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.

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

feat: extract config for finngen ingestion to yaml file #15

Merged
merged 4 commits into from
Sep 9, 2024
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
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: 17 additions & 0 deletions src/ot_orchestration/dags/config/finngen_ingestion.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
finngen_release_prefix: FINNGEN_R11_

# inputs
efo_mappings_path: https://raw.githubusercontent.com/opentargets/curation/24.09.1/mappings/disease/manual_string.tsv
finngen_credible_set_input_glob: gs://finngen-public-data-r11/finemap/summary/*.cred.summary.tsv
finngen_snp_input_glob: gs://finngen-public-data-r11/finemap/full/susie/*.snp.bgz
phenotype_table_url: https://r11.finngen.fi/api/phenos
finngen_summary_stats_url_prefix: gs://finngen-public-data-r11/summary_stats/finngen_R11_
finngen_summary_stats_url_suffix: ".gz"

# outputs
credible_set_output_path: gs://finngen_data/r11/credible_set_datasets/finngen_r11_susie
study_index_output_path: gs://finngen_data/r11/study_index

# cluster setup
cluster_name: otg-ingestion-finngen
autoscaling_policy: finngen-preprocess
Original file line number Diff line number Diff line change
Expand Up @@ -15,18 +15,10 @@
install_dependencies,
submit_step,
)
from ot_orchestration.utils.utils import read_yaml_config

EFO_MAPPINGS_PATH = "https://raw.githubusercontent.com/opentargets/curation/24.09.1/mappings/disease/manual_string.tsv"
STUDY_INDEX_OUT = "gs://finngen_data/r11/study_index"
CREDIBLE_SETS_SUMMARY_IN = (
"gs://finngen-public-data-r11/finemap/summary/*.cred.summary.tsv"
)
SNP_IN = "gs://finngen-public-data-r11/finemap/full/susie/*.snp.bgz"
FINNGEN_PREFIX = "FINNGEN_R11_"
FINEMAPPING_OUT = "gs://finngen_data/r11/finemapping"

CLUSTER_NAME = "otg-finemapping-ingestion-finngen"
AUTOSCALING = "finngen-preprocess"
SOURCE_CONFIG_FILE_PATH = Path(__file__).parent / "config" / "finngen_ingestion.yaml"
config = read_yaml_config(SOURCE_CONFIG_FILE_PATH)

with DAG(
dag_id=Path(__file__).stem,
Expand All @@ -35,39 +27,42 @@
**common.shared_dag_kwargs,
):
finngen_finemapping_ingestion = submit_step(
cluster_name=CLUSTER_NAME,
cluster_name=config["cluster_name"],
step_id="finngen_finemapping_ingestion",
task_id="finngen_finemapping_ingestion",
other_args=[
f"step.finngen_finemapping_out={FINEMAPPING_OUT}",
f"step.finngen_release_prefix={FINNGEN_PREFIX}",
f"step.finngen_susie_finemapping_snp_files={SNP_IN}",
f"step.finngen_susie_finemapping_cs_summary_files={CREDIBLE_SETS_SUMMARY_IN}",
f"step.finngen_finemapping_out={config['credible_set_output_path']}",
f"step.finngen_susie_finemapping_snp_files={config['finngen_snp_input_glob']}",
f"step.finngen_susie_finemapping_cs_summary_files={config['finngen_credible_set_input_glob']}",
"step.session.start_hail=true",
"step.session.write_mode=overwrite",
],
trigger_rule=TriggerRule.ALL_DONE,
)

finngen_study_index = submit_step(
cluster_name=CLUSTER_NAME,
cluster_name=config["cluster_name"],
step_id="finngen_studies",
task_id="finngen_studies",
other_args=[
f"step.finngen_study_index_out={STUDY_INDEX_OUT}",
f"step.finngen_study_index_out={config['study_index_output_path']}",
f"step.finngen_phenotype_table_url={config['phenotype_table_url']}",
f"step.finngen_release_prefix={config['finngen_release_prefix']}",
f"step.finngen_summary_stats_url_prefix={config['finngen_summary_stats_url_prefix']}",
f"step.finngen_summary_stats_url_suffix={config['finngen_summary_stats_url_suffix']}",
"step.session.write_mode=overwrite",
],
trigger_rule=TriggerRule.ALL_DONE,
)
chain(
create_cluster(
CLUSTER_NAME,
autoscaling_policy=AUTOSCALING,
config["cluster_name"],
autoscaling_policy=config["autoscaling_policy"],
master_disk_size=2000,
num_workers=6,
),
install_dependencies(CLUSTER_NAME),
install_dependencies(config["cluster_name"]),
finngen_study_index,
finngen_finemapping_ingestion,
delete_cluster(CLUSTER_NAME),
delete_cluster(config["cluster_name"]),
)