@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 "Filename for the kallisto index to be constructed\n" ;
sld:type xsd:string , sld:null .
rdfs:comment "Replace repeated target names with unique names\n" ;
sld:type xsd:boolean , sld:null .
rdfs:comment "k-mer (odd) length (default: 31, max value: 31)\n" ;
cwl:inputBinding [ CommandLineBinding:position 6 ;
CommandLineBinding:prefix "--kmer-size"
] ;
sld:type xsd:int , sld:null .
cwl:source .
cwl:outputSource ;
sld:type cwl:File .
rdfs:comment "Genome file in FASTA format, uncompressed\n" ;
sld:type cwl:File .
rdfs:comment "GTF annotation file\n" ;
sld:type cwl:File .
a cwl:CommandLineTool ;
rdfs:comment "kallisto index builds an index from a FASTA formatted file of target sequences\n" ;
ns2:original_cwlVersion "v1.0" ;
ns1:about "Usage: kallisto index [arguments] FASTA-files\n\nRequired argument:\n-i, --index=STRING Filename for the kallisto index to be constructed \n\nOptional argument:\n-k, --kmer-size=INT k-mer (odd) length (default: 31, max value: 31)\n --make-unique Replace repeated target names with unique names" ;
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/kallisto-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:name "kallisto-index" ;
cwl:baseCommand ( "kallisto" "index" ) ;
cwl:cwlVersion ;
cwl:hints [ a cwl:DockerRequirement ;
DockerRequirement:dockerPull "quay.io/biocontainers/kallisto:0.46.2--h4f7b962_1"
] ;
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 get_output_filename = function() { if (inputs.output_filename == \"\"){ var ext = \".idx\"; var root = inputs.transcriptome_fasta_file.basename.split('.').slice(0,-1).join('.'); return (root == \"\")?inputs.transcriptome_fasta_file.basename+ext:root+ext; } else { return inputs.output_filename; } };"
] ;
cwl:stderr "kallisto_index_stderr.log" ;
cwl:stdout "kallisto_index_stdout.log" .
cwl:in , ;
cwl:out ;
cwl:run .
cwl:outputSource ;
sld:type cwl:File .
cwl:source .
rdfs:comment "Filename for the kallisto index to be constructed\n" ;
cwl:default "" ;
cwl:inputBinding [ CommandLineBinding:position 7 ;
CommandLineBinding:prefix "--index" ;
cwl:valueFrom "$(get_output_filename())"
] ;
sld:type xsd:string , sld:null .
rdfs:comment "Transcriptome FASTA file, optionally gzipped\n" ;
cwl:inputBinding [ CommandLineBinding:position
10 ] ;
sld:type cwl:File .
rdfs:comment "Genome file in FASTA format, uncompressed\n" ;
cwl:inputBinding [ CommandLineBinding:position 5 ;
CommandLineBinding:prefix "-g"
] ;
cwl:secondaryFiles [] ;
sld:type cwl:File .
cwl:outputSource ;
sld:type cwl:File .
a cwl:CommandLineTool ;
rdfs:comment "Generates a FASTA file with the DNA sequences for all transcripts in a GFF file\n" ;
ns2:original_cwlVersion "v1.0" ;
ns1:about "Usage:\n gffread [-g | ][-s ] \n [-o ] [-t ] [-r [[]:].. [-R]]\n [-CTVNJMKQAFPGUBHZWTOLE] [-w ] [-x ] [-y ]\n [-i ] [--bed] [--table ] [--sort-by ]\n \n Filter, convert or cluster GFF/GTF/BED records, extract the sequence of\n transcripts (exon or CDS) and more.\n By default (i.e. without -O) only transcripts are processed, discarding any\n other non-transcript features. Default output is a simplified GFF3 with only\n the basic attributes.\n \n is a GFF file, use '-' for stdin\n \n Options:\n -i discard transcripts having an intron larger than \n -l discard transcripts shorter than bases\n -r only show transcripts overlapping coordinate range ..\n (on chromosome/contig , strand if provided)\n -R for -r option, discard all transcripts that are not fully \n contained within the given range\n -U discard single-exon transcripts\n -C coding only: discard mRNAs that have no CDS features\n --nc non-coding only: discard mRNAs that have CDS features\n --ignore-locus : discard locus features and attributes found in the input\n -A use the description field from and add it\n as the value for a 'descr' attribute to the GFF record\n -s is a tab-delimited file providing this info\n for each of the mapped sequences:\n \n (useful for -A option with mRNA/EST/protein mappings)\n Sorting: (by default, chromosomes are kept in the order they were found)\n --sort-alpha : chromosomes (reference