Skip to content

Commit

Permalink
Create examples using public gs link from the broad-references-privat…
Browse files Browse the repository at this point in the history
…e sources
  • Loading branch information
mr-c committed Jun 30, 2023
1 parent d5b689a commit bbf273f
Show file tree
Hide file tree
Showing 3 changed files with 200 additions and 0 deletions.
Original file line number Diff line number Diff line change
@@ -0,0 +1,77 @@
{
"ExomeGermlineSingleSample.sample_and_unmapped_bams": {
"sample_name": "NA17-308",
"base_file_name": "NA17-308",
"flowcell_unmapped_bams": [
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HM5NCBBXX.1.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HM5NCBBXX.3.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HM5NCBBXX.4.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HM5NCBBXX.2.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF2NBBXX.5.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF2NBBXX.6.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF2NBBXX.8.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF2NBBXX.7.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF7MBBXX.3.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF7MBBXX.4.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF7MBBXX.5.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF7MBBXX.1.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF7MBBXX.6.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF7MBBXX.8.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF7MBBXX.7.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HM5LFBBXX.8.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF7MBBXX.2.unmapped.bam",
"gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HM5NCBBXX.5.unmapped.bam"
],
"final_gvcf_base_name": "NA17-308",
"unmapped_bam_suffix": ".unmapped.bam"
},

"ExomeGermlineSingleSample.references": {
"contamination_sites_ud": "gs://gcp-public-data--broad-references/hg38/v0/contamination-resources/1000g/1000g.phase3.100k.b38.vcf.gz.dat.UD",
"contamination_sites_bed": "gs://gcp-public-data--broad-references/hg38/v0/contamination-resources/1000g/1000g.phase3.100k.b38.vcf.gz.dat.bed",
"contamination_sites_mu": "gs://gcp-public-data--broad-references/hg38/v0/contamination-resources/1000g/1000g.phase3.100k.b38.vcf.gz.dat.mu",
"calling_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/exome_calling_regions.v1.interval_list",
"reference_fasta": {
"ref_dict": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dict",
"ref_fasta": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta",
"ref_fasta_index": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.fai",
"ref_alt": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.alt",
"ref_sa": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.sa",
"ref_amb": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.amb",
"ref_bwt": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.bwt",
"ref_ann": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.ann",
"ref_pac": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.pac"
},
"known_indels_sites_vcfs": [
"gs://gcp-public-data--broad-references/hg38/v0/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz",
"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.known_indels.vcf.gz"
],
"known_indels_sites_indices": [
"gs://gcp-public-data--broad-references/hg38/v0/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz.tbi",
"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.known_indels.vcf.gz.tbi"
],
"dbsnp_vcf": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf",
"dbsnp_vcf_index": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf.idx",
"evaluation_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/exome_evaluation_regions.v1.interval_list",
"haplotype_database_file": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.haplotype_database.txt"
},

"ExomeGermlineSingleSample.scatter_settings": {
"haplotype_scatter_count": 50,
"break_bands_at_multiples_of": 0
},

"ExomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/RP-1535.NA17-308.reference.fingerprint.vcf.gz",
"ExomeGermlineSingleSample.fingerprint_genotypes_index": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/RP-1535.NA17-308.reference.fingerprint.vcf.gz.tbi",
"ExomeGermlineSingleSample.target_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.targets.interval_list",
"ExomeGermlineSingleSample.bait_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.baits.interval_list",
"ExomeGermlineSingleSample.bait_set_name": "whole_exome_illumina_coding_v1",

"ExomeGermlineSingleSample.papi_settings": {
"preemptible_tries": 3,
"agg_preemptible_tries": 3
},

"ExomeGermlineSingleSample.AggregatedBamQC.CollectReadgroupBamQualityMetrics.collect_gc_bias_metrics": false,
"ExomeGermlineSingleSample.AggregatedBamQC.CollectAggregationMetrics.collect_gc_bias_metrics": false
}
60 changes: 60 additions & 0 deletions pipelines/broad/reprocessing/exome/test_inputs/example_inputs.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,60 @@
{
"ExomeReprocessing.input_cram": "gs://broad-gotc-test-storage/germline_single_sample/exome/plumbing/truth/{TRUTH_BRANCH}/RP-929.NA12878/NA12878_PLUMBING.cram",
"ExomeReprocessing.output_map": "gs://broad-gotc-test-storage/germline_single_sample/exome/plumbing/bams/RP-929.NA12878/readgroupid_to_bamfilename_map.txt",

"ExomeReprocessing.sample_name": "NA12878 PLUMBING",
"ExomeReprocessing.base_file_name": "RP-929.NA12878",
"ExomeReprocessing.final_gvcf_base_name": "RP-929.NA12878",
"ExomeReprocessing.unmapped_bam_suffix": ".unmapped.bam",

"ExomeReprocessing.references": {
"contamination_sites_ud": "gs://gcp-public-data--broad-references/hg38/v0/contamination-resources/1000g/1000g.phase3.100k.b38.vcf.gz.dat.UD",
"contamination_sites_bed": "gs://gcp-public-data--broad-references/hg38/v0/contamination-resources/1000g/1000g.phase3.100k.b38.vcf.gz.dat.bed",
"contamination_sites_mu": "gs://gcp-public-data--broad-references/hg38/v0/contamination-resources/1000g/1000g.phase3.100k.b38.vcf.gz.dat.mu",
"calling_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/exome_calling_regions.v1.interval_list",
"reference_fasta": {
"ref_dict": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dict",
"ref_fasta": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta",
"ref_fasta_index": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.fai",
"ref_alt": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.alt",
"ref_sa": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.sa",
"ref_amb": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.amb",
"ref_bwt": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.bwt",
"ref_ann": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.ann",
"ref_pac": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.pac"
},
"known_indels_sites_vcfs": [
"gs://gcp-public-data--broad-references/hg38/v0/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz",
"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.known_indels.vcf.gz"
],
"known_indels_sites_indices": [
"gs://gcp-public-data--broad-references/hg38/v0/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz.tbi",
"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.known_indels.vcf.gz.tbi"
],
"dbsnp_vcf": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf",
"dbsnp_vcf_index": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf.idx",
"evaluation_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/exome_evaluation_regions.v1.interval_list",
"haplotype_database_file": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.haplotype_database.txt"
},

