Update VCFs in AnnotateVcf test JSON (#256)

* generate and use new clean VCF for test_large AnnotateVcf test data

* remove or move data in gs://talkowskicromwellresults

Author: epiercehoffman

input_values/test_batch_large.json

@@ -221,6 +221,7 @@
   "base_metrics_module03" : "gs://gatk-sv-resources/test/module03/large/module03.test_large.metrics.tsv",
   "base_metrics_module04" : "gs://gatk-sv-resources/test/module04/large/module04.test_large.metrics.tsv",
   "baseline_cleaned_vcf" : "gs://gatk-sv-resources/test/module0506/large/output/test_large.cleaned.vcf.gz",
+  "baseline_cleaned_vcf_idx": "gs://gatk-sv-resources/test/module0506/large/output/test_large.cleaned.vcf.gz.tbi",
   "baseline_filtered_depth_vcf" : "gs://gatk-sv-resources/test/module03/large/output/test_large.depth.outliers_removed.vcf.gz",
   "baseline_filtered_pesr_vcf" : "gs://gatk-sv-resources/test/module03/large/output/test_large.filtered_pesr_merged.vcf.gz",
   "baseline_final_vcf" : "gs://gatk-sv-resources/test/module0506/large/output/test_large.resolved_regenotyped.vcf.gz",
@@ -876,12 +877,11 @@
     "gs://gatk-sv-resources/test/module00a/large/outputs/wham_vcf/TCGA-W9-A837-10A-01D-A706-36.wham.vcf.gz"
   ],
   "batch_name" : "test_large",
-  "cluster_combined_bed" : "gs://talkowskicromwellresults/M04/MergeCohortVcfs/190da1da-75b8-485e-82fc-b2c5ff07a8e6/call-MergeDepthVcfs/cluster.combined.bed",
-  "cohort_combined_bed" : "gs://talkowskicromwellresults/M04/MergeCohortVcfs/190da1da-75b8-485e-82fc-b2c5ff07a8e6/call-MergeDepthVcfs/master_cluster_dups.bed",
+  "clean_vcf": "gs://gatk-sv-resources/test/module0506/large/output/test_large.20211115.cleaned.vcf.gz",
+  "clean_vcf_idx": "gs://gatk-sv-resources/test/module0506/large/output/test_large.20211115.cleaned.vcf.gz.tbi",
   "cohort_samplelist" : "gs://gatk-sv-resources/test/module04b/large/inputs/samplelist.txt",
-  "cohort_depth_vcf" : "gs://talkowskicromwellresults/M04/MergeCohortVcfs/190da1da-75b8-485e-82fc-b2c5ff07a8e6/call-MergeDepthVcfs/all_batches.depth.vcf.gz",
-  "cohort_pesr_vcf" : "gs://talkowskicromwellresults/M04/MergeCohortVcfs/190da1da-75b8-485e-82fc-b2c5ff07a8e6/call-MergePESRVcfs/all_batches.pesr.vcf.gz",
-  "cohort_sort" : "gs://talkowskicromwellresults/M04/MergeCohortVcfs/190da1da-75b8-485e-82fc-b2c5ff07a8e6/call-MergeDepthVcfs/cohort.sort.bed",
+  "cohort_depth_vcf" : "gs://gatk-sv-resources/test/module04/input/all_batches.depth.vcf.gz",
+  "cohort_pesr_vcf" : "gs://gatk-sv-resources/test/module04/input/all_batches.pesr.vcf.gz",
   "contig_ploidy_model_tar" : "gs://gatk-sv-resources/test/gcnv_model_v2/ref_panel_v1b-contig-ploidy-model.tar.gz",
   "counts" : [
     "gs://gatk-sv-resources/test/module00a/large/outputs/coverage_counts/counts_100bp.SM-BZNZQ.tsv.gz",

test_input_templates/AnnotateVcf/AnnotateVcf.json.tmpl

@@ -1,6 +1,6 @@
 {
-  "AnnotateVcf.vcf" :     "gs://fc-fae972fb-9dbf-41c7-926f-f419a767a1ab/61a7ce7c-3b3c-4716-977a-ffb6e34464b6/minGQ_filter_workflow_v2/d841eeb6-90c3-4ff2-8b99-7a793c85cfea/call-combine_vcfs/Talkowski_SV_PCR-free_WGS_144.minGQ_filtered.vcf.gz",
-  "AnnotateVcf.vcf_idx" : "gs://fc-fae972fb-9dbf-41c7-926f-f419a767a1ab/61a7ce7c-3b3c-4716-977a-ffb6e34464b6/minGQ_filter_workflow_v2/d841eeb6-90c3-4ff2-8b99-7a793c85cfea/call-combine_vcfs/Talkowski_SV_PCR-free_WGS_144.minGQ_filtered.vcf.gz.tbi",
+  "AnnotateVcf.vcf" :   {{ test_batch.clean_vcf | tojson }},
+  "AnnotateVcf.vcf_idx" : {{ test_batch.clean_vcf_idx | tojson }},
 
   "AnnotateVcf.protein_coding_gtf" : {{ reference_resources.protein_coding_gtf | tojson }},
   "AnnotateVcf.linc_rna_gtf" :       {{ reference_resources.linc_rna_gtf | tojson }},
@@ -12,7 +12,7 @@
 
 
   "AnnotateVcf.contig_list" :  {{ reference_resources.primary_contigs_list | tojson }},
-  "AnnotateVcf.ped_file":      "gs://fc-fae972fb-9dbf-41c7-926f-f419a767a1ab/FINAL_full_prenatal_dosage_sex.ped",
+  "AnnotateVcf.ped_file":      {{ test_batch.ped_file | tojson }},
   "AnnotateVcf.sv_per_shard" : "5000",
   "AnnotateVcf.max_shards_per_chrom_step1" : 200,
   "AnnotateVcf.min_records_per_shard_step1" :  5000,