feat(pipeline): VEP database mode, and a pipeline-specific database URL
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.
This commit is contained in:
@@ -124,3 +124,28 @@ async def test_pubsub_failure_marks_the_job_failed(
|
||||
job = (await client.post(f"/api/samples/{sample_id}/annotate")).json()
|
||||
assert job["status"] == "failed"
|
||||
assert "403 denied" in job["log"]
|
||||
|
||||
|
||||
@pytest.mark.usefixtures("db")
|
||||
async def test_the_pipeline_gets_its_own_database_url(
|
||||
client: AsyncClient, monkeypatch: pytest.MonkeyPatch
|
||||
) -> None:
|
||||
"""The loader runs in a container, where the API's own localhost URL would point at itself."""
|
||||
monkeypatch.setattr(settings, "pubsub_topic", None)
|
||||
monkeypatch.setattr(settings, "cloudrun_job", None)
|
||||
monkeypatch.setattr(
|
||||
settings, "pipeline_database_url", "postgresql+asyncpg://u:[email protected]:5432/db"
|
||||
)
|
||||
monkeypatch.setattr(events.shutil, "which", lambda _: "/usr/bin/nextflow")
|
||||
launched: dict[str, Any] = {}
|
||||
|
||||
async def fake_exec(*cmd: str, **kw: Any) -> FakeProcess:
|
||||
launched["env"] = kw["env"]
|
||||
return FakeProcess(0, b"")
|
||||
|
||||
monkeypatch.setattr(events.asyncio, "create_subprocess_exec", fake_exec)
|
||||
sample_id = await new_sample(client)
|
||||
|
||||
await client.post(f"/api/samples/{sample_id}/annotate")
|
||||
await events.drain()
|
||||
assert launched["env"]["DATABASE_URL"] == "postgresql+asyncpg://u:[email protected]:5432/db"
|
||||
|
||||
Reference in New Issue
Block a user