (inputs.output_filename == \"\"){ let root = inputs.input_bed_file.basename.split('.').slice(0,-1).join('.'); return (root == \"\")?inputs.input_bed_file.basename+ext:root+ext; } else { return inputs.output_filename; } };"
] .
a ns1:ScholarlyArticle ;
ns1:name "(Li, 2011) Improving SNP discovery by base alignment quality. Bioinformatics." ;
ns1:url "http://www.ncbi.nlm.nih.gov/pubmed/21320865" .
rdfs:comment "pair-end chip seq experiment\n" ;
cwl:inputBinding [ CommandLineBinding:position 10 ;
CommandLineBinding:prefix "-pc"
] ;
sld:type xsd:boolean , sld:null .
rdfs:comment "The input file can be in BAM format (Note: BAM must be sorted by position) or .\nPrefix is selected on the base of input file extension\n" ;
cwl:inputBinding [ CommandLineBinding:position 16 ;
cwl:valueFrom "${\n var prefix = ((/.*\\.bam$/i).test(inputs.input_file.path))?'-ibam':'-i';\n return [prefix, inputs.input_file.path];\n}\n"
] ;
sld:type cwl:File .
cwl:source .
rdfs:comment "Number of threads for those steps that support multithreading" ;
rdfs:label "Number of threads" ;
cwl:default 2 ;
sld:type xsd:int , sld:null .
cwl:default "sort-bed \"$0\" > `basename $0`" .
a ns1:ScholarlyArticle ;
ns1:name "(Li et al., 2009) The Sequence Alignment/Map format and SAMtools. Bioinformatics." ;
ns1:url "http://www.ncbi.nlm.nih.gov/pubmed/19505943" .
rdfs:comment "Mapped to concatenated genome reads number to calculate scaling factor" ;
rdfs:label "Mapped to concatenated genome reads number" ;
sld:type xsd:int .
rdfs:comment "If set, writes the output bigWig file to output_filename,\notherwise generates filename from default_output_filename()\n" ;
cwl:default "" ;
cwl:inputBinding [ CommandLineBinding:position 12 ;
cwl:valueFrom "${\n if (self == \"\"){\n return default_output_filename();\n } else {\n return self;\n }\n}\n"
] ;
sld:type xsd:string , sld:null .
rdfs:comment "Corresponds to UID" ;
rdfs:label "Prefix for all generated output files" ;
sld:type xsd:string .
rdfs:comment "If true - run samtools, if false - return sort_input and optional index file in secondaryFiles, previously staged\ninto output directory.\n" ;
cwl:default true ;
sld:type xsd:boolean , sld:null .
rdfs:comment "Generate CSI-format index for BAM files. If input isn't cram.\n" ;
sld:type xsd:boolean , sld:null .
rdfs:comment "Input HAL file\n" ;
cwl:inputBinding [ CommandLineBinding:position
4 ] ;
sld:type cwl:File .
cwl:in , , , ;
cwl:out ;
cwl:run .
rdfs:comment "HAL file that includes current and reference strain information" ;
rdfs:label "HAL file" ;
sld:type cwl:File .
cwl:outputBinding [ CommandOutputBinding:glob
"${\n if (inputs.output_filename == \"\"){\n return default_output_filename();\n } else {\n return inputs.output_filename;\n }\n}\n" ] ;
sld:type cwl:File .
