@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: .
@prefix ExpressionTool: .
rdfs:comment "Number of threads\n" ;
cwl:default 1 ;
cwl:inputBinding [ CommandLineBinding:position 11 ;
CommandLineBinding:prefix "-threads"
] ;
sld:type xsd:int .
cwl:source .
rdfs:comment "If running with --casava then don't remove read flagged by\ncasava as poor quality when performing the QC analysis.\n" ;
cwl:inputBinding [ CommandLineBinding:position 14 ;
CommandLineBinding:prefix "--nofilter"
] ;
cwl:inputBinding [ CommandLineBinding:position 14 ;
CommandLineBinding:prefix "--nofilter"
] ;
sld:type xsd:boolean , sld:null .
rdfs:comment "If true - run trimmomatic, if false - return input fastq files, previously staged into output directory.\nUse valueFrom to return string instead of boolean, because if return boolean False, argument is not printed\n" ;
cwl:default true ;
cwl:inputBinding [ CommandLineBinding:position 5 ;
cwl:valueFrom "${ return self ? \"true\" : \"false\" }\n"
] ;
sld:type xsd:boolean , sld:null .
cwl:source , ;
cwl:valueFrom "${\n return self[0] && self[1];\n}\n" .
rdfs:comment "FASTQ file for read R2 in Paired End mode\n" ;
cwl:inputBinding [ CommandLineBinding:position
14 ] ;
sld:type cwl:File , sld:null .
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 105 ;
CommandLineBinding:prefix "HEADCROP:" ;
CommandLineBinding:separate false
] ;
sld:type xsd:int , sld:null .
rdfs:comment "Formats sequence using color space (default\nfor SOLiD),\"cskey\" may be specified for\ntranslation\n" ;
cwl:inputBinding [ CommandLineBinding:position 25 ;
CommandLineBinding:prefix "--dumpcs"
] ;
sld:type xsd:string , sld:null .
cwl:in , , , , , , ;
cwl:out , ;
cwl:run .
rdfs:comment "Filter used in current 1000 Genomes data\n" ;
cwl:inputBinding [ CommandLineBinding:position 10 ;
CommandLineBinding:prefix "--qual-filter-1"
] ;
sld:type xsd:boolean , sld:null .
rdfs:comment "Bash function to run trimmomatic with all input parameters or skip it if trigger is false\n" ;
cwl:default "#!/bin/bash\nif [ \"$0\" = \"true\" ]\nthen\n echo \"Run trimmomatic\"\n java \"${@:1}\"\nelse\n echo \"Skip run trimmomatic\"\nfi\n" ;
cwl:inputBinding [ CommandLineBinding:position
1 ] ;
sld:type xsd:string , sld:null .
cwl:outputBinding [ CommandOutputBinding:glob
"${\n return [\n inputs.sra_file.basename.split(\".\")[0] + \".fastq\",\n inputs.sra_file.basename.split(\".\")[0] + \"_1.fastq\"\n ];\n}\n" ] ;
sld:type cwl:File .
rdfs:comment "Filter used in early 1000 Genomes data: no sequences starting or ending with >= 10N\n" ;
cwl:inputBinding [ CommandLineBinding:position 9 ;
CommandLineBinding:prefix "--qual-filter"
] ;
sld:type xsd:boolean , sld:null .
rdfs:comment "Defline format specification for quality.\n is string of characters and/or\nvariables. The variables can be one of: $ac\n- accession, $si spot id, $sn spot\nname, $sg spot group (barcode), $sl spot\nlength in bases, $ri read number, $rn\nread name, $rl read length in bases. '[]'\ncould be used for an optional output: if\nall vars in [] yield empty values whole\ngroup is not printed. Empty value is empty\nstring or for numeric variables. Ex:\n@$sn[_$rn]/$ri '_$rn' is omitted if name\nis empty\n" ;
cwl:inputBinding [ CommandLineBinding:position 34 ;
CommandLineBinding:prefix "--defline-qual"
] ;
sld:type xsd:string , sld:null .
cwl:outputBinding [ CommandOutputBinding:glob
"${\n return \"*/summary.txt\";\n}\n" ] ;
cwl:outputBinding [ CommandOutputBinding:glob
"${\n return \"*/summary.txt\";\n}\n" ] ;
sld:type cwl:File .
cwl:source .
