@prefix SchemaDefRequirement: . @prefix CommandLineBinding: . @prefix EnvVarRequirement: . @prefix xsd: . @prefix Workflow: . @prefix sld: . @prefix rdfs: . @prefix CommandOutputBinding: . @prefix ns2: . @prefix SoftwarePackage: . @prefix ns1: . @prefix SoftwareRequirement: . @prefix rdf: . @prefix EnvironmentDef: . @prefix Parameter: . @prefix cwl: . @prefix ResourceRequirement: . @prefix CommandLineTool: . cwl:source . cwl:outputSource ; sld:type xsd:int . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.sequences.basename).filtered.fasta" ] ; sld:type cwl:File . rdfs:label "label to add to the top of the outfile OTU table" ; cwl:inputBinding [ CommandLineBinding:prefix "--label" ] ; sld:type xsd:string . sld:type cwl:File . rdfs:label "continue with the main workflow" ; cwl:in , , , , , , , , , ; cwl:out , , , , , , , , , , , , , , , , , , , , , , , , , , ; cwl:run . cwl:source . a cwl:CommandLineTool ; ns2:original_cwlVersion "v1.2" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:baseCommand ( "cat" ) ; cwl:baseCommand ( "cat" ) ; cwl:baseCommand ( "cat" ) ; cwl:baseCommand ( "cat" ) ; cwl:baseCommand ( "cat" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:stdout "result" . Parameter:streamable true ; cwl:format ; sld:type cwl:File . cwl:outputSource ; sld:type xsd:int . a cwl:Workflow ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; Workflow:steps , ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs . cwl:source . cwl:source . a cwl:CommandLineTool ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( [ CommandLineBinding:prefix "--output-file" ; cwl:valueFrom "go-summary" ] ) ; cwl:baseCommand ( "go_summary_pipeline-1.0.py" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "owltools" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_005732" ; SoftwarePackage:version "8d53bbce1ffe60d9aa3357c1001599f9a882317a" ] ] ; cwl:inputs , ; cwl:outputs , ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 10240 ] . cwl:format ; sld:type cwl:File . cwl:source . sld:fields , , , , , , , , ; sld:type sld:record . cwl:source . cwl:in , , ; cwl:out ; cwl:run . cwl:format ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:source . rdfs:label "Output as JSON-formatted table." ; cwl:inputBinding [ CommandLineBinding:prefix "--to-json" ] ; cwl:inputBinding [ CommandLineBinding:prefix "--to-json" ] ; sld:type xsd:boolean , sld:null . a cwl:CommandLineTool ; rdfs:comment "sequence read classification tools designed to assign taxonomy and OTU\nclassifications to ribosomal RNA sequences.\nhttp://meringlab.org/software/mapseq/\n" ; rdfs:label "MAPseq" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( [ CommandLineBinding:prefix "-nthreads" ; cwl:valueFrom "4" ] ) ; cwl:baseCommand ( "mapseq" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "mapseq" ; SoftwarePackage:version "1.0" ] ] ; cwl:hints [ a ] ; cwl:inputs , , ; cwl:outputs ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 10240 ] ; cwl:stdout "classifications" . cwl:outputSource ; sld:type cwl:File . cwl:in ; cwl:out ; cwl:run . cwl:source . cwl:in ; cwl:out , , ; cwl:run . sld:fields , ; sld:type sld:record . sld:type xsd:string . a cwl:CommandLineTool ; rdfs:comment "http://eddylab.org/infernal/Userguide.pdf" ; rdfs:label "search sequence(s) against a covariance model database" ; ns2:original_cwlVersion "v1.2" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( [ CommandLineBinding:prefix "--tblout" ; cwl:valueFrom "matches.tbl" ] [ CommandLineBinding:prefix "--cpu" ; cwl:valueFrom "$(runtime.cores)" ] ) ; cwl:arguments ( [ CommandLineBinding:prefix "--tblout" ; cwl:valueFrom "matches.tbl" ] [ CommandLineBinding:prefix "--cpu" ; cwl:valueFrom "$(runtime.cores)" ] ) ; cwl:baseCommand ( "cmsearch" ) ; cwl:baseCommand ( "cmsearch" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "infernal" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_011809" ; SoftwarePackage:version "1.1.2" ] ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "infernal" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_011809" ; SoftwarePackage:version "1.1.2" ] ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , , , , , ; cwl:outputs ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMin 4 ; ResourceRequirement:ramMin 10240 ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMin 4 ; ResourceRequirement:ramMin 10240 ] . Parameter:streamable true ; cwl:format ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:inputBinding [ CommandLineBinding:prefix "-p" ] ; sld:type xsd:int , sld:null . cwl:source . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "reformatted_sequences" ] ; cwl:outputBinding [ CommandOutputBinding:glob "reformatted_sequences" ] ; sld:type cwl:File . cwl:source . cwl:outputSource ; sld:type xsd:int . cwl:outputSource ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:source . cwl:source . rdfs:comment "Matches are generated against predicted CDS, using a sub set of databases\n(Pfam, TIGRFAM, PRINTS, PROSITE patterns, Gene3d) from InterPro. \n" ; cwl:in , ; cwl:out ; cwl:run ; cwl:scatter ( ) . cwl:source . cwl:source . cwl:source . cwl:default true . cwl:outputSource ; sld:type cwl:File . cwl:source . cwl:outputSource ; sld:type cwl:File . a cwl:Workflow ; rdfs:label "EMG assembly for paired end Illumina" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; Workflow:steps , , ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , , , , , , , , , , , , ; cwl:outputs , , , , , , , , , , , , , , , , , , , , , , , , , , , ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types , , , , ] ; cwl:requirements [ a cwl:SubworkflowFeatureRequirement ] ; cwl:requirements [ a cwl:StepInputExpressionRequirement ] . sld:type cwl:File . sld:type xsd:int . cwl:in ; cwl:out ; cwl:run . cwl:format ; sld:type cwl:File . cwl:source . cwl:default true . cwl:source . cwl:outputSource ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "predicted_cds.faa" ] ; sld:type cwl:File . Parameter:streamable true ; sld:type cwl:File . cwl:in , , ; cwl:out ; cwl:run . sld:symbols , , , , , , , , , , , , , , ; sld:type sld:enum . cwl:outputSource ; sld:type cwl:File . cwl:default false . cwl:default "OTU table" . sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . sld:type xsd:int . cwl:source . cwl:source . a cwl:Workflow ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; Workflow:steps , ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs . rdfs:label "Contains the binned length distribution, real numbers" ; cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.length_sum)_bin" ] ; sld:type cwl:File . cwl:in , , ; cwl:out , , ; cwl:run . cwl:in , , , , ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatter ( ) . sld:type xsd:int . rdfs:label "Maximum number of sequences to sub-sample" ; cwl:default 2000000 ; cwl:inputBinding [ CommandLineBinding:prefix "-m" ] ; sld:type xsd:int , sld:null . rdfs:comment "http://eddylab.org/infernal/Userguide.pdf#page=60" ; rdfs:label "target hits table, format 2" ; cwl:outputBinding [ CommandOutputBinding:glob "matches.tbl" ] ; cwl:outputBinding [ CommandOutputBinding:glob "matches.tbl" ] ; sld:type cwl:File . cwl:in , , ; cwl:out ; cwl:run . rdfs:label "Contains the binned GC distribution, real numbers" ; cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.gc_sum)_bin" ] ; sld:type cwl:File . cwl:default 100000 . cwl:default true . cwl:source . rdfs:label "Backward probability model" ; sld:type cwl:File . cwl:inputBinding [ CommandLineBinding:itemSeparator "," ; CommandLineBinding:prefix "--applications" ] ; sld:type sld:null ; sld:type [ sld:items ; sld:type sld:array ] . Parameter:streamable true ; sld:type cwl:File . Parameter:streamable true ; sld:type cwl:File . a cwl:CommandLineTool ; rdfs:comment "https://github.com/EddyRivasLab/easel" ; rdfs:label "index a sequence file for use by esl-sfetch" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:baseCommand ( "esl-sfetch" "--index" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "easel" ] ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 1024 ] ; cwl:requirements [ a cwl:InitialWorkDirRequirement ; cwl:listing "$(inputs.sequences)" ] . cwl:in ; cwl:out , , , , , , , ; cwl:run . cwl:outputSource ; sld:type cwl:File . cwl:source . sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:source . cwl:in , ; cwl:out ; cwl:run . cwl:default "OTU table" . rdfs:label "Contains the binned length distribution expressed as percentage" ; cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.length_sum)_pcbin" ] ; sld:type cwl:File . a cwl:Workflow ; ns2:original_cwlVersion "v1.2" ; Workflow:steps , , ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , , ; cwl:outputs ; cwl:requirements [ a cwl:ScatterFeatureRequirement ] ; cwl:requirements [ a cwl:ScatterFeatureRequirement ] . rdfs:label "Tab-delimited text file" ; cwl:format ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . a cwl:CommandLineTool ; ns2:original_cwlVersion "v1.2" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( [ CommandLineBinding:prefix "--output-fp" ; cwl:valueFrom "${ var ext = \"\";\n if (inputs.json) { ext = \".json\"; }\n if (inputs.hdf5) { ext = \".hdf5\"; }\n if (inputs.tsv) { ext = \".tsv\"; }\n return inputs.biom.nameroot + ext; }\n" ] ) ; cwl:arguments ( [ CommandLineBinding:prefix "--output-fp" ; cwl:valueFrom "${ var ext = \"\";\n if (inputs.json) { ext = \".json\"; }\n if (inputs.hdf5) { ext = \".hdf5\"; }\n if (inputs.tsv) { ext = \".tsv\"; }\n return inputs.biom.nameroot + ext; }\n" ] ) ; cwl:baseCommand ( "biom" "convert" ) ; cwl:baseCommand ( "biom" "convert" ) ; cwl:cwlVersion ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "biom-format" ; SoftwarePackage:specs "https://doi.org/10.1186/2047-217X-1-7" ; SoftwarePackage:version "2.1.6" ] ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "biom-format" ; SoftwarePackage:specs "https://doi.org/10.1186/2047-217X-1-7" ; SoftwarePackage:version "2.1.6" ] ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , , , , , ; cwl:outputs ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types ] ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . rdfs:label "sequence file indexed by esl-sfetch-index" ; cwl:format ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-f" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-f" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-f" ] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; sld:type cwl:File . sld:type cwl:File . cwl:outputBinding [ CommandOutputBinding:glob "scaffolds.paths" ] ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . rdfs:label "sequence token replacement" ; sld:fields , ; sld:type sld:record . cwl:format ; sld:type cwl:File . cwl:in ; cwl:out ; cwl:run . sld:type . cwl:format ; cwl:outputSource ; sld:type cwl:File . rdfs:label "information about SPAdes parameters in this run" ; cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "params.txt" ] ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . Parameter:streamable true ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . Parameter:streamable true ; cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "pCDS.fasta" ] ; sld:type cwl:File . cwl:in ; cwl:out ; cwl:run . cwl:format ; cwl:inputBinding [ CommandLineBinding:position 3 ] ; cwl:inputBinding [ CommandLineBinding:position 3 ] ; sld:type cwl:File . cwl:outputBinding [ CommandOutputBinding:glob "matched_seqs_with_coords" ] ; cwl:outputBinding [ CommandOutputBinding:glob "matched_seqs_with_coords" ] ; cwl:outputBinding [ CommandOutputBinding:glob "matched_seqs_with_coords" ] ; sld:type cwl:File . sld:type xsd:int . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.proteinFile.nameroot).i5_annotations" ] ; sld:type cwl:File . cwl:source . sld:type xsd:string . Parameter:streamable true ; cwl:format ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:source . cwl:outputSource ; sld:type cwl:File . sld:type . cwl:source . rdfs:comment "True if the sequence file has complete genomic sequences\nFalse if the sequence file has short sequence reads\n" ; cwl:inputBinding [ cwl:valueFrom "${ if (self) {\n return [ \"-w\", \"1\" ];\n } else {\n return [ \"-w\", \"0\" ];\n }\n }\n" ] ; sld:type xsd:boolean . sld:type xsd:int . cwl:source . cwl:format ; sld:type cwl:File , sld:null . cwl:outputSource ; sld:type cwl:File . Parameter:streamable true ; cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "noFunction.fasta" ] ; sld:type cwl:File . sld:symbols , , ; sld:type sld:enum . cwl:outputSource ; sld:type cwl:File . cwl:in , , ; cwl:out ; cwl:run . cwl:format ; sld:type cwl:File . cwl:outputSource ; sld:type xsd:int . