{"@id":"https://w3id.org/cwl/view/git/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl","retrievedFrom":{"repoUrl":"https://github.com/ProteinsWebTeam/ebi-metagenomics-cwl.git","branch":"ca6ca613f0d3728d9589a6ca6293e66dfde87bfb","path":"workflows/emg-pipeline-v3.cwl","packedId":null,"type":"GITHUB","rawUrl":"https://raw.githubusercontent.com/ProteinsWebTeam/ebi-metagenomics-cwl/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl","url":"https://github.com/ProteinsWebTeam/ebi-metagenomics-cwl/blob/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl"},"retrievedOn":"2023-01-09T03:57:44.980+00:00","lastCommit":"ca6ca613f0d3728d9589a6ca6293e66dfde87bfb","label":"EMG pipeline v3.0 (single end version)","inputs":{"reads":{"type":"File [FASTQ]","format":"http://edamontology.org/format_1930"},"5S_model":{"type":"File [HMMER format]","format":"http://edamontology.org/format_1370"},"16S_model":{"type":"File [HMMER format]","format":"http://edamontology.org/format_1370"},"23S_model":{"type":"File [HMMER format]","format":"http://edamontology.org/format_1370"},"tRNA_model":{"type":"File [HMMER format]","format":"http://edamontology.org/format_1370"},"go_summary_config":{"type":"File"},"fraggenescan_model":{"type":"https://w3id.org/cwl/view/git/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/tools/FragGeneScan-model.yaml#model"}},"outputs":{"tree":{"type":"File"},"biom_json":{"type":"File"},"go_summary":{"type":"File"},"predicted_CDS":{"type":"File"},"otu_table_summary":{"type":"File"},"processed_sequences":{"type":"File"},"functional_annotations":{"type":"File"}},"steps":{"ORF_prediction":{"label":"FragGeneScan: find (fragmented) genes in short reads","doc":"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","run":"../tools/FragGeneScan1_20.cwl","runType":"COMMANDLINETOOL","sources":{"ORF_prediction":{"defaultVal":"true"},"https://w3id.org/cwl/view/git/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl#ORF_prediction/model":{"sourceIDs":["fraggenescan_model"]},"https://w3id.org/cwl/view/git/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl#ORF_prediction/sequence":{"sourceIDs":["find_SSUs_and_mask"]}}},"find_SSUs_and_mask":{"label":"RNASelector as a CWL workflow","doc":"https://doi.org/10.1007/s12275-011-1213-z","run":"rna-selector.cwl","runType":"WORKFLOW","sources":{"find_SSUs_and_mask":{"sourceIDs":["16S_model"]},"https://w3id.org/cwl/view/git/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl#find_SSUs_and_mask/reads":{"sourceIDs":["convert_trimmed-reads_to_fasta"]},"https://w3id.org/cwl/view/git/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl#find_SSUs_and_mask/5S_model":{"sourceIDs":["5S_model"]},"https://w3id.org/cwl/view/git/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl#find_SSUs_and_mask/23S_model":{"sourceIDs":["23S_model"]},"https://w3id.org/cwl/view/git/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl#find_SSUs_and_mask/tRNA_model":{"sourceIDs":["tRNA_model"]}}},"functional_analysis":{"label":"functional analysis prediction with