cwl:in ;
cwl:out ;
cwl:run .
a ns1:SoftwareSourceCode ;
ns1:about "FastQC is a program designed to spot potential problems in high througput sequencing datasets.\nIt runs a set of analyses on one or more raw sequence files in fastq or bam format and produces\na report which summarises the results.\n" ;
ns1:codeRepository "https://github.com/s-andrews/FastQC/releases" ;
ns1:creator [ a ns1:Organization ;
ns1:member [ a ns1:Person ;
ns1:name "Simon Andrews"
] ;
ns1:name "Babraham Bioinformatics"
] ;
ns1:creator [ a ns1:Organization ;
ns1:member [ a ns1:Person ;
ns1:name "Simon Andrews"
] ;
ns1:name "Babraham Bioinformatics"
] ;
ns1:discussionUrl "https://github.com/s-andrews/FastQC/issues" ;
ns1:license "https://opensource.org/licenses/GPL-2.0" ;
ns1:name "fastqc" ;
ns1:programmingLanguage "Java" ;
ns1:targetProduct [ a ns1:SoftwareApplication ;
ns1:applicationCategory "command line tool" ;
ns1:softwareVersion "0.11.5"
] ;
ns1:targetProduct [ a ns1:SoftwareApplication ;
ns1:applicationCategory "command line tool" ;
ns1:softwareVersion "0.11.5"
] ;
ns1:url "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/" .
rdfs:comment "Specifies a non-default file which contains a set of criteria\nwhich will be used to determine the warn/error limits for the\nvarious modules. This file can also be used to selectively\nremove some modules from the output all together. The format\nneeds to mirror the default limits.txt file found in the\nConfiguration folder.\n" ;
cwl:inputBinding [ CommandLineBinding:position 10 ;
CommandLineBinding:prefix "--limits"
] ;
cwl:inputBinding [ CommandLineBinding:position 10 ;
CommandLineBinding:prefix "--limits"
] ;
sld:type cwl:File , sld:null .
rdfs:comment "Bypasses the normal sequence file format detection and\nforces the program to use the specified format. Valid\nformats are bam,sam,bam_mapped,sam_mapped and fastq\n" ;
cwl:inputBinding [ CommandLineBinding:position 6 ;
CommandLineBinding:prefix "--format"
] ;
cwl:inputBinding [ CommandLineBinding:position 6 ;
CommandLineBinding:prefix "--format"
] ;
sld:type , sld:null .
sld:symbols , ;
sld:type sld:enum .
a ns1:SoftwareSourceCode ;
ns1:about "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.\n" ;
ns1:codeRepository "http://www.usadellab.org/cms/uploads/supplementary/Trimmomatic/Trimmomatic-Src-0.35.zip" ;
ns1:creator [ a ns1:Organization ;
ns1:member [ a ns1:Person ;
ns1:name "Usadel B"
] ;
ns1:member [ a ns1:Person ;
ns1:name "Bolger AM"
] ;
ns1:member [ a ns1:Person ;
ns1:name "Lohse M"
] ;
ns1:name "USADELLAB"
] ;
ns1:license "https://opensource.org/licenses/GPL-3.0" ;
ns1:name "trimmomatic" ;
ns1:programmingLanguage "Java" ;
ns1:targetProduct [ a ns1:SoftwareApplication ;
ns1:applicationCategory "command line tool" ;
ns1:softwareVersion "0.35"
] ;
ns1:url "http://www.usadellab.org/cms/?page=trimmomatic" .
rdfs:comment "Dump only aligned sequences\n" ;
cwl:inputBinding [ CommandLineBinding:position 11 ;
CommandLineBinding:prefix "--aligned"
] ;
sld:type xsd:boolean , sld:null .
rdfs:comment "Run -validatePairs. No official documentation\n" ;
cwl:inputBinding [ CommandLineBinding:position 10 ;
CommandLineBinding:prefix "-validatePairs"
] ;
sld:type xsd:boolean , sld:null .
cwl:in ;
cwl:out ;
cwl:run .
rdfs:comment "Append read id after spot id as 'accession.spot.readid' on defline\n" ;
cwl:inputBinding [ CommandLineBinding:position 31 ;
CommandLineBinding:prefix "--readids"
] ;
sld:type xsd:boolean , sld:null .
