{"@id":"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl","retrievedFrom":{"repoUrl":"https://github.com/genome/analysis-workflows.git","branch":"509938802c5e42bb8084c6a5a26ab6425c60e69a","path":"definitions/pipelines/rnaseq_star_fusion.cwl","packedId":null,"type":"GITHUB","rawUrl":"https://raw.githubusercontent.com/genome/analysis-workflows/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl","url":"https://github.com/genome/analysis-workflows/blob/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl"},"retrievedOn":"2026-10-25T11:50:40.854+00:00","lastCommit":"509938802c5e42bb8084c6a5a26ab6425c60e69a","label":"STAR-RNA-Seq alignment and transcript/gene abundance workflow","inputs":{"strand":{},"refFlat":{"type":"File"},"gtf_file":{"type":"File"},"cdna_fasta":{"type":"File"},"sample_name":{"type":"String"},"kallisto_index":{"type":"File"},"star_genome_dir":{"type":"Directory"},"trimming_adapters":{"type":"File"},"outsam_attrrg_line":{"type":"String[]"},"ribosomal_intervals":{"type":"File"},"instrument_data_bams":{"type":"File[]"},"trimming_max_uncalled":{"type":"Integer"},"star_fusion_genome_dir":{"type":"Directory"},"trimming_min_readlength":{"type":"Integer"},"trimming_adapter_trim_end":{"type":"String"},"gene_transcript_lookup_table":{"type":"File"},"trimming_adapter_min_overlap":{"type":"Integer"}},"outputs":{"chart":{"type":"File"},"metrics":{"type":"File"},"final_bam":{"type":"File"},"strand_info":{"type":"File[]"},"gene_abundance":{"type":"File"},"fusion_evidence":{"type":"File"},"star_fusion_log":{"type":"File"},"star_fusion_out":{"type":"File"},"star_junction_out":{"type":"File"},"star_fusion_abridge":{"type":"File"},"star_fusion_predict":{"type":"File"},"transcript_abundance_h5":{"type":"File"},"stringtie_transcript_gtf":{"type":"File"},"transcript_abundance_tsv":{"type":"File"},"stringtie_gene_expression_tsv":{"type":"File"}},"steps":{"kallisto":{"label":"Kallisto: Quant","run":"../tools/kallisto.cwl","runType":"COMMANDLINETOOL","sources":{"kallisto":{"sourceIDs":["kallisto_index"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#kallisto/fastqs":{"sourceIDs":["bam_to_trimmed_fastq"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#kallisto/strand":{"sourceIDs":["strand"]}}},"mark_dup":{"label":"Mark duplicates and Sort","run":"../tools/mark_duplicates_and_sort.cwl","runType":"COMMANDLINETOOL","sources":{"mark_dup":{"defaultVal":"\\\"coordinate\\\""},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#mark_dup/bam":{"sourceIDs":["sort_bam"]}}},"sort_bam":{"label":"samtools sort","run":"../tools/samtools_sort.cwl","runType":"COMMANDLINETOOL","sources":{"sort_bam":{"sourceIDs":["star_align_fusion"]}}},"index_bam":{"label":"samtools index","run":"../tools/index_bam.cwl","runType":"COMMANDLINETOOL","sources":{"index_bam":{"sourceIDs":["mark_dup"]}}},"stringtie":{"label":"StringTie","run":"../tools/stringtie.cwl","runType":"COMMANDLINETOOL","sources":{"stringtie":{"sourceIDs":["strand"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#stringtie/bam":{"sourceIDs":["mark_dup"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#stringtie/sample_name":{"sourceIDs":["sample_name"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#stringtie/reference_annotation":{"sourceIDs":["gtf_file"]}}},"star_align_fusion":{"label":"STAR: align reads to transcriptome","run":"../tools/star_align_fusion.cwl","runType":"COMMANDLINETOOL","sources":{"star_align_fusion":{"sourceIDs":["star_genome_dir"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#star_align_fusion/fastq":{"sourceIDs":["bam_to_trimmed_fastq"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#star_align_fusion/fastq2":{"sourceIDs":["bam_to_trimmed_fastq"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#star_align_fusion/gtf_file":{"sourceIDs":["gtf_file"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#star_align_fusion/outsam_attrrg_line":{"sourceIDs":["outsam_attrrg_line"]}}},"star_fusion_detect":{"label":"STAR-Fusion