Kemal Yaylali
ae58e33fe2
Makes a real annotation runnable locally without the 25 GB VEP cache, which is what the demo needs and what a reviewer can reproduce in minutes. - params.vep_database (VEP_DATABASE=true) queries Ensembl's public database instead of a local cache. Slower per variant and fewer fields, so --everything is swapped for the flags the loader actually stores. Its cache placeholder is NO_CACHE, not NO_FILE: Nextflow rejects two staged inputs sharing a filename. - PIPELINE_DATABASE_URL is handed to the pipeline when set. The loader runs inside a container, where the API's own localhost URL would point at the container itself. - README: how to run the UI's annotate button locally against host Nextflow + Docker. Verified end to end on pipeline/tests/data/tiny.vcf: bcftools norm split the multiallelic record, VEP 113 annotated 4 variants live, the loader wrote them and marked the job succeeded, and the UI shows them. The deletion came back as 22:42126611 CT>C with exact VCF alleles, which is the case the audit's ID-tagging fix exists for. Tests: api 51, loader 16, stub run 3/3; ruff, mypy clean.
37 lines
1.7 KiB
Python
37 lines
1.7 KiB
Python
from pathlib import Path
|
|
|
|
from pydantic_settings import BaseSettings, SettingsConfigDict
|
|
|
|
# api/app/config.py -> repo root locally; "/" in the API image, where compose mounts /pipeline.
|
|
REPO_ROOT = Path(__file__).resolve().parents[2]
|
|
|
|
|
|
class Settings(BaseSettings):
|
|
model_config = SettingsConfigDict(env_file=".env", extra="ignore")
|
|
|
|
database_url: str = "postgresql+asyncpg://rarelens:rarelens@localhost:5432/rarelens"
|
|
mlflow_tracking_uri: str = "http://localhost:5000"
|
|
model_name: str = "rarelens-pathogenicity"
|
|
# Registry alias set by `rarelens_ml.train --register` (stages are deprecated in MLflow 3).
|
|
model_alias: str = "production"
|
|
# A model artifact URI (gs://...) scores without an MLflow server running; wins over the registry.
|
|
model_uri: str | None = None
|
|
gcs_bucket: str | None = None # set in GCP; local uses ./data
|
|
pubsub_topic: str | None = None # "vcf-uploaded" in GCP; local runs pipeline inline
|
|
# Serverless track: run the Nextflow driver as a Cloud Run job instead of Argo + Pub/Sub.
|
|
cloudrun_job: str | None = None
|
|
gcp_project: str | None = None # required with pubsub_topic or cloudrun_job
|
|
gcp_region: str = "europe-west2"
|
|
pipeline_dir: Path = REPO_ROOT / "pipeline"
|
|
# Handed to the pipeline when it differs from the API's own: the loader runs inside a
|
|
# container, where the API's localhost would be the container itself.
|
|
pipeline_database_url: str | None = None
|
|
nextflow_profile: str = "docker"
|
|
# Local (non-gs://) VCFs must live under this directory.
|
|
local_data_root: Path = Path("/data")
|
|
# Browsers calling the API cross-origin; behind the ingress the UI is same-origin.
|
|
cors_origins: list[str] = ["http://localhost:5173"]
|
|
|
|
|
|
settings = Settings()
|