Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update CombineBatches workflow #732

Open
wants to merge 8 commits into
base: main
Choose a base branch
from
Open

Update CombineBatches workflow #732

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
e3adbd0
Add cluster_batch_format.py; clean up MCNV formatting
mwalker174 Jul 17, 2024
ead6c1a
Remove old arguments grep option in SVCluster
mwalker174 Dec 3, 2024
b4ec33a
Fix clustering track array inputs for terra configs
mwalker174 Dec 3, 2024
4263132
Fix CombineBatches config strat input
mwalker174 Dec 3, 2024
3501227
Add to single sample in yaml
mwalker174 Dec 5, 2024
51ef3b2
Update gatk docker to nightly build
mwalker174 Dec 5, 2024
40b175d
Revert yaml
mwalker174 Dec 9, 2024
195f557
Add scramble docker to single sample template
mwalker174 Dec 10, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 13 additions & 4 deletions ...s/templates/terra_workspaces/cohort_mode/workflow_configurations/CombineBatches.json.tmpl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,15 @@
{
"CombineBatches.contig_list": "${workspace.primary_contigs_fai}",
"CombineBatches.pe_exclude_list": "${workspace.pesr_exclude_list}",
"CombineBatches.depth_exclude_list": "${workspace.depth_exclude_list}",
"CombineBatches.empty_file" : "${workspace.empty_file}",

"CombineBatches.clustering_config_part1" : "${workspace.clustering_config_part1}",
"CombineBatches.stratification_config_part1" : "${workspace.stratification_config_part1}",
"CombineBatches.clustering_config_part2" : "${workspace.clustering_config_part2}",
"CombineBatches.stratification_config_part2" : "${workspace.stratification_config_part2}",
"CombineBatches.track_bed_files": {{ reference_resources.clustering_tracks | tojson }},
"CombineBatches.track_names": {{ reference_resources.clustering_track_names | tojson }},

"CombineBatches.min_sr_background_fail_batches": 0.5,
"CombineBatches.gatk_docker": "${workspace.gatk_docker}",
"CombineBatches.sv_pipeline_docker": "${workspace.sv_pipeline_docker}",
"CombineBatches.sv_base_mini_docker": "${workspace.sv_base_mini_docker}",

Expand All @@ -13,6 +18,10 @@
"CombineBatches.pesr_vcfs": "${this.sample_sets.genotyped_pesr_vcf}",
"CombineBatches.depth_vcfs": "${this.regenotyped_depth_vcfs}",
"CombineBatches.raw_sr_bothside_pass_files": "${this.sample_sets.sr_bothside_pass}",
"CombineBatches.raw_sr_background_fail_files": "${this.sample_sets.sr_background_fail}"
"CombineBatches.raw_sr_background_fail_files": "${this.sample_sets.sr_background_fail}",
"CombineBatches.ped_file": "${workspace.cohort_ped_file}",

"CombineBatches.reference_dict" : "${workspace.reference_dict}",
"CombineBatches.reference_fasta" : "${workspace.reference_fasta}",
"CombineBatches.reference_fasta_fai" : "${workspace.reference_index}"
}
52 changes: 0 additions & 52 deletions ...ts/templates/terra_workspaces/cohort_mode/workflow_configurations/MakeCohortVcf.json.tmpl
View file
Open in desktop

This file was deleted.