rdfs:comment "Dump only biological reads\n" ;
cwl:inputBinding [ CommandLineBinding:position 15 ;
CommandLineBinding:prefix "--skip-technical"
] ;
sld:type xsd:boolean , sld:null .
a cwl:ExpressionTool ;
ns2:original_cwlVersion "v1.0" ;
ExpressionTool:expression "${\n var criteria_array = inputs.summary_file.contents.match(/.*Per base sequence quality.*|.*Per sequence quality scores.*|.*Overrepresented sequences.*|.*Adapter Content.*/g);\n if (criteria_array.length > 0){\n if (criteria_array.toString().match(/FAIL/g) != null){\n return { \"trigger\": true };\n } else {\n return { \"trigger\": false };\n }\n } else {\n return { \"trigger\": true };\n }\n}" ;
cwl:cwlVersion ;
cwl:hints [ a ;
LoadListingRequirement:loadListing
"deep_listing"
] ;
cwl:hints [ a ;
LoadListingRequirement:loadListing
"deep_listing"
] ;
cwl:hints [ a ;
NetworkAccess:networkAccess true
] ;
cwl:hints [ a ;
NetworkAccess:networkAccess true
] ;
cwl:inputs ;
cwl:outputs ;
cwl:requirements [ a cwl:InlineJavascriptRequirement ] ;
cwl:requirements [ a cwl:InlineJavascriptRequirement ] .
rdfs:comment "Offset to use for quality conversion, default is 33\n" ;
cwl:inputBinding [ CommandLineBinding:position 27 ;
CommandLineBinding:prefix "--offset"
] ;
sld:type xsd:int , sld:null .
cwl:source .
sld:symbols , ;
sld:type sld:enum .
a ns1:SoftwareSourceCode ;
ns1:about "The SRA Toolkit and SDK from NCBI is a collection of tools and libraries for using data in the INSDC Sequence Read Archives\n" ;
ns1:codeRepository "https://github.com/ncbi/sra-tools" ;
ns1:creator [ a ns1:Organization ;
ns1:member [ a ns1:Organization ;
ns1:name "SRA Toolkit Development Team"
] ;
ns1:name "National Center for Biotechnology Information"
] ;
ns1:discussionUrl "https://github.com/ncbi/sra-tools/issues" ;
ns1:license "United States Government Work" ;
ns1:name "sratoolkit" ;
ns1:programmingLanguage "C" ;
ns1:targetProduct [ a ns1:SoftwareApplication ;
ns1:applicationCategory "command line tool" ;
ns1:softwareVersion "2.8.2-1"
] ;
ns1:url "https://trace.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=toolkit_doc" .
rdfs:comment "Input file\n" ;
cwl:inputBinding [ CommandLineBinding:position
60 ] ;
sld:type cwl:File .
cwl:default "2:30:15" .
rdfs:comment "FASTA only, no qualities, optional line\nwrap width (set to zero for no wrapping)\n" ;
cwl:inputBinding [ CommandLineBinding:position 28 ;
CommandLineBinding:prefix "--fasta"
] ;
sld:type xsd:int , sld:null .
rdfs:comment "Minimum spot id\n" ;
cwl:inputBinding [ CommandLineBinding:position 3 ;
CommandLineBinding:prefix "--minSpotId"
] ;
sld:type xsd:string , sld:null .
cwl:outputSource ;
sld:type cwl:File .
rdfs:comment "Filter by position on genome.\nName can either be accession.version\n(ex:NC_000001.10) or file specific name\n(ex:\"chr1\" or \"1\"). \"from\" and \"to\" are 1-based coordinates\n" ;
cwl:inputBinding [ CommandLineBinding:position 13 ;
CommandLineBinding:prefix "--aligned-region"
] ;
sld:type xsd:string , sld:null .
rdfs:comment "Specifies a non-default file which contains the list of\nadapter sequences which will be explicity searched against\nthe library. The file must contain sets of named adapters\nin the form name[tab]sequence. Lines prefixed with a hash\nwill be ignored.\n" ;
cwl:inputBinding [ CommandLineBinding:position 9 ;
CommandLineBinding:prefix "--adapters"
] ;
cwl:inputBinding [ CommandLineBinding:position 9 ;
CommandLineBinding:prefix "--adapters"
] ;
sld:type cwl:File , sld:null .
sld:type xsd:boolean .
cwl:in , ;
cwl:out , ;
cwl:run .
rdfs:comment "Trimmomatic Log file.\n" ;
cwl:outputBinding [ CommandOutputBinding:glob
"$(inputs.log_filename)" ] ;
sld:type cwl:File , sld:null .
rdfs:comment "Maximum spot id\n" ;
cwl:inputBinding [ CommandLineBinding:position 4 ;
CommandLineBinding:prefix "--maxSpotId"
] ;
sld:type xsd:string , sld:null .