a cwl:CommandLineTool ;
rdfs:comment "Tool calculates genome coverage from input bam/bed/gff/vcf using `bedtools genomecov`\n\nDepending on `input_file` extension additional prefix is used: if `*.bam` use `-ibam`, else use `-i`.\n\n`scale` and `mapped_reads_number` inputs result in the same parameter `-scale`. If `scale` is not provided, check if\n`mapped_reads_number` is not null and calculate `-scale` as `1000000/mapped_reads_number`. If both inputs are\nnull, `bedtools genomecov` will use its default scaling value.\n\n`default_output_filename` function returns default output filename and is used when `output_filename` is not provided.\nDefault output file extention is `.tab`. If bedGraph should be generated (check flags `inputs.depth`), extension is\nupdated to `.bedGraph`. Default basename of the output file is generated on the base of `input_file` basename.\n" ;
ns2:original_cwlVersion "v1.0" ;
ns1:about "Usage: bedtools genomecov [OPTIONS] -i -g \n\nOptions:\n\t-ibam\t\tThe input file is in BAM format.\n\t\t\tNote: BAM _must_ be sorted by position\n\n\t-d\t\tReport the depth at each genome position (with one-based coordinates).\n\t\t\tDefault behavior is to report a histogram.\n\n\t-dz\t\tReport the depth at each genome position (with zero-based coordinates).\n\t\t\tReports only non-zero positions.\n\t\t\tDefault behavior is to report a histogram.\n\n\t-bg\t\tReport depth in BedGraph format. For details, see:\n\t\t\tgenome.ucsc.edu/goldenPath/help/bedgraph.html\n\n\t-bga\t\tReport depth in BedGraph format, as above (-bg).\n\t\t\tHowever with this option, regions with zero\n\t\t\tcoverage are also reported. This allows one to\n\t\t\tquickly extract all regions of a genome with 0\n\t\t\tcoverage by applying: \"grep -w 0$\" 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-pc\t\tCalculate coverage of pair-end fragments.\n\t\t\tWorks for BAM files only\n\t-fs\t\tForce to use provided fragment size instead of read length\n\t\t\tWorks for BAM files only\n\t-du\t\tChange strand af the mate read (so both reads from the same strand) useful for strand specific\n\t\t\tWorks for BAM files only\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\n" ;
ns1:codeRepository "https://github.com/Barski-lab/workflows" ;
ns1:creator [ a ns1:Organization ;
ns1:department [ a ns1:Organization ;
ns1:department [ a ns1:Organization ;
ns1:legalName "Barski Research Lab" ;
ns1:member [ a ns1:Person ;
ns1:email "mailto:misha.kotliar@gmail.com" ;
ns1:name "Michael Kotliar" ;
ns1:sameAs
]
] ;
ns1:legalName "Allergy and Immunology"
] ;
ns1:legalName "Cincinnati Children's Hospital Medical Center" ;
ns1:location [ a ns1:PostalAddress ;
ns1:addressCountry "USA" ;
ns1:addressLocality "Cincinnati" ;
ns1:addressRegion "OH" ;
ns1:postalCode "45229" ;
ns1:streetAddress "3333 Burnet Ave" ;
ns1:telephone "+1(513)636-4200"
] ;
ns1:logo "https://www.cincinnatichildrens.org/-/media/cincinnati%20childrens/global%20shared/childrens-logo-new.png"
] ;
ns1:downloadUrl "https://raw.githubusercontent.com/Barski-lab/workflows/master/tools/bedtools-genomecov.cwl" ;
ns1:isPartOf [ a ns1:CreativeWork ;
ns1:name "Common Workflow Language" ;
ns1:url "http://commonwl.org/"
] ;
ns1:license "http://www.apache.org/licenses/LICENSE-2.0" ;
ns1:mainEntity ;
ns1:name "bedtools-genomecov" ;
cwl:baseCommand ( "bedtools" "genomecov" ) ;
cwl:cwlVersion ;
cwl:hints [ a cwl:DockerRequirement ;
DockerRequirement:dockerPull "biowardrobe2/bedtools2:v2.26.0"
] ;
cwl:hints [ a ;
LoadListingRequirement:loadListing
"deep_listing"
] ;
cwl:hints [ a ;
NetworkAccess:networkAccess true
] ;
cwl:inputs , , , , , , , , , , , , , ;
cwl:outputs ;
cwl:requirements [ a cwl:InlineJavascriptRequirement ;
InlineJavascriptRequirement:expressionLib
"var default_output_filename = function() { let ext = (inputs.depth == \"-bg\" || inputs.depth == \"-bga\")?\".bedGraph\":\".tab\"; return inputs.input_file.location.split('/').slice(-1)[0].split('.').slice(0,-1).join('.') + ext; };"
] ;
cwl:stdout "${\n if (inputs.output_filename == null){\n return default_output_filename();\n } else {\n return inputs.output_filename;\n }\n}\n" .
rdfs:comment "-k, --key=POS1[,POS2]\nstart a key at POS1, end it at POS2 (origin 1)\n" ;
cwl:inputBinding [ CommandLineBinding:position
1 ] ;
sld:type [ cwl:inputBinding [ CommandLineBinding:prefix
"-k" ] ;
sld:items xsd:string ;
sld:type sld:array
] .
rdfs:comment "Combine 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 13 ;
CommandLineBinding:prefix "-max"
] ;
sld:type xsd:int , sld:null .
cwl:source .
cwl:in , ;
cwl:out ;
cwl:run .
rdfs:comment "Target genome name\n" ;
cwl:inputBinding [ CommandLineBinding:position
7 ] ;
sld:type xsd:string .
