modify tools/pvacsplice and regtools wdl

Author: mhoang22

definitions/tools/pvacsplice.wdl

@@ -6,7 +6,7 @@ task pvacsplice {
     File input_vcf
     File input_vcf_tbi
     File input_regtools_tsv
-    File input_reference_fasta
+    File input_reference_dna_fasta
     File input_reference_gtf 
     String sample_name
     Array[String] alleles
@@ -36,6 +36,13 @@ task pvacsplice {
     Int? maximum_transcript_support_level  # enum [1, 2, 3, 4, 5]
     Int? aggregate_inclusion_binding_threshold
     Array[String]? problematic_amino_acids
+    Array[String] biotypes_list = select_first([biotypes, []])
+    Int? aggregate_inclusion_count_limit
+    
+    Int? juction_score
+    Int? variant_distance
+    Boolean save_gtf = false
+    Array[String]? junction_anchor_types
 
     Boolean allele_specific_binding_thresholds = false
     Boolean keep_tmp_files = false
@@ -45,7 +52,7 @@ task pvacsplice {
     Float? tumor_purity
   }
 
-  Float input_size = size([input_vcf, input_vcf_tbi, input_regtools_tsv, input_reference_fasta,input_reference_gtf], "GB") #input files: annotated vcf, regtools tsv, reference fasta, reference gtf 
+  Float input_size = size([input_vcf, input_vcf_tbi, input_regtools_tsv, input_reference_dna_fasta,input_reference_gtf], "GB") #input files: annotated vcf, regtools tsv, reference fasta, reference gtf 
   Int space_needed_gb = 10 + round(input_size) 
   runtime {
     preemptible: 1
@@ -67,13 +74,14 @@ task pvacsplice {
     ln -s "$TMPDIR" /tmp/pvacsplice && export TMPDIR=/tmp/pvacsplice && \
     /usr/local/bin/pvacsplice run --iedb-install-directory /opt/iedb \
     --pass-only \
-    #~{if defined(tumor_purity) then "--tumor-purity " + select_first([tumor_purity]) else ""} \
+    ~{if defined(tumor_purity) then "--tumor-purity " + select_first([tumor_purity]) else ""} \
     ~{if length(epitope_i ) > 0 then "-e1 " else ""} ~{sep="," epitope_i} \
     ~{if length(epitope_ii) > 0 then "-e2 " else ""} ~{sep="," epitope_ii} \
     ~{if defined(binding_threshold) then "-b ~{binding_threshold}" else ""} \
     ~{if defined(percentile_threshold) then "--percentile-threshold ~{percentile_threshold}" else ""} \
     ~{if allele_specific_binding_thresholds then "--allele-specific-binding-thresholds" else ""} \
     ~{if defined(aggregate_inclusion_binding_threshold) then "--aggregate-inclusion-binding-threshold ~{aggregate_inclusion_binding_threshold}" else ""} \
+    ~{if defined(aggregate_inclusion_count_limit) then "--aggregate-inclusion-count-limit ~{aggregate_inclusion_count_limit}" else ""} \
     ~{if defined(iedb_retries) then "-r ~{iedb_retries}" else ""} \
     ~{if keep_tmp_files then "-k" else ""} \
     ~{if defined(normal_sample_name) then "--normal-sample-name ~{normal_sample_name}" else ""} \
@@ -93,28 +101,28 @@ task pvacsplice {
     ~{if defined(tdna_vaf) then "--tdna-vaf ~{tdna_vaf}" else ""} \
     ~{if defined(trna_vaf) then "--trna-vaf ~{trna_vaf}" else ""} \
     ~{if defined(expn_val) then "--expn-val ~{expn_val}" else ""} \
-    #~{if defined(maximum_transcript_support_level) then "--maximum-transcript-support-level ~{maximum_transcript_support_level}" else ""} \
-    #~{if length(problematic_aa) > 0 then "--problematic-amino-acids" else ""} ~{sep="," problematic_aa} \
-    #~{if allele_specific_anchors then "--allele-specific-anchors" else ""} \
-    #~{if defined(anchor_contribution_threshold) then "--anchor-contribution-threshold ~{anchor_contribution_threshold}" else ""} \
+    ~{if defined(maximum_transcript_support_level) then "--maximum-transcript-support-level ~{maximum_transcript_support_level}" else ""} \
+    ~{if length(problematic_aa) > 0 then "--problematic-amino-acids" else ""} ~{sep="," problematic_aa} \
+    ~{if length(biotypes_list) > 0 then "--biotypes" else ""} ~{sep="," biotypes_list} \
+    ~{if defined(juction_score) then "--junction-score ~{junction_score}" else ""} \
+    ~{if defined(variant_distance) then "--variant-distance ~{variant_distance}" else ""} \
+    ~{if save_gtf then "-g" else ""} \
+    ~{if length(junction_anchor_types) > 0 then "--anchor-types" else ""} ~{sep="," junction_anchor_types}
     --n-threads ~{n_threads} \
-    ~{input_vcf} ~{sample_name} ~{sep="," alleles} ~{sep=" " prediction_algorithms} \
-    pvacsplice_predictions
+    ~{input_regtools_tsv} ~{sample_name} ~{sep="," alleles} ~{sep=" " prediction_algorithms} \
+    pvacsplice_predictions ~{input_vcf} ~{input_reference_dna_fasta} ~{input_reference_gtf} 
   >>>
 