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:StepInputExpressionRequirement ] ;
cwl:requirements [ a cwl:InlineJavascriptRequirement ] ;
cwl:requirements [ a cwl:MultipleInputFeatureRequirement ] .
rdfs:comment "Filter by distance beiween matepairs.\nUse \"unknown\" to find matepairs split\nbetween the references. Use from-to to limit\nmatepair distance on the same reference\n" ;
cwl:inputBinding [ CommandLineBinding:position 14 ;
CommandLineBinding:prefix "--matepair-distance"
] ;
sld:type , sld:null .
cwl:outputSource ;
sld:type cwl:File .
rdfs:comment "Disable grouping of bases for reads >50bp. All reports will\nshow data for every base in the read. WARNING: Using this\noption will cause fastqc to crash and burn if you use it on\nreally long reads, and your plots may end up a ridiculous size.\nYou have been warned!\n" ;
cwl:inputBinding [ CommandLineBinding:position 15 ;
CommandLineBinding:prefix "--nogroup"
] ;
cwl:inputBinding [ CommandLineBinding:position 15 ;
CommandLineBinding:prefix "--nogroup"
] ;
sld:type xsd:boolean , sld:null .
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 12 ;
CommandLineBinding:prefix "-trimlog"
] ;
sld:type xsd:string , sld:null .
sld:type cwl:File .
rdfs:comment "Dump only unaligned sequences\n" ;
cwl:inputBinding [ CommandLineBinding:position 12 ;
CommandLineBinding:prefix "--unaligned"
] ;
sld:type xsd:boolean , sld:null .
rdfs:comment "Defline contains only original sequence name\n" ;
cwl:inputBinding [ CommandLineBinding:position 30 ;
CommandLineBinding:prefix "--origfmt"
] ;
sld:type xsd:boolean , sld:null .
rdfs:comment "JVM arguments should be a quoted, space separated list (e.g. \"-Xms128m -Xmx512m\")" ;
cwl:inputBinding [ CommandLineBinding:position 6 ;
CommandLineBinding:shellQuote false
] ;
sld:type xsd:string , sld:null .
cwl:outputBinding [ CommandOutputBinding:glob
"${\n return inputs.lib_type==\"PE\"?default_output_filename(inputs.fastq_file_upstream, '.unpaired.trimmed.fastq'):null;\n}\n" ] ;
sld:type cwl:File , sld:null .
cwl:outputBinding [ CommandOutputBinding:glob
"${\n return inputs.sra_file.basename.split(\".\")[0] + \"_2.fastq\";\n}\n" ] ;
sld:type cwl:File , sld:null .
rdfs:comment "\nThis module removes reads that fall below the specified minimal length. If required, it should\nnormally be after all other processing steps. Reads removed by this step will be counted and\nincluded in the „dropped reads‟ count presented in the trimmomatic summary.\n: Specifies the minimum length of reads to be kept\n" ;
cwl:inputBinding [ CommandLineBinding:position 106 ;
CommandLineBinding:prefix "MINLEN:" ;
CommandLineBinding:separate false
] ;
sld:type xsd:int , sld:null .
rdfs:comment "Input bam,sam,bam_mapped,sam_mapped or fastq file\n" ;
cwl:inputBinding [ CommandLineBinding:position
50 ] ;
cwl:inputBinding [ CommandLineBinding:position
50 ] ;
sld:type cwl:File .
rdfs:comment "Dump each read into separate file.\nFiles will receive suffix corresponding to read number\n" ;
cwl:inputBinding [ CommandLineBinding:position 20 ;
CommandLineBinding:prefix "--split-files"
] ;
sld:type xsd:boolean , sld:null .
cwl:in ;
cwl:out ;
cwl:run .
cwl:outputBinding [ CommandOutputBinding:glob
"${\n if (inputs.lib_type==\"PE\"){\n return inputs.trigger?default_output_filename(inputs.fastq_file_downstream,'.trimmed.fastq'):inputs.fastq_file_downstream.basename;\n }\n return null;\n}\n" ] ;
sld:type cwl:File , sld:null .