4 changes: 4 additions & 0 deletions inputs/templates/terra_workspaces/cohort_mode/workspace.tsv.tmpl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,6 @@
workspace:cloud_sdk_docker {{ dockers.cloud_sdk_docker }}
clustering_config_part1 {{ reference_resources.clustering_config_part1 }}
clustering_config_part2 {{ reference_resources.clustering_config_part2 }}
cnmops_docker {{ dockers.cnmops_docker }}
condense_counts_docker {{ dockers.condense_counts_docker }}
gatk_docker {{ dockers.gatk_docker }}
Expand Down Expand Up @@ -57,6 +59,8 @@ reference_version {{ reference_resources.reference_version }}
rmsk {{ reference_resources.rmsk }}
segdups {{ reference_resources.segdups }}
seed_cutoffs {{ reference_resources.seed_cutoffs }}
stratification_config_part1 {{ reference_resources.stratification_config_part1 }}
stratification_config_part2 {{ reference_resources.stratification_config_part2 }}
wgd_scoring_mask {{ reference_resources.wgd_scoring_mask }}
wham_include_list_bed_file {{ reference_resources.wham_include_list_bed_file }}
chr_x {{ reference_resources.chr_x }}
Expand Down
10 changes: 9 additions & 1 deletion inputs/templates/terra_workspaces/single_sample/GATKSVPipelineSingleSample.json.tmpl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@

"GATKSVPipelineSingleSample.linux_docker" : "${workspace.linux_docker}",
"GATKSVPipelineSingleSample.manta_docker": "${workspace.manta_docker}",
"GATKSVPipelineSingleSample.scramble_docker": "${workspace.scramble_docker}",
"GATKSVPipelineSingleSample.sv_base_docker": "${workspace.sv_base_docker}",
"GATKSVPipelineSingleSample.sv_base_mini_docker": "${workspace.sv_base_mini_docker}",
"GATKSVPipelineSingleSample.sv_pipeline_docker": "${workspace.sv_pipeline_docker}",
Expand All @@ -42,7 +43,6 @@
"GATKSVPipelineSingleSample.autosome_file" : "${workspace.reference_autosome_file}",
"GATKSVPipelineSingleSample.primary_contigs_list" : "${workspace.reference_primary_contigs_list}",
"GATKSVPipelineSingleSample.primary_contigs_fai" : "${workspace.reference_primary_contigs_fai}",
"GATKSVPipelineSingleSample.empty_file" : "${workspace.reference_empty_file}",
"GATKSVPipelineSingleSample.genome_file" : "${workspace.reference_genome_file}",
"GATKSVPipelineSingleSample.max_ref_panel_carrier_freq": 0.03,
"GATKSVPipelineSingleSample.manta_region_bed" : "${workspace.reference_manta_region_bed}",
Expand Down Expand Up @@ -86,6 +86,14 @@
"GATKSVPipelineSingleSample.depth_interval_overlap": "0.8",
"GATKSVPipelineSingleSample.depth_clustering_algorithm": "SINGLE_LINKAGE",

"GATKSVPipelineSingleSample.clustering_config_part1" : "${workspace.clustering_config_part1}",
"GATKSVPipelineSingleSample.stratification_config_part1" : "${workspace.clustering_config_part1}",
"GATKSVPipelineSingleSample.clustering_config_part2" : "${workspace.clustering_config_part2}",
"GATKSVPipelineSingleSample.stratification_config_part2" : "${workspace.stratification_config_part2}",

"GATKSVPipelineSingleSample.clustering_track_names" : {{ reference_resources.clustering_track_names | tojson }},
"GATKSVPipelineSingleSample.clustering_track_bed_files" : {{ reference_resources.clustering_tracks | tojson }},

"GATKSVPipelineSingleSample.ref_copy_number_autosomal_contigs" : 2,
"GATKSVPipelineSingleSample.clean_vcf_min_sr_background_fail_batches": 0.5,
"GATKSVPipelineSingleSample.max_shard_size_resolve" : 500,
Expand Down
4 changes: 4 additions & 0 deletions inputs/templates/terra_workspaces/single_sample/workspace.tsv.tmpl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,6 @@
workspace:cloud_sdk_docker {{ dockers.cloud_sdk_docker }}
clustering_config_part1 {{ reference_resources.clustering_config_part1 }}
clustering_config_part2 {{ reference_resources.clustering_config_part2 }}
cnmops_docker {{ dockers.cnmops_docker }}
condense_counts_docker {{ dockers.condense_counts_docker }}
gatk_docker {{ dockers.gatk_docker }}
Expand Down Expand Up @@ -77,3 +79,5 @@ reference_segdups {{ reference_resources.segdups }}
reference_seed_cutoffs {{ reference_resources.seed_cutoffs }}
reference_wgd_scoring_mask {{ reference_resources.wgd_scoring_mask }}
reference_wham_include_list_bed_file {{ reference_resources.wham_include_list_bed_file }}
stratification_config_part1 {{ reference_resources.stratification_config_part1 }}
stratification_config_part2 {{ reference_resources.stratification_config_part2 }}
10 changes: 7 additions & 3 deletions inputs/templates/test/GATKSVPipelineBatch/GATKSVPipelineBatch.FromSampleEvidence.json.tmpl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,7 +123,6 @@
"GATKSVPipelineBatch.RegenotypeCNVs.n_per_split": "5000",