rdfs:comment "input is tab-separated. this allows column entries to\ncontain spaces. if this flag is not set, both spaces\nand tabs are used to separate input columns\n" ;
cwl:default true ;
cwl:inputBinding [ CommandLineBinding:position 3 ;
CommandLineBinding:prefix "--tab"
] ;
sld:type xsd:boolean , sld:null .
a ns1:ScholarlyArticle ;
ns1:author [ a ns1:Person ;
ns1:name "Aaron R. Quinlan"
] ;
ns1:author [ a ns1:Person ;
ns1:name "Ira M. Hall"
] ;
ns1:name "BEDTools: a flexible suite of utilities for comparing genomic features" ;
ns1:url "https://academic.oup.com/bioinformatics/article-lookup/doi/10.1093/bioinformatics/btq033" .
cwl:source .
cwl:default "bedops --partition \"$0\" | bedmap --echo --echo-map-id --delim \"\\t\" - \"$0\" | awk '{n=split($4,reads,\";\"); sum=0; for(i=1;i<=n;i++) sum+=reads[i]; $4=sum; print $0 }' > `basename $0`" .
cwl:source ;
cwl:valueFrom "$(self+\"_\")" .
a cwl:Workflow ;
ns2: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:MultipleInputFeatureRequirement ] ;
cwl:requirements [ a cwl:InlineJavascriptRequirement ] ;
cwl:requirements [ a cwl:StepInputExpressionRequirement ] ;
cwl:requirements [ a cwl:SubworkflowFeatureRequirement ] .
cwl:in , ;
cwl:out ;
cwl:run .
rdfs:comment "Write the final sorted output to FILE. Only out.bam|out.cram.\nIf output file extension is set to SAM, tool will fail on the index step\n" ;
cwl:default "" ;
cwl:inputBinding [ CommandLineBinding:position 12 ;
CommandLineBinding:prefix "-o" ;
cwl:valueFrom "${\n if (self == \"\" || inputs.trigger == false){\n return default_bam();\n } else {\n return self;\n }\n}\n"
] ;
sld:type xsd:string , sld:null .
rdfs:comment "Output filename\n" ;
cwl:default "" ;
cwl:inputBinding [ CommandLineBinding:position 8 ;
cwl:valueFrom "$(default_output_filename())"
] ;
sld:type xsd:string , sld:null .
a ns1:SoftwareSourceCode ;
ns1:about "A software suite for the comparison, manipulation and annotation of genomic features in browser extensible data (BED) and general feature format (GFF) format. BEDTools also supports the comparison of sequence alignments in BAM format to both BED and GFF features. The tools are extremely efficient and allow the user to compare large datasets (e.g. next-generation sequencing data) with both public and custom genome annotation tracks. BEDTools can be combined with one another as well as with standard UNIX commands, thus facilitating routine genomics tasks as well as pipelines that can quickly answer intricate questions of large genomic datasets.\n" ;
ns1:codeRepository "https://github.com/arq5x/bedtools2" ;
ns1:creator [ a ns1:Organization ;
ns1:member [ a ns1:Person ;
ns1:description "Main author" ;
ns1:name "Neil Kindlon"
] ;
ns1:member [ a ns1:Person ;
ns1:description "Main author" ;
ns1:name "Aaron Quinlan"
] ;
ns1:name "University of Utah"
] ;
ns1:discussionUrl "https://groups.google.com/forum/#!forum/bedtools-discuss" , "https://github.com/arq5x/bedtools2/issues" ;
ns1:license "https://opensource.org/licenses/GPL-2.0" ;
ns1:name "bowtie2" ;
ns1:programmingLanguage "C++" ;
ns1:publication ;
ns1:targetProduct [ a ns1:SoftwareApplication ;
ns1:applicationCategory "command line tool" ;
ns1:softwareVersion "2.26.0"
] ;
ns1:url "http://bedtools.readthedocs.org" .
cwl:source .
rdfs:comment "Calculate 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 9 ;
CommandLineBinding:prefix "-strand"
] ;
sld:type xsd:string , sld:null .
rdfs:comment "Bash function to run samtools sort with all input parameters or skip it if trigger is false\n" ;
cwl:default "#!/bin/bash\nif [ \"$0\" = \"true\" ]\nthen\n echo \"Run: samtools sort \" ${@:1}\n samtools sort \"${@:1}\"\nelse\n echo \"Skip samtools sort \" ${@:1}\nfi\n" ;
cwl:inputBinding [ CommandLineBinding:position
5 ] ;
sld:type xsd:string , sld:null .
