kemal
5463f489a3
ci / api (push) Failing after 10s
ci / terraform (push) Failing after 11s
ci / web (push) Failing after 35s
ci / pipeline (push) Failing after 2m29s
ci / images (api) (push) Skipped
ci / images (ml) (push) Skipped
ci / images (pipeline) (push) Skipped
ci / images (web) (push) Skipped
End-to-end variant interpretation platform for rare genetic disease research: SvelteKit UI, FastAPI + PostgreSQL API, Nextflow/Ensembl VEP pipeline, LightGBM pathogenicity scoring with MLflow, K8s/ArgoCD/GCP infrastructure. Public test data only; no clinical claims.
46 lines
1.5 KiB
Python
46 lines
1.5 KiB
Python
import uuid
|
|
|
|
import mlflow
|
|
import pandas as pd
|
|
from sqlalchemy import select
|
|
from sqlalchemy.ext.asyncio import AsyncSession
|
|
|
|
from app.config import settings
|
|
from app.models import Prediction, Variant
|
|
|
|
_model = None
|
|
|
|
|
|
def load_model():
|
|
global _model
|
|
if _model is None:
|
|
mlflow.set_tracking_uri(settings.mlflow_tracking_uri)
|
|
_model = mlflow.pyfunc.load_model(f"models:/{settings.model_name}/{settings.model_stage}")
|
|
return _model
|
|
|
|
|
|
def featurise(variants: list[Variant]) -> pd.DataFrame:
|
|
# Mirror ml/rarelens_ml/features.py exactly; shared package later.
|
|
return pd.DataFrame(
|
|
{
|
|
"impact": [v.impact for v in variants],
|
|
"consequence": [v.consequence for v in variants],
|
|
"gnomad_af": [v.gnomad_af if v.gnomad_af is not None else 0.0 for v in variants],
|
|
"cadd_phred": [v.annotations.get("CADD_PHRED") for v in variants],
|
|
"am_pathogenicity": [v.annotations.get("am_pathogenicity") for v in variants],
|
|
}
|
|
)
|
|
|
|
|
|
async def score_job(job_id: uuid.UUID, session: AsyncSession) -> int:
|
|
variants = (await session.scalars(select(Variant).where(Variant.job_id == job_id))).all()
|
|
if not variants:
|
|
return 0
|
|
model = load_model()
|
|
scores = model.predict(featurise(variants))
|
|
for v, s in zip(variants, scores):
|
|
session.add(Prediction(variant_id=v.id, model_name=settings.model_name,
|
|
model_version=settings.model_stage, score=float(s)))
|
|
await session.commit()
|
|
return len(variants)
|