cwl:inputBinding [ cwl:loadContents true ] ;
cwl:inputBinding [ cwl:loadContents true ] ;
sld:type cwl:File .
rdfs:comment "FASTA file containing adapters, PCR sequences, etc. It is used to search\nfor and remove these sequences in the input FASTQ file(s)\n" ;
sld:type cwl:File .
rdfs:comment "This (re)encodes the quality part of the FASTQ file to base 64.\n" ;
cwl:inputBinding [ CommandLineBinding:position 107 ;
CommandLineBinding:prefix "TOPHRED64" ;
CommandLineBinding:separate false
] ;
sld:type xsd:boolean , sld:null .
rdfs:comment "Specifies the length of Kmer to look for in the Kmer content\nmodule. Specified Kmer length must be between 2 and 10. Default\nlength is 7 if not specified.\n" ;
cwl:inputBinding [ CommandLineBinding:position 11 ;
CommandLineBinding:prefix "--kmers"
] ;
cwl:inputBinding [ CommandLineBinding:position 11 ;
CommandLineBinding:prefix "--kmers"
] ;
sld:type xsd:int , sld:null .
cwl:source .
cwl:in ;
cwl:out ;
cwl:run .
rdfs:comment "SE|PE\nSingle End (SE) or Paired End (PE) mode\n" ;
cwl:inputBinding [ CommandLineBinding:position
8 ] ;
sld:type .
rdfs:comment "Defline format specification for sequence.\n" ;
cwl:inputBinding [ CommandLineBinding:position 33 ;
CommandLineBinding:prefix "--defline-seq"
] ;
sld:type xsd:string , sld:null .
sld:symbols , ;
sld:type sld:enum .
cwl:default true .
rdfs:comment "supress quality-value for cskey\n" ;
cwl:inputBinding [ CommandLineBinding:position 29 ;
CommandLineBinding:prefix "--suppress-qual-for-cskey"
] ;
sld:type xsd:boolean , sld:null .
rdfs:comment "FASTQ file for input read (read R1 in Paired End mode)\n" ;
cwl:inputBinding [ CommandLineBinding:position
13 ] ;
sld:type cwl:File .
rdfs:comment "Helicos style defline\n" ;
cwl:inputBinding [ CommandLineBinding:position 32 ;
CommandLineBinding:prefix "--helicos"
] ;
sld:type xsd:boolean , sld:null .
rdfs:comment "disable multithreading\n" ;
cwl:inputBinding [ CommandLineBinding:position 35 ;
CommandLineBinding:prefix "--disable-multithreading"
] ;
sld:type xsd:boolean , sld:null .
rdfs:comment "Formats sequence using base space (default\nfor other than SOLiD).\n" ;
cwl:inputBinding [ CommandLineBinding:position 26 ;
CommandLineBinding:prefix "--dumpbase"
] ;
sld:type xsd:boolean , sld:null .
cwl:source .
sld:type cwl:File .
rdfs:comment "Specifies the number of files which can be processed\nsimultaneously. Each thread will be allocated 250MB of\nmemory so you shouldn't run more threads than your\navailable memory will cope with, and not more than\n6 threads on a 32 bit machine\n" ;
cwl:inputBinding [ CommandLineBinding:position 7 ;
CommandLineBinding:prefix "--threads"
] ;
cwl:inputBinding [ CommandLineBinding:position 7 ;
CommandLineBinding:prefix "--threads"
] ;
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:inputBinding [ CommandLineBinding:position 9 ;
CommandLineBinding:prefix "-phred" ;
CommandLineBinding:separate false
] ;
sld:type , sld:null .
rdfs:comment "Specifies a non-default file which contains the list of\ncontaminants to screen overrepresented sequences against.\nThe file must contain sets of named contaminants in the\nform name[tab]sequence. Lines prefixed with a hash will\nbe ignored.\n" ;
cwl:inputBinding [ CommandLineBinding:position 8 ;
CommandLineBinding:prefix "--contaminants"
] ;
cwl:inputBinding [ CommandLineBinding:position 8 ;
CommandLineBinding:prefix "--contaminants"
] ;
sld:type cwl:File , sld:null .
cwl:outputBinding [ CommandOutputBinding:glob
"*.zip" ] ;
cwl:outputBinding [ CommandOutputBinding:glob
"*.zip" ] ;
sld:type cwl:File .