"GATKSVPipelineBatch.MakeCohortVcf.bin_exclude": {{ reference_resources.bin_exclude | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.empty_file" : {{ reference_resources.empty_file | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.site_level_comparison_datasets": [
{{ reference_resources.ccdg_abel_site_level_benchmarking_dataset | tojson }},
{{ reference_resources.gnomad_v2_collins_site_level_benchmarking_dataset | tojson }},
Expand All @@ -133,7 +132,6 @@
"GATKSVPipelineBatch.MakeCohortVcf.cytobands": {{ reference_resources.cytobands | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.mei_bed": {{ reference_resources.mei_bed | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.pe_exclude_list": {{ reference_resources.pesr_exclude_list | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.depth_exclude_list": {{ reference_resources.depth_exclude_list | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.HERVK_reference": {{ reference_resources.hervk_reference | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.LINE1_reference": {{ reference_resources.line1_reference | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.min_sr_background_fail_batches": 0.5,
Expand All @@ -143,5 +141,11 @@
"GATKSVPipelineBatch.MakeCohortVcf.samples_per_clean_vcf_step2_shard": 100,
"GATKSVPipelineBatch.MakeCohortVcf.clean_vcf5_records_per_shard": 5000,
"GATKSVPipelineBatch.MakeCohortVcf.random_seed": 0,
"GATKSVPipelineBatch.MakeCohortVcf.max_shard_size_resolve": 500
"GATKSVPipelineBatch.MakeCohortVcf.max_shard_size_resolve": 500,
"GATKSVPipelineBatch.MakeCohortVcf.clustering_config_part1" : {{ reference_resources.clustering_config_part1 | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.stratification_config_part1" : {{ reference_resources.clustering_config_part1 | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.clustering_config_part2" : {{ reference_resources.clustering_config_part2 | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.stratification_config_part2" : {{ reference_resources.stratification_config_part2 | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.track_bed_files": {{ reference_resources.clustering_tracks | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.track_names": {{ reference_resources.clustering_track_names | tojson }}
}
8 changes: 6 additions & 2 deletions inputs/templates/test/GATKSVPipelineBatch/GATKSVPipelineBatch.json.tmpl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,7 +116,6 @@
"GATKSVPipelineBatch.RegenotypeCNVs.n_per_split": "5000",

