@prefix SchemaDefRequirement: . @prefix CommandLineBinding: . @prefix xsd: . @prefix Workflow: . @prefix sld: . @prefix rdfs: . @prefix CommandOutputBinding: . @prefix ns2: . @prefix SoftwarePackage: . @prefix ns1: . @prefix SoftwareRequirement: . @prefix rdf: . @prefix Parameter: . @prefix cwl: . @prefix CommandLineTool: . cwl:default 3 . cwl:source . cwl:source . rdfs:label "Forward probability model" ; sld:type cwl:File . cwl:source . rdfs:comment "FASTQ file of reads (R1 reads in Paired End mode)" ; cwl:format ; cwl:inputBinding [ CommandLineBinding:position 5 ] ; sld:type cwl:File . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "${ if (inputs.reads2 ) {\n return inputs.reads2.nameroot + '.unpaired.trimmed.fastq';\n } else {\n return null;\n }\n }\n" ] ; sld:type cwl:File , sld:null . cwl:inputBinding [ CommandLineBinding:prefix "--input_tree_filepath=" ; CommandLineBinding:separate false ] ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . rdfs:label "Start1 probability model" ; sld:type cwl:File . 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 "result" ] ) ; cwl:arguments ( [ CommandLineBinding:prefix "--output_fp" ; cwl:valueFrom "result" ] ) ; cwl:baseCommand ( "biom" "convert" ) ; cwl:baseCommand ( "biom" "convert" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "qiime" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_008249" ; SoftwarePackage:version "1.9.1" ] ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "qiime" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_008249" ; SoftwarePackage:version "1.9.1" ] ] ; cwl:inputs , , , , ; cwl:outputs ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types ] ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types ] . cwl:format ; sld:type cwl:File . cwl:in ; cwl:out , ; cwl:run . cwl:outputSource ; sld:type cwl:File . cwl:source . rdfs:label "Noncoding probability model" ; sld:type cwl:File . cwl:inputBinding [ CommandLineBinding:prefix "--table-type" ] ; cwl:inputBinding [ CommandLineBinding:prefix "--table-type" ] ; sld:type , sld:null . cwl:in ; cwl:out ; cwl:run . sld:type cwl:File . rdfs:comment "Single End (SE) or Paired End (PE) mode\n" ; cwl:inputBinding [ CommandLineBinding:position 3 ] ; sld:type . cwl:default true . cwl:outputSource ; 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" ; cwl:arguments ( [ CommandLineBinding:prefix "-c" ; cwl:valueFrom "from Bio import SeqIO; SeqIO.convert(\"$(inputs.fastq.path)\", \"fastq\", \"$(inputs.fastq.basename).fasta\", \"fasta\");\n" ] ) ; cwl:baseCommand ( "python" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "biopython" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_007173" ; SoftwarePackage:version "1.65" , "1.66" , "1.69" ] ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs . cwl:source . cwl:default true . cwl:default "1.0E-5" . cwl:source . cwl:outputBinding [ CommandOutputBinding:glob "sorted_uniq_names" ] ; cwl:outputBinding [ CommandOutputBinding:glob "sorted_uniq_names" ] ; cwl:outputBinding [ CommandOutputBinding:glob "sorted_uniq_names" ] ; cwl:outputBinding [ CommandOutputBinding:glob "sorted_uniq_names" ] ; sld:type cwl:File . a cwl:CommandLineTool ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; CommandLineTool:stdin "$(inputs.tsv_otu_table.path)" ; cwl:baseCommand ( "awk" "/#/ {next};{print $1}" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs ; cwl:stdout "observations" . sld:type cwl:File . cwl:in , , ; cwl:out ; cwl:run . cwl:in , , ; cwl:out ; cwl:run . cwl:format ; sld:type cwl:File . rdfs:label "Backward probability model" ; 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 "v1.0" ; 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:baseCommand ( "esl-reformat" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , ; cwl:outputs ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types ] ; cwl:stdout "reformatted_sequences" . cwl:source . 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 ] . cwl:in ; cwl:out ; cwl:run . rdfs:label "tRNA model to search with" ; cwl:format ; sld:type cwl:File . cwl:default true . 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 "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:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "interproscan" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_005829" ; SoftwarePackage:version "5.21-60" ] ] ; cwl:hints [ a ] ; cwl:inputs , ; cwl:outputs ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types , ] . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatter ( ) . cwl:default "33" . cwl:outputSource ; sld:type cwl:File . cwl:inputBinding [ CommandLineBinding:prefix "--input-file" ] ; sld:type cwl:File . a cwl:CommandLineTool ; cwl:baseCommand ( "awk" "{print $1, $7, $8, $1}" ) ; cwl:baseCommand ( "awk" "{print $1, $7, $8, $1}" ) ; cwl:inputs ; cwl:outputs ; cwl:stdout "formatted_names_and_coords" . cwl:in ; cwl:out ; cwl:run . cwl:inputBinding [ CommandLineBinding:position 2 ] ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; sld:type cwl:File . cwl:source . cwl:in , ; cwl:out ; cwl:run . cwl:outputSource ; sld:type cwl:File . cwl:format ; sld:type cwl:File . rdfs:comment "Perform a sliding window trimming, cutting once the average quality\nwithin the window falls below a threshold. By considering multiple\nbases, a single poor quality base will not cause the removal of high\nquality data later in the read.\n specifies the number of bases to average across\n specifies the average quality required\n" ; cwl:inputBinding [ CommandLineBinding:position 15 ; cwl:valueFrom "SLIDINGWINDOW:$(self.windowSize):$(self.requiredQuality)\n" ] ; sld:type , sld:null . cwl:source . sld:fields , , , , , , , , ; sld:type sld:record . a cwl:CommandLineTool ; rdfs:comment "https://github.com/EddyRivasLab/easel" ; rdfs:label "extract by names from an indexed sequence file" ; ns2:original_cwlVersion "v1.2" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:baseCommand ( "esl-sfetch" ) ; cwl:baseCommand ( "esl-sfetch" ) ; cwl:baseCommand ( "esl-sfetch" ) ; cwl:baseCommand ( "esl-sfetch" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , , ; cwl:outputs ; cwl:stdout "sequences" . cwl:in ; cwl:out ; cwl:run . cwl:source . rdfs:comment "Find reads with predicted coding sequences (pCDS) above 60 nucleotides in\nlength.\n" ; cwl:in , , ; cwl:out ; cwl:run . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.reads1.nameroot).unpaired.trimmed.fastq" ] ; sld:type cwl:File , sld:null . cwl:format ; sld:type cwl:File . sld:fields , ; sld:type sld:record . cwl:source . cwl:format ; 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:arguments ( "cp" "$(inputs.sequences.path)" "$(runtime.outdir)" [ CommandLineBinding:shellQuote false ; cwl:valueFrom ";" ] "esl-sfetch" "--index" ) ; cwl:baseCommand () ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:ShellCommandRequirement ] . a cwl:CommandLineTool ; cwl:baseCommand ( "sort" "--unique" ) ; cwl:baseCommand ( "sort" "--unique" ) ; cwl:baseCommand ( "sort" "--unique" ) ; cwl:baseCommand ( "sort" "--unique" ) ; cwl:inputs ; cwl:outputs ; cwl:stdout "sorted_uniq_names" . a cwl:CommandLineTool ; rdfs:comment "Trimmomatic is a fast, multithreaded command line tool that can be used to trim and crop\nIllumina (FASTQ) data as well as to remove adapters. These adapters can pose a real problem\ndepending on the library preparation and downstream application.\nThere are two major modes of the program: Paired end mode and Single end mode. The\npaired end mode will maintain correspondence of read pairs and also use the additional\ninformation contained in paired reads to better find adapter or PCR primer fragments\nintroduced by the library preparation process.\nTrimmomatic works with FASTQ files (using phred + 33 or phred + 64 quality scores,\ndepending on the Illumina pipeline used).\n" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( [ CommandLineBinding:position 4 ; CommandLineBinding:prefix "-trimlog" ; cwl:valueFrom "trim.log" ] [ CommandLineBinding:position 7 ; cwl:valueFrom "$(inputs.reads1.nameroot).trimmed.fastq" ] [ CommandLineBinding:position 8 ; cwl:valueFrom "${\n if (inputs.end_mode == \"PE\" && inputs.reads2) {\n return inputs.reads1.nameroot + '.trimmed.unpaired.fastq';\n } else {\n return null;\n }\n}\n" ] [ CommandLineBinding:position 9 ; cwl:valueFrom "${\n if (inputs.end_mode == \"PE\" && inputs.reads2) {\n return inputs.reads2.nameroot + '.trimmed.fastq';\n } else {\n return null;\n }\n}\n" ] [ CommandLineBinding:position 10 ; cwl:valueFrom "${\n if (inputs.end_mode == \"PE\" && inputs.reads2) {\n return inputs.reads2.nameroot + '.trimmed.unpaired.fastq';\n } else {\n return null;\n }\n}\n" ] ) ; cwl:baseCommand ( "java" "org.usadellab.trimmomatic.Trimmomatic" ) ; cwl:cwlVersion ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "trimmomatic" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_011848" ; SoftwarePackage:version "0.32" , "0.35" , "0.36" ] ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , , , , , , , , , , , , , , , , ; cwl:outputs , , , , ; cwl:requirements [ a cwl:ShellCommandRequirement ] ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types , , , , ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . sld:type xsd:int . cwl:default 40 . cwl:source . cwl:outputBinding [ CommandOutputBinding:glob "97_otus.tree" ] ; sld:type cwl:File . cwl:in , , ; cwl:out ; cwl:run . cwl:format ; sld:type cwl:File . rdfs:comment "Drop the read if the average quality is below the specified level\n" ; cwl:inputBinding [ CommandLineBinding:position 101 ; CommandLineBinding:prefix "AVGQUAL:" ; CommandLineBinding:separate false ] ; sld:type xsd:int , sld:null . cwl:inputBinding [ CommandLineBinding:prefix "--input" ] ; sld:type cwl:File . cwl:in ; cwl:out ; cwl:run . cwl:in , ; cwl:out , ; cwl:run . 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 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:source . a cwl:CommandLineTool ; cwl:baseCommand ( "awk" "{print $1, $18, $19, $1}" ) ; cwl:baseCommand ( "awk" "{print $1, $18, $19, $1}" ) ; cwl:baseCommand ( "awk" "{print $1, $18, $19, $1}" ) ; cwl:baseCommand ( "awk" "{print $1, $18, $19, $1}" ) ; cwl:baseCommand ( "awk" "{print $1, $18, $19, $1}" ) ; cwl:baseCommand ( "awk" "{print $1, $18, $19, $1}" ) ; cwl:inputs ; cwl:outputs ; cwl:stdout "formatted_names_and_coords" . cwl:format ; cwl:outputSource ; sld:type cwl:File . cwl:format , , , , , ; cwl:inputBinding [ CommandLineBinding:position 3 ] ; sld:type cwl:File . cwl:outputSource ; 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 . cwl:source . cwl:outputSource ; sld:type cwl:File . rdfs:comment "16s rRNA are annotated using the Greengenes reference database\n(default closed-reference OTU picking protocol with Greengenes\n13.8 reference with reverse strand matching enabled).\n" ; cwl:in ; cwl:out , , ; cwl:run . cwl:default [] . cwl:in , , , , , , ; cwl:out ; cwl:run . rdfs:comment "The required columns are as follows:\n(1) target name: The name of the target sequence or profile.\n(7) alifrom: The position in the target sequence at which the hit\n starts\n(8) ali to: The position in the target sequence at which the hit\n ends.\n" ; Parameter:streamable true ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:default true . cwl:source . a cwl:Workflow ; rdfs:label "EMG pipeline v3.0 (single end version)" ; 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:SchemaDefRequirement ; SchemaDefRequirement:types , , , ] . cwl:in ; cwl:out ; cwl:run . 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:outputBinding [ CommandOutputBinding:glob "formatted_names_and_coords" ] ; cwl:outputBinding [ CommandOutputBinding:glob "formatted_names_and_coords" ] ; cwl:outputBinding [ CommandOutputBinding:glob "formatted_names_and_coords" ] ; cwl:outputBinding [ CommandOutputBinding:glob "formatted_names_and_coords" ] ; cwl:outputBinding [ CommandOutputBinding:glob "formatted_names_and_coords" ] ; cwl:outputBinding [ CommandOutputBinding:glob "formatted_names_and_coords" ] ; sld:type cwl:File . cwl:source , , . sld:type cwl:File . cwl:in , , , ; cwl:out ; cwl:run . cwl:format ; cwl:inputBinding [ CommandLineBinding:prefix "--input_fp" ] ; sld:type cwl:File . cwl:source . cwl:in ; cwl:out ; cwl:run . cwl:outputBinding [ CommandOutputBinding:glob "observations" ] ; sld:type cwl:File . cwl:format ; cwl:inputBinding [ CommandLineBinding:prefix "-s" ] ; sld:type cwl:File . rdfs:label "report sequences >= this bit score threshold in output" ; cwl:inputBinding [ CommandLineBinding:prefix "-T" ] ; sld:type xsd:int , sld:null . cwl:source . cwl:in , , , , ; cwl:out , ; cwl:run . 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 . cwl:source . cwl:source . rdfs:comment "Removes the specified number of bases, regardless of quality, from the\nbeginning of the read.\nThe numbser specified is the number of bases to keep, from the start of\nthe read.