rdfs:comment "Calculate coverage of 5\" positions (instead of entire interval)\n" ;
cwl:inputBinding [ CommandLineBinding:position 14 ;
CommandLineBinding:prefix "-5"
] ;
sld:type xsd:boolean , sld:null .
cwl:inputBinding [ CommandLineBinding:position
3 ] ;
cwl:inputBinding [ CommandLineBinding:position
3 ] ;
sld:type xsd:string , sld:null ;
sld:type [ sld:items xsd:string ;
sld:type sld:array
] ;
sld:type [ sld:items xsd:string ;
sld:type sld:array
] .
rdfs:comment "Number of data points bundled at lowest level. Default 1024\n" ;
cwl:inputBinding [ CommandLineBinding:position 6 ;
CommandLineBinding:prefix "-itemsPerSlot=" ;
CommandLineBinding:separate false
] ;
sld:type xsd:int , sld:null .
cwl:outputBinding [ CommandOutputBinding:glob
"$(inputs.input_file.basename)" ] ;
cwl:outputBinding [ CommandOutputBinding:glob
"$(inputs.input_file.basename)" ] ;
sld:type cwl:File .
cwl:default "cat \"$0\" | grep \"$1\" | sed \"s/$1/chr/g\" > `basename $0`" .
a ns1:SoftwareSourceCode ;
ns1:about "A suite of programs for interacting with high-throughput sequencing data. It consists of three separate repositories: Samtools (Reading/writing/editing/indexing/viewing SAM/BAM/CRAM format), BCFtools (Reading/writing BCF2/VCF/gVCF files and calling/filtering/summarising SNP and short indel sequence variants) and HTSlib (A C library for reading/writing high-throughput sequencing data).\n" ;
ns1:codeRepository "https://github.com/samtools/samtools.git" ;
ns1:creator [ a ns1:Person ;
ns1:description "contributed the header parsing library sam_header.c and sam2vcf.pl script." ;
ns1:name "Petr Danecek"
] ;
ns1:creator [ a ns1:Organization ;
ns1:member [ a ns1:Person ;
ns1:description "wrote most of the initial source codes of SAMtools and various converters." ;
ns1:name "Heng Li"
] ;
ns1:name "Sanger Institute"
] ;
ns1:creator [ a ns1:Organization ;
ns1:member [ a ns1:Person ;
ns1:description "Designed and implemented the\nRAZF format, an alternative indexable compression format. RAZF is no longer\nused by or provided with SAMtools. Source code remains available in older\nSAMtools 0.1.x releases and from the standalone branch in the repository.\n" ;
ns1:name "Jue Ruan"
] ;
ns1:name "Beijing Genome Institute"
] ;
ns1:creator [ a ns1:Organization ;
ns1:member [ a ns1:Person ;
ns1:description "A major contributor to the\nSAM/BAM specification. He designed and implemented the BGZF format, the\nunderlying indexable compression format for the BAM format. BGZF does\nnot support arithmetic between file offsets.\n" ;
ns1:name "Bob Handsaker"
] ;
ns1:name "Broad Institute"
] ;
ns1:creator [ a ns1:Person ;
ns1:description "updated novo2sam.pl to support gapped alignment by novoalign." ;
ns1:name "Colin Hercus"
] ;
ns1:discussionUrl "https://lists.sourceforge.net/lists/listinfo/samtools-devel" , "https://lists.sourceforge.net/lists/listinfo/samtools-help" ;
ns1:license "https://opensource.org/licenses/MIT" , "https://opensource.org/licenses/BSD-3-Clause" ;
ns1:name "samtools" ;
ns1:programmingLanguage "C, Perl" ;
ns1:publication , , ;
ns1:targetProduct [ a ns1:SoftwareApplication ;
ns1:applicationCategory "commandline tool" ;
ns1:softwareVersion "1.4"
] ;
ns1:url "http://www.htslib.org/" .
cwl:outputBinding [ CommandOutputBinding:glob
"${\n if (inputs.sort_output_filename == \"\" || inputs.trigger == false){\n return default_bam();\n } else {\n return inputs.sort_output_filename;\n }\n}\n" ] ;
cwl:secondaryFiles [] ;
sld:type cwl:File .
rdfs:comment "Name for generated output file\n" ;
sld:type xsd:string , sld:null .
cwl:source