"GATKSVPipelineBatch.MakeCohortVcf.bin_exclude": {{ reference_resources.bin_exclude | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.empty_file" : {{ reference_resources.empty_file | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.site_level_comparison_datasets": [
{{ reference_resources.ccdg_abel_site_level_benchmarking_dataset | tojson }},
{{ reference_resources.gnomad_v2_collins_site_level_benchmarking_dataset | tojson }},
Expand All @@ -126,7 +125,6 @@
"GATKSVPipelineBatch.MakeCohortVcf.cytobands": {{ reference_resources.cytobands | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.mei_bed": {{ reference_resources.mei_bed | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.pe_exclude_list": {{ reference_resources.pesr_exclude_list | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.depth_exclude_list": {{ reference_resources.depth_exclude_list | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.HERVK_reference": {{ reference_resources.hervk_reference | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.LINE1_reference": {{ reference_resources.line1_reference | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.min_sr_background_fail_batches": 0.5,
Expand All @@ -137,6 +135,12 @@
"GATKSVPipelineBatch.MakeCohortVcf.clean_vcf5_records_per_shard": 5000,
"GATKSVPipelineBatch.MakeCohortVcf.random_seed": 0,
"GATKSVPipelineBatch.MakeCohortVcf.max_shard_size_resolve": 500,
"GATKSVPipelineBatch.MakeCohortVcf.clustering_config_part1" : {{ reference_resources.clustering_config_part1 | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.stratification_config_part1" : {{ reference_resources.clustering_config_part1 | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.clustering_config_part2" : {{ reference_resources.clustering_config_part2 | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.stratification_config_part2" : {{ reference_resources.stratification_config_part2 | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.track_bed_files": {{ reference_resources.clustering_tracks | tojson }},
"GATKSVPipelineBatch.MakeCohortVcf.track_names": {{ reference_resources.clustering_track_names | tojson }},

"GATKSVPipelineBatch.GATKSVPipelinePhase1.runtime_attr_postprocess": {
"cpu_cores": 1,
Expand Down
8 changes: 7 additions & 1 deletion inputs/templates/test/GATKSVPipelineSingleSample/GATKSVPipelineSingleSample.json.tmpl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,6 @@
"GATKSVPipelineSingleSample.autosome_file" : {{ reference_resources.autosome_file | tojson }},
"GATKSVPipelineSingleSample.primary_contigs_list" : {{ reference_resources.primary_contigs_list | tojson }},
"GATKSVPipelineSingleSample.primary_contigs_fai" : {{ reference_resources.primary_contigs_fai | tojson }},
"GATKSVPipelineSingleSample.empty_file" : {{ reference_resources.empty_file | tojson }},
"GATKSVPipelineSingleSample.genome_file" : {{ reference_resources.genome_file | tojson }},
"GATKSVPipelineSingleSample.max_ref_panel_carrier_freq": 0.03,
"GATKSVPipelineSingleSample.manta_region_bed" : {{ reference_resources.manta_region_bed | tojson }},
Expand Down Expand Up @@ -90,6 +89,13 @@
"GATKSVPipelineSingleSample.depth_interval_overlap": "0.8",
"GATKSVPipelineSingleSample.depth_clustering_algorithm": "SINGLE_LINKAGE",

"GATKSVPipelineSingleSample.clustering_config_part1" : {{ reference_resources.clustering_config_part1 | tojson }},
"GATKSVPipelineSingleSample.stratification_config_part1" : {{ reference_resources.clustering_config_part1 | tojson }},
"GATKSVPipelineSingleSample.clustering_config_part2" : {{ reference_resources.clustering_config_part2 | tojson }},
"GATKSVPipelineSingleSample.stratification_config_part2" : {{ reference_resources.stratification_config_part2 | tojson }},
"GATKSVPipelineSingleSample.clustering_track_bed_files": {{ reference_resources.clustering_tracks | tojson }},
"GATKSVPipelineSingleSample.clustering_track_names": {{ reference_resources.clustering_track_names | tojson }},