identify candidate fusion transcript","run":"../tools/star_fusion_detect.cwl","runType":"COMMANDLINETOOL","sources":{"star_fusion_detect":{"sourceIDs":["star_fusion_genome_dir"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#star_fusion_detect/junction_file":{"sourceIDs":["star_align_fusion"]}}},"strandedness_check":{"label":"runs how_are_we_stranded_here to determine RNAseq data strandedness","doc":"Uses how_are_we_stranded_here, a python package for testing strandedness. Runs Kallisto and Rseqc (infer-experiment-py) to\nto check which direction reads align once mapped in transcripts. It first creates a Kallisto index (or uses a pre-made index)\nof your organism's transcriptome. It then maps a small subset of reads (default 200000) to the transcriptome and uses Kallisto's\n--genomebam argument to project pseudoalignments to the genome sorted BAM file. (Currently only Kallisto version 0.44.0 works well with\nhow_are_we_stranded_here.) It finally runs RSeQC's infer_experiment.py to check which direction reads from the first and second pairs\nare aligned in relation to the transcript strand, and provides output with the likely strandedness of your data.\n","run":"../tools/strandedness_check.cwl","runType":"COMMANDLINETOOL","sources":{"strandedness_check":{"sourceIDs":["bam_to_trimmed_fastq"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#strandedness_check/reads2":{"sourceIDs":["bam_to_trimmed_fastq"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#strandedness_check/gtf_file":{"sourceIDs":["gtf_file"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#strandedness_check/cdna_fasta":{"sourceIDs":["cdna_fasta"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#strandedness_check/kallisto_index":{"sourceIDs":["kallisto_index"]}}},"transcript_to_gene":{"label":"Kallisto: TranscriptToGene","run":"../tools/transcript_to_gene.cwl","runType":"COMMANDLINETOOL","sources":{"transcript_to_gene":{"sourceIDs":["gene_transcript_lookup_table"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#transcript_to_gene/transcript_table_h5":{"sourceIDs":["kallisto"]}}},"generate_qc_metrics":{"label":"Picard: RNA Seq Metrics","run":"../tools/generate_qc_metrics.cwl","runType":"COMMANDLINETOOL","sources":{"generate_qc_metrics":{"sourceIDs":["strand"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#generate_qc_metrics/bam":{"sourceIDs":["mark_dup"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#generate_qc_metrics/refFlat":{"sourceIDs":["refFlat"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#generate_qc_metrics/ribosomal_intervals":{"sourceIDs":["ribosomal_intervals"]}}},"bam_to_trimmed_fastq":{"label":"bam to trimmed fastqs","run":"../subworkflows/bam_to_trimmed_fastq.cwl","runType":"WORKFLOW","sources":{"bam_to_trimmed_fastq":{"sourceIDs":["trimming_min_readlength"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#bam_to_trimmed_fastq/bam":{"sourceIDs":["instrument_data_bams"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#bam_to_trimmed_fastq/adapters":{"sourceIDs":["trimming_adapters"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#bam_to_trimmed_fastq/max_uncalled":{"sourceIDs":["trimming_max_uncalled"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#bam_to_trimmed_fastq/adapter_trim_end":{"sourceIDs":["trimming_adapter_trim_end"]},"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl#bam_to_trimmed_fastq/adapter_min_overlap":{"sourceIDs":["trimming_adapter_min_overlap"]}}}},"cwltoolVersion":"3.1.20230201224320","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    \"gene_transcript_lookup_table\" [fillcolor=\"#94DDF4\",label=\"gene_transcript_lookup_table\"];\n    \"trimming_min_readlength\" [fillcolor=\"#94DDF4\",label=\"trimming_min_readlength\"];\n    \"star_genome_dir\" [fillcolor=\"#94DDF4\",label=\"star_genome_dir\"];\n    \"strand\" [fillcolor=\"#94DDF4\",label=\"strand\"];\n    \"ribosomal_intervals\" [fillcolor=\"#94DDF4\",label=\"ribosomal_intervals\"];\n    \"kallisto_index\" [fillcolor=\"#94DDF4\",label=\"kallisto_index\"];\n    \"trimming_adapter_min_overlap\" [fillcolor=\"#94DDF4\",label=\"trimming_adapter_min_overlap\"];\n    \"trimming_adapters\" [fillcolor=\"#94DDF4\",label=\"trimming_adapters\"];\n    \"sample_name\" [fillcolor=\"#94DDF4\",label=\"sample_name\"];\n    \"instrument_data_bams\" [fillcolor=\"#94DDF4\",label=\"instrument_data_bams\"];\n    \"outsam_attrrg_line\" [fillcolor=\"#94DDF4\",label=\"outsam_attrrg_line\"];\n    \"refFlat\" [fillcolor=\"#94DDF4\",label=\"refFlat\"];\n    \"star_fusion_genome_dir\" [fillcolor=\"#94DDF4\",label=\"star_fusion_genome_dir\"];\n    \"gtf_file\" [fillcolor=\"#94DDF4\",label=\"gtf_file\"];\n    \"cdna_fasta\" [fillcolor=\"#94DDF4\",label=\"cdna_fasta\"];\n    \"trimming_max_uncalled\" [fillcolor=\"#94DDF4\",label=\"trimming_max_uncalled\"];\n    \"trimming_adapter_trim_end\" [fillcolor=\"#94DDF4\",label=\"trimming_adapter_trim_end\"];\n  }\n  subgraph cluster_outputs {\n    rank = \"same\";\n    style = \"dashed\";\n    labelloc = \"b\";\n    label = \"Workflow Outputs\";\n    \"metrics\" [fillcolor=\"#94DDF4\",label=\"metrics\"];\n    \"stringtie_transcript_gtf\" [fillcolor=\"#94DDF4\",label=\"stringtie_transcript_gtf\"];\n    \"star_fusion_log\" [fillcolor=\"#94DDF4\",label=\"star_fusion_log\"];\n    \"stringtie_gene_expression_tsv\" [fillcolor=\"#94DDF4\",label=\"stringtie_gene_expression_tsv\"];\n    \"transcript_abundance_h5\" [fillcolor=\"#94DDF4\",label=\"transcript_abundance_h5\"];\n    \"star_fusion_out\" [fillcolor=\"#94DDF4\",label=\"star_fusion_out\"];\n    \"gene_abundance\" [fillcolor=\"#94DDF4\",label=\"gene_abundance\"];\n    \"chart\" [fillcolor=\"#94DDF4\",label=\"chart\"];\n    \"strand_info\" [fillcolor=\"#94DDF4\",label=\"strand_info\"];\n    \"final_bam\" [fillcolor=\"#94DDF4\",label=\"final_bam\"];\n    \"fusion_evidence\" [fillcolor=\"#94DDF4\",label=\"fusion_evidence\"];\n    \"transcript_abundance_tsv\" [fillcolor=\"#94DDF4\",label=\"transcript_abundance_tsv\"];\n    \"star_fusion_abridge\" [fillcolor=\"#94DDF4\",label=\"star_fusion_abridge\"];\n    \"star_fusion_predict\" [fillcolor=\"#94DDF4\",label=\"star_fusion_predict\"];\n    \"star_junction_out\" [fillcolor=\"#94DDF4\",label=\"star_junction_out\"];\n  }\n  \"mark_dup\" [label=\"Mark duplicates and Sort\"];\n  \"generate_qc_metrics\" [label=\"Picard: RNA Seq Metrics\"];\n  \"star_align_fusion\" [label=\"STAR: align reads to transcriptome\"];\n  \"stringtie\" [label=\"StringTie\"];\n  \"star_fusion_detect\" [label=\"STAR-Fusion identify candidate fusion transcript\"];\n  \"sort_bam\" [label=\"samtools sort\"];\n  \"transcript_to_gene\" [label=\"Kallisto: TranscriptToGene\"];\n  \"kallisto\" [label=\"Kallisto: Quant\"];\n  \"strandedness_check\" [label=\"runs how_are_we_stranded_here to determine RNAseq data strandedness\"];\n  \"bam_to_trimmed_fastq\" [label=\"bam to trimmed fastqs\", fillcolor=\"#F3CEA1\"];\n  \"index_bam\" [label=\"samtools index\"];\n  \"default1\" -> \"mark_dup\" [label=\"input_sort_order\"];\n  \"default1\" [label=\"\\\"coordinate\\\"\", fillcolor=\"#D5AEFC\"];\n  \"sort_bam\" -> \"mark_dup\" [label=\"bam\"];\n  \"strand\" -> \"generate_qc_metrics\" [label=\"strand\"];\n  \"ribosomal_intervals\" -> \"generate_qc_metrics\" [label=\"ribosomal_intervals\"];\n  \"refFlat\" -> \"generate_qc_metrics\" [label=\"refFlat\"];\n  \"mark_dup\" -> \"generate_qc_metrics\" [label=\"bam\"];\n  \"star_genome_dir\" -> \"star_align_fusion\" [label=\"star_genome_dir\"];\n  \"bam_to_trimmed_fastq\" -> \"star_align_fusion\" [label=\"fastq\"];\n  \"bam_to_trimmed_fastq\" -> \"star_align_fusion\" [label=\"fastq2\"];\n  \"gtf_file\" -> \"star_align_fusion\" [label=\"gtf_file\"];\n  \"outsam_attrrg_line\" -> \"star_align_fusion\" [label=\"outsam_attrrg_line\"];\n  \"strand\" -> \"stringtie\" [label=\"strand\"];\n  \"sample_name\" -> \"stringtie\" [label=\"sample_name\"];\n  \"gtf_file\" -> \"stringtie\" [label=\"reference_annotation\"];\n  \"mark_dup\" -> \"stringtie\" [label=\"bam\"];\n  \"star_fusion_genome_dir\" -> \"star_fusion_detect\" [label=\"star_fusion_genome_dir\"];\n  \"star_align_fusion\" -> \"star_fusion_detect\" [label=\"junction_file\"];\n  \"star_align_fusion\" -> \"sort_bam\" [label=\"input_bam\"];\n  \"gene_transcript_lookup_table\" -> \"transcript_to_gene\" [label=\"gene_transcript_lookup_table\"];\n  \"kallisto\" -> \"transcript_to_gene\" [label=\"transcript_table_h5\"];\n  \"kallisto_index\" -> \"kallisto\" [label=\"kallisto_index\"];\n  \"strand\" -> \"kallisto\" [label=\"strand\"];\n  \"bam_to_trimmed_fastq\" -> \"kallisto\" [label=\"fastqs\"];\n  \"bam_to_trimmed_fastq\" -> \"strandedness_check\" [label=\"reads1\"];\n  \"bam_to_trimmed_fastq\" -> \"strandedness_check\" [label=\"reads2\"];\n  \"kallisto_index\" -> \"strandedness_check\" [label=\"kallisto_index\"];\n  \"gtf_file\" -> \"strandedness_check\" [label=\"gtf_file\"];\n  \"cdna_fasta\" -> \"strandedness_check\" [label=\"cdna_fasta\"];\n  \"trimming_min_readlength\" -> \"bam_to_trimmed_fastq\" [label=\"min_readlength\"];\n  \"trimming_adapters\" -> \"bam_to_trimmed_fastq\" [label=\"adapters\"];\n  \"instrument_data_bams\" -> \"bam_to_trimmed_fastq\" [label=\"bam\"];\n  \"trimming_max_uncalled\" -> \"bam_to_trimmed_fastq\" [label=\"max_uncalled\"];\n  \"trimming_adapter_trim_end\" -> \"bam_to_trimmed_fastq\" [label=\"adapter_trim_end\"];\n  \"trimming_adapter_min_overlap\" -> \"bam_to_trimmed_fastq\" [label=\"adapter_min_overlap\"];\n  \"mark_dup\" -> \"index_bam\" [label=\"bam\"];\n  \"generate_qc_metrics\" -> \"metrics\";\n  \"stringtie\" -> \"stringtie_transcript_gtf\";\n  \"star_align_fusion\" -> \"star_fusion_log\";\n  \"stringtie\" -> \"stringtie_gene_expression_tsv\";\n  \"kallisto\" -> \"transcript_abundance_h5\";\n  \"star_align_fusion\" -> \"star_fusion_out\";\n  \"transcript_to_gene\" -> \"gene_abundance\";\n  \"generate_qc_metrics\" -> \"chart\";\n  \"strandedness_check\" -> \"strand_info\";\n  \"index_bam\" -> \"final_bam\";\n  \"kallisto\" -> \"fusion_evidence\";\n  \"kallisto\" -> \"transcript_abundance_tsv\";\n  \"star_fusion_detect\" -> \"star_fusion_abridge\";\n  \"star_fusion_detect\" -> \"star_fusion_predict\";\n  \"star_align_fusion\" -> \"star_junction_out\";\n}\n","licenseLink":"https://spdx.org/licenses/MIT","permalink":"https://w3id.org/cwl/view/git/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl","packed":false,"visualisationXdot":"/graph/xdot/github.com/genome/analysis-workflows/blob/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl","visualisationPng":"/graph/png/github.com/genome/analysis-workflows/blob/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl","visualisationSvg":"/graph/svg/github.com/genome/analysis-workflows/blob/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl","roBundle":"/robundle/github.com/genome/analysis-workflows/blob/509938802c5e42bb8084c6a5a26ab6425c60e69a/definitions/pipelines/rnaseq_star_fusion.cwl","licenseName":"MIT License"}