   output {
     File? mhc_i_all_epitopes = "pvacsplice_predictions/MHC_Class_I/~{sample_name}.all_epitopes.tsv"
     File? mhc_i_aggregated_report = "pvacsplice_predictions/MHC_Class_I/~{sample_name}.all_epitopes.aggregated.tsv"
     File? mhc_i_filtered_epitopes = "pvacsplice_predictions/MHC_Class_I/~{sample_name}.filtered.tsv"
-    File? mhc_i_aggregated_metrics_file = "pvacsplice_predictions/MHC_Class_I/" + sample_name + ".all_epitopes.aggregated.metrics.json"
     File? mhc_ii_all_epitopes = "pvacsplice_predictions/MHC_Class_II/~{sample_name}.all_epitopes.tsv"
     File? mhc_ii_aggregated_report = "pvacsplice_predictions/MHC_Class_II/~{sample_name}.all_epitopes.aggregated.tsv"
     File? mhc_ii_filtered_epitopes = "pvacsplice_predictions/MHC_Class_II/~{sample_name}.filtered.tsv"
-    File? mhc_ii_aggregated_metrics_file = "pvacsplice_predictions/MHC_Class_II/" + sample_name + ".all_epitopes.aggregated.metrics.json"
     File? combined_all_epitopes = "pvacsplice_predictions/combined/~{sample_name}.all_epitopes.tsv"
     File? combined_aggregated_report = "pvacsplice_predictions/combined/~{sample_name}.all_epitopes.aggregated.tsv"
     File? combined_filtered_epitopes = "pvacsplice_predictions/combined/~{sample_name}.filtered.tsv"
-    File? combined_aggregated_metrics_file = "pvacsplice_predictions/combined/" + sample_name + ".all_epitopes.aggregated.metrics.json"
 
     # glob documentations
     # https://github.com/openwdl/wdl/blob/main/versions/1.0/SPEC.md#globs
@@ -124,90 +132,3 @@ task pvacsplice {
 
