#!/usr/bin/env cwl-runner

cwlVersion: v1.0
class: Workflow
label: "exome alignment and germline variant detection"
requirements:
    - class: SchemaDefRequirement
      types:
          - $import: ../types/labelled_file.yml
          - $import: ../types/sequence_data.yml
    - class: SubworkflowFeatureRequirement
inputs:
    reference: string
    sequence:
        type: ../types/sequence_data.yml#sequence_data[]
    mills:
        type: File
        secondaryFiles: [.tbi]
    known_indels:
        type: File
        secondaryFiles: [.tbi]
    dbsnp_vcf:
        type: File
        secondaryFiles: [.tbi]
    bqsr_intervals:
        type: string[]?
    bait_intervals:
        type: File
    target_intervals:
        type: File
    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[]
    omni_vcf:
        type: File
        secondaryFiles: [.tbi]
    picard_metric_accumulation_level:
        type: string
    emit_reference_confidence:
        type: string
    gvcf_gq_bands:
        type: string[]
    intervals:
        type:
            type: array
            items:
                type: array
                items: string
    vep_cache_dir:
        type: string
    vep_ensembl_assembly:
        type: string
        doc: "genome assembly to use in vep. Examples: GRCh38 or GRCm38"
    vep_ensembl_version:
        type: string
        doc: "ensembl version - Must be present in the cache directory. Example: 95"
    vep_ensembl_species:
        type: string
        doc: "ensembl species - Must be present in the cache directory. Examples: homo_sapiens or mus_musculus"
    vep_plugins:
        type: string[]?
        doc: "array of plugins to use when running vep"
    synonyms_file:
        type: File?
    annotate_coding_only:
        type: boolean?
    custom_gnomad_vcf:
        type: File?
        secondaryFiles: [.tbi]
    qc_minimum_mapping_quality:
        type: int?
    qc_minimum_base_quality:
        type: int?
    custom_clinvar_vcf:
        type: File?
        secondaryFiles: [.tbi]
    variants_to_table_fields:
         type: string[]?
    variants_to_table_genotype_fields:
         type: string[]?
    vep_to_table_fields:
         type: string[]?
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
    hs_metrics:
        type: File
        outputSource: alignment_and_qc/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
    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
    summary_hs_metrics:
        type: File[]
        outputSource: alignment_and_qc/summary_hs_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
    gvcf:
        type: File[]
        outputSource: detect_variants/gvcf
    final_vcf:
        type: File
        outputSource: detect_variants/final_vcf
        secondaryFiles: [.tbi]
    coding_vcf:
        type: File
        outputSource: detect_variants/coding_vcf
        secondaryFiles: [.tbi]
    limited_vcf:
        type: File
        outputSource: detect_variants/limited_vcf
        secondaryFiles: [.tbi]
    vep_summary:
        type: File
        outputSource: detect_variants/vep_summary
    final_tsv:
       type: File
       outputSource: detect_variants/final_tsv
steps:
    alignment_and_qc:
        run: alignment_exome.cwl
        in:
            reference: reference
            sequence: sequence
            mills: mills
            known_indels: known_indels
            dbsnp_vcf: dbsnp_vcf
            bqsr_intervals: bqsr_intervals
            bait_intervals: bait_intervals
            target_intervals: target_intervals
            per_base_intervals: per_base_intervals
            per_target_intervals: per_target_intervals
            summary_intervals: summary_intervals
            omni_vcf: omni_vcf
            picard_metric_accumulation_level: picard_metric_accumulation_level   
            qc_minimum_mapping_quality: qc_minimum_mapping_quality
            qc_minimum_base_quality: qc_minimum_base_quality
        out:
            [bam, mark_duplicates_metrics, insert_size_metrics, insert_size_histogram, alignment_summary_metrics, hs_metrics, per_target_coverage_metrics, per_target_hs_metrics, per_base_coverage_metrics, per_base_hs_metrics, summary_hs_metrics, flagstats, verify_bam_id_metrics, verify_bam_id_depth]
    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 };
                            }
                        }
    detect_variants:
        run: ../subworkflows/germline_detect_variants.cwl
        in:
            reference: reference
            bam: alignment_and_qc/bam
            emit_reference_confidence: emit_reference_confidence
            gvcf_gq_bands: gvcf_gq_bands
            intervals: intervals
            contamination_fraction: extract_freemix/freemix_score
            vep_cache_dir: vep_cache_dir
            synonyms_file: synonyms_file
            annotate_coding_only: annotate_coding_only
            custom_gnomad_vcf: custom_gnomad_vcf
            limit_variant_intervals: target_intervals
            custom_clinvar_vcf: custom_clinvar_vcf
            vep_ensembl_assembly: vep_ensembl_assembly
            vep_ensembl_version: vep_ensembl_version
            vep_ensembl_species: vep_ensembl_species
            vep_plugins: vep_plugins
            vep_to_table_fields: vep_to_table_fields
            variants_to_table_fields: variants_to_table_fields
            variants_to_table_genotype_fields: variants_to_table_genotype_fields
        out:
            [gvcf, final_vcf, coding_vcf, limited_vcf, vep_summary, final_tsv]
    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]