{"@id":"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl","retrievedFrom":{"repoUrl":"https://github.com/datirium/workflows.git","branch":"46a077b51619c6a14f85e0aa5260ae8a04426fab","path":"workflows/rnaseq-se-dutp.cwl","packedId":null,"type":"GITHUB","rawUrl":"https://raw.githubusercontent.com/datirium/workflows/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl","url":"https://github.com/datirium/workflows/blob/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl"},"retrievedOn":"2023-01-03T20:02:44.411+00:00","lastCommit":"46a077b51619c6a14f85e0aa5260ae8a04426fab","label":"RNA-Seq pipeline single-read strand specific","doc":"Note: should be updated\nThe original [BioWardrobe's](https://biowardrobe.com) [PubMed ID:26248465](https://www.ncbi.nlm.nih.gov/pubmed/26248465)\n**RNA-Seq** basic analysis for **strand specific single-read** experiment.\nA corresponded input [FASTQ](http://maq.sourceforge.net/fastq.shtml) file has to be provided.\n\nCurrent workflow should be used only with the single-read RNA-Seq data. It performs the following steps:\n1. Use STAR to align reads from input FASTQ file according to the predefined reference indices; generate unsorted BAM file and alignment statistics file\n2. Use fastx_quality_stats to analyze input FASTQ file and generate quality statistics file\n3. Use samtools sort to generate coordinate sorted BAM(+BAI) file pair from the unsorted BAM file obtained on the step 1 (after running STAR)\n5. Generate BigWig file on the base of sorted BAM file\n6. Map input FASTQ file to predefined rRNA reference indices using Bowtie to define the level of rRNA contamination; export resulted statistics to file\n7. Calculate isoform expression level for the sorted BAM file and GTF/TAB annotation file using GEEP reads-counting utility; export results to file","inputs":{"threads":{"label":"Number of threads","doc":"Number of threads for those steps that support multithreading","type":"Integer (Optional)"},"fastq_file":{"label":"FASTQ input file","doc":"Reads data in a FASTQ format","type":"File [FASTQ]","format":"http://edamontology.org/format_1930"},"clip_3p_end":{"label":"Clip from 3p end","doc":"Number of bases to clip from the 3p end","type":"Integer (Optional)"},"clip_5p_end":{"label":"Clip from 5p end","doc":"Number of bases to clip from the 5p end","type":"Integer (Optional)"},"exclude_chr":{"label":"Chromosome to be excluded in rpkm calculation","doc":"Chromosome to be excluded in rpkm calculation","type":"String (Optional)"},"annotation_file":{"label":"Annotation file","doc":"GTF or TAB-separated annotation file","type":"File [GTF]","format":"http://edamontology.org/format_2306"},"chrom_length_file":{"label":"Chromosome length file","doc":"Chromosome length file","type":"File [Textual format]","format":"http://edamontology.org/format_2330"},"star_indices_folder":{"label":"STAR indices folder","doc":"Path to STAR generated indices","type":"Directory"},"bowtie_indices_folder":{"label":"BowTie Ribosomal Indices","doc":"Path to Bowtie generated indices","type":"Directory"}},"outputs":{"bowtie_log":{"label":"Bowtie alignment log","doc":"Bowtie alignment log file","type":"File [Textual format]","format":"http://edamontology.org/format_2330"},"rpkm_genes":{"label":"RPKM, grouped by gene name","doc":"Calculated rpkm values, grouped by gene name","type":"File [TSV]","format":"http://edamontology.org/format_3475"},"bambai_pair":{"label":"Coordinate sorted BAM alignment file (+index BAI)","doc":"Coordinate sorted BAM file and BAI index file","type":"File [BAM]","format":"http://edamontology.org/format_2572"},"star_sj_log":{"label":"STAR sj log","doc":"STAR SJ.out.tab","type":"File (Optional) [Textual format]","format":"http://edamontology.org/format_2330"},"get_stat_log":{"label":"YAML formatted combined log","doc":"YAML formatted combined log","type":"File (Optional) [YAML]","format":"http://edamontology.org/format_3750"},"star_out_log":{"label":"STAR log out","doc":"STAR Log.out","type":"File (Optional) [Textual format]","format":"http://edamontology.org/format_2330"},"rpkm_isoforms":{"label":"RPKM, grouped by isoforms","doc":"Calculated rpkm values, grouped by isoforms","type":"File [CSV]","format":"http://edamontology.org/format_3752"},"star_final_log":{"label":"STAR final log","doc":"STAR Log.final.out","type":"File [Textual format]","format":"http://edamontology.org/format_2330"},"bigwig_upstream":{"label":"BigWig file","doc":"Generated BigWig file","type":"File [bigWig]","format":"http://edamontology.org/format_3006"},"rpkm_common_tss":{"label":"RPKM, grouped by common TSS","doc":"Calculated rpkm values, grouped by common TSS","type":"File [TSV]","format":"http://edamontology.org/format_3475"},"star_stdout_log":{"label":"STAR stdout log","doc":"STAR Log.std.out","type":"File (Optional) [Textual format]","format":"http://edamontology.org/format_2330"},"fastx_statistics":{"label":"FASTQ statistics","doc":"fastx_quality_stats generated FASTQ file quality statistics file","type":"File [Textual format]","format":"http://edamontology.org/format_2330"},"bigwig_downstream":{"label":"BigWig file","doc":"Generated BigWig file","type":"File [bigWig]","format":"http://edamontology.org/format_3006"},"get_stat_markdown":{"label":"Markdown formatted combined log","doc":"Markdown formatted combined log","type":"File (Optional) [TIDE TXT]","format":"http://edamontology.org/format_3835"},"star_progress_log":{"label":"STAR progress log","doc":"STAR Log.progress.out","type":"File (Optional) [Textual format]","format":"http://edamontology.org/format_2330"},"get_formatted_stats":{"label":"Bowtie, STAR and GEEP mapping stats","doc":"Processed and combined Bowtie & STAR aligner and GEEP logs","type":"File (Optional) [Textual format]","format":"http://edamontology.org/format_2330"},"bam_statistics_report":{"label":"BAM statistics report","doc":"BAM statistics report (right after alignment and sorting)","type":"File [Textual format]","format":"http://edamontology.org/format_2330"}},"steps":{"get_stat":{"doc":"Tool processes and combines log files generated by Trimgalore, Bowtie, Samtools and MACS2.\n\n`get_output_prefix` function returns output file prefix equal to `output_prefix`+`_collected_statistics_report` (if this input is provided) or\ngenerated on the base of bowtie log basename with `_collected_statistics_report` extension.\n","run":"../tools/collect-statistics-rna-seq.cwl","runType":"COMMANDLINETOOL","sources":{"get_stat":{"sourceIDs":["bowtie_aligner"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#get_stat/isoforms_file":{"sourceIDs":["rpkm_calculation"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#get_stat/bam_statistics_report":{"sourceIDs":["get_bam_statistics"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#get_stat/star_alignment_report":{"sourceIDs":["star_aligner"]}}},"star_aligner":{"doc":"Tool runs STAR alignReads.\n\n`default_output_name_prefix` function returns output files prefix if `outFileNamePrefix` is not set. By default prefix\nis equal to basename of `readFilesIn`.\n","run":"../tools/star-alignreads.cwl","runType":"COMMANDLINETOOL","sources":{"star_aligner":{"sourceIDs":["threads"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#star_aligner/genomeDir":{"sourceIDs":["star_indices_folder"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#star_aligner/readFilesIn":{"sourceIDs":["extract_fastq"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#star_aligner/clip3pNbases":{"sourceIDs":["clip_3p_end"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#star_aligner/clip5pNbases":{"sourceIDs":["clip_5p_end"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#star_aligner/seedSearchStartLmax":{"defaultVal":"15"},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#star_aligner/alignSJDBoverhangMin":{"defaultVal":"1"},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#star_aligner/outFilterMismatchNmax":{"defaultVal":"5"},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#star_aligner/outFilterMultimapNmax":{"defaultVal":"1"}}},"extract_fastq":{"doc":"Tool