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "contigs.fasta" ] ; sld:type cwl:File . sld:type cwl:File . cwl:source . cwl:outputSource ; sld:type cwl:File . sld:type . rdfs:comment "Find reads with predicted coding sequences (pCDS)\n" ; cwl:in , , ; cwl:out , ; cwl:run ; cwl:scatter ( ) . rdfs:label "File names for summary of sequences, e.g. number, min/max length etc." ; cwl:default "summary.out" ; cwl:inputBinding [ CommandLineBinding:prefix "-o" ] ; sld:type xsd:string . cwl:source . cwl:in , , ; cwl:out ; cwl:run . cwl:source . cwl:source . cwl:default 1000 . cwl:source . cwl:in , , ; cwl:out ; cwl:run . cwl:outputSource ; sld:type cwl:File . Parameter:streamable true ; sld:type cwl:File . rdfs:label "Prefix for the files associated with GC distribution" ; cwl:default "GC-distribution.out" ; cwl:inputBinding [ CommandLineBinding:prefix "-g" ] ; sld:type xsd:string . rdfs:label "Start1 probability model" ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . rdfs:comment "GDF format: \nspace/tabdelimited\n" ; cwl:inputBinding [ CommandLineBinding:prefix "-C" ] ; cwl:inputBinding [ CommandLineBinding:prefix "-C" ] ; cwl:inputBinding [ CommandLineBinding:prefix "-C" ] ; sld:type xsd:boolean . cwl:outputBinding [ CommandOutputBinding:glob "SSUs" ] ; sld:type cwl:File . cwl:source . cwl:outputSource ; sld:type cwl:File . cwl:in , ; cwl:out ; cwl:run . cwl:format ; cwl:inputBinding [ CommandLineBinding:position 1 ; cwl:valueFrom "$(self.basename)" ] ; sld:type cwl:File . cwl:source . a cwl:CommandLineTool ; rdfs:comment "https://github.com/EddyRivasLab/easel" ; rdfs:label "extract by names from an indexed sequence file" ; ns2:original_cwlVersion "v1.2" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:baseCommand ( "esl-sfetch" ) ; cwl:baseCommand ( "esl-sfetch" ) ; cwl:baseCommand ( "esl-sfetch" ) ; cwl:cwlVersion ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "easel" ] ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "easel" ] ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "easel" ] ] ; cwl:inputs , , ; cwl:outputs ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:stdout "$(inputs.indexed_sequences.nameroot)_$(inputs.names.nameroot).fasta" . cwl:in ; cwl:out ; cwl:run . cwl:outputSource ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . a cwl:CommandLineTool ; rdfs:label "categorise sequences" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( [ CommandLineBinding:prefix "-c" ; cwl:valueFrom "import json\nfrom Bio import SeqIO\nipr_idset = frozenset(json.load(open(\"$(inputs.ipr_idset.path)\", \"r\")))\ncds_idset = frozenset(json.load(open(\"$(inputs.cds_idset.path)\", \"r\")))\nipr_output = open(\"interproscan.fasta\", \"w\")\ncds_output = open(\"pCDS.fasta\", \"w\")\nnof_output = open(\"noFunction.fasta\", \"w\")\nfor seq in SeqIO.parse(\"$(inputs.seqs.path)\", \"fasta\"):\n ipr_seen = False\n if seq.name in ipr_idset:\n ipr_output.write(str(\">\" + seq.name + \"\\\\n\" + seq.seq + \"\\\\n\"))\n ipr_seen = True\n if seq.name in cds_idset:\n cds_output.write(str(\">\" + seq.name + \"\\\\n\" + seq.seq + \"\\\\n\"))\n if not ipr_seen:\n nof_output.write(str(\">\" + seq.name + \"\\\\n\" + seq.seq + \"\\\\n\"))\n" ] ) ; cwl:baseCommand ( "python" ) ; cwl:cwlVersion ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "biopython" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_007173" ; SoftwarePackage:version "1.65" , "1.66" , "1.69" ] ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , , ; cwl:outputs , , ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 1024 ] . cwl:outputSource ; sld:type cwl:File . cwl:format ; cwl:outputSource ; sld:type cwl:File . rdfs:label "Contains the summary statistics for the input sequence file" ; cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.summary)" ] ; sld:type cwl:File . cwl:source . rdfs:label "internal YAML data set file" ; cwl:outputBinding [ CommandOutputBinding:glob "input_dataset.yaml" ] ; sld:type cwl:File . cwl:inputBinding [ CommandLineBinding:prefix "--table-type" ] ; cwl:inputBinding [ CommandLineBinding:prefix "--table-type" ] ; sld:type , sld:null . cwl:default true . cwl:source . sld:type xsd:int . cwl:outputSource ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:source . cwl:format ; cwl:secondaryFiles [] ; sld:type cwl:File . cwl:format ; sld:type cwl:File , sld:null . cwl:source . sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:label "sequence names to retrieve, one per line" ; Parameter:streamable true ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; sld:type cwl:File . cwl:in ; cwl:out ; cwl:run . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.indexed_sequences.nameroot)_$(inputs.names.nameroot).fasta" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.indexed_sequences.nameroot)_$(inputs.names.nameroot).fasta" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.indexed_sequences.nameroot)_$(inputs.names.nameroot).fasta" ] ; sld:type cwl:File . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "go-summary" ] ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:source . cwl:outputSource ; sld:type cwl:File . rdfs:label "Output as HDF5-formatted table." ; cwl:inputBinding [ CommandLineBinding:prefix "--to-hdf5" ] ; cwl:inputBinding [ CommandLineBinding:prefix "--to-hdf5" ] ; sld:type xsd:boolean , sld:null . cwl:source . a cwl:CommandLineTool ; rdfs:comment "FragGeneScan is an application for finding (fragmented) genes in short\nreads. It can also be applied to predict prokaryotic genes in incomplete\nassemblies or complete genomes.