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 104 ;
CommandLineBinding:prefix "CROP:" ;
CommandLineBinding:separate false
] ;
sld:type xsd:int , sld:null .
a cwl:CommandLineTool ;
rdfs:comment "Tool runs fastq-dump from NCBI SRA toolkit\nSupports only file inputs.\nOutput file names are formed on the base of `sra_file` input basename.\n" ;
ns2:original_cwlVersion "v1.0" ;
ns1:about "Usage:\n fastq-dump [options] [...]\n fastq-dump [options] \n\nINPUT\n -A|--accession Replaces accession derived from in\n filename(s) and deflines (only for single\n table dump)\n --table Table name within cSRA object, default is\n \"SEQUENCE\"\n\nPROCESSING\n\nRead Splitting Sequence data may be used in raw form or\n split into individual reads\n --split-spot Split spots into individual reads\n\nFull Spot Filters Applied to the full spot independently\n of --split-spot\n -N|--minSpotId Minimum spot id\n -X|--maxSpotId Maximum spot id\n --spot-groups <[list]> Filter by SPOT_GROUP (member): name[,...]\n -W|--clip Clip adapter sequences\n\nCommon Filters Applied to spots when --split-spot is not\n set, otherwise - to individual reads\n -M|--minReadLen Filter by sequence length >= \n -R|--read-filter <[filter]> Split into files by READ_FILTER value\n optionally filter by value:\n pass|reject|criteria|redacted\n -E|--qual-filter Filter used in early 1000 Genomes data: no\n sequences starting or ending with >= 10N\n --qual-filter-1 Filter used in current 1000 Genomes data\n\nFilters based on alignments Filters are active when alignment\n data are present\n --aligned Dump only aligned sequences\n --unaligned Dump only unaligned sequences\n --aligned-region Filter by position on genome. Name can\n either be accession.version (ex:\n NC_000001.10) or file specific name (ex:\n \"chr1\" or \"1\"). \"from\" and \"to\" are 1-based\n coordinates\n --matepair-distance Filter by distance between matepairs.\n Use \"unknown\" to find matepairs split\n between the references. Use from-to to limit\n matepair distance on the same reference\n\nFilters for individual reads Applied only with --split-spot set\n --skip-technical Dump only biological reads\n\nOUTPUT\n -O|--outdir Output directory, default is working\n directory '.' )\n -Z|--stdout Output to stdout, all split data become\n joined into single stream\n --gzip Compress output using gzip\n --bzip2 Compress output using bzip2\n\nMultiple File Options Setting these options will produce more\n than 1 file, each of which will be suffixed\n according to splitting criteria.\n --split-files Dump each read into separate file.Files\n will receive suffix corresponding to read\n number\n --split-3 Legacy 3-file splitting for mate-pairs:\n First biological reads satisfying dumping\n conditions are placed in files *_1.fastq and\n *_2.fastq If only one biological read is\n present it is placed in *.fastq Biological\n reads and above are ignored.\n -G|--spot-group Split into files by SPOT_GROUP (member name)\n -R|--read-filter <[filter]> Split into files by READ_FILTER value\n optionally filter by value:\n pass|reject|criteria|redacted\n -T|--group-in-dirs Split into subdirectories instead of files\n -K|--keep-empty-files Do not delete empty files\n\nFORMATTING\n\nSequence\n -C|--dumpcs <[cskey]> Formats sequence using color space (default\n for SOLiD),\"cskey\" may be specified for\n translation\n -B|--dumpbase Formats sequence using base space (default\n for other than SOLiD).