to decompress input FASTQ file\nBash script's logic:\n- disable case sensitive glob check\n- check if root name of input file already include '.fastq' or '.fq' extension. If yes, set DEFAULT_EXT to \\\"\\\"\n- check file type, decompress if needed\n- return 1, if file type is not recognized\nThis script also works of input file doesn't have any extension at all\n","run":"../tools/extract-fastq.cwl","runType":"COMMANDLINETOOL","sources":{"extract_fastq":{"sourceIDs":["fastq_file"]}}},"bowtie_aligner":{"doc":"Tool maps input raw reads files to reference genome using Bowtie.\n\n`default_output_filename` function returns default name for SAM output and log files. In case when `sam` and\n`output_filename` inputs are not set, default filename will have `.sam` extension but format may not correspond SAM\nspecification. To set output filename manually use `output_filename` input. Default output filename is based on\n`output_filename` or basename of `upstream_filelist`, `downstream_filelist` or `crossbow_filelist` file (if array,\nthe first file in array is taken). If function is called without argenments and `output_filename` input is set, it\nwill be returned from the function.\n\nFor single-end input data any of the `upstream_filelist` or `downstream_filelist` inputs can be used.\n\nLog filename (`log_file` output) is generated by `default_output_filename` function with ex='.bw'\n\n`indices_folder` defines folder to contain Bowtie indices. Based on the first found file with `rev.1.ebwt` or\n`rev.1.ebwtl` extension, bowtie index prefix is returned from input's `valueFrom` field.\n","run":"../tools/bowtie-alignreads.cwl","runType":"COMMANDLINETOOL","sources":{"bowtie_aligner":{"sourceIDs":["clip_3p_end"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bowtie_aligner/m":{"defaultVal":"1"},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bowtie_aligner/v":{"defaultVal":"3"},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bowtie_aligner/sam":{"defaultVal":"true"},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bowtie_aligner/best":{"defaultVal":"true"},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bowtie_aligner/strata":{"defaultVal":"true"},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bowtie_aligner/threads":{"sourceIDs":["threads"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bowtie_aligner/clip_5p_end":{"sourceIDs":["clip_5p_end"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bowtie_aligner/indices_folder":{"sourceIDs":["bowtie_indices_folder"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bowtie_aligner/upstream_filelist":{"sourceIDs":["extract_fastq"]}}},"group_isoforms":{"doc":"Tool runs get_gene_n_tss.R script to group isoforms by gene and common TSS\n","run":"../tools/group-isoforms.cwl","runType":"COMMANDLINETOOL","sources":{"group_isoforms":{"sourceIDs":["rpkm_calculation"]}}},"rpkm_calculation":{"label":"geep","doc":"Tool calculates RPKM values grouped by isoforms or genes.\n\n`default_output_prefix` function returns default prefix based on `bam_file` basename, if `output_prefix` is not\nprovided.\n\nBefore running `baseCommand` `bam_file` is staged into output directory with write permissions (`\\\"writable\\\": true`).\nThis allow to automatically generate index file at the same directory as input `bam_file`. In case when index file\nis provided in `secondaryFiles` of `bam_file`, it's not generated twice.\n","run":"../tools/geep.cwl","runType":"COMMANDLINETOOL","sources":{"rpkm_calculation":{"defaultVal":"1e-03"},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#rpkm_calculation/dutp":{"defaultVal":"true"},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#rpkm_calculation/threads":{"sourceIDs":["threads"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#rpkm_calculation/bam_file":{"sourceIDs":["samtools_sort_index"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#rpkm_calculation/exclude_chr":{"sourceIDs":["exclude_chr"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#rpkm_calculation/annotation_file":{"sourceIDs":["annotation_file"]}}},"get_bam_statistics":{"doc":"Generates statistics for the input BAM file.