"GATKSVPipelineSingleSample.ref_copy_number_autosomal_contigs" : {{ reference_resources.copy_number_autosomal_contigs | tojson }},
"GATKSVPipelineSingleSample.clean_vcf_min_sr_background_fail_batches": 0.5,
"GATKSVPipelineSingleSample.max_shard_size_resolve" : 500,
Expand Down
8 changes: 7 additions & 1 deletion inputs/templates/test/GATKSVPipelineSingleSample/GATKSVPipelineSingleSample.melt.json.tmpl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,6 @@
"GATKSVPipelineSingleSample.autosome_file" : {{ reference_resources.autosome_file | tojson }},
"GATKSVPipelineSingleSample.primary_contigs_list" : {{ reference_resources.primary_contigs_list | tojson }},
"GATKSVPipelineSingleSample.primary_contigs_fai" : {{ reference_resources.primary_contigs_fai | tojson }},
"GATKSVPipelineSingleSample.empty_file" : {{ reference_resources.empty_file | tojson }},
"GATKSVPipelineSingleSample.genome_file" : {{ reference_resources.genome_file | tojson }},
"GATKSVPipelineSingleSample.max_ref_panel_carrier_freq": 0.03,
"GATKSVPipelineSingleSample.manta_region_bed" : {{ reference_resources.manta_region_bed | tojson }},
Expand Down Expand Up @@ -89,6 +88,13 @@
"GATKSVPipelineSingleSample.depth_interval_overlap": "0.8",
"GATKSVPipelineSingleSample.depth_clustering_algorithm": "SINGLE_LINKAGE",

"GATKSVPipelineSingleSample.clustering_config_part1" : {{ reference_resources.clustering_config_part1 | tojson }},
"GATKSVPipelineSingleSample.stratification_config_part1" : {{ reference_resources.clustering_config_part1 | tojson }},
"GATKSVPipelineSingleSample.clustering_config_part2" : {{ reference_resources.clustering_config_part2 | tojson }},
"GATKSVPipelineSingleSample.stratification_config_part2" : {{ reference_resources.stratification_config_part2 | tojson }},
"GATKSVPipelineSingleSample.clustering_track_bed_files": {{ reference_resources.clustering_tracks | tojson }},
"GATKSVPipelineSingleSample.clustering_track_names": {{ reference_resources.clustering_track_names | tojson }},

"GATKSVPipelineSingleSample.ref_copy_number_autosomal_contigs" : 2,

"GATKSVPipelineSingleSample.MakeCohortVcf.HERVK_reference": {{ reference_resources.hervk_reference | tojson }},
Expand Down
16 changes: 13 additions & 3 deletions inputs/templates/test/MakeCohortVcf/CombineBatches.json.tmpl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,14 +1,24 @@
{
"CombineBatches.contig_list": {{ reference_resources.primary_contigs_fai | tojson }},
"CombineBatches.pe_exclude_list": {{ reference_resources.pesr_exclude_list | tojson }},
"CombineBatches.depth_exclude_list": {{ reference_resources.depth_exclude_list | tojson }},
"CombineBatches.empty_file" : {{ reference_resources.empty_file | tojson }},

"CombineBatches.clustering_config_part1" : {{ reference_resources.clustering_config_part1 | tojson }},
"CombineBatches.stratification_config_part1" : {{ reference_resources.clustering_config_part1 | tojson }},
"CombineBatches.clustering_config_part2" : {{ reference_resources.clustering_config_part2 | tojson }},
"CombineBatches.stratification_config_part2" : {{ reference_resources.stratification_config_part2 | tojson }},
"CombineBatches.track_bed_files": {{ reference_resources.clustering_tracks | tojson }},
"CombineBatches.track_names": {{ reference_resources.clustering_track_names | tojson }},

"CombineBatches.reference_fasta": {{ reference_resources.reference_fasta | tojson }},
"CombineBatches.reference_dict": {{ reference_resources.reference_dict | tojson }},
"CombineBatches.reference_fasta_fai": {{ reference_resources.reference_index | tojson }},

"CombineBatches.min_sr_background_fail_batches": 0.5,
"CombineBatches.gatk_docker": {{ dockers.gatk_docker | tojson }},
"CombineBatches.sv_pipeline_docker": {{ dockers.sv_pipeline_docker | tojson }},
"CombineBatches.sv_base_mini_docker":{{ dockers.sv_base_mini_docker | tojson }},

"CombineBatches.cohort_name": {{ test_batch.name | tojson }},
"CombineBatches.ped_file": {{ test_batch.ped_file | tojson }},
"CombineBatches.batches": [
{{ test_batch.name | tojson }}
],
Expand Down
Loading
Loading