sequences) are sorted alphabetically\n --sort-by : sort the reference sequences by the order in which their\n names are given in the file\n Misc options: \n -F preserve all GFF attributes (for non-exon features)\n --keep-exon-attrs : for -F option, do not attempt to reduce redundant\n exon/CDS attributes\n -G do not keep exon attributes, move them to the transcript feature\n (for GFF3 output)\n --keep-genes : in transcript-only mode (default), also preserve gene records\n --keep-comments: for GFF3 input/output, try to preserve comments\n -O process other non-transcript GFF records (by default non-transcript\n records are ignored)\n -V discard any mRNAs with CDS having in-frame stop codons (requires -g)\n -H for -V option, check and adjust the starting CDS phase\n if the original phase leads to a translation with an \n in-frame stop codon\n -B for -V option, single-exon transcripts are also checked on the\n opposite strand (requires -g)\n -P add transcript level GFF attributes about the coding status of each\n transcript, including partialness or in-frame stop codons (requires -g)\n --add-hasCDS : add a \"hasCDS\" attribute with value \"true\" for transcripts\n that have CDS features\n --adj-stop stop codon adjustment: enables -P and performs automatic\n adjustment of the CDS stop coordinate if premature or downstream\n -N discard multi-exon mRNAs that have any intron with a non-canonical\n splice site consensus (i.e. not GT-AG, GC-AG or AT-AC)\n -J discard any mRNAs that either lack initial START codon\n or the terminal STOP codon, or have an in-frame stop codon\n (i.e. only print mRNAs with a complete CDS)\n --no-pseudo: filter out records matching the 'pseudo' keyword\n --in-bed: input should be parsed as BED format (automatic if the input\n filename ends with .bed*)\n --in-tlf: input GFF-like one-line-per-transcript format without exon/CDS\n features (see --tlf option below); automatic if the input\n filename ends with .tlf)\n Clustering:\n -M/--merge : cluster the input transcripts into loci, discarding\n \"duplicated\" transcripts (those with the same exact introns\n and fully contained or equal boundaries)\n -d : for -M option, write duplication info to file \n --cluster-only: same as -M/--merge but without discarding any of the\n \"duplicate\" transcripts, only create \"locus\" features\n -K for -M option: also discard as redundant the shorter, fully contained\n transcripts (intron chains matching a part of the container)\n -Q for -M option, no longer require boundary containment when assessing\n redundancy (can be combined with -K); only introns have to match for\n multi-exon transcripts, and >=80% overlap for single-exon transcripts\n -Y for -M option, enforce -Q but also discard overlapping single-exon \n transcripts, even on the opposite strand (can be combined with -K)\n Output options:\n --force-exons: make sure that the lowest level GFF features are considered\n \"exon\" features\n --gene2exon: for single-line genes not parenting any transcripts, add an\n exon feature spanning the entire gene (treat it as a transcript)\n --t-adopt: try to find a parent gene overlapping/containing a transcript\n that does not have any explicit gene Parent\n -D decode url encoded characters within attributes\n -Z merge very close exons into a single exon (when intron size<4)\n -g full path to a multi-fasta file with the genomic sequences\n for all input mappings, OR a directory with single-fasta files\n (one per genomic sequence, with file names matching sequence names)\n -w write a fasta file with spliced exons for each transcript\n --w-add for the -w option, extract additional bases\n both upstream and downstream of the transcript boundaries\n -x write a fasta file with spliced CDS for each GFF transcript\n -y write a protein fasta file with the translation of CDS for each record\n -W for -w and -x options, write in the FASTA defline the exon\n coordinates projected onto the spliced sequence;\n for -y option, write transcript attributes in the FASTA defline\n -S for -y option, use '*' instead of '.' as stop codon translation\n -L Ensembl GTF to GFF3 conversion (implies -F; should be used with -m)\n -m is a name mapping table for converting reference \n sequence names, having this 2-column format:\n \n -t use in the 2nd column of each GFF/GTF output line\n -o write the records into instead of stdout\n -T main output will be GTF instead of GFF3\n --bed output records in BED format instead of default GFF3\n --tlf output \"transcript line format\" which is like GFF\n but exons, CDS features and related data are stored as GFF \n attributes in the transcript feature line, like this:\n exoncount=N;exons=;CDSphase=;CDS= \n is a comma-delimited list of exon_start-exon_end coordinates;\n is CDS_start:CDS_end coordinates or a list like \n --table output a simple tab delimited format instead of GFF, with columns\n having the values of GFF attributes given in ; special\n pseudo-attributes (prefixed by @) are recognized:\n @id, @geneid, @chr, @start, @end, @strand, @numexons, @exons, \n @cds, @covlen, @cdslen\n -v,-E expose (warn about) duplicate transcript IDs and other potential\n problems with the given GFF/GTF records" ;
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/gffread.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 "gffread" ;
cwl:baseCommand ( "gffread" ) ;
cwl:cwlVersion ;
cwl:hints [ a cwl:DockerRequirement ;
DockerRequirement:dockerPull "quay.io/biocontainers/gffread:0.11.7--h8b12597_0"
] ;
cwl:hints [ a ;
NetworkAccess:networkAccess true
] ;
cwl:hints [ a ;
LoadListingRequirement:loadListing
"deep_listing"
] ;
cwl:inputs , , ;
cwl:outputs , , ;
cwl:requirements [ a cwl:InlineJavascriptRequirement ;
InlineJavascriptRequirement:expressionLib
"var get_output_filename = function() { if (inputs.output_filename == \"\"){ var ext = \".fa\"; var root = inputs.genome_fasta_file.basename.split('.').slice(0,-1).join('.'); return (root == \"\")?inputs.genome_fasta_file.basename+ext:root+ext; } else { return inputs.output_filename; } };"
] ;
cwl:stderr "gffread_stderr.log" ;
cwl:stdout "gffread_stdout.log" .
cwl:outputBinding [ CommandOutputBinding:glob
"gffread_stdout.log" ] ;
sld:type cwl:File .
cwl:source .
cwl:source .
cwl:outputBinding [ CommandOutputBinding:glob
"$(get_output_filename())" ] ;
sld:type cwl:File .
cwl:outputSource ;
sld:type cwl:File .
cwl:outputBinding [ CommandOutputBinding:glob
"kallisto_index_stdout.log" ] ;
sld:type cwl:File .
cwl:outputBinding [ CommandOutputBinding:glob
"kallisto_index_stderr.log" ] ;
sld:type cwl:File .
rdfs:comment "k-mer (odd) length (default: 31, max value: 31)\n" ;
sld:type xsd:int , sld:null .
a cwl:Workflow ;
rdfs:comment "Generates a FASTA file with the DNA sequences for all transcripts in a GFF file and builds kallisto index\n" ;
ns2:original_cwlVersion "v1.0" ;
ns1:about "Usage: kallisto index [arguments] FASTA-files\n\nRequired argument:\n-i, --index=STRING Filename for the kallisto index to be constructed \n\nOptional argument:\n-k, --kmer-size=INT k-mer (odd) length (default: 31, max value: 31)\n --make-unique Replace repeated target names with unique names" ;
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/genome-kallisto-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:name "genome-kallisto-index" ;
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:StepInputExpressionRequirement ] ;
cwl:requirements [ a cwl:InlineJavascriptRequirement ] .
rdfs:comment "GTF annotation file\n" ;
cwl:inputBinding [ CommandLineBinding:position
10 ] ;
sld:type cwl:File .
cwl:outputBinding [ CommandOutputBinding:glob
"gffread_stderr.log" ] ;
sld:type cwl:File .
cwl:source .
cwl:source .
cwl:outputBinding [ CommandOutputBinding:glob
"$(get_output_filename())" ] ;
sld:type cwl:File .
rdfs:comment "Replace repeated target names with unique names\n" ;
cwl:inputBinding [ CommandLineBinding:position 5 ;
CommandLineBinding:prefix "--make-unique"
] ;
sld:type xsd:boolean , sld:null .
rdfs:comment "Filename for generated transcriptome FASTA file\n" ;
cwl:default "" ;
cwl:inputBinding [ CommandLineBinding:position 6 ;
CommandLineBinding:prefix "-w" ;
cwl:valueFrom "$(get_output_filename())"
] ;
sld:type xsd:string , sld:null .
cwl:in , , , ;
cwl:out , , ;
cwl:run .