\n" ; cwl:inputBinding [ CommandLineBinding:position 13 ; CommandLineBinding:prefix "HEADCROP:" ; CommandLineBinding:separate false ] ; sld:type xsd:int , sld:null . cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "--replace" ; cwl:valueFrom "$(self.find):$(self.replace)" ] ; sld:type , sld:null . cwl:source . cwl:default "OTU Table" . cwl:outputBinding [ CommandOutputBinding:glob "formatted_names_and_coords" ] ; cwl:outputBinding [ CommandOutputBinding:glob "formatted_names_and_coords" ] ; sld:type cwl:File . sld:symbols , , , , , , , , , , , , , , ; sld:type sld:enum . sld:type cwl:File . cwl:source . rdfs:comment "This (re)encodes the quality part of the FASTQ file to base 64." ; cwl:inputBinding [ CommandLineBinding:position 12 ; CommandLineBinding:prefix "TOPHRED64" ; CommandLineBinding:separate false ] ; sld:type xsd:boolean , sld:null . 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_tree_filepath=" ; CommandLineBinding:separate false ; cwl:valueFrom "pruned.tree" ] ) ; cwl:baseCommand ( "filter_tree.py" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "qiime" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_008249" ; SoftwarePackage:version "1.9.1" ] ] ; cwl:inputs , ; cwl:outputs . cwl:source . 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:SchemaDefRequirement ; SchemaDefRequirement:types , , ] ; cwl:requirements [ a cwl:SubworkflowFeatureRequirement ] . sld:type cwl:File . sld:symbols , , ; sld:type sld:enum . cwl:source . cwl:format ; cwl:inputBinding [ CommandLineBinding:prefix "--input_fp" ] ; cwl:inputBinding [ CommandLineBinding:prefix "--input_fp" ] ; sld:type cwl:File . rdfs:comment "The required columns are as follows:\n(1) target name: The name of the target sequence or profile.\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:source . sld:type cwl:File . cwl:source . cwl:in ; cwl:out ; cwl:run ; cwl:scatter ( ) ; cwl:scatter ( ) . rdfs:comment "Remove low quality bases from the end. As long as a base has a value\nbelow this threshold the base is removed and the next base (which as\ntrimmomatic is starting from the 3' prime end would be base preceding\nthe just removed base) will be investigated. This approach can be used\nremoving the special Illumina \"low quality segment\" regions (which are\nmarked with quality score of 2), but we recommend Sliding Window or\nMaxInfo instead\n" ; cwl:inputBinding [ CommandLineBinding:position 14 ; CommandLineBinding:prefix "TRAILING:" ; CommandLineBinding:separate false ] ; sld:type xsd:int , sld:null . 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:format ; cwl:secondaryFiles [] ; sld:type cwl:File . cwl:source . cwl:format ; sld:type cwl:File . 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 ( "mkdir" "train" ";" "ln" "-s" "$(inputs.model.main.path)" "train/" ";" "ln" "-s" "$(inputs.model.prob_forward.path)" "train/gene" ";" "ln" "-s" "$(inputs.model.prob_backward.path)" "train/rgene" ";" "ln" "-s" "$(inputs.model.prob_noncoding.path)" "train/noncoding" ";" "ln" "-s" "$(inputs.model.prob_start.path)" "train/start" ";" "ln" "-s" "$(inputs.model.prob_stop.path)" "train/stop" ";" "ln" "-s" "$(inputs.model.prob_start1.path)" "train/start1" ";" "ln" "-s" "$(inputs.model.prob_stop1.path)" "train/stop1" ";" "ln" "-s" "$(inputs.model.pwm_dist.path)" "train/pwm" ";" "FragGeneScan" "-o" "$(runtime.outdir)/predicted_cds" "-t" "train/$(inputs.model.main.basename)" ) ; cwl:baseCommand () ; cwl:cwlVersion ; cwl:hints [ a ] ; 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:inputs , , , ; cwl:outputs ; cwl:requirements [ a cwl:ShellCommandRequirement ] ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types ] ; cwl:requirements [ a cwl:InlineJavascriptRequirement ] . cwl:default [] . rdfs:label "Start probability model" ; sld:type cwl:File . cwl:source . 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 "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:outputBinding [ CommandOutputBinding:glob "otu_table_summary.txt" ] ; sld:type cwl:File . cwl:outputBinding [ CommandOutputBinding:glob "per_target_summary.txt" ] ; sld:type cwl:File . cwl:source . rdfs:comment "JVM arguments should be a quoted, space separated list\n(e.g. \"-Xms128m -Xmx512m\")\n" ; cwl:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:shellQuote false ] ; sld:type xsd:string , sld:null . cwl:format ; sld:type cwl:File . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.sequences.basename)" ] ; cwl:secondaryFiles [] ; sld:type cwl:File . rdfs:comment "The required columns are as follows:\n(1) target name: The name of the target sequence or profile.\n(18) from (ali coord): The start of the MEA alignment of this\n domain with respect to the sequence, numbered 1..L for a\n sequence of L residues.