\n\nFragGeneScan was first released through omics website (http://omics.informatics.indiana.edu/FragGeneScan/)\nin March 2010, where you can find its old releases. FragGeneScan migrated to SourceForge in October, 2013\n(https://sourceforge.net/projects/fraggenescan/).\n\nVersion 1.20 can be downloaded here:\nhttps://sourceforge.net/projects/fraggenescan/files/\n" ; rdfs:label "FragGeneScan: find (fragmented) genes in short reads" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( [ CommandLineBinding:prefix "-o" ; cwl:valueFrom "$(runtime.outdir)/predicted_cds" ] [ CommandLineBinding:prefix "-t" ; cwl:valueFrom "model" ] ) ; cwl:baseCommand ( "FragGeneScan" ) ; cwl:cwlVersion ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "fraggenescan" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_011929" ; SoftwarePackage:version "1.20" ] ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , , , ; cwl:outputs , ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 1024 ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types ] ; cwl:requirements [ a cwl:InitialWorkDirRequirement ; cwl:listing [ cwl:entry "$(inputs.model.prob_backward)" ; cwl:entryname "train/rgene" ] ; cwl:listing [ cwl:entry "$(inputs.model.prob_start1)" ; cwl:entryname "train/start1" ] ; cwl:listing [ cwl:entry "$(inputs.model.prob_start)" ; cwl:entryname "train/start" ] ; cwl:listing [ cwl:entry "$(inputs.model.prob_forward)" ; cwl:entryname "train/gene" ] ; cwl:listing [ cwl:entry "$(inputs.model.prob_stop1)" ; cwl:entryname "train/stop1" ] ; cwl:listing [ cwl:entry "$(inputs.model.main)" ; cwl:entryname "train/model" ] ; cwl:listing [ cwl:entry "$(inputs.model.prob_stop)" ; cwl:entryname "train/stop" ] ; cwl:listing [ cwl:entry "$(inputs.model.pwm_dist)" ; cwl:entryname "train/pwm" ] ; cwl:listing [ cwl:entry "$(inputs.model.prob_noncoding)" ; cwl:entryname "train/noncoding" ] ] . cwl:source . rdfs:label "Stop probability model" ; sld:type cwl:File . cwl:source . cwl:default 100 . rdfs:comment "Must be equal length with \"replace\". Each character from the input file\nwill be replaced by its counterpart (at the same position) from \"replace\"\n" ; sld:type xsd:string . cwl:source . cwl:source . a cwl:CommandLineTool ; rdfs:comment "https://github.com/nawrockie/cmsearch_tblout_deoverlap/blob/master/00README.txt" ; rdfs:label "remove lower scoring overlaps from cmsearch --tblout files." ; ns2:original_cwlVersion "v1.2" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:baseCommand ( "cmsearch-deoverlap.pl" ) ; cwl:baseCommand ( "cmsearch-deoverlap.pl" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "cmsearch_tblout_deoverlap" ; SoftwarePackage:specs "https://github.com/nawrockie/cmsearch_tblout_deoverlap" ] ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "cmsearch_tblout_deoverlap" ; SoftwarePackage:specs "https://github.com/nawrockie/cmsearch_tblout_deoverlap" ] ] ; cwl:inputs , ; cwl:outputs ; cwl:requirements [ a cwl:EnvVarRequirement ; EnvVarRequirement:envDef [ EnvironmentDef:envName "LC_ALL" ; EnvironmentDef:envValue "C" ] ] ; cwl:requirements [ a cwl:InitialWorkDirRequirement ; cwl:listing "$(inputs.cmsearch_matches)" ] ; cwl:requirements [ a cwl:EnvVarRequirement ; EnvVarRequirement:envDef [ EnvironmentDef:envName "LC_ALL" ; EnvironmentDef:envValue "C" ] ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:requirements [ a cwl:InitialWorkDirRequirement ; cwl:listing "$(inputs.cmsearch_matches)" ] . cwl:in ; cwl:out ; cwl:run . cwl:source . rdfs:comment "the OTU table produced for the taxonomies found in the reference\ndatabases that was used with MAPseq\n" ; cwl:inputBinding [ CommandLineBinding:prefix "--otuTable" ] ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:source . cwl:in , ; cwl:out ; cwl:run . cwl:outputSource ; sld:type cwl:File . cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--replace" ; cwl:valueFrom "$(self.find):$(self.replace)" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--replace" ; cwl:valueFrom "$(self.find):$(self.replace)" ] ; sld:type , sld:null . cwl:in ; cwl:out ; cwl:run . cwl:outputSource ; sld:type cwl:File . sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:label "Start probability model" ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . Parameter:streamable true ; cwl:format ; sld:type cwl:File . cwl:source . cwl:inputBinding [ CommandLineBinding:prefix "-2" ] ; sld:type cwl:File , sld:null . cwl:source . cwl:source . rdfs:comment "http://eddylab.org/infernal/Userguide.pdf#page=60" ; rdfs:label "target hits table, format 2" ; cwl:outputBinding [ CommandOutputBinding:glob "*.deoverlapped" ] ; cwl:outputBinding [ CommandOutputBinding:glob "*.deoverlapped" ] ; sld:type cwl:File . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "predicted_cds.ffn" ] ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:outputBinding [ CommandOutputBinding:glob "assembly_graph.fastg" ] ; sld:type cwl:File . cwl:source . sld:type xsd:int . rdfs:label "search space size in *Mb* to for E-value calculations" ; cwl:inputBinding [ CommandLineBinding:prefix "-Z" ] ; cwl:inputBinding [ CommandLineBinding:prefix "-Z" ] ; sld:type xsd:int . rdfs:label "output of infernal's cmsearch" ; sld:type cwl:File . rdfs:label "Forward probability model" ; sld:type cwl:File . cwl:in , , ; cwl:out ; cwl:run . cwl:source . cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.biom.nameroot)*" ] ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.biom.nameroot)*" ] ; sld:type cwl:File . cwl:default 10000 . rdfs:label "Stop1 probability model" ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . a cwl:CommandLineTool ; rdfs:label "drop short seqs" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( [ CommandLineBinding:prefix "-c" ; cwl:valueFrom "from Bio import SeqIO\ninput_seq_iterator = SeqIO.parse(\"$(inputs.sequences.path)\", \"fasta\")\nshort_seq_iterator = (record for record in input_seq_iterator if len(record.seq) >= $(inputs.minimum_length))\nSeqIO.write(short_seq_iterator, \"$(inputs.sequences.basename).filtered.fasta\", \"fasta\")\n" ] ) ; cwl:baseCommand ( "python" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "biopython" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_007173" ; SoftwarePackage:version "1.65" , "1.66" , "1.69" ] ] ; cwl:inputs , ; cwl:outputs ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] . cwl:outputSource ; sld:type cwl:File . cwl:in , ; cwl:out ; cwl:run . cwl:format ; cwl:inputBinding [ CommandLineBinding:prefix "-s" ] ; sld:type cwl:File . cwl:inputBinding [ CommandLineBinding:prefix "-1" ] ; sld:type cwl:File , sld:null . a cwl:Workflow ; rdfs:label "functional analysis prediction with InterProScan" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; Workflow:steps , , , , ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , ; cwl:outputs , , ; cwl:requirements [ a cwl:SubworkflowFeatureRequirement ] ; cwl:requirements [ a cwl:ScatterFeatureRequirement ] ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types , , ] . rdfs:label "contigs before repeat resolution" ; cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "before_rr.fasta" ] ; sld:type cwl:File . cwl:in , , ; cwl:out ; cwl:run . cwl:in ; cwl:out ; cwl:run . sld:type [ sld:items cwl:File ; sld:type sld:array ] . Parameter:streamable true ; cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "interproscan.fasta" ] ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . rdfs:label "use CM's GA gathering cutoffs as reporting thresholds" ; cwl:default false ; cwl:inputBinding [ CommandLineBinding:prefix "--cut_ga" ] ; cwl:inputBinding [ CommandLineBinding:prefix "--cut_ga" ] ; sld:type xsd:boolean , sld:null . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "scaffolds.fasta" ] ; sld:type cwl:File . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.otu_counts.nameroot).html" ] ; sld:type cwl:File . cwl:in ; cwl:out ; cwl:run . cwl:inputBinding [ CommandLineBinding:position 3 ] ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:in , , ; cwl:out , ; cwl:run . a cwl:CommandLineTool ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( [ CommandLineBinding:prefix "--outfile" ; cwl:valueFrom "$(inputs.query.basename).tsv" ] [ CommandLineBinding:prefix "--krona" ; cwl:valueFrom "$(inputs.label).txt" ] ) ; cwl:baseCommand ( "mapseq2biom.pl" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , , ; cwl:outputs , ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 1024 ] . cwl:source . cwl:source . Parameter:streamable true ; cwl:format ; sld:type cwl:File . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "*" ] ; cwl:outputBinding [ CommandOutputBinding:glob "*" ] ; sld:type [ sld:items cwl:File ; sld:type sld:array ] ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:label "Contains all the lengths observed and frequencies" ; cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.length_sum)" ] ; sld:type cwl:File . sld:type cwl:File . rdfs:label "output from infernal cmsearch" ; Parameter:streamable true ; sld:type cwl:File . cwl:in ; cwl:out ; cwl:run . rdfs:label "Contains all GC fractsions observed and sequence counts" ; cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.gc_sum)" ] ; sld:type cwl:File . cwl:outputSource ; sld:type xsd:int . rdfs:label "Prefix for the files associated with nucleotide distribution" ; cwl:default "nucleotide-distribution.out" ; cwl:inputBinding [ CommandLineBinding:prefix "-d" ] ; sld:type xsd:string . rdfs:label "the output from the MAPseq that assigns a taxonomy to a sequence" ; cwl:inputBinding [ CommandLineBinding:prefix "--query" ] ; sld:type cwl:File . cwl:outputBinding [ CommandOutputBinding:glob "LSUs" ] ; sld:type cwl:File . cwl:inputBinding [ CommandLineBinding:position 1 ; cwl:valueFrom "$(self.basename)" ] ; cwl:inputBinding [ CommandLineBinding:position 1 ; cwl:valueFrom "$(self.basename)" ] ; sld:type cwl:File . rdfs:comment "This can greatly reduce the output volume." ; rdfs:label "Omit the alignment section from the main output." ; cwl:inputBinding [ CommandLineBinding:prefix "--noali" ] ; cwl:inputBinding [ CommandLineBinding:prefix "--noali" ] ; sld:type xsd:boolean , sld:null . a cwl:CommandLineTool ; rdfs:comment "based upon code by Maxim Scheremetjew, EMBL-EBI" ; rdfs:label "split FASTA by number of records" ; ns2:original_cwlVersion "v1.2" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( [ CommandLineBinding:prefix "-c" ; cwl:valueFrom "from Bio import SeqIO\ncurrentSequences = []\nfor record in SeqIO.parse(\"$(inputs.seqs.path)\", \"fasta\"):\n currentSequences.append(record)\n if len(currentSequences) == $(inputs.chunk_size):\n fileName = currentSequences[0].id + \"_\" + \\\\\n currentSequences[-1].id + \".fasta\"\n for char in [ \"/\", \" \", \":\" ]:\n fileName = fileName.replace(char, \"_\")\n SeqIO.write(currentSequences, \"$(runtime.outdir)/\"+fileName, \"fasta\")\n currentSequences = []\n\n# write any remaining sequences\nif len(currentSequences) > 0:\n fileName = currentSequences[0].id + \"_\" + \\\\\n currentSequences[-1].id + \".fasta\"\n for char in [ \"/\", \" \", \":\" ]:\n fileName = fileName.replace(char, \"_\")\n SeqIO.write(currentSequences, \"$(runtime.outdir)/\"+fileName, \"fasta\")\n" ] ) ; cwl:arguments ( [ CommandLineBinding:prefix "-c" ; cwl:valueFrom "from Bio import SeqIO\ncurrentSequences = []\nfor record in SeqIO.parse(\"$(inputs.seqs.path)\", \"fasta\"):\n currentSequences.append(record)\n if len(currentSequences) == $(inputs.chunk_size):\n fileName = currentSequences[0].id + \"_\" + \\\\\n currentSequences[-1].id + \".fasta\"\n for char in [ \"/\", \" \", \":\" ]:\n fileName = fileName.replace(char, \"_\")\n SeqIO.write(currentSequences, \"$(runtime.outdir)/\"+fileName, \"fasta\")\n currentSequences = []\n\n# write any remaining sequences\nif len(currentSequences) > 0:\n fileName = currentSequences[0].id + \"_\" + \\\\\n currentSequences[-1].id + \".fasta\"\n for char in [ \"/\", \" \", \":\" ]:\n fileName = fileName.replace(char, \"_\")\n SeqIO.write(currentSequences, \"$(runtime.outdir)/\"+fileName, \"fasta\")\n" ] ) ; cwl:baseCommand ( "python" ) ; cwl:baseCommand ( "python" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "biopython" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_007173" ; SoftwarePackage:version "1.65" , "1.66" , "1.69" ] ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "biopython" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_007173" ; SoftwarePackage:version "1.65" , "1.66" , "1.69" ] ] ; cwl:hints [ a ] ; cwl:inputs , ; cwl:outputs ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] . rdfs:comment "A summary of Gene Ontology (GO) terms derived from InterPro matches to\nthe sample. It is generated using a reduced list of GO terms called\nGO slim (http://www.geneontology.org/ontology/subsets/goslim_metagenomics.obo)\n" ; cwl:in , ; cwl:out , ; cwl:run . a cwl:CommandLineTool ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; CommandLineTool:stdin "${inputs.hits.path}" ; cwl:baseCommand ( "grep" "RF00002" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:stdout "5Ss" . cwl:outputSource ; sld:type cwl:File . a cwl:CommandLineTool ; rdfs:comment "normalizes input sequeces to FASTA with fixed number of sequence characters\nper line using esl-reformat from https://github.com/EddyRivasLab/easel\n" ; rdfs:label "normalize to fasta" ; ns2:original_cwlVersion "v1.2" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( [ CommandLineBinding:position 2 ; cwl:valueFrom "fasta" ] ) ; cwl:arguments ( [ CommandLineBinding:position 2 ; cwl:valueFrom "fasta" ] ) ; cwl:baseCommand ( "esl-reformat" ) ; cwl:baseCommand ( "esl-reformat" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "easel" ] ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "easel" ] ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , ; cwl:outputs ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types ] ; cwl:stdout "reformatted_sequences" . sld:type cwl:File . cwl:default "Gene3D" , "PRINTS" , "Pfam" , "ProSitePatterns" , "TIGRFAM" . a cwl:CommandLineTool ; rdfs:label "visualize using krona" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( [ CommandLineBinding:prefix "-o" ; cwl:valueFrom "$(inputs.otu_counts.nameroot).html" ] ) ; cwl:baseCommand ( "ktImportText" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "krona" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_012785" ; SoftwarePackage:version "2.3" , "2.7" ] ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 1024 ] . rdfs:label "SPAdes log" ; cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "spades.log" ] ; sld:type cwl:File . a cwl:CommandLineTool ; rdfs:label "Post QC-ed input analysis of sequence file" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:baseCommand ( "MGRAST_base.py" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , , , , , ; cwl:outputs , , , , , , , ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 1024 ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . cwl:source . cwl:source . cwl:source . cwl:source . cwl:source . cwl:format ; cwl:inputBinding [ CommandLineBinding:prefix "--input-fp" ] ; cwl:inputBinding [ CommandLineBinding:prefix "--input-fp" ] ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . rdfs:label "internal configuration file" ; cwl:outputBinding [ CommandOutputBinding:glob "dataset.info" ] ; sld:type cwl:File . rdfs:label "Output as TSV-formatted (classic) table." ; cwl:inputBinding [ CommandLineBinding:prefix "--to-tsv" ] ; cwl:inputBinding [ CommandLineBinding:prefix "--to-tsv" ] ; sld:type xsd:boolean , sld:null . sld:symbols , ; sld:type sld:enum . cwl:inputBinding [ CommandLineBinding:prefix "-s" ] ; sld:type cwl:File , sld:null . cwl:in , , ; cwl:out ; cwl:run . sld:type cwl:File . cwl:default true . cwl:in ; cwl:out ; cwl:run . Parameter:streamable true ; cwl:format ; sld:type cwl:File . a cwl:Workflow ; rdfs:label "EMG core analysis" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; Workflow:steps , , , , , , , , , , , , , , , , , , , , ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , , , , , , , , , ; cwl:outputs , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types , , , , , , , ] ; cwl:requirements [ a cwl:SubworkflowFeatureRequirement ] ; cwl:requirements [ a cwl:StepInputExpressionRequirement ] . cwl:source . cwl:in ; cwl:out , , , , ; cwl:run . cwl:source . sld:type xsd:boolean . rdfs:label "Prefix for the files assocaited with sequence length distribution" ; cwl:default "seq-length.out" ; cwl:inputBinding [ CommandLineBinding:prefix "-l" ] ; sld:type xsd:string . sld:type [ sld:items cwl:File ; sld:type sld:array ] ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:outputBinding [ CommandOutputBinding:glob "result" ; CommandOutputBinding:outputEval "${ self[0].format = inputs.files[0].format;\n return self; }\n" ] ; cwl:outputBinding [ CommandOutputBinding:glob "result" ; CommandOutputBinding:outputEval "${ self[0].format = inputs.files[0].format;\n return self; }\n" ] ; cwl:outputBinding [ CommandOutputBinding:glob "result" ; CommandOutputBinding:outputEval "${ self[0].format = inputs.files[0].format;\n return self; }\n" ] ; cwl:outputBinding [ CommandOutputBinding:glob "result" ; CommandOutputBinding:outputEval "${ self[0].format = inputs.files[0].format;\n return self; }\n" ] ; cwl:outputBinding [ CommandOutputBinding:glob "result" ; CommandOutputBinding:outputEval "${ self[0].format = inputs.files[0].format;\n return self; }\n" ] ; sld:type cwl:File . sld:symbols , ; sld:type sld:enum . a cwl:CommandLineTool ; rdfs:comment "https://arxiv.org/abs/1604.03071\nhttp://cab.spbu.ru/files/release3.10.1/manual.html#meta\n" ; rdfs:label "metaSPAdes: de novo metagenomics assembler" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( [ CommandLineBinding:prefix "-o" ; cwl:valueFrom "$(runtime.outdir)" ] [ CommandLineBinding:prefix "--tmp-dir" ; cwl:valueFrom "$(runtime.tmpdir)" ] [ CommandLineBinding:prefix "--memory" ; cwl:valueFrom "$(runtime.ram / 1024)" ] [ CommandLineBinding:prefix "--threads" ; cwl:valueFrom "$(runtime.cores)" ] ) ; cwl:baseCommand ( "metaspades.py" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "spades" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_000131" ; SoftwarePackage:version "3.10.1" ] ] ; cwl:inputs , , ; cwl:outputs , , , , , , , , , ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMin 16 ; ResourceRequirement:ramMin 102400 ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . cwl:source . a cwl:Workflow ; rdfs:label "Find reads with predicted coding sequences above 60 AA in length" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; Workflow:steps , , , ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , , ; cwl:outputs , ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types ] ; cwl:requirements [ a cwl:ScatterFeatureRequirement ] . cwl:in , ; cwl:out ; cwl:run . cwl:source . rdfs:label "pwm distribution" ; sld:type cwl:File . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.query.basename).tsv" ] ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.label).txt" ] ; sld:type cwl:File . cwl:format ; sld:type cwl:File , sld:null . cwl:source . cwl:source . cwl:outputSource ; sld:type cwl:File . rdfs:comment "Matches are generated against predicted CDS, using a sub set of databases\n(Pfam, TIGRFAM, PRINTS, PROSITE patterns, Gene3d) from InterPro. \n" ; cwl:in , ; cwl:out , , ; cwl:run . cwl:in ; cwl:out ; cwl:run . sld:type xsd:int . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.sequences.basename)" ] ; cwl:secondaryFiles [] ; sld:type cwl:File . rdfs:label "Contains the binned GC distribution, percentage" ; cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.gc_sum)_pcbin" ] ; sld:type cwl:File . sld:type [ sld:items cwl:File ; sld:type sld:array ] . rdfs:label "output of infernal's cmsearch" ; sld:type cwl:File . cwl:source . cwl:source . cwl:outputBinding [ CommandOutputBinding:glob "contigs.paths" ] ; sld:type cwl:File . cwl:inputBinding [ CommandLineBinding:prefix "--input-file" ] ; sld:type cwl:File . rdfs:label "Contains the normalised fraction of nucleotides on the sequences" ; cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.nucleotide_distribution)" ] ; sld:type cwl:File . cwl:outputSource ; sld:type xsd:int . rdfs:comment "The observation metadata to include from the input BIOM table file when\ncreating a tsv table file. By default no observation metadata will be\nincluded.\n" ; cwl:inputBinding [ CommandLineBinding:prefix "--header-key" ] ; cwl:inputBinding [ CommandLineBinding:prefix "--header-key" ] ; sld:type xsd:string , sld:null . cwl:source . cwl:outputSource ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . rdfs:comment "Not all models provided need to be a member of a clan" ; rdfs:label "clan information on the models provided" ; cwl:inputBinding [ CommandLineBinding:prefix "--clanin" ] ; cwl:inputBinding [ CommandLineBinding:prefix "--clanin" ] ; sld:type cwl:File , sld:null . cwl:format ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; cwl:secondaryFiles [] ; sld:type cwl:File . cwl:source . a cwl:CommandLineTool ; rdfs:comment "The awk script takes the output of Infernal's cmsearch so-called fmt=1 mode\nand makes it suitable for use by esl-sfetch, a sequence selector\n\nReading the user's guide for Infernal, Version 1.1.2; July 2016\nhttp://eddylab.org/infernal/Userguide.pdf#page=60 we see that\nthe relevant fields in the cmsearch output are:\n(column number: explanation)\n1: The name of the target sequence or profile\n3: The name of the query sequence or profile\n8: The start of the alignment of this hit with respect to the\n sequence, numbered 1..L for a sequence of L residues.\n9: The end of the alignment of this hit with respect to the sequence,\n numbered 1..L for a sequence of L residues\n\nLikewise the format esl-sfetch wants is: \n\nPutting it all together we see that the newname (which esl-sfetch with\noutput using) is a concatenation of the original name, the sequence\nnumber, and the coordinates.\n" ; ns2:original_cwlVersion "v1.2" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( "{print $1\"-\"$3\"/\"$8\"-\"$9\" \"$8\" \"$9\" \"$1}" "$(inputs.infernal_matches.path)" ) ; cwl:arguments ( "{print $1\"-\"$3\"/\"$8\"-\"$9\" \"$8\" \"$9\" \"$1}" "$(inputs.infernal_matches.path)" ) ; cwl:arguments ( "{print $1\"-\"$3\"/\"$8\"-\"$9\" \"$8\" \"$9\" \"$1}" "$(inputs.infernal_matches.path)" ) ; cwl:baseCommand ( "awk" ) ; cwl:baseCommand ( "awk" ) ; cwl:baseCommand ( "awk" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:stdout "matched_seqs_with_coords" . cwl:in ; cwl:out ; cwl:run . cwl:inputBinding [ CommandLineBinding:prefix "--config" ] ; sld:type cwl:File . sld:type cwl:File . rdfs:label "Noncoding probability model" ; sld:type cwl:File . cwl:outputSource ; sld:type xsd:int . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "classifications" ] ; sld:type cwl:File . rdfs:comment "Only filter stages F1 through F3 will be executed, using strict P-value\nthresholds (0.02 for F1, 0.001 for F2 and 0.00001 for F3). Additionally\na bias composition filter is used after the F1 stage (with P=0.02\nsurvival threshold). Any hit that survives all stages and has an HMM\nE-value or bit score above the reporting threshold will be output. \n" ; rdfs:label "Only use the filter profile HMM for searches, do not use the CM" ; cwl:default false ; cwl:inputBinding [ CommandLineBinding:prefix "--hmmonly" ] ; cwl:inputBinding [ CommandLineBinding:prefix "--hmmonly" ] ; sld:type xsd:boolean , sld:null . Parameter:streamable true ; cwl:format ; sld:type cwl:File . cwl:source . sld:type cwl:File . cwl:source . cwl:outputSource ; sld:type xsd:int . cwl:source . rdfs:label "output of infernal's cmsearch" ; sld:type cwl:File . rdfs:comment "must be equal length with \"find\"" ; sld:type xsd:string . sld:type . cwl:format ; cwl:secondaryFiles [] ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . a cwl:CommandLineTool ; rdfs:label "gather stats from ORF caller" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( [ CommandLineBinding:prefix "-c" ; cwl:valueFrom "from __future__ import print_function\nimport re\nimport json\nfrom Bio import SeqIO\naccessionPattern = re.compile(\"(\\\\S+)_\\\\d+_\\\\d+_[+-]\")\nnumberOrfs = 0\nreadsWithOrf = set()\nfor record in SeqIO.parse(\"$(inputs.orfs.path)\", \"fasta\"):\n readAccessionMatch = re.match(accessionPattern, record.id)\n readAccession = readAccessionMatch.group(1)\n readsWithOrf.add(readAccession)\n numberOrfs += 1\nnumberReadsWithOrf = len(readsWithOrf)\nwith