Kemal Yaylali
197975cc42
"Variants are unscored" was accurate: nothing was ever trained, so a quarter of every rank was dead weight and the UI leaked a connection error at the reader. - scripts/make-training-set.sh derives a training table from ClinVar directly. ClinVar already carries the molecular consequence, the gene and an allele frequency, which is the feature set serving sends, so this avoids running VEP over hundreds of thousands of variants. 2-star records only. - train.py now holds out whole genes (GroupShuffleSplit). docs/data.md had said to do this since the data pass; the code was still doing a random split, which is the leak Grimm 2015 describes. - evaluate() reports missense on its own. On the last run: AUROC 0.986 over 74,239 held-out variants, but 0.872 over the 13,553 missense ones, and the docs say plainly why even that is flattered — within missense the only live feature is allele frequency, and ClinVar's benign calls often use allele frequency as evidence (ACMG BA1/BS1), so the feature partly caused the label. - the 503 now names what is missing (model@alias via tracking URI) and leaves the exception in the server log instead of the UI. - make training-set / make train; the 58 MB table is gitignored. Verified end to end: model registered as v2, the simulated NF2 case scores 0.999 on the planted variant, and it now ranks 1.00 with all four components live. Tests: api 77, ml 22, loader 16, web 32; ruff, mypy, svelte-check clean.
92 lines
4.1 KiB
Makefile
92 lines
4.1 KiB
Makefile
.PHONY: up down clean migrate test lint data hpo demo-case training-set train loader pipeline annotate images kind serverless-deploy serverless-destroy gcp-configure gcp-secrets
|
|
|
|
VCF ?= data/example.vcf.gz
|
|
MLFLOW_URI ?= http://localhost:5001
|
|
TAG ?= latest
|
|
# The loader container reaches docker-compose's Postgres through the host.
|
|
HOST_DB_URL ?= postgresql://rarelens:[email protected]:5432/rarelens
|
|
|
|
up:
|
|
docker compose up -d --build
|
|
|
|
down:
|
|
docker compose down
|
|
|
|
clean: ## also deletes the Postgres and MLflow volumes
|
|
docker compose down -v
|
|
|
|
migrate:
|
|
docker compose exec api alembic upgrade head
|
|
|
|
test:
|
|
cd api && uv run --extra dev pytest -q
|
|
cd ml && uv run --extra dev pytest -q
|
|
cd pipeline && uv run --no-project --with-requirements requirements.txt --with pytest --with pgserver pytest -q tests
|
|
cd web && npm test
|
|
|
|
lint:
|
|
cd api && uv run --extra dev ruff check . && uv run --extra dev mypy app
|
|
cd web && npm run check
|
|
|
|
data: ## download the public demo slice: GIAB HG002 + ClinVar, chr22 (see docs/data.md)
|
|
scripts/fetch-demo-data.sh
|
|
|
|
hpo: ## load HPO gene-to-phenotype annotations, which the ranking matches against
|
|
scripts/load-hpo.py
|
|
|
|
demo-case: ## build the simulated proband: GIAB background + one ClinVar pathogenic variant
|
|
scripts/make-demo-case.sh
|
|
|
|
training-set: ## build a ClinVar training table, shaped like VEP --tab output
|
|
scripts/make-training-set.sh
|
|
|
|
train: ## train the pathogenicity model and point the production alias at it (needs `make up`)
|
|
cd ml && MLFLOW_TRACKING_URI=$(MLFLOW_URI) uv run --extra dev \
|
|
python -m rarelens_ml.train --tsv ../data/clinvar-training.vep.tsv --register
|
|
|
|
loader:
|
|
docker build -t rarelens/loader:dev -f pipeline/loader.Dockerfile pipeline
|
|
|
|
pipeline: loader ## dry run: annotate $(VCF) without touching the database
|
|
cd pipeline && nextflow run main.nf -profile docker --vcf ../$(VCF)
|
|
|
|
annotate: loader ## make annotate JOB=<job id> [VCF=data/x.vcf.gz]
|
|
@test -n "$(JOB)" || (echo "usage: make annotate JOB=<job id> [VCF=...]"; exit 1)
|
|
cd pipeline && DATABASE_URL=$(HOST_DB_URL) nextflow run main.nf -profile docker \
|
|
--vcf ../$(VCF) --job_id $(JOB)
|
|
|
|
images:
|
|
docker build -t rarelens-api:dev api
|
|
docker build -t rarelens-web:dev web
|
|
|
|
kind: images
|
|
kind create cluster --name rarelens 2>/dev/null || true
|
|
kind load docker-image rarelens-api:dev rarelens-web:dev --name rarelens
|
|
kubectl apply -k infra/k8s/overlays/local
|
|
kubectl -n rarelens rollout status deploy/postgres deploy/api deploy/web
|
|
@echo "kubectl -n rarelens port-forward svc/web 8080:80 (UI)"
|
|
@echo "kubectl -n rarelens port-forward svc/api 8000:80 (API, used by the UI)"
|
|
|
|
serverless-deploy: ## deploy the Cloud Run track: make serverless-deploy PROJECT=<id> [TAG=<sha>]
|
|
@test -n "$(PROJECT)" || (echo "usage: make serverless-deploy PROJECT=<gcp project id> [TAG=<image tag>]"; exit 1)
|
|
@test -n "$$TF_VAR_database_url" || echo "note: TF_VAR_database_url is unset; add -var deploy_cloud_sql=true or export a Postgres URL"
|
|
cd infra/terraform && terraform apply -var project=$(PROJECT) -var image_tag=$(TAG)
|
|
|
|
serverless-destroy: ## tear it all down
|
|
cd infra/terraform && terraform destroy -var project=$(PROJECT) -var deletion_protection=false
|
|
|
|
gcp-configure: ## one-time: write your GCP project id into the gcp overlay and Argo manifests
|
|
@test -n "$(PROJECT)" || (echo "usage: make gcp-configure PROJECT=<gcp project id>"; exit 1)
|
|
grep -rl __GCP_PROJECT__ infra/k8s/overlays/gcp infra/argo-workflows \
|
|
| xargs sed -i.bak "s/__GCP_PROJECT__/$(PROJECT)/g"
|
|
find infra -name '*.bak' -delete
|
|
|
|
gcp-secrets: ## after terraform apply: copy DB URLs from Secret Manager into k8s secrets
|
|
@test -n "$(PROJECT)" || (echo "usage: make gcp-secrets PROJECT=<gcp project id>"; exit 1)
|
|
kubectl -n rarelens create secret generic api-secrets --dry-run=client -o yaml \
|
|
--from-literal=DATABASE_URL="$$(gcloud secrets versions access latest --project $(PROJECT) --secret rarelens-api-database-url)" \
|
|
| kubectl apply -f -
|
|
kubectl -n rarelens create secret generic pipeline-secrets --dry-run=client -o yaml \
|
|
--from-literal=DATABASE_URL="$$(gcloud secrets versions access latest --project $(PROJECT) --secret DATABASE_URL)" \
|
|
| kubectl apply -f -
|