InterProScan","run":"functional_analysis.cwl","runType":"WORKFLOW","sources":{"functional_analysis":{"sourceIDs":["ORF_prediction"]},"https://w3id.org/cwl/view/git/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl#functional_analysis/go_summary_config":{"sourceIDs":["go_summary_config"]}}},"trim_quality_control":{"doc":"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","run":"../tools/trimmomatic.cwl","runType":"COMMANDLINETOOL","sources":{"trim_quality_control":{"defaultVal":"3"},"https://w3id.org/cwl/view/git/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl#trim_quality_control/phred":{"defaultVal":"\\\"33\\\""},"https://w3id.org/cwl/view/git/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl#trim_quality_control/reads1":{"sourceIDs":["reads"]},"https://w3id.org/cwl/view/git/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl#trim_quality_control/leading":{"defaultVal":"3"},"https://w3id.org/cwl/view/git/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl#trim_quality_control/end_mode":{"defaultVal":"\\\"SE\\\""},"https://w3id.org/cwl/view/git/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl#trim_quality_control/slidingwindow":{"defaultVal":"\\\"aea98650b1228763d0de71e6b1504853\\\""}}},"16S_taxonomic_analysis":{"label":"Functional analyis of sequences that match the 16S SSU","run":"16S_taxonomic_analysis.cwl","runType":"WORKFLOW","sources":{"16S_taxonomic_analysis":{"sourceIDs":["find_SSUs_and_mask"]}}},"convert_trimmed-reads_to_fasta":{"run":"../tools/fastq_to_fasta.cwl","runType":"COMMANDLINETOOL","sources":{"convert_trimmed-reads_to_fasta":{"sourceIDs":["trim_quality_control"]}}}},"cwltoolVersion":"3.1.20221201130942","visualisationDot":"digraph workflow {\n  graph [\n    bgcolor = \"#eeeeee\"\n    color = \"black\"\n    fontsize = \"10\"\n    labeljust = \"left\"\n    clusterrank = \"local\"\n    ranksep = \"0.22\"\n    nodesep = \"0.05\"\n  ]\n  node [\n    fontname = \"Helvetica\"\n    fontsize = \"10\"\n    fontcolor = \"black\"\n    shape = \"record\"\n    height = \"0\"\n    width = \"0\"\n    color = \"black\"\n    fillcolor = \"lightgoldenrodyellow\"\n    style = \"filled\"\n  ];\n  edge [\n    fontname=\"Helvetica\"\n    fontsize=\"8\"\n    fontcolor=\"black\"\n    color=\"black\"\n    arrowsize=\"0.7\"\n  ];\n  subgraph cluster_inputs {\n    rank = \"same\";\n    style = \"dashed\";\n    label = \"Workflow Inputs\";\n    \"16S_model\" [fillcolor=\"#94DDF4\",label=\"16S_model\"];\n    \"5S_model\" [fillcolor=\"#94DDF4\",label=\"5S_model\"];\n    \"fraggenescan_model\" [fillcolor=\"#94DDF4\",label=\"fraggenescan_model\"];\n    \"reads\" [fillcolor=\"#94DDF4\",label=\"reads\"];\n    \"23S_model\" [fillcolor=\"#94DDF4\",label=\"23S_model\"];\n    \"go_summary_config\" [fillcolor=\"#94DDF4\",label=\"go_summary_config\"];\n    \"tRNA_model\" [fillcolor=\"#94DDF4\",label=\"tRNA_model\"];\n  }\n  subgraph cluster_outputs {\n    rank = \"same\";\n    style = \"dashed\";\n    labelloc = \"b\";\n    label = \"Workflow Outputs\";\n    \"predicted_CDS\" [fillcolor=\"#94DDF4\",label=\"predicted_CDS\"];\n    \"processed_sequences\" [fillcolor=\"#94DDF4\",label=\"processed_sequences\"];\n    \"tree\" [fillcolor=\"#94DDF4\",label=\"tree\"];\n    \"go_summary\" [fillcolor=\"#94DDF4\",label=\"go_summary\"];\n    \"otu_table_summary\" [fillcolor=\"#94DDF4\",label=\"otu_table_summary\"];\n    \"biom_json\" [fillcolor=\"#94DDF4\",label=\"biom_json\"];\n    \"functional_annotations\" [fillcolor=\"#94DDF4\",label=\"functional_annotations\"];\n  }\n  \"ORF_prediction\" [label=\"FragGeneScan: find (fragmented) genes in short reads\"];\n  \"16S_taxonomic_analysis\" [label=\"Functional analyis of sequences that match the 16S SSU\", fillcolor=\"#F3CEA1\"];\n  \"convert_trimmed-reads_to_fasta\" [label=\"convert_trimmed-reads_to_fasta\"];\n  \"trim_quality_control\" [label=\"trim_quality_control\"];\n  \"functional_analysis\" [label=\"functional analysis prediction with InterProScan\", fillcolor=\"#F3CEA1\"];\n  \"find_SSUs_and_mask\" [label=\"RNASelector as a CWL workflow\", fillcolor=\"#F3CEA1\"];\n  \"default1\" -> \"ORF_prediction\" [label=\"completeSeq\"];\n  \"default1\" [label=\"true\", fillcolor=\"#D5AEFC\"];\n  \"find_SSUs_and_mask\" -> \"ORF_prediction\" [label=\"sequence\"];\n  \"fraggenescan_model\" -> \"ORF_prediction\" [label=\"model\"];\n  \"find_SSUs_and_mask\" -> \"16S_taxonomic_analysis\" [label=\"16S_matches\"];\n  \"trim_quality_control\" -> \"convert_trimmed-reads_to_fasta\" [label=\"fastq\"];\n  \"default2\" -> \"trim_quality_control\" [label=\"trailing\"];\n  \"default2\" [label=\"3\", fillcolor=\"#D5AEFC\"];\n  \"default3\" -> \"trim_quality_control\" [label=\"phred\"];\n  \"default3\" [label=\"\\\"33\\\"\", fillcolor=\"#D5AEFC\"];\n  \"default4\" -> \"trim_quality_control\" [label=\"slidingwindow\"];\n  \"default4\" [label=\"[Complex Object]\", fillcolor=\"#D5AEFC\"];\n  \"reads\" -> \"trim_quality_control\" [label=\"reads1\"];\n  \"default5\" -> \"trim_quality_control\" [label=\"leading\"];\n  \"default5\" [label=\"3\", fillcolor=\"#D5AEFC\"];\n  \"default6\" -> \"trim_quality_control\" [label=\"end_mode\"];\n  \"default6\" [label=\"\\\"SE\\\"\", fillcolor=\"#D5AEFC\"];\n  \"ORF_prediction\" -> \"functional_analysis\" [label=\"predicted_CDS\"];\n  \"go_summary_config\" -> \"functional_analysis\" [label=\"go_summary_config\"];\n  \"16S_model\" -> \"find_SSUs_and_mask\" [label=\"16S_model\"];\n  \"tRNA_model\" -> \"find_SSUs_and_mask\" [label=\"tRNA_model\"];\n  \"convert_trimmed-reads_to_fasta\" -> \"find_SSUs_and_mask\" [label=\"reads\"];\n  \"5S_model\" -> \"find_SSUs_and_mask\" [label=\"5S_model\"];\n  \"23S_model\" -> \"find_SSUs_and_mask\" [label=\"23S_model\"];\n  \"ORF_prediction\" -> \"predicted_CDS\";\n  \"find_SSUs_and_mask\" -> \"processed_sequences\";\n  \"16S_taxonomic_analysis\" -> \"tree\";\n  \"functional_analysis\" -> \"go_summary\";\n  \"16S_taxonomic_analysis\" -> \"otu_table_summary\";\n  \"16S_taxonomic_analysis\" -> \"biom_json\";\n  \"functional_analysis\" -> \"functional_annotations\";\n}\n","licenseLink":"https://spdx.org/licenses/Apache-2.0","permalink":"https://w3id.org/cwl/view/git/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl","packed":false,"visualisationXdot":"/graph/xdot/github.com/ProteinsWebTeam/ebi-metagenomics-cwl/blob/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl","visualisationPng":"/graph/png/github.com/ProteinsWebTeam/ebi-metagenomics-cwl/blob/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl","visualisationSvg":"/graph/svg/github.com/ProteinsWebTeam/ebi-metagenomics-cwl/blob/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl","roBundle":"/robundle/github.com/ProteinsWebTeam/ebi-metagenomics-cwl/blob/ca6ca613f0d3728d9589a6ca6293e66dfde87bfb/workflows/emg-pipeline-v3.cwl","licenseName":"Apache License 2.0"}