open(\"reads.json\", \"w\") as readsFile:\n json.dump(list(readsWithOrf), readsFile)\nprint(json.dumps({\n \"numberReadsWithOrf\": numberReadsWithOrf,\n \"numberOrfs\": numberOrfs,\n \"readsWithOrf\":{\n \"class\": \"File\",\n \"format\": \"https://www.iana.org/assignments/media-types/application/json\",\n \"path\": \"$(runtime.outdir)/reads.json\" } }))\n" ] ) ; cwl:baseCommand ( "python" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "biopython" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_007173" ; SoftwarePackage:version "1.65" , "1.66" , "1.69" ] ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs , , ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 1024 ] ; cwl:stdout "cwl.output.json" . a cwl:CommandLineTool ; rdfs:label "gather stats from InterProScan" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( [ CommandLineBinding:prefix "-c" ; cwl:valueFrom "from __future__ import print_function\nimport re\nimport json\nimport yaml\naccessionPattern = re.compile(\"(\\\\S+)_\\\\d+_\\\\d+_[+-]\")\nmatch_count = CDS_with_match_number = reads_with_match_count = 0\ncds = set(); reads = set()\nentry2protein = {}; entry2name = {}\nfor line in open(\"$(inputs.iprscan.path)\", \"r\"):\n splitLine = line.strip().split(\"\\\\t\")\n cdsAccessions = splitLine[0].split(\"|\")\n for cdsAccession in cdsAccessions:\n if len(splitLine) >= 13 and splitLine[11].startswith(\"IPR\"):\n entry = splitLine[11]\n entry2protein.setdefault(entry, set()).add(cdsAccession)\n entry2name[entry] = splitLine[12]\n cds.add(cdsAccession)\n readAccessionMatch = re.match(accessionPattern, cdsAccession)\n readAccession = readAccessionMatch.group(1)\n reads.add(readAccession)\n match_count += 1\nCDS_with_match_count = len(cds)\nwithFunctionFaaList = sorted(list(cds))\nwith open(\"id_list.txt\", \"w\") as idFile:\n for id in withFunctionFaaList:\n idFile.write(id + \"\\\\n\")\nreads_with_match_count = len(reads)\nwith open(\"reads.json\", \"w\") as readsFile:\n json.dump(list(reads), readsFile)\nwith open(\"ipr_entry_maps.yaml\", \"w\") as mapsFile:\n yaml.dump({\"entry2protein\": entry2protein,\n \"entry2name\": entry2name}, mapsFile)\nprint(json.dumps({\n \"match_count\": match_count,\n \"CDS_with_match_count\": CDS_with_match_count,\n \"reads_with_match_count\": reads_with_match_count,\n \"id_list\": {\n \"class\": \"File\",\n \"path\": \"$(runtime.outdir)/id_list.txt\" },\n \"ipr_entry_maps\": {\n \"class\": \"File\",\n \"format\": \"https://www.iana.org/assignments/media-types/application/yaml\",\n \"path\": \"$(runtime.outdir)/ipr_entry_maps.yaml\" },\n \"reads\": {\n \"class\": \"File\",\n \"format\": \"https://www.iana.org/assignments/media-types/application/json\",\n \"path\": \"$(runtime.outdir)/reads.json\" } }))\n" ] ) ; cwl:baseCommand ( "python" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "python" ] ] ; cwl:inputs ; cwl:outputs , , , , , ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 1024 ] ; cwl:stdout "cwl.output.json" . cwl:in ; cwl:out ; cwl:run . rdfs:label "The type of the table to produce" ; sld:symbols , , , ; sld:type sld:enum . cwl:outputSource ; sld:type xsd:int . cwl:outputSource ; sld:type cwl:File . cwl:source . cwl:inputBinding [ CommandLineBinding:prefix "--input" ] ; sld:type cwl:File . cwl:default true . cwl:default [] . cwl:in , , ; cwl:out ; cwl:run . Parameter:streamable true ; 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 [ sld:items cwl:File ; sld:type sld:array ] ; sld:type [ sld:items cwl:File ; sld:type sld:array ] ; sld:type [ sld:items cwl:File ; sld:type sld:array ] ; sld:type [ sld:items cwl:File ; sld:type sld:array ] ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . sld:type cwl:File . rdfs:label "discard if number of bases is less than this amount" ; sld:type xsd:int . cwl:outputBinding [ CommandOutputBinding:glob "5Ss" ] ; sld:type cwl:File . cwl:in , ; cwl:out ; cwl:run . cwl:outputSource ; sld:type cwl:File . cwl:source . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "go-summary_slim" ] ; sld:type cwl:File . a cwl:CommandLineTool ; rdfs:comment "Version 5.21-60 can be downloaded here:\nhttps://github.com/ebi-pf-team/interproscan/wiki/HowToDownload\n\nDocumentation on how to run InterProScan 5 can be found here:\nhttps://github.com/ebi-pf-team/interproscan/wiki/HowToRun\n" ; rdfs:label "InterProScan: protein sequence classifier" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( [ CommandLineBinding:prefix "--outfile" ; cwl:valueFrom "$(inputs.proteinFile.nameroot).i5_annotations" ] [ CommandLineBinding:prefix "--formats" ; cwl:valueFrom "TSV" ] "--disable-precalc" "--goterms" "--pathways" [ CommandLineBinding:prefix "--tempdir" ; cwl:valueFrom "$(runtime.tmpdir)" ] ) ; cwl:baseCommand ( "interproscan.sh" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "interproscan" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_005829" ; SoftwarePackage:version "5.21-60" ] ] ; cwl:inputs , ; cwl:outputs ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMin 3 ; ResourceRequirement:ramMin 10240 ] ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types , ] . a cwl:Workflow ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; Workflow:steps , ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs . sld:type cwl:File . a cwl:CommandLineTool ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; CommandLineTool:stdin "$(inputs.hits.path)" ; cwl:baseCommand ( "grep" "-e RF02543 -e RF02541 -e RF02541 -e RF00002" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:stdout "LSUs" . a cwl:CommandLineTool ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; CommandLineTool:stdin "$(inputs.hits.path)" ; cwl:baseCommand ( "grep" "SSU" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:ResourceRequirement ; ResourceRequirement:coresMax 1 ; ResourceRequirement:ramMin 100 ] ; cwl:stdout "SSUs" . cwl:format ; cwl:inputBinding [ CommandLineBinding:prefix "-i" ] ; sld:type cwl:File . cwl:default true . cwl:outputSource ; sld:type cwl:File . cwl:default [] . Parameter:streamable true ; cwl:format ; sld:type cwl:File . cwl:outputSource ; sld:type xsd:int .