germline_wgs_gvcf.cwl

#!/usr/bin/env cwl-runner

cwlVersion: v1.0
class: Workflow
label: "wgs alignment and germline variant detection"
requirements:
    - class: SchemaDefRequirement
      types:
          - $import: ../types/labelled_file.yml
          - $import: ../types/sequence_data.yml
          - $import: ../types/trimming_options.yml
    - class: SubworkflowFeatureRequirement
    - class: StepInputExpressionRequirement
inputs:
    reference:
        type:
            - string
            - File
        secondaryFiles: [.fai, ^.dict, .amb, .ann, .bwt, .pac, .sa]
    sequence:
        type: ../types/sequence_data.yml#sequence_data[]
        label: "sequence: sequencing data and readgroup information"
        doc: |
          sequence represents the sequencing data as either FASTQs or BAMs with accompanying
          readgroup information. Note that in the @RG field ID and SM are required.
    trimming:
        type:
            - ../types/trimming_options.yml#trimming_options
            - "null"
    omni_vcf:
        type: File
        secondaryFiles: [.tbi]
    picard_metric_accumulation_level:
        type: string
    emit_reference_confidence:
        type:
            type: enum
            symbols: ['NONE', 'BP_RESOLUTION', 'GVCF']
    gvcf_gq_bands:
        type: string[]
    intervals:
        type:
            type: array
            items:
                type: array
                items: string
    ploidy:
        type: int?
    qc_intervals:
        type: File
    synonyms_file:
        type: File?
    annotate_coding_only:
        type: boolean?
    bqsr_known_sites:
        type: File[]
        secondaryFiles: [.tbi]
        doc: "One or more databases of known polymorphic sites used to exclude regions around known polymorphisms from analysis."
    bqsr_intervals:
        type: string[]?
    minimum_mapping_quality:
        type: int?
    minimum_base_quality:
        type: int?
    per_base_intervals:
        type: ../types/labelled_file.yml#labelled_file[]
    per_target_intervals:
        type: ../types/labelled_file.yml#labelled_file[]
    summary_intervals:
        type: ../types/labelled_file.yml#labelled_file[]
outputs:
    cram:
        type: File
        outputSource: index_cram/indexed_cram
    mark_duplicates_metrics:
        type: File
        outputSource: alignment_and_qc/mark_duplicates_metrics
    insert_size_metrics:
        type: File
        outputSource: alignment_and_qc/insert_size_metrics
    insert_size_histogram:
        type: File
        outputSource: alignment_and_qc/insert_size_histogram
    alignment_summary_metrics:
        type: File
        outputSource: alignment_and_qc/alignment_summary_metrics
    gc_bias_metrics:
        type: File
        outputSource: alignment_and_qc/gc_bias_metrics
    gc_bias_metrics_chart:
        type: File
        outputSource: alignment_and_qc/gc_bias_metrics_chart
    gc_bias_metrics_summary:
        type: File
        outputSource: alignment_and_qc/gc_bias_metrics_summary
    wgs_metrics:
        type: File
        outputSource: alignment_and_qc/wgs_metrics
    flagstats:
        type: File
        outputSource: alignment_and_qc/flagstats
    verify_bam_id_metrics:
        type: File
        outputSource: alignment_and_qc/verify_bam_id_metrics
    verify_bam_id_depth:
        type: File
        outputSource: alignment_and_qc/verify_bam_id_depth
    per_base_coverage_metrics:
        type: File[]
        outputSource: alignment_and_qc/per_base_coverage_metrics
    per_base_hs_metrics:
        type: File[]
        outputSource: alignment_and_qc/per_base_hs_metrics
    per_target_coverage_metrics:
        type: File[]
        outputSource: alignment_and_qc/per_target_coverage_metrics
    per_target_hs_metrics:
        type: File[]
        outputSource: alignment_and_qc/per_target_hs_metrics
    summary_hs_metrics:
        type: File[]
        outputSource: alignment_and_qc/summary_hs_metrics
    gvcf:
        type: File[]
        outputSource: generate_gvcfs/gvcf
steps:
    alignment_and_qc:
        run: alignment_wgs.cwl
        in:
            reference: reference
            sequence: sequence
            trimming: trimming
            bqsr_known_sites: bqsr_known_sites
            omni_vcf: omni_vcf
            intervals: qc_intervals
            picard_metric_accumulation_level: picard_metric_accumulation_level
            bqsr_intervals: bqsr_intervals
            minimum_mapping_quality: minimum_mapping_quality
            minimum_base_quality: minimum_base_quality
            per_base_intervals: per_base_intervals
            per_target_intervals: per_target_intervals
            summary_intervals: summary_intervals
        out:
            [bam, mark_duplicates_metrics, insert_size_metrics, insert_size_histogram, alignment_summary_metrics, gc_bias_metrics, gc_bias_metrics_chart, gc_bias_metrics_summary, wgs_metrics, flagstats, verify_bam_id_metrics, verify_bam_id_depth, per_base_coverage_metrics, per_base_hs_metrics, per_target_coverage_metrics, per_target_hs_metrics, summary_hs_metrics]
    extract_freemix:
        in:
            verify_bam_id_metrics: alignment_and_qc/verify_bam_id_metrics
        out:
            [freemix_score]
        run:
            class: ExpressionTool
            requirements:
                - class: InlineJavascriptRequirement
            inputs:
                verify_bam_id_metrics:
                    type: File
                    inputBinding:
                        loadContents: true
            outputs:
                freemix_score:
                    type: string?
            expression: |
                        ${
                            var metrics = inputs.verify_bam_id_metrics.contents.split("\n");
                            if ( metrics[0].split("\t")[6] == 'FREEMIX' ) {
                                return {'freemix_score': metrics[1].split("\t")[6]};
                            } else {
                                return {'freemix_score:': null };
                            }
                        }
    generate_gvcfs:
        run: ../subworkflows/gatk_haplotypecaller_iterator.cwl
        in:
            bam: alignment_and_qc/bam
            reference: reference
            emit_reference_confidence: emit_reference_confidence
            gvcf_gq_bands: gvcf_gq_bands
            intervals: intervals
            contamination_fraction: extract_freemix/freemix_score
            ploidy: ploidy
        out:
            [gvcf]
    bam_to_cram:
        run: ../tools/bam_to_cram.cwl
        in:
            bam: alignment_and_qc/bam
            reference: reference
        out:
            [cram]
    index_cram:
         run: ../tools/index_cram.cwl
         in:
            cram: bam_to_cram/cram
         out:
            [indexed_cram]