"ExomeReprocessing.scatter_settings": {
"haplotype_scatter_count": 10,
"break_bands_at_multiples_of": 0
},

"ExomeReprocessing.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/exome/plumbing/bams/RP-929.NA12878/RP-929.NA12878.reference.fingerprint.vcf.gz",
"ExomeReprocessing.fingerprint_genotypes_index": "gs://broad-gotc-test-storage/germline_single_sample/exome/plumbing/bams/RP-929.NA12878/RP-929.NA12878.reference.fingerprint.vcf.gz.tbi",

"ExomeReprocessing.target_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.targets.interval_list",
"ExomeReprocessing.bait_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.baits.interval_list",
"ExomeReprocessing.bait_set_name": "whole_exome_illumina_coding_v1",

"ExomeReprocessing.papi_settings": {
"preemptible_tries": 3,
"agg_preemptible_tries": 3
},

"ExomeReprocessing.ExomeGermlineSingleSample.UnmappedBamToAlignedBam.CheckContamination.disable_sanity_check": true,
"ExomeReprocessing.ExomeGermlineSingleSample.AggregatedBamQC.CollectReadgroupBamQualityMetrics.collect_gc_bias_metrics": false,
"ExomeReprocessing.ExomeGermlineSingleSample.AggregatedBamQC.CollectAggregationMetrics.collect_gc_bias_metrics": false
}
63 changes: 63 additions & 0 deletions pipelines/broad/reprocessing/external/exome/example_inputs.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,63 @@
{
"ExternalExomeReprocessing.input_cram": "gs://broad-public-datasets/NA12878/germline_single_sample/exome/plumbing/RP-929.NA12878/NA12878_PLUMBING.cram",

"ExternalExomeReprocessing.sample_name": "NA12878 PLUMBING",
"ExternalExomeReprocessing.base_file_name": "RP-929.NA12878",
"ExternalExomeReprocessing.final_gvcf_base_name": "NA12878_PLUMBING",
"ExternalExomeReprocessing.unmapped_bam_suffix": ".unmapped.bam",

"ExternalExomeReprocessing.cram_ref_fasta": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta",
"ExternalExomeReprocessing.cram_ref_fasta_index": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.fai",

"ExternalExomeReprocessing.references": {
"haplotype_database_file": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.haplotype_database.txt",
"contamination_sites_ud": "gs://gcp-public-data--broad-references/hg38/v0/contamination-resources/1000g/1000g.phase3.100k.b38.vcf.gz.dat.UD",
"contamination_sites_bed": "gs://gcp-public-data--broad-references/hg38/v0/contamination-resources/1000g/1000g.phase3.100k.b38.vcf.gz.dat.bed",
"contamination_sites_mu": "gs://gcp-public-data--broad-references/hg38/v0/contamination-resources/1000g/1000g.phase3.100k.b38.vcf.gz.dat.mu",
"calling_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/exome_calling_regions.v1.interval_list",
"reference_fasta": {
"ref_dict": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dict",
"ref_fasta": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta",
"ref_fasta_index": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.fai",
"ref_alt": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.alt",
"ref_sa": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.sa",
"ref_amb": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.amb",
"ref_bwt": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.bwt",
"ref_ann": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.ann",
"ref_pac": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.64.pac"
},
"known_indels_sites_vcfs": [
"gs://gcp-public-data--broad-references/hg38/v0/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz",
"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.known_indels.vcf.gz"
],
"known_indels_sites_indices": [
"gs://gcp-public-data--broad-references/hg38/v0/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz.tbi",
"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.known_indels.vcf.gz.tbi"
],
"dbsnp_vcf": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf",
"dbsnp_vcf_index": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf.idx",
"evaluation_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/exome_evaluation_regions.v1.interval_list"
},

"ExternalExomeReprocessing.scatter_settings": {
"haplotype_scatter_count": 50,
"break_bands_at_multiples_of": 0
},

"ExternalExomeReprocessing.target_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.targets.interval_list",
"ExternalExomeReprocessing.bait_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.baits.interval_list",
"ExternalExomeReprocessing.bait_set_name": "whole_exome_illumina_coding_v1",

"ExternalExomeReprocessing.papi_settings": {
"preemptible_tries": 3,
"agg_preemptible_tries": 3
},

"ExternalExomeReprocessing.ExomeReprocessing.ExomeGermlineSingleSample.UnmappedBamToAlignedBam.CheckContamination.disable_sanity_check": true,
"ExternalExomeReprocessing.ExomeReprocessing.ExomeGermlineSingleSample.AggregatedBamQC.CollectReadgroupBamQualityMetrics.collect_gc_bias_metrics": false,
"ExternalExomeReprocessing.ExomeReprocessing.ExomeGermlineSingleSample.AggregatedBamQC.CollectAggregationMetrics.collect_gc_bias_metrics": false,

"ExternalExomeReprocessing.destination_cloud_path": "{DESTINATION_CLOUD_PATH}",
"ExternalExomeReprocessing.vault_token_path": "{VAULT_TOKEN_PATH}",
"ExternalExomeReprocessing.google_account_vault_path": "{GOOGLE_ACCOUNT_VAULT_PATH}"
}

0 comments on commit bbf273f

Please sign in to comment.