Non-human WGS Pipeline with Basic QC and Variant Calls (SNVs/Indels)

definitions/pipelines/germline_wgs_non_human.cwl

@@ -0,0 +1,173 @@
+#!/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
+    - class: SubworkflowFeatureRequirement
+inputs:
+    reference: string
+    bams:
+        type: File[]
+    readgroups:
+        type: string[]
+    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
+    qc_intervals:
+        type: File
+    variant_reporting_intervals:
+        type: File
+    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"
+    synonyms_file:
+        type: File?
+    annotate_coding_only:
+        type: boolean?
+    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[]
+    ploidy:
+        type: int
+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
+    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
+    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
+    bamcoverage_bigwig:
+        type: File
+        outputSource: alignment_and_qc/bamcoverage_bigwig
+steps:
+    alignment_and_qc:
+        run: wgs_alignment_and_qc_non_human.cwl
+        in:
+            reference: reference
+            bams: bams
+            readgroups: readgroups
+            intervals: qc_intervals
+            picard_metric_accumulation_level: picard_metric_accumulation_level
+            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, per_base_coverage_metrics, per_base_hs_metrics, per_target_coverage_metrics, per_target_hs_metrics, summary_hs_metrics, bamcoverage_bigwig]
+    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
+            vep_cache_dir: vep_cache_dir
+            synonyms_file: synonyms_file
+            annotate_coding_only: annotate_coding_only
+            limit_variant_intervals: variant_reporting_intervals
+            vep_ensembl_assembly: vep_ensembl_assembly
+            vep_ensembl_version: vep_ensembl_version
+            vep_ensembl_species: vep_ensembl_species
+            ploidy: ploidy
+        out:
+            [gvcf, final_vcf, coding_vcf, limited_vcf, vep_summary]
+    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]

definitions/pipelines/wgs_alignment_and_qc_non_human.cwl

@@ -0,0 +1,100 @@
+#!/usr/bin/env cwl-runner
+
+cwlVersion: v1.0
+class: Workflow
+label: "wgs alignment with qc"
+requirements:
+    - class: SchemaDefRequirement
+      types:
+          - $import: ../types/labelled_file.yml
+    - class: SubworkflowFeatureRequirement
+inputs:
+    reference: string
+    bams:
+        type: File[]
+    readgroups:
+        type: string[]
+    intervals:
+        type: File
+    picard_metric_accumulation_level:
+        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:
+    bam:
+        type: File
+        outputSource: alignment/final_bam
+    mark_duplicates_metrics:
+        type: File
+        outputSource: alignment/mark_duplicates_metrics_file
+    insert_size_metrics:
+        type: File
+        outputSource: qc/insert_size_metrics
+    insert_size_histogram:
+        type: File
+        outputSource: qc/insert_size_histogram
+    alignment_summary_metrics:
+        type: File
+        outputSource: qc/alignment_summary_metrics
+    gc_bias_metrics:
+        type: File
+        outputSource: qc/gc_bias_metrics
+    gc_bias_metrics_chart:
+        type: File
+        outputSource: qc/gc_bias_metrics_chart
+    gc_bias_metrics_summary:
+        type: File
+        outputSource: qc/gc_bias_metrics_summary
+    wgs_metrics:
+        type: File
+        outputSource: qc/wgs_metrics
+    flagstats:
+        type: File
+        outputSource: qc/flagstats
+    per_base_coverage_metrics:
+        type: File[]
+        outputSource: qc/per_base_coverage_metrics
+    per_base_hs_metrics:
+        type: File[]
+        outputSource: qc/per_base_hs_metrics
+    per_target_coverage_metrics:
+        type: File[]
+        outputSource: qc/per_target_coverage_metrics
+    per_target_hs_metrics:
+        type: File[]
+        outputSource: qc/per_target_hs_metrics
+    summary_hs_metrics:
+        type: File[]
+        outputSource: qc/summary_hs_metrics
+    bamcoverage_bigwig:
+        type: File
+        outputSource: qc/bamcoverage_bigwig
+steps:
+    alignment:
+        run: ../subworkflows/align_sort_markdup.cwl
+        in:
+            reference: reference
+            bams: bams
+            readgroups: readgroups
+        out: [final_bam,mark_duplicates_metrics_file]
+    qc:
+        run: ../subworkflows/qc_wgs_no_verify_bam.cwl
+        in:
+            bam: alignment/final_bam
+            reference: reference
+            intervals: intervals
+            picard_metric_accumulation_level: picard_metric_accumulation_level
+            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: [insert_size_metrics, insert_size_histogram, alignment_summary_metrics, gc_bias_metrics, gc_bias_metrics_chart, gc_bias_metrics_summary, wgs_metrics, flagstats, per_base_coverage_metrics, per_base_hs_metrics, per_target_coverage_metrics, per_target_hs_metrics, summary_hs_metrics, bamcoverage_bigwig]

definitions/subworkflows/germline_detect_variants.cwl

@@ -48,6 +48,8 @@ inputs:
     custom_clinvar_vcf:
         type: File?
         secondaryFiles: [.tbi]
+    ploidy:
+        type: int?
 outputs:
     gvcf:
         type: File[]
@@ -77,13 +79,15 @@ steps:
             gvcf_gq_bands: gvcf_gq_bands
             intervals: intervals
             contamination_fraction: contamination_fraction
+            ploidy: ploidy
         out:
             [gvcf]
     genotype_gvcfs:
         run: ../tools/gatk_genotypegvcfs.cwl
         in:
             reference: reference
             gvcfs: haplotype_caller/gvcf
+            ploidy: ploidy
         out:
             [genotype_vcf]
     annotate_variants: