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.
99 lines
2.6 KiB
Python
99 lines
2.6 KiB
Python
import re
|
|
import uuid
|
|
from datetime import datetime
|
|
from pathlib import PurePosixPath
|
|
from typing import Literal
|
|
|
|
from pydantic import BaseModel, ConfigDict, Field, field_validator
|
|
|
|
from app.config import settings
|
|
from app.models import JobStatus
|
|
|
|
|
|
class ORMModel(BaseModel):
|
|
model_config = ConfigDict(from_attributes=True)
|
|
|
|
|
|
Assembly = Literal["GRCh38", "GRCh37"]
|
|
VCF_SUFFIXES = (".vcf", ".vcf.gz", ".vcf.bgz", ".bcf")
|
|
GCS_URI = re.compile(r"gs://[a-z0-9][a-z0-9._-]{1,220}[a-z0-9]/\S+")
|
|
|
|
|
|
class SampleCreate(BaseModel):
|
|
name: str = Field(min_length=1, max_length=120)
|
|
vcf_uri: str
|
|
# Passed to VEP --assembly; the VEP cache must contain it.
|
|
assembly: Assembly = "GRCh38"
|
|
|
|
@field_validator("vcf_uri")
|
|
@classmethod
|
|
def _gcs_object_or_file_under_data_root(cls, v: str) -> str:
|
|
# The URI becomes a Nextflow argument and a path the pipeline reads: accept a GCS object or
|
|
# a file under the local data root, never something that parses as an option.
|
|
if not v or any(ord(c) < 32 for c in v):
|
|
raise ValueError("vcf_uri must be a non-empty single line")
|
|
if not v.lower().endswith(VCF_SUFFIXES):
|
|
raise ValueError(f"vcf_uri must end in one of {', '.join(VCF_SUFFIXES)}")
|
|
if v.startswith("gs://"):
|
|
if not GCS_URI.fullmatch(v):
|
|
raise ValueError("vcf_uri is not a valid gs://bucket/object URI")
|
|
return v
|
|
path, root = PurePosixPath(v), PurePosixPath(settings.local_data_root)
|
|
if not path.is_absolute() or ".." in path.parts or not path.is_relative_to(root):
|
|
raise ValueError(f"local VCFs must be absolute paths under {root}")
|
|
return v
|
|
|
|
|
|
class SampleOut(ORMModel):
|
|
id: uuid.UUID
|
|
name: str
|
|
vcf_uri: str
|
|
assembly: str
|
|
created_at: datetime
|
|
|
|
|
|
class JobOut(ORMModel):
|
|
id: uuid.UUID
|
|
sample_id: uuid.UUID
|
|
status: JobStatus
|
|
workflow_ref: str | None
|
|
vep_version: str | None
|
|
log: str | None
|
|
created_at: datetime
|
|
finished_at: datetime | None
|
|
|
|
|
|
class PredictionOut(ORMModel):
|
|
model_name: str
|
|
model_version: str
|
|
score: float
|
|
|
|
|
|
class VariantOut(ORMModel):
|
|
id: int
|
|
chrom: str
|
|
pos: int
|
|
ref: str
|
|
alt: str
|
|
gene: str | None
|
|
consequence: str | None
|
|
impact: str | None
|
|
hgvsc: str | None
|
|
hgvsp: str | None
|
|
gnomad_af: float | None
|
|
clinvar_sig: str | None
|
|
prediction: PredictionOut | None = None
|
|
|
|
|
|
class ScoreOut(BaseModel):
|
|
job_id: uuid.UUID
|
|
scored: int
|
|
model_version: str
|
|
|
|
|
|
class VariantPage(BaseModel):
|
|
items: list[VariantOut]
|
|
total: int
|
|
limit: int
|
|
offset: int
|