   }
 }
-############################### may delete these######
-workflow wf {
-  input {
-    Int? n_threads
-    File input_vcf
-    File input_vcf_tbi
-    String sample_name
-    Array[String] alleles
-    Array[String] prediction_algorithms
-
-    Array[Int]? epitope_lengths_class_i
-    Array[Int]? epitope_lengths_class_ii
-    Int? binding_threshold
-    Int? percentile_threshold
-    Int? iedb_retries
-
-    String? normal_sample_name
-    String? net_chop_method  # enum [cterm , 20s]
-    String? top_score_metric  # enum [lowest, median]
-    Float? net_chop_threshold
-    String? additional_report_columns  # enum [sample_name]
-    Int? fasta_size
-    Int? downstream_sequence_length
-    Boolean exclude_nas = false
-    File? phased_proximal_variants_vcf
-    File? phased_proximal_variants_vcf_tbi
-    Float? minimum_fold_change
-    Int? normal_cov
-    Int? tdna_cov
-    Int? trna_cov
-    Float? normal_vaf
-    Float? tdna_vaf
-    Float? trna_vaf
-    Float? expn_val
-    String? maximum_transcript_support_level  # enum [1, 2, 3, 4, 5]
-    Int? aggregate_inclusion_binding_threshold
-    Array[String]? problematic_amino_acids
-    Float? anchor_contribution_threshold
-
-    Boolean? allele_specific_binding_thresholds
-    Boolean? keep_tmp_files
-    Boolean? netmhc_stab
-    Boolean? run_reference_proteome_similarity
-    Boolean allele_specific_anchors = false
-  }
-  call pvacsplice {
-    input:
-    n_threads=n_threads,
-    input_vcf=input_vcf,
-    input_vcf_tbi=input_vcf_tbi,
-    sample_name=sample_name,
-    alleles=alleles,
-    prediction_algorithms=prediction_algorithms,
-    epitope_lengths_class_i=epitope_lengths_class_i,
-    epitope_lengths_class_ii=epitope_lengths_class_ii,
-    binding_threshold=binding_threshold,
-    percentile_threshold=percentile_threshold,
-    aggregate_inclusion_binding_threshold=aggregate_inclusion_binding_threshold,
-    iedb_retries=iedb_retries,
-    normal_sample_name=normal_sample_name,
-    net_chop_method=net_chop_method,
-    top_score_metric=top_score_metric,
-    net_chop_threshold=net_chop_threshold,
-    additional_report_columns=additional_report_columns,
-    fasta_size=fasta_size,
-    downstream_sequence_length=downstream_sequence_length,
-    exclude_nas=exclude_nas,
-    phased_proximal_variants_vcf=phased_proximal_variants_vcf,
-    phased_proximal_variants_vcf_tbi=phased_proximal_variants_vcf_tbi,
-    minimum_fold_change=minimum_fold_change,
-    normal_cov=normal_cov,
-    tdna_cov=tdna_cov,
-    trna_cov=trna_cov,
-    normal_vaf=normal_vaf,
-    tdna_vaf=tdna_vaf,
-    trna_vaf=trna_vaf,
-    expn_val=expn_val,
-    maximum_transcript_support_level=maximum_transcript_support_level,
-    allele_specific_binding_thresholds=allele_specific_binding_thresholds,
-    problematic_amino_acids=problematic_amino_acids,
-    allele_specific_anchors=allele_specific_anchors,
-    anchor_contribution_threshold=anchor_contribution_threshold,
-    keep_tmp_files=keep_tmp_files,
-    netmhc_stab=netmhc_stab,
-    run_reference_proteome_similarity=run_reference_proteome_similarity
-  }
-}

definitions/tools/regtools.wdl

@@ -0,0 +1,59 @@
+version 1.0
+
+task regtools {
+  input {
+    String output_filename_tsv = "splice_junction.tsv"
+    String? output_filename_vcf = "splice_junction.vcf"
+    String? output_filename_bed = "splice_junction.bed"
+
+    String strand # enum [XS, RF, FR]
+    Int? window_size
+    Int? max_distance_exon # max distance from exon/intron boundary to annotate a variant in exonic region as splicing variant
+    Int? max_distance_intron
+
+    Boolean annotate_intronic_variant = false
+    Boolean annotate_exonic_variant = false
+    Boolean not_skipping_single_exon_transcripts = false
+    Boolean singecell_barcode = false
+    Boolean intron_motif_priority = false
+
+    File input_vcf
+    File input_bam # indexed,aligned (and preferably sorted) bam or cram
+    File input_reference_dna_fasta
+    File input_reference_gtf
+
+  }
+
+  Float input_size = size([input_vcf,input_bam, input_reference_dna_fasta,input_reference_gtf], "GB")  
+  Int space_needed_gb = 10 + round(input_size) 
+  runtime {
+    preemptible: 1
+    maxRetries: 2
+    memory: "32GB"
+    cpu: n_threads
+    docker: "griffithlab/regtools:release-1.0.0"
+    disks: "local-disk ~{space_needed_gb} HDD"
+  }
+
+  command <<<
+    /regtools/build/regtools cis-splice-effects identify \
+    -o ~{output_filename_tsv} \
+    ~{if defined(output_filename_vcf) then "-v ~{output_filename_vcf}" else ""} \
+    ~{if defined(output_filename_bed) then "-j ~{output_filename_bed}" else ""} \
+    -s ~{strand} \
+    ~{if defined(window_size) then "-w ~{window_size}" else ""} \
+    ~{if defined(max_distance_exon) then "-e ~{max_distance_exon}" else ""} \
+    ~{if defined(max_distance_intron) then "-i ~{max_distance_intron}" else ""} \
+    ~{if annotate_intronic_variant then "-I" else ""} \
+    ~{if annotate_exonic_variant then "-E" else ""} \
+    ~{if not_skipping_single_exon_transcripts then "-S" else ""} \
+    ~{if singecell_barcode then "-b" else ""} \
+    ~{if intron_motif_priority then "-C" else ""} \
+    ~{input_vcf} ~{input_bam} ~{input_reference_dna_fasta} ~{input_reference_gtf}
+  >>>
+
+  output {
+    File? output_splice_junction_tsv = output_filename_tsv
+  }
+}
+