\n(19) to (ali coord): The end of the MEA alignment of this domain\n with respect to the sequence, numbered 1..L for a sequence of\n L residues.\n" ; Parameter:streamable true ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "otu_table.biom" ] ; sld:type cwl:File . cwl:default "OTU Table" . rdfs:comment "Remove low quality bases from the beginning. As long as a base has a\nvalue below this threshold the base is removed and the next base will be\ninvestigated.\n" ; cwl:inputBinding [ CommandLineBinding:position 14 ; CommandLineBinding:prefix "LEADING:" ; CommandLineBinding:separate false ] ; sld:type xsd:int , sld:null . cwl:inputBinding [ CommandLineBinding:prefix "-p" ] ; sld:type xsd:int , sld:null . cwl:outputBinding [ CommandOutputBinding:glob "pruned_tree" ] ; sld:type cwl:File . rdfs:label "Stop1 probability model" ; sld:type cwl:File . rdfs:comment "Number of threads" ; cwl:default 1 ; cwl:inputBinding [ CommandLineBinding:position 4 ; CommandLineBinding:prefix "-threads" ] ; sld:type xsd:int . cwl:outputSource ; sld:type cwl:File . cwl:format , , , , ; cwl:inputBinding [ CommandLineBinding:position 10 ; cwl:valueFrom "$(self.basename)" ] ; sld:type cwl:File . rdfs:label "The type of the table to produce" ; sld:symbols , , , ; sld:type sld:enum . cwl:format ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:source . cwl:source . rdfs:comment "must be equal length with \"find\"" ; sld:type xsd:string . a cwl:CommandLineTool ; ns2:original_cwlVersion "v1.2" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; CommandLineTool:successCodes 1 , 0 ; cwl:baseCommand ( "grep" "-v" "^#" ) ; cwl:baseCommand ( "grep" "-v" "^#" ) ; cwl:baseCommand ( "grep" "-v" "^#" ) ; cwl:baseCommand ( "grep" "-v" "^#" ) ; cwl:baseCommand ( "grep" "-v" "^#" ) ; cwl:baseCommand ( "grep" "-v" "^#" ) ; 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:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs ; cwl:stdout "coord_lines" . cwl:outputBinding [ CommandOutputBinding:glob "i5_annotations" ] ; sld:type cwl:File . a cwl:Workflow ; ns2:original_cwlVersion "v1.2" ; 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:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:ScatterFeatureRequirement ] ; cwl:requirements [ a cwl:ScatterFeatureRequirement ] . 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 "${ if (self) {\n return [ \"-w\", \"1\" ];\n } else {\n return [ \"-w\", \"0\" ];\n }\n }\n" ] ; sld:type xsd:boolean . cwl:outputSource ; sld:type cwl:File . rdfs:comment "Matches are generated against predicted CDS, using a sub set of databases\n(Pfam, TIGRFAM, PRINTS, PROSITE patterns, Gene3d) from InterPro. \n" ; cwl:in , ; cwl:out ; cwl:run . rdfs:comment "In addition to the alignment score, palindrome mode can verify that a\nminimum length of adapter has been detected. If unspecified, this\ndefaults to 8 bases, for historical reasons. However, since palindrome\nmode has a very low false positive rate, this can be safely reduced, even\ndown to 1, to allow shorter adapter fragments to be removed.\n" ; sld:type xsd:int , sld:null . cwl:source . rdfs:comment "Low quality trimming (low quality ends and sequences with < quality scores\nless than 15 over a 4 nucleotide wide window are removed)\n" ; cwl:in , , , , , ; cwl:out ; cwl:run . a cwl:CommandLineTool ; rdfs:label "search profile(s) against a sequence database" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( "--tblout" "per_target_summary.txt" [ CommandLineBinding:prefix "--cpu" ; cwl:valueFrom "$(runtime.cores)" ] ) ; cwl:baseCommand ( "nhmmer" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "hmmer" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_005305" ; SoftwarePackage:version "3.1b2" ] ] ; cwl:hints [ a ] ; cwl:inputs , , ; cwl:outputs . cwl:source . rdfs:comment "FASTQ file of R2 reads in Paired End mode" ; cwl:format ; cwl:inputBinding [ CommandLineBinding:position 6 ] ; sld:type cwl:File , sld:null . cwl:source . 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 ] ; cwl:inputBinding [ CommandLineBinding:position 2 ] ; sld:type cwl:File . cwl:source . cwl:format ; cwl:inputBinding [ CommandLineBinding:prefix "--input_fp" ] ; sld:type cwl:File . sld:type cwl:File . rdfs:label "pwm distribution" ; sld:type cwl:File . cwl:default true . cwl:default "SE" . sld:type [ sld:items cwl:File ; sld:type sld:array ] ; sld:type [ sld:items cwl:File ; sld:type sld:array ] . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "predicted_cds.faa" ] ; sld:type cwl:File . cwl:in , ; cwl:out , ; cwl:run . cwl:source . rdfs:label "rRNA protein model to search with" ; cwl:format ; sld:type cwl:File . sld:type xsd:int . rdfs:comment "A list of tips (one tip per line) or sequence identifiers (tab-delimited\nlines with a seq identifier in the first field) which should be retained \n" ; cwl:inputBinding [ CommandLineBinding:prefix "--tips_fp=" ; CommandLineBinding:separate false ] ; sld:type cwl:File , sld:null . cwl:source . sld:type xsd:int . cwl:in , ; cwl:out , ; cwl:run . cwl:outputSource ; 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" ; cwl:arguments ( [ CommandLineBinding:prefix "--output_dir" ; cwl:valueFrom "$(runtime.outdir)" ] "--force" ) ; cwl:baseCommand ( "pick_closed_reference_otus.py" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "qiime" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_008249" ; SoftwarePackage:version "1.9.1" ] ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs , , , . cwl:outputBinding [ CommandOutputBinding:glob "coord_lines" ] ; cwl:outputBinding [ CommandOutputBinding:glob "coord_lines" ] ; cwl:outputBinding [ CommandOutputBinding:glob "coord_lines" ] ; cwl:outputBinding [ CommandOutputBinding:glob "coord_lines" ] ; cwl:outputBinding [ CommandOutputBinding:glob "coord_lines" ] ; cwl:outputBinding [ CommandOutputBinding:glob "coord_lines" ] ; sld:type cwl:File . cwl:in ; cwl:out ; cwl:run . rdfs:comment "\"33\" or \"64\" specifies the base quality encoding. Default: 64\n" ; cwl:default "64" ; cwl:inputBinding [ CommandLineBinding:position 4 ; CommandLineBinding:prefix "-phred" ; CommandLineBinding:separate false ] ; sld:type . 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:format ; cwl:outputBinding [ CommandOutputBinding:glob "masked_sequences.fasta" ] ; sld:type cwl:File . cwl:outputBinding [ CommandOutputBinding:glob "names" ] ; cwl:outputBinding [ CommandOutputBinding:glob "names" ] ; cwl:outputBinding [ CommandOutputBinding:glob "names" ] ; cwl:outputBinding [ CommandOutputBinding:glob "names" ] ; sld:type cwl:File . cwl:source . sld:fields , ; sld:type sld:record . cwl:inputBinding [ CommandLineBinding:prefix "--config" ] ; sld:type cwl:File . sld:type cwl:File . cwl:source . rdfs:comment "specifies how accurate the match between the two 'adapter ligated' reads\nmust be for PE palindrome read alignment.\n" ; sld:type xsd:int . rdfs:comment "Removes bases regardless of quality from the end of the read, so that the\nread has maximally the specified length after this step has been\nperformed. Steps performed after CROP might of course further shorten the\nread. The value is the number of bases to keep, from the start of the read.\n" ; cwl:inputBinding [ CommandLineBinding:position 13 ; CommandLineBinding:prefix "CROP:" ; CommandLineBinding:separate false ] ; sld:type xsd:int , sld:null . cwl:source . cwl:outputBinding [ CommandOutputBinding:glob "uclust_ref_picked_otus" ] ; sld:type cwl:Directory . cwl:source . rdfs:label "sequence token replacement" ; sld:fields , ; sld:type sld:record . cwl:format ; sld:type cwl:File . sld:type cwl:File . cwl:source . a cwl:CommandLineTool ; rdfs:label "search profile(s) against a sequence database" ; ns2:original_cwlVersion "v1.2" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; cwl:arguments ( "--domtblout" "per_domain_summary.txt" [ CommandLineBinding:prefix "--cpu" ; cwl:valueFrom "$(runtime.cores)" ] ) ; cwl:arguments ( "--domtblout" "per_domain_summary.txt" [ CommandLineBinding:prefix "--cpu" ; cwl:valueFrom "$(runtime.cores)" ] ) ; cwl:arguments ( "--domtblout" "per_domain_summary.txt" [ CommandLineBinding:prefix "--cpu" ; cwl:valueFrom "$(runtime.cores)" ] ) ; cwl:baseCommand ( "hmmsearch" ) ; cwl:baseCommand ( "hmmsearch" ) ; cwl:baseCommand ( "hmmsearch" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "hmmer" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_005305" ; SoftwarePackage:version "3.1b2" ] ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "hmmer" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_005305" ; SoftwarePackage:version "3.1b2" ] ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "hmmer" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_005305" ; SoftwarePackage:version "3.1b2" ] ] ; cwl:hints [ a ] ; cwl:inputs , , ; cwl:outputs . rdfs:label "report sequences <= this E-value threshold in output" ; cwl:inputBinding [ CommandLineBinding:prefix "-E" ] ; cwl:inputBinding [ CommandLineBinding:prefix "-E" ] ; cwl:inputBinding [ CommandLineBinding:prefix "-E" ] ; sld:type xsd:string , sld:null . cwl:source . cwl:source . cwl:inputBinding [ CommandLineBinding:itemSeparator "," ; CommandLineBinding:prefix "--applications" ] ; sld:type sld:null ; sld:type [ sld:items ; sld:type sld:array ] . