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
2.0 KiB
Python
61 lines
2.0 KiB
Python
import uuid
|
|
|
|
from fastapi import APIRouter, Query
|
|
from sqlalchemy import Integer, case, cast, func, select
|
|
from sqlalchemy.orm import selectinload
|
|
|
|
from app.db import SessionDep
|
|
from app.models import Prediction, Variant
|
|
from app.schemas import VariantOut, VariantPage
|
|
|
|
router = APIRouter()
|
|
|
|
# Karyotype order (1..22, X, Y, MT) instead of text order, where "10" sorts before "2".
|
|
_chrom = func.regexp_replace(Variant.chrom, "^chr", "", "i")
|
|
CHROM_ORDER = case(
|
|
(_chrom.regexp_match("^[0-9]+$"), cast(_chrom, Integer)),
|
|
(_chrom == "X", 23),
|
|
(_chrom == "Y", 24),
|
|
(_chrom.in_(["M", "MT"]), 25),
|
|
else_=26,
|
|
)
|
|
|
|
|
|
@router.get("", response_model=VariantPage)
|
|
async def list_variants(
|
|
job_id: uuid.UUID,
|
|
session: SessionDep,
|
|
gene: str | None = None,
|
|
impact: str | None = Query(None, pattern="^(HIGH|MODERATE|LOW|MODIFIER)$"),
|
|
max_af: float | None = Query(None, ge=0, le=1),
|
|
min_score: float | None = Query(None, ge=0, le=1),
|
|
limit: int = Query(50, ge=1, le=500),
|
|
offset: int = Query(0, ge=0),
|
|
) -> VariantPage:
|
|
stmt = select(Variant).where(Variant.job_id == job_id)
|
|
if gene:
|
|
stmt = stmt.where(Variant.gene == gene.upper())
|
|
if impact:
|
|
stmt = stmt.where(Variant.impact == impact)
|
|
if max_af is not None:
|
|
stmt = stmt.where((Variant.gnomad_af.is_(None)) | (Variant.gnomad_af <= max_af))
|
|
if min_score is not None:
|
|
stmt = stmt.join(Prediction, Prediction.variant_id == Variant.id).where(
|
|
Prediction.score >= min_score
|
|
)
|
|
|
|
total = await session.scalar(select(func.count()).select_from(stmt.subquery()))
|
|
rows = await session.scalars(
|
|
stmt.options(selectinload(Variant.prediction))
|
|
# id breaks ties between split multiallelics at one position, keeping pages stable.
|
|
.order_by(CHROM_ORDER, Variant.chrom, Variant.pos, Variant.id)
|
|
.limit(limit)
|
|
.offset(offset)
|
|
)
|
|
return VariantPage(
|
|
items=[VariantOut.model_validate(v) for v in rows],
|
|
total=total or 0,
|
|
limit=limit,
|
|
offset=offset,
|
|
)
|