Kemal Yaylali
11fb6b3d73
An end-to-end audit found the repo could not build, test or run as shipped. This fixes every finding, then adds a Cloud Run track so the demo costs about £1/month idle instead of ~£150. CI (red on its first run) - api: setuptools could not build the package (flat layout with app/ and alembic/) - web: missing @types/node; `vitest run` exited 1 with no test files - pipeline: the stub run needed a gitignored VCF, and no process had a stub block - ruff pinned, mypy configured, DB tests on real Postgres (pgserver locally, service in CI) ML serving (scores were meaningless) - the registered model now carries its own feature engineering and returns predict_proba, so serving sends raw columns and cannot drift from training - resolve by registry alias (stages are deprecated in MLflow 3) and record the real version; re-scoring upserts instead of failing on the unique constraint - ClinVar labels parsed from VEP's lowercase terms Pipeline - exact ref/alt recovered from a CHROM_POS_REF_ALT VCF ID; loading is idempotent - job status reaches running/failed/succeeded, so the UI stops polling dead jobs - DATABASE_URL travels in the environment or a Nextflow secret, never on a command line - VEP cache and plugins staged as inputs; the gcp profile runs tasks on Google Batch Deployment - the API serves /api (matching the ingress); the web app reads its API URL at runtime - migrations run in an init container under a Postgres advisory lock - terraform: custom VPC shared with Batch, private Cloud SQL, API enablement, Workload Identity bindings, Secret Manager, deletion protection - serverless track, now the default: Cloud Run services scaling to zero, a Cloud Run job for the Nextflow driver, and Neon or Cloud SQL behind one DATABASE_URL secret. GKE and Argo remain, behind -var deploy_kubernetes=true. See docs/cloud.md. Correctness and security - 409 on duplicate sample names, 422 on bad paging, natural chromosome ordering, wider VEP text columns, enum dropped on downgrade, the sample's assembly actually used - vcf_uri restricted to gs:// objects or files under the data root, blocking option injection - CORS restricted to configured origins; `make down` no longer deletes volumes Data - docs/data.md records the peer-reviewed, openly licensed sources (GIAB HG002, ClinVar, gnomAD) with citations and an honest evaluation plan; `make data` fetches a chr22 slice Verified: api 50 tests, ml 18, loader 16, web 12; ruff, mypy, svelte-check, terraform validate and both kustomize overlays clean.
61 lines
1.8 KiB
Python
61 lines
1.8 KiB
Python
"""Loader tests. DB tests use DATABASE_URL (CI's Postgres service) or a throwaway pgserver."""
|
|
import os
|
|
import sys
|
|
import tempfile
|
|
from collections.abc import Iterator
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "bin"))
|
|
|
|
# The subset of the Alembic schema (api/alembic/versions) that the loader writes to.
|
|
SCHEMA = """
|
|
CREATE TYPE jobstatus AS ENUM ('queued', 'running', 'succeeded', 'failed');
|
|
CREATE TABLE jobs (
|
|
id uuid PRIMARY KEY,
|
|
status jobstatus NOT NULL,
|
|
vep_version text,
|
|
log text,
|
|
finished_at timestamptz
|
|
);
|
|
CREATE TABLE variants (
|
|
id serial PRIMARY KEY,
|
|
job_id uuid NOT NULL,
|
|
chrom text NOT NULL, pos integer NOT NULL, ref text NOT NULL, alt text NOT NULL,
|
|
gene text, consequence text, impact text, hgvsc text, hgvsp text,
|
|
gnomad_af double precision, clinvar_sig text, annotations jsonb NOT NULL
|
|
);
|
|
"""
|
|
|
|
_server = None
|
|
|
|
|
|
def _url() -> str | None:
|
|
global _server
|
|
if url := os.environ.get("DATABASE_URL"):
|
|
return url
|
|
try:
|
|
import pgserver
|
|
except ImportError:
|
|
return None
|
|
_server = pgserver.get_server(tempfile.mkdtemp(prefix="loader-pg-"), cleanup_mode="delete")
|
|
return "postgresql://postgres@/postgres?host=" + _server.get_uri().split("host=", 1)[1]
|
|
|
|
|
|
@pytest.fixture
|
|
def engine() -> Iterator:
|
|
url = _url()
|
|
if not url:
|
|
if os.environ.get("REQUIRE_DB"):
|
|
pytest.fail("REQUIRE_DB is set but no database is available")
|
|
pytest.skip("no DATABASE_URL and pgserver is not installed")
|
|
from load_db import engine_for
|
|
|
|
eng = engine_for(url)
|
|
with eng.begin() as conn:
|
|
conn.exec_driver_sql("DROP TABLE IF EXISTS variants, jobs; DROP TYPE IF EXISTS jobstatus")
|
|
conn.exec_driver_sql(SCHEMA)
|
|
yield eng
|
|
eng.dispose()
|