\n","run":"../tools/samtools-stats.cwl","runType":"COMMANDLINETOOL","sources":{"get_bam_statistics":{"sourceIDs":["samtools_sort_index"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#get_bam_statistics/bambai_pair":{"sourceIDs":["samtools_sort_index"]}}},"fastx_quality_stats":{"doc":"Tool calculates statistics on the base of FASTQ file quality scores.\nIf `output_filename` is not provided call function `default_output_filename` to return default output file name\ngenerated as `input_file` basename + `.fastxstat` extension.\n","run":"../tools/fastx-quality-stats.cwl","runType":"COMMANDLINETOOL","sources":{"fastx_quality_stats":{"sourceIDs":["extract_fastq"]}}},"samtools_sort_index":{"doc":"Tool to sort and index input BAM/SAM/CRAM.\nIf input `trigger` is set to `true` or isn't set at all (`true` is used by default), run `samtools sort` and\n`samtools index`, return sorted BAM and BAI/CSI index file.\nIf input `trigger` is set to `false`, return unchanged `sort_input` (BAM/SAM/CRAM) and index (BAI/CSI, if provided in\n`secondaryFiles`) files, previously staged into output directory.\n\nBefore execution `baseCommand`, `sort_input` and `secondaryFiles` (if provided) are staged into directory\nset as docker parameter `--workdir` (tool's output directory), using `InitialWorkDirRequirement`. Setting\n`writable: true` makes cwl-runner to make copies of the `sort_input` and `secondaryFiles` (if provided) and mount\nthem to docker container with `rw` mode as part of `--workdir` (if set to false, the files staged into output\ndirectory will be mounted to docker container separately with `ro` mode). Because both `samtools sort` and\n`samtools index` can overwrite files with the same names (and in case of `samtools sort` even the input file can be\noverwritten), we don't need to rename any of the staged files.\n\nTrigger logic is implemented in two bash scripts set by default as `bash_script_sort` and `bash_script_index` inputs.\nFor both of then, if the first argument $0 (which is `trigger` input) is true, run `samtools sort/index` with the rest\nof the arguments. If $0 is not true, skip `samtools sort/index` and return `sort_input` and `secondaryFiles`\n(if provided) staged into output directory.\n\nInput `trigger` is Boolean, but returns String, because of `valueFrom` field. The `valueFrom` is used, because if `trigger`\nis false, cwl-runner doesn't append this argument at all to the the `baseCommand` - new feature of CWL v1.0.2. Alternatively,\n`prefix` field could be used, but it causes changing in script logic.\n\nIf using `sort_output_filename`, the output file extension should be `*.bam`, because `samtools sort` defines the output\nfile format on the base of the file extension. If `*.sam` is sed as output filename, it cannot be usefully indexed\nby `samtools index`.\n\n`default_bam` function is used to generate output filename for `samtools sort` if input `sort_output_filename` is not\nset or when `trigger` is false and we need to return `sort_input` and `secondaryFiles` (if provided) files staged into\noutput directory. Output filename is generated on the base of `sort_input` basename with `.bam` extension by default.\n\n`ext` function is used to return the index file extension (BAI/CSI) based on `csi` and `bai` inputs according to the\nfollowing logic\n  `csi` &&  `bai`  => BAI\n !`csi` && !`bai ` => BAI\n  `csi` && !`bai ` => CSI\n","run":"../tools/samtools-sort-index.cwl","runType":"COMMANDLINETOOL","sources":{"samtools_sort_index":{"sourceIDs":["threads"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#samtools_sort_index/sort_input":{"sourceIDs":["star_aligner"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#samtools_sort_index/sort_output_filename":{"sourceIDs":["extract_fastq"]}}},"bam_to_bigwig_upstream":{"doc":"Workflow converts input BAM file into bigWig and bedGraph files.