Skip to content

Commit

Permalink
Remove branch name parameter from multiple WDLs
Browse files Browse the repository at this point in the history
  • Loading branch information
mcovarr committed Jul 10, 2023
1 parent 1e83927 commit 6e62f49
Show file tree
Hide file tree
Showing 3 changed files with 1 addition and 8 deletions.
2 changes: 0 additions & 2 deletions scripts/variantstore/wdl/GvsBulkIngestGenomes.wdl
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,6 @@ workflow GvsBulkIngestGenomes {
Int? load_data_preemptible_override
Int? load_data_maxretries_override
# End GvsImportGenomes
String branch_name = "ah_var_store"
}

parameter_meta {
Expand Down Expand Up @@ -106,7 +105,6 @@ workflow GvsBulkIngestGenomes {
load_data_maxretries_override = load_data_maxretries_override,
load_data_preemptible_override = load_data_preemptible_override,
load_data_gatk_override = gatk_override,
branch_name = branch_name,
drop_state = drop_state,
}

Expand Down
6 changes: 1 addition & 5 deletions scripts/variantstore/wdl/GvsImportGenomes.wdl
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,6 @@ workflow GvsImportGenomes {
Int? load_data_maxretries_override
Boolean process_vcf_headers = false
File? load_data_gatk_override
String branch_name
}

Int max_auto_batch_size = 20000
Expand Down Expand Up @@ -100,7 +99,6 @@ workflow GvsImportGenomes {
load_data_preemptible = effective_load_data_preemptible,
load_data_maxretries = effective_load_data_maxretries,
process_vcf_headers = process_vcf_headers,
branch_name = branch_name,
}
}
if (process_vcf_headers) {
Expand Down Expand Up @@ -172,7 +170,6 @@ task LoadData {
Boolean process_vcf_headers

File? gatk_override
String branch_name
Int load_data_preemptible
Int load_data_maxretries
}
Expand Down Expand Up @@ -243,14 +240,13 @@ task LoadData {
bq --apilog=false --project_id=~{project_id} rm -f=true ~{temp_table}

## now we want to create a sub list of these samples (without the ones that have already been loaded)
curl --location --remote-name https://raw.githubusercontent.com/broadinstitute/gatk/~{branch_name}/scripts/variantstore/wdl/extract/curate_bulk_import_tsv.py

# *re-*curated because the curation script is run again in this task. The curation script was already run at least
# once before in a separate task to filter out already-loaded samples before the call to `LoadTask`. Here the
# `LoadTask` job might be retried due to preemption so we only want to load the samples which still need loading.
RECURATED_OUTPUT="bulk_import_recurated.tsv"

python3 curate_bulk_import_tsv.py \
python3 /gatk/scripts/variantstore/wdl/extract/curate_bulk_import_tsv.py \
--samples-to-load $SAMPLE_MAP \
--bulk-import-input-tsv ~{bulk_import_fofn} \
--bulk-import-output-tsv $RECURATED_OUTPUT
Expand Down
1 change: 0 additions & 1 deletion scripts/variantstore/wdl/GvsUnified.wdl
Original file line number Diff line number Diff line change
Expand Up @@ -80,7 +80,6 @@ workflow GvsUnified {
dataset_name = dataset_name,
project_id = project_id,
gatk_override = gatk_override,
branch_name = branch_name,
interval_list = interval_list,
drop_state = drop_state,
sample_id_column_name = sample_id_column_name,
Expand Down

0 comments on commit 6e62f49

Please sign in to comment.