\n\nQuality\n -Q|--offset Offset to use for quality conversion,\n default is 33\n --fasta <[line width]> FASTA only, no qualities, optional line\n wrap width (set to zero for no wrapping)\n --suppress-qual-for-cskey suppress quality-value for cskey\n\nDefline\n -F|--origfmt Defline contains only original sequence name\n -I|--readids Append read id after spot id as\n 'accession.spot.readid' on defline\n --helicos Helicos style defline\n --defline-seq Defline format specification for sequence.\n --defline-qual Defline format specification for quality.\n is string of characters and/or\n variables. The variables can be one of: $ac\n - accession, $si spot id, $sn spot\n name, $sg spot group (barcode), $sl spot\n length in bases, $ri read number, $rn\n read name, $rl read length in bases. '[]'\n could be used for an optional output: if\n all vars in [] yield empty values whole\n group is not printed. Empty value is empty\n string or for numeric variables. Ex:\n @$sn[_$rn]/$ri '_$rn' is omitted if name\n is empty\n\nOTHER:\n --disable-multithreading disable multithreading\n -h|--help Output brief explanation of program usage\n -V|--version Display the version of the program\n -L|--log-level Logging level as number or enum string One\n of (fatal|sys|int|err|warn|info) or (0-5)\n Current/default is warn\n -v|--verbose Increase the verbosity level of the program\n Use multiple times for more verbosity\n --ncbi_error_report Control program execution environment\n report generation (if implemented). One of\n (never|error|always). Default is error\n --legacy-report use legacy style 'Written spots' for tool\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/fastq-dump.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 "fastq-dump" ;
cwl:baseCommand ( "fastq-dump" ) ;
cwl:cwlVersion ;
cwl:hints [ a cwl:DockerRequirement ;
DockerRequirement:dockerPull "biowardrobe2/sratoolkit:v2.8.2-1"
] ;
cwl:hints [ a ;
NetworkAccess:networkAccess true
] ;
cwl:hints [ a ;
LoadListingRequirement:loadListing
"deep_listing"
] ;
cwl:inputs , , , , , , , , , , , , , , , , , , , , , , , , , ;
cwl:outputs , ;
cwl:requirements [ a cwl:InlineJavascriptRequirement ] .
rdfs:comment "Files come from raw casava output. Files in the same sample\ngroup (differing only by the group number) will be analysed\nas a set rather than individually. Sequences with the filter\nflag set in the header will be excluded from the analysis.\nFiles must have the same names given to them by casava\n(including being gzipped and ending with .gz) otherwise they\nwon't be grouped together correctly.\n" ;
cwl:inputBinding [ CommandLineBinding:position 13 ;
CommandLineBinding:prefix "--casava"
] ;
cwl:inputBinding [ CommandLineBinding:position 13 ;
CommandLineBinding:prefix "--casava"
] ;
sld:type xsd:boolean , sld:null .
sld:type xsd:int , sld:null .
cwl:outputBinding [ CommandOutputBinding:glob
"${\n return inputs.lib_type==\"PE\"?default_output_filename(inputs.fastq_file_downstream, '.unpaired.trimmed.fastq'):null;\n}\n" ] ;
sld:type cwl:File , sld:null .
rdfs:comment "This (re)encodes the quality part of the FASTQ file to base 33.\n" ;
cwl:inputBinding [ CommandLineBinding:position 107 ;
CommandLineBinding:prefix "TOPHRED33" ;
CommandLineBinding:separate false
] ;
sld:type xsd:boolean , sld:null .
cwl:default "/usr/share/java/trimmomatic.jar" ;
cwl:inputBinding [ CommandLineBinding:position 7 ;
CommandLineBinding:prefix "-jar"
] ;
sld:type xsd:string .
rdfs:comment "Clip adapter sequences\n" ;
cwl:inputBinding [ CommandLineBinding:position 6 ;
CommandLineBinding:prefix "--clip"
] ;
sld:type xsd:boolean , sld:null .