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.fastq.basename).fasta" ] ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:in ; cwl:out ; cwl:run . cwl:in , , ; cwl:out ; cwl:run . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "$(inputs.reads1.nameroot).trimmed.fastq" ] ; sld:type cwl:File . rdfs:comment "Performs an adaptive quality trim, balancing the benefits of retaining\nlonger reads against the costs of retaining bases with errors.\n: This specifies the read length which is likely to allow\nthe location of the read within the target sequence to be determined.\n: This value, which should be set between 0 and 1, specifies\nthe balance between preserving as much read length as possible vs.\nremoval of incorrect bases. A low value of this parameter (<0.2) favours\nlonger reads, while a high value (>0.8) favours read correctness.\n" ; cwl:inputBinding [ CommandLineBinding:position 15 ; cwl:valueFrom "MAXINFO:$(self.targetLength):$(strictness)\n" ] ; sld:type , sld:null . cwl:default "taxonomy" . a cwl:Workflow ; rdfs:comment "https://doi.org/10.1007/s12275-011-1213-z" ; rdfs:label "RNASelector as 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:requirements [ a cwl:SubworkflowFeatureRequirement ] ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types , , ] ; cwl:requirements [ a cwl:StepInputExpressionRequirement ] ; cwl:requirements [ a cwl:MultipleInputFeatureRequirement ] . cwl:outputSource ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:source . 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 . rdfs:comment "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" ; rdfs:label "Trimmomatic log" ; cwl:outputBinding [ CommandOutputBinding:glob "trim.log" ] ; 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" ] ; cwl:inputBinding [ CommandLineBinding:prefix "-C" ] ; sld:type xsd:boolean . 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 ( "ln" "-s" "$(inputs.unique_rRNA_hits.path)" "nhmmer.txt" ";" "ln" "-s" "$(inputs.16s_rRNA_hmmer_matches.path)" "nhmmer.16s.txt" ";" "ln" "-s" "$(inputs.23s_rRNA_hmmer_matches.path)" "nhmmer.23s.txt" ";" "ln" "-s" "$(inputs.5s_rRNA_hmmer_matches.path)" "nhmmer.5s.txt" ";" "rnaMaskingStep.py" "--hmmer" "nhmmer.txt" "--nhmmer" "$(inputs.unique_tRNA_hits.path)" "--seq_id" "$(inputs.tRNA_matches.path)" "--input" "$(inputs.sequences.path)" "--output" "masked_sequences.fasta" ) ; cwl:baseCommand () ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , , , , , , ; cwl:outputs ; cwl:requirements [ a cwl:ShellCommandRequirement ] . cwl:default "Gene3D" , "PRINTS" , "Pfam" , "ProSitePatterns" , "TIGRFAM" . sld:type cwl:File . cwl:default 3 . sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:format ; cwl:outputSource ; sld:type cwl:File . rdfs:comment "specifies how accurate the match between any adapter etc. sequence must\nbe against a read\n" ; sld:type xsd:int . cwl:source . cwl:outputSource ; sld:type cwl:File . cwl:source . rdfs:comment "specifies the maximum mismatch count which will still allow a full match\nto be performed\n" ; sld:type xsd:int . cwl:in ; cwl:out ; cwl:run . cwl:source . sld:type . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "reformatted_sequences" ] ; sld:type cwl:File . cwl:source ; cwl:valueFrom "${ return [ self ]; }" . cwl:source . cwl:source . rdfs:comment "This module removes reads that fall below the specified minimal length.\nIf required, it should normally be after all other processing steps.\nReads removed by this step will be counted and included in the \"dropped\nreads\" count presented in the trimmomatic summary.\n" ; cwl:inputBinding [ CommandLineBinding:position 100 ; CommandLineBinding:prefix "MINLEN:" ; CommandLineBinding:separate false ] ; sld:type xsd:int , sld:null . sld:symbols , ; sld:type sld:enum . cwl:source . 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:inputBinding [ CommandLineBinding:position 1 ; CommandLineBinding:prefix "-f" ] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; sld:type cwl:File . cwl:source . cwl:format ; sld:type cwl:File . sld:fields , , , , , ; sld:type sld:record . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "sequences" ] ; cwl:outputBinding [ CommandOutputBinding:glob "sequences" ] ; cwl:outputBinding [ CommandOutputBinding:glob "sequences" ] ; cwl:outputBinding [ CommandOutputBinding:glob "sequences" ] ; sld:type cwl:File . sld:type xsd:int . sld:type cwl:File . cwl:outputBinding [ CommandOutputBinding:glob "go-summary" ] ; 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" ; 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 . a cwl:CommandLineTool ; cwl:baseCommand ( "awk" "{print $1}" ) ; cwl:baseCommand ( "awk" "{print $1}" ) ; cwl:baseCommand ( "awk" "{print $1}" ) ; cwl:baseCommand ( "awk" "{print $1}" ) ; cwl:inputs ; cwl:outputs ; cwl:stdout "names" . cwl:in , , ; cwl:out ; cwl:run . sld:type . cwl:format ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; cwl:secondaryFiles [] ; sld:type cwl:File . rdfs:comment "After read-though has been detected by palindrome mode, and the adapter\nsequence removed, the reverse read contains the same sequence information\nas the forward read, albeit in reverse complement. For this reason, the\ndefault behaviour is to entirely drop the reverse read. By specifying\n\"true\" for this parameter, the reverse read will also be retained, which\nmay be useful e.g. if the downstream tools cannot handle a combination of\npaired and unpaired reads. \n" ; sld:type xsd:boolean . cwl:outputSource ; sld:type cwl:File . sld:symbols , ; sld:type sld:enum . rdfs:label "Stop probability model" ; sld:type cwl:File . cwl:in , ; cwl:out ; cwl:run . a cwl:Workflow ; rdfs:label "Functional analyis of sequences that match the 16S SSU" ; ns2:original_cwlVersion "v1.0" ; ns1:copyrightHolder "EMBL - European Bioinformatics Institute" ; ns1:license "https://www.apache.org/licenses/LICENSE-2.0" ; Workflow:steps , , , , , ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs ; cwl:outputs , , ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types ] . rdfs:comment "This (re)encodes the quality part of the FASTQ file to base 33." ; cwl:inputBinding [ CommandLineBinding:position 12 ; CommandLineBinding:prefix "TOPHRED33" ; CommandLineBinding:separate false ] ; sld:type xsd:boolean , sld:null . cwl:source . cwl:outputBinding [ CommandOutputBinding:glob "log_*.txt" ] ; sld:type cwl:File . cwl:inputBinding [ CommandLineBinding:position 2 ] ; sld:type cwl:File . cwl:in ; cwl:out ; cwl:run . cwl:format ; cwl:outputBinding [ CommandOutputBinding:glob "${ if (inputs.reads2 ) {\n return inputs.reads2.nameroot + '.trimmed.fastq';\n } else {\n return null;\n }\n }\n" ] ; sld:type cwl:File , sld:null . cwl:format ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; cwl:inputBinding [ CommandLineBinding:position 1 ] ; sld:type cwl:File . cwl:outputSource ; sld:type cwl:File . cwl:outputBinding [ CommandOutputBinding:glob "result" ] ; cwl:outputBinding [ CommandOutputBinding:glob "result" ] ; sld:type cwl:File . cwl:outputBinding [ CommandOutputBinding:glob "per_domain_summary.txt" ] ; cwl:outputBinding [ CommandOutputBinding:glob "per_domain_summary.txt" ] ; cwl:outputBinding [ CommandOutputBinding:glob "per_domain_summary.txt" ] ; sld:type cwl:File . cwl:source . a cwl:Workflow ; ns2:original_cwlVersion "v1.2" ; 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:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:inputs , ; cwl:outputs , . cwl:format ; 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" ; cwl:arguments ( [ CommandLineBinding:prefix "--output_fp" ; cwl:valueFrom "otu_table_summary.txt" ] ) ; cwl:baseCommand ( "biom" "summarize-table" ) ; cwl:cwlVersion ; cwl:hints [ a ] ; cwl:hints [ a ] ; cwl:hints [ a cwl:SoftwareRequirement ; SoftwareRequirement:packages [ SoftwarePackage:package "qiime" ; SoftwarePackage:specs "https://identifiers.org/rrid/RRID:SCR_008249" ; SoftwarePackage:version "1.9.1" ] ] ; cwl:inputs ; cwl:outputs ; cwl:requirements [ a cwl:SchemaDefRequirement ; SchemaDefRequirement:types ] . rdfs:comment "Cut adapter and other illumina-specific sequences from the read." ; cwl:inputBinding [ CommandLineBinding:position 11 ; cwl:valueFrom "ILLUMINACLIP:$(self.adapters_file.path):$(self.seedMismatches):$(self.palindromeClipThreshold):$(self.simpleClipThreshold):$(self.minAdapterLength):$(self.keepBothReads)\n" ] ; sld:type , sld:null .