\n\nInput BAM file should be sorted by coordinates (required by `bam_to_bedgraph` step).\n\nIf `split` input is not provided use true by default. Default logic is implemented in `valueFrom` field of `split`\ninput inside `bam_to_bedgraph` step to avoid possible bug in cwltool with setting default values for workflow inputs.\n\n`scale` has higher priority over the `mapped_reads_number`. The last one is used to calculate `-scale` parameter for\n`bedtools genomecov` (step `bam_to_bedgraph`) only in a case when input `scale` is not provided. All logic is\nimplemented inside `bedtools-genomecov.cwl`.\n\n`bigwig_filename` defines the output name only for generated bigWig file. `bedgraph_filename` defines the output name\nfor generated bedGraph file and can influence on generated bigWig filename in case when `bigwig_filename` is not provided.\n\nAll workflow inputs and outputs don't have `format` field to avoid format incompatibility errors when workflow is used\nas subworkflow.","run":"../tools/bam-bedgraph-bigwig.cwl","runType":"WORKFLOW","sources":{"bam_to_bigwig_upstream":{"sourceIDs":["samtools_sort_index"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bam_to_bigwig_upstream/strand":{"defaultVal":"\\\"+\\\""},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bam_to_bigwig_upstream/bam_file":{"sourceIDs":["samtools_sort_index"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bam_to_bigwig_upstream/chrom_length_file":{"sourceIDs":["chrom_length_file"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bam_to_bigwig_upstream/mapped_reads_number":{"sourceIDs":["star_aligner"]}}},"bam_to_bigwig_downstream":{"doc":"Workflow converts input BAM file into bigWig and bedGraph files.\n\nInput BAM file should be sorted by coordinates (required by `bam_to_bedgraph` step).\n\nIf `split` input is not provided use true by default. Default logic is implemented in `valueFrom` field of `split`\ninput inside `bam_to_bedgraph` step to avoid possible bug in cwltool with setting default values for workflow inputs.\n\n`scale` has higher priority over the `mapped_reads_number`. The last one is used to calculate `-scale` parameter for\n`bedtools genomecov` (step `bam_to_bedgraph`) only in a case when input `scale` is not provided. All logic is\nimplemented inside `bedtools-genomecov.cwl`.\n\n`bigwig_filename` defines the output name only for generated bigWig file. `bedgraph_filename` defines the output name\nfor generated bedGraph file and can influence on generated bigWig filename in case when `bigwig_filename` is not provided.\n\nAll workflow inputs and outputs don't have `format` field to avoid format incompatibility errors when workflow is used\nas subworkflow.","run":"../tools/bam-bedgraph-bigwig.cwl","runType":"WORKFLOW","sources":{"bam_to_bigwig_downstream":{"sourceIDs":["samtools_sort_index"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bam_to_bigwig_downstream/strand":{"defaultVal":"\\\"-\\\""},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bam_to_bigwig_downstream/bam_file":{"sourceIDs":["samtools_sort_index"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bam_to_bigwig_downstream/chrom_length_file":{"sourceIDs":["chrom_length_file"]},"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl#bam_to_bigwig_downstream/mapped_reads_number":{"sourceIDs":["star_aligner"]}}}},"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    \"threads\" [fillcolor=\"#94DDF4\",label=\"Number of threads\"];\n    \"clip_5p_end\" [fillcolor=\"#94DDF4\",label=\"Clip from 5p end\"];\n    \"fastq_file\" [fillcolor=\"#94DDF4\",label=\"FASTQ input file\"];\n    \"star_indices_folder\" [fillcolor=\"#94DDF4\",label=\"STAR indices folder\"];\n    \"clip_3p_end\" [fillcolor=\"#94DDF4\",label=\"Clip from 3p end\"];\n    \"chrom_length_file\" [fillcolor=\"#94DDF4\",label=\"Chromosome length file\"];\n    \"bowtie_indices_folder\" [fillcolor=\"#94DDF4\",label=\"BowTie