a cwl:CommandLineTool ;
rdfs:comment "Tool runs trimmomatic with ILLUMINACLIP step by default.\n\n`-basein` and `-baseout` inputs are skipped.\n\nIf set `lib_type` to `PE`, both of the inputs `fastq_file_upstream` and `fastq_file_downstream` shoul be provided.\n\nIf input `trigger` is set to `true` or isn't set at all (`true` is used by default), run `trimmomatic` and return\nFASTQ file[s] with trimmed adapters, alongside with the uppaired reads FASTQ files (if `lib_type` is set to `PE` and\nsuch files are present after running `trimmomatic`)\nIf input `trigger` is set to `false`, return unchanged `fastq_file_upstream` and `fastq_file_downstream`, previously\nstaged into output directory.\n\nBefore execution `baseCommand`, `fastq_file_upstream` and `fastq_file_downstream` (if provided) are staged into directory\nset as docker parameter `--workdir` (tool's output directory), using `InitialWorkDirRequirement`. They are mount\nto docker container with `ro` mode as part of `--workdir`, because all generated files will have `trimmed` suffix\nin their names, so the staged files will not be overwritten.\n\nTrigger logic is implemented in a bash scripts set by default as `bash_script` input. If the first argument $0 (which is\n`trigger` input) is true, run `trimmomatic` with the rest of the arguments. If $0 is not true, skip `trimmomatic` and\nreturn `fastq_file_upstream` and `fastq_file_downstream` (if provided) staged into output directory.\n\nInput `trigger` is Boolean, but returns String, because of `valueFrom` field. The `valueFrom` is used, because if `trigger`\nis false, cwl-runner doesn't append this argument at all to the the `baseCommand` - new feature of CWL v1.0.2. Alternatively,\n`prefix` field could be used, but it causes changing in script logic.\n\n`default_output_name` function is used for generating output filename based on `input_file.basename` and provided\nextension.\n" ;
ns2:original_cwlVersion "v1.0" ;
ns1:about "Usage:\n PE [-threads ] [-phred33|-phred64] [-trimlog ] [-quiet] [-validatePairs] [-basein | ] [-baseout | ] ...\n or:\n SE [-threads ] [-phred33|-phred64] [-trimlog ] [-quiet] ...\n" ;
ns1:codeRepository "https://github.com/Barski-lab/workflows" ;
ns1:creator [ a ns1:Organization ;
ns1:department [ a ns1:Organization ;
ns1:department [ a ns1:Organization ;
ns1:legalName "Barski Research Lab" ;
ns1:member [ a ns1:Person ;
ns1:email "mailto:misha.kotliar@gmail.com" ;
ns1:name "Michael Kotliar" ;
ns1:sameAs
]
] ;
ns1:legalName "Allergy and Immunology"
] ;
ns1:legalName "Cincinnati Children's Hospital Medical Center" ;
ns1:location [ a ns1:PostalAddress ;
ns1:addressCountry "USA" ;
ns1:addressLocality "Cincinnati" ;
ns1:addressRegion "OH" ;
ns1:postalCode "45229" ;
ns1:streetAddress "3333 Burnet Ave" ;
ns1:telephone "+1(513)636-4200"
] ;
ns1:logo "https://www.cincinnatichildrens.org/-/media/cincinnati%20childrens/global%20shared/childrens-logo-new.png"
] ;
ns1:downloadUrl "https://raw.githubusercontent.com/Barski-lab/workflows/master/tools/trimmomatic.cwl" ;
ns1:isPartOf [ a ns1:CreativeWork ;
ns1:name "Common Workflow Language" ;
ns1:url "http://commonwl.org/"
] ;
ns1:license "http://www.apache.org/licenses/LICENSE-2.0" ;
ns1:mainEntity ;
ns1:name "trimmomatic" ;
cwl:arguments ( [ CommandLineBinding:position 15 ;
cwl:valueFrom "$(default_output_filename(inputs.fastq_file_upstream, '.trimmed.fastq'))"
]
[ CommandLineBinding:position 16 ;
cwl:valueFrom "$(inputs.lib_type==\"PE\"?default_output_filename(inputs.fastq_file_upstream, '.trimmed.unpaired.fastq'):null)"
]
[ CommandLineBinding:position 17 ;
cwl:valueFrom "$(inputs.lib_type==\"PE\"?default_output_filename(inputs.fastq_file_downstream, '.trimmed.fastq'):null)"
]
[ CommandLineBinding:position 18 ;
cwl:valueFrom "$(inputs.lib_type==\"PE\"?default_output_filename(inputs.fastq_file_downstream, '.trimmed.unpaired.fastq'):null)"
]
[ CommandLineBinding:position 100 ;
cwl:valueFrom "$(\"ILLUMINACLIP:\" + inputs.adapters_file.path + \":\"+ inputs.illuminaclip_step_param)"
]
) ;
cwl:baseCommand ( "bash" "-c" ) ;
cwl:cwlVersion ;
cwl:hints [ a ;
NetworkAccess:networkAccess true
] ;
cwl:hints [ a ;
LoadListingRequirement:loadListing
"deep_listing"
] ;
cwl:hints [ a cwl:DockerRequirement ;
DockerRequirement:dockerPull "biowardrobe2/trimmomatic:v0.35"
] ;
cwl:inputs , , , , , , , , , ,