Make genome_tracks optional in FilterGenotypes (#593)

* Adds explicit parameters to FilterGenotypes
broadinstitute · Sep 5, 2023 · 2c97aad · 2c97aad
1 parent 98ec699
commit 2c97aad
Show file tree

Hide file tree

Showing 3 changed files with 28 additions and 10 deletions.
diff --git a/inputs/templates/test/FilterGenotypes/FilterGenotypes.fixed_cutoffs.json.tmpl b/inputs/templates/test/FilterGenotypes/FilterGenotypes.fixed_cutoffs.json.tmpl
@@ -5,32 +5,32 @@
   "FilterGenotypes.gq_recalibrator_model_file": {{ reference_resources.aou_recalibrate_gq_model_file | tojson }},
   "FilterGenotypes.sl_filter_args": "--small-del-threshold 93 --medium-del-threshold 150 --small-dup-threshold -51 --medium-dup-threshold -4 --ins-threshold -13 --inv-threshold -19",
 
-  "FilterGenotypes.RecalibrateGq.genome_tracks": {{ reference_resources.recalibrate_gq_genome_tracks | tojson }},
-  "FilterGenotypes.RecalibrateGq.recalibrate_gq_args": [
+  "FilterGenotypes.genome_tracks": {{ reference_resources.recalibrate_gq_genome_tracks | tojson }},
+  "FilterGenotypes.recalibrate_gq_args": [
     "--keep-homvar false",
     "--keep-homref true",
     "--keep-multiallelic true",
     "--skip-genotype-filtering true",
     "--min-samples-to-estimate-allele-frequency -1"
   ],
 
-  "FilterGenotypes.MainVcfQc.ped_file": {{ test_batch.ped_file | tojson }},
-  "FilterGenotypes.MainVcfQc.primary_contigs_fai": {{ reference_resources.primary_contigs_fai | tojson }},
-  "FilterGenotypes.MainVcfQc.site_level_comparison_datasets": [
+  "FilterGenotypes.ped_file": {{ test_batch.ped_file | tojson }},
+  "FilterGenotypes.primary_contigs_fai": {{ reference_resources.primary_contigs_fai | tojson }},
+  "FilterGenotypes.site_level_comparison_datasets": [
     {{ reference_resources.ccdg_abel_site_level_benchmarking_dataset | tojson }},
     {{ reference_resources.gnomad_v2_collins_site_level_benchmarking_dataset | tojson }},
     {{ reference_resources.hgsv_byrska_bishop_site_level_benchmarking_dataset | tojson }},
     {{ reference_resources.thousand_genomes_site_level_benchmarking_dataset | tojson }}
   ],
-  "FilterGenotypes.MainVcfQc.sample_level_comparison_datasets": [
+  "FilterGenotypes.sample_level_comparison_datasets": [
     {{ reference_resources.hgsv_byrska_bishop_sample_level_benchmarking_dataset | tojson }}
   ],
-  "FilterGenotypes.MainVcfQc.sample_renaming_tsv": {{ reference_resources.hgsv_byrska_bishop_sample_renaming_tsv | tojson }},
-  "FilterGenotypes.MainVcfQc.runtime_override_per_sample_benchmark_plot": {
+  "FilterGenotypes.sample_renaming_tsv": {{ reference_resources.hgsv_byrska_bishop_sample_renaming_tsv | tojson }},
+  "FilterGenotypes.runtime_override_per_sample_benchmark_plot": {
     "mem_gb": 30,
     "disk_gb": 50
   },
-  "FilterGenotypes.MainVcfQc.runtime_override_plot_qc_per_family": {
+  "FilterGenotypes.runtime_override_plot_qc_per_family": {
     "mem_gb": 15,
     "disk_gb": 100
   },

diff --git a/wdl/FilterGenotypes.wdl b/wdl/FilterGenotypes.wdl
@@ -13,6 +13,8 @@ workflow FilterGenotypes {
     File ploidy_table
 
     File gq_recalibrator_model_file
+    Array[String] recalibrate_gq_args = []
+    Array[File] genome_tracks = []
     Float no_call_rate_cutoff = 0.05  # Set to 1 to disable NCR filtering
     Float fmax_beta = 0.5  # Recommended range [0.3, 0.5] (use lower values for higher specificity)
 
@@ -24,10 +26,17 @@ workflow FilterGenotypes {
     Int filter_vcf_records_per_shard = 20000
 
     # For MainVcfQc
+    File primary_contigs_fai
+    File? ped_file
+    Array[Array[String]]? site_level_comparison_datasets    # Array of two-element arrays, one per dataset, each of format [prefix, gs:// path to directory with one BED per population]
+    Array[Array[String]]? sample_level_comparison_datasets  # Array of two-element arrays, one per dataset, each of format [prefix, gs:// path to per-sample tarballs]
+    File? sample_renaming_tsv # File with mapping to rename per-sample benchmark sample IDs for compatibility with cohort
     Boolean run_qc = true
     String qc_bcftools_preprocessing_options = "-e 'FILTER~\"UNRESOLVED\" || FILTER~\"HIGH_NCR\"'"
     Int qc_sv_per_shard = 2500
     Int qc_samples_per_shard = 600
+    RuntimeAttr? runtime_override_plot_qc_per_family
+    RuntimeAttr? runtime_override_per_sample_benchmark_plot
 
     String linux_docker
     String gatk_docker
@@ -43,6 +52,8 @@ workflow FilterGenotypes {
       vcf = vcf,
       vcf_index = vcf + ".tbi",
       gq_recalibrator_model_file=gq_recalibrator_model_file,
+      recalibrate_gq_args=recalibrate_gq_args,
+      genome_tracks=genome_tracks,
       gatk_docker=gatk_docker,
       sv_base_mini_docker=sv_base_mini_docker,
       sv_pipeline_docker=sv_pipeline_docker
@@ -113,8 +124,15 @@ workflow FilterGenotypes {
       input:
         vcfs=[ConcatVcfs.concat_vcf],
         prefix="~{output_prefix_}.filter_genotypes",
+        ped_file=ped_file,
         bcftools_preprocessing_options=qc_bcftools_preprocessing_options,
+        primary_contigs_fai=primary_contigs_fai,
+        site_level_comparison_datasets=site_level_comparison_datasets,
+        sample_level_comparison_datasets=sample_level_comparison_datasets,
+        sample_renaming_tsv=sample_renaming_tsv,
         sv_per_shard=qc_sv_per_shard,
+        runtime_override_per_sample_benchmark_plot=runtime_override_per_sample_benchmark_plot,
+        runtime_override_plot_qc_per_family=runtime_override_plot_qc_per_family,
         samples_per_shard=qc_samples_per_shard,
         sv_pipeline_qc_docker=sv_pipeline_docker,
         sv_base_mini_docker=sv_base_mini_docker,

diff --git a/wdl/RecalibrateGq.wdl b/wdl/RecalibrateGq.wdl
@@ -9,7 +9,7 @@ workflow RecalibrateGq {
         File vcf
         File vcf_index
         Int? recalibrate_records_per_shard
-        Array[File] genome_tracks
+        Array[File] genome_tracks = []
         File gq_recalibrator_model_file
         Array[String] recalibrate_gq_args = []
         String gatk_docker