Ribosomal Indices\"];\n    \"annotation_file\" [fillcolor=\"#94DDF4\",label=\"Annotation file\"];\n    \"annotation_file\" [fillcolor=\"#94DDF4\",label=\"Annotation file\"];\n    \"exclude_chr\" [fillcolor=\"#94DDF4\",label=\"Chromosome to be excluded in rpkm calculation\"];\n  }\n  subgraph cluster_outputs {\n    rank = \"same\";\n    style = \"dashed\";\n    labelloc = \"b\";\n    label = \"Workflow Outputs\";\n    \"bambai_pair\" [fillcolor=\"#94DDF4\",label=\"Coordinate sorted BAM alignment file (+index BAI)\"];\n    \"get_stat_markdown\" [fillcolor=\"#94DDF4\",label=\"Markdown formatted combined log\"];\n    \"fastx_statistics\" [fillcolor=\"#94DDF4\",label=\"FASTQ statistics\"];\n    \"bam_statistics_report\" [fillcolor=\"#94DDF4\",label=\"BAM statistics report\"];\n    \"star_sj_log\" [fillcolor=\"#94DDF4\",label=\"STAR sj log\"];\n    \"rpkm_genes\" [fillcolor=\"#94DDF4\",label=\"RPKM, grouped by gene name\"];\n    \"star_progress_log\" [fillcolor=\"#94DDF4\",label=\"STAR progress log\"];\n    \"star_final_log\" [fillcolor=\"#94DDF4\",label=\"STAR final log\"];\n    \"star_out_log\" [fillcolor=\"#94DDF4\",label=\"STAR log out\"];\n    \"bowtie_log\" [fillcolor=\"#94DDF4\",label=\"Bowtie alignment log\"];\n    \"rpkm_common_tss\" [fillcolor=\"#94DDF4\",label=\"RPKM, grouped by common TSS\"];\n    \"bigwig_upstream\" [fillcolor=\"#94DDF4\",label=\"BigWig file\"];\n    \"rpkm_isoforms\" [fillcolor=\"#94DDF4\",label=\"RPKM, grouped by isoforms\"];\n    \"get_formatted_stats\" [fillcolor=\"#94DDF4\",label=\"Bowtie, STAR and GEEP mapping stats\"];\n    \"bigwig_downstream\" [fillcolor=\"#94DDF4\",label=\"BigWig file\"];\n    \"star_stdout_log\" [fillcolor=\"#94DDF4\",label=\"STAR stdout log\"];\n    \"get_stat_log\" [fillcolor=\"#94DDF4\",label=\"YAML formatted combined log\"];\n  }\n  \"bowtie_aligner\" [label=\"bowtie_aligner\"];\n  \"get_bam_statistics\" [label=\"get_bam_statistics\"];\n  \"rpkm_calculation\" [label=\"geep\"];\n  \"bam_to_bigwig_upstream\" [label=\"bam_to_bigwig_upstream\", fillcolor=\"#F3CEA1\"];\n  \"get_stat\" [label=\"get_stat\"];\n  \"group_isoforms\" [label=\"group_isoforms\"];\n  \"star_aligner\" [label=\"star_aligner\"];\n  \"fastx_quality_stats\" [label=\"fastx_quality_stats\"];\n  \"bam_to_bigwig_downstream\" [label=\"bam_to_bigwig_downstream\", fillcolor=\"#F3CEA1\"];\n  \"samtools_sort_index\" [label=\"samtools_sort_index\"];\n  \"extract_fastq\" [label=\"extract_fastq\"];\n  \"clip_3p_end\" -> \"bowtie_aligner\" [label=\"clip_3p_end\"];\n  \"clip_5p_end\" -> \"bowtie_aligner\" [label=\"clip_5p_end\"];\n  \"default1\" -> \"bowtie_aligner\" [label=\"sam\"];\n  \"default1\" [label=\"true\", fillcolor=\"#D5AEFC\"];\n  \"extract_fastq\" -> \"bowtie_aligner\" [label=\"upstream_filelist\"];\n  \"threads\" -> \"bowtie_aligner\" [label=\"threads\"];\n  \"default2\" -> \"bowtie_aligner\" [label=\"m\"];\n  \"default2\" [label=\"1\", fillcolor=\"#D5AEFC\"];\n  \"bowtie_indices_folder\" -> \"bowtie_aligner\" [label=\"indices_folder\"];\n  \"default3\" -> \"bowtie_aligner\" [label=\"v\"];\n  \"default3\" [label=\"3\", fillcolor=\"#D5AEFC\"];\n  \"default4\" -> \"bowtie_aligner\" [label=\"best\"];\n  \"default4\" [label=\"true\", fillcolor=\"#D5AEFC\"];\n  \"default5\" -> \"bowtie_aligner\" [label=\"strata\"];\n  \"default5\" [label=\"true\", fillcolor=\"#D5AEFC\"];\n  \"samtools_sort_index\" -> \"get_bam_statistics\" [label=\"output_filename\"];\n  \"samtools_sort_index\" -> \"get_bam_statistics\" [label=\"bambai_pair\"];\n  \"default6\" -> \"rpkm_calculation\" [label=\"rpkm_threshold\"];\n  \"default6\" [label=\"1e-03\", fillcolor=\"#D5AEFC\"];\n  \"threads\" -> \"rpkm_calculation\" [label=\"threads\"];\n  \"exclude_chr\" -> \"rpkm_calculation\" [label=\"exclude_chr\"];\n  \"default7\" -> \"rpkm_calculation\" [label=\"dutp\"];\n  \"default7\" [label=\"true\", fillcolor=\"#D5AEFC\"];\n  \"samtools_sort_index\" -> \"rpkm_calculation\" [label=\"bam_file\"];\n  \"annotation_file\" -> \"rpkm_calculation\" [label=\"annotation_file\"];\n  \"samtools_sort_index\" -> \"bam_to_bigwig_upstream\" [label=\"bigwig_filename\"];\n  \"default8\" -> \"bam_to_bigwig_upstream\" [label=\"strand\"];\n  \"default8\" [label=\"\\\"+\\\"\", fillcolor=\"#D5AEFC\"];\n  \"star_aligner\" -> \"bam_to_bigwig_upstream\" [label=\"mapped_reads_number\"];\n  \"chrom_length_file\" -> \"bam_to_bigwig_upstream\" [label=\"chrom_length_file\"];\n  \"samtools_sort_index\" -> \"bam_to_bigwig_upstream\" [label=\"bam_file\"];\n  \"bowtie_aligner\" -> \"get_stat\" [label=\"bowtie_alignment_report\"];\n  \"star_aligner\" -> \"get_stat\" [label=\"star_alignment_report\"];\n  \"rpkm_calculation\" -> \"get_stat\" [label=\"isoforms_file\"];\n  \"get_bam_statistics\" -> \"get_stat\" [label=\"bam_statistics_report\"];\n  \"rpkm_calculation\" -> \"group_isoforms\" [label=\"isoforms_file\"];\n  \"threads\" -> \"star_aligner\" [label=\"threads\"];\n  \"default9\" -> \"star_aligner\" [label=\"seedSearchStartLmax\"];\n  \"default9\" [label=\"15\", fillcolor=\"#D5AEFC\"];\n  \"default10\" -> \"star_aligner\" [label=\"outFilterMultimapNmax\"];\n  \"default10\" [label=\"1\", fillcolor=\"#D5AEFC\"];\n  \"star_indices_folder\" -> \"star_aligner\" [label=\"genomeDir\"];\n  \"default11\" -> \"star_aligner\" [label=\"alignSJDBoverhangMin\"];\n  \"default11\" [label=\"1\", fillcolor=\"#D5AEFC\"];\n  \"extract_fastq\" -> \"star_aligner\" [label=\"readFilesIn\"];\n  \"default12\" -> \"star_aligner\" [label=\"outFilterMismatchNmax\"];\n  \"default12\" [label=\"5\", fillcolor=\"#D5AEFC\"];\n  \"clip_5p_end\" -> \"star_aligner\" [label=\"clip5pNbases\"];\n  \"clip_3p_end\" -> \"star_aligner\" [label=\"clip3pNbases\"];\n  \"extract_fastq\" -> \"fastx_quality_stats\" [label=\"input_file\"];\n  \"samtools_sort_index\" -> \"bam_to_bigwig_downstream\" [label=\"bigwig_filename\"];\n  \"samtools_sort_index\" -> \"bam_to_bigwig_downstream\" [label=\"bam_file\"];\n  \"chrom_length_file\" -> \"bam_to_bigwig_downstream\" [label=\"chrom_length_file\"];\n  \"default13\" -> \"bam_to_bigwig_downstream\" [label=\"strand\"];\n  \"default13\" [label=\"\\\"-\\\"\", fillcolor=\"#D5AEFC\"];\n  \"star_aligner\" -> \"bam_to_bigwig_downstream\" [label=\"mapped_reads_number\"];\n  \"threads\" -> \"samtools_sort_index\" [label=\"threads\"];\n  \"extract_fastq\" -> \"samtools_sort_index\" [label=\"sort_output_filename\"];\n  \"star_aligner\" -> \"samtools_sort_index\" [label=\"sort_input\"];\n  \"fastq_file\" -> \"extract_fastq\" [label=\"compressed_file\"];\n  \"samtools_sort_index\" -> \"bambai_pair\";\n  \"get_stat\" -> \"get_stat_markdown\";\n  \"fastx_quality_stats\" -> \"fastx_statistics\";\n  \"get_bam_statistics\" -> \"bam_statistics_report\";\n  \"star_aligner\" -> \"star_sj_log\";\n  \"group_isoforms\" -> \"rpkm_genes\";\n  \"star_aligner\" -> \"star_progress_log\";\n  \"star_aligner\" -> \"star_final_log\";\n  \"star_aligner\" -> \"star_out_log\";\n  \"bowtie_aligner\" -> \"bowtie_log\";\n  \"group_isoforms\" -> \"rpkm_common_tss\";\n  \"bam_to_bigwig_upstream\" -> \"bigwig_upstream\";\n  \"rpkm_calculation\" -> \"rpkm_isoforms\";\n  \"get_stat\" -> \"get_formatted_stats\";\n  \"bam_to_bigwig_downstream\" -> \"bigwig_downstream\";\n  \"star_aligner\" -> \"star_stdout_log\";\n  \"get_stat\" -> \"get_stat_log\";\n}\n","licenseLink":"https://spdx.org/licenses/Apache-2.0","packed":false,"permalink":"https://w3id.org/cwl/view/git/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl","visualisationXdot":"/graph/xdot/github.com/datirium/workflows/blob/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl","roBundle":"/robundle/github.com/datirium/workflows/blob/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl","licenseName":"Apache License 2.0","visualisationPng":"/graph/png/github.com/datirium/workflows/blob/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl","visualisationSvg":"/graph/svg/github.com/datirium/workflows/blob/46a077b51619c6a14f85e0aa5260ae8a04426fab/workflows/rnaseq-se-dutp.cwl"}