Initial release: rarelens platform skeleton (AGPL-3.0)

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.

ml/Dockerfile

@@ -0,0 +1,7 @@
+FROM python:3.12-slim
+WORKDIR /ml
+RUN pip install --no-cache-dir uv
+COPY pyproject.toml .
+RUN uv pip install --system -e .
+COPY rarelens_ml ./rarelens_ml
+ENTRYPOINT ["python", "-m", "rarelens_ml.train"]

ml/pyproject.toml

@@ -0,0 +1,8 @@
+[project]
+name = "rarelens-ml"
+version = "0.1.0"
+requires-python = ">=3.12"
+dependencies = ["lightgbm>=4.5", "mlflow>=2.16", "pandas", "scikit-learn", "sqlalchemy", "psycopg[binary]"]
+
+[project.optional-dependencies]
+gpu = ["torch"]   # for the optional deep-learning baseline on GPU

ml/rarelens_ml/features.py

@@ -0,0 +1,16 @@
+"""Feature engineering shared by training and serving. Keep this identical to api/app/services/scoring.py."""
+import pandas as pd
+
+IMPACT_ORDER = {"MODIFIER": 0, "LOW": 1, "MODERATE": 2, "HIGH": 3}
+CATEGORICAL = ["consequence"]
+NUMERIC = ["impact_rank", "gnomad_af", "cadd_phred", "am_pathogenicity"]
+
+
+def build(df: pd.DataFrame) -> pd.DataFrame:
+    out = pd.DataFrame()
+    out["impact_rank"] = df["impact"].map(IMPACT_ORDER).fillna(0)
+    out["gnomad_af"] = pd.to_numeric(df["gnomad_af"], errors="coerce").fillna(0.0)
+    out["cadd_phred"] = pd.to_numeric(df["cadd_phred"], errors="coerce")
+    out["am_pathogenicity"] = pd.to_numeric(df["am_pathogenicity"], errors="coerce")
+    out["consequence"] = df["consequence"].astype("category")
+    return out

ml/rarelens_ml/train.py

@@ -0,0 +1,55 @@
+"""Train a pathogenicity classifier on ClinVar labels (Pathogenic/Likely pathogenic vs Benign/Likely benign).
+
+Label leakage warning: CLIN_SIG must never be a feature. This is a learning exercise, not a clinical model.
+Usage: python -m rarelens_ml.train --tsv results/clinvar.vep.tsv
+"""
+import argparse
+
+import lightgbm as lgb
+import mlflow
+import mlflow.lightgbm
+import pandas as pd
+from sklearn.metrics import average_precision_score, roc_auc_score
+from sklearn.model_selection import train_test_split
+
+from rarelens_ml.features import build
+
+POS = {"Pathogenic", "Likely_pathogenic", "Pathogenic/Likely_pathogenic"}
+NEG = {"Benign", "Likely_benign", "Benign/Likely_benign"}
+
+
+def load(tsv: str) -> tuple[pd.DataFrame, pd.Series]:
+    df = pd.read_csv(tsv, sep="\t", comment="#", header=None, dtype=str)
+    with open(tsv) as fh:
+        df.columns = next(l for l in fh if l.startswith("#Uploaded")).lstrip("#").rstrip().split("\t")
+    df = df.rename(columns={"IMPACT": "impact", "Consequence": "consequence", "gnomADe_AF": "gnomad_af",
+                            "CADD_PHRED": "cadd_phred"})
+    y = df["CLIN_SIG"].map(lambda s: 1 if s in POS else 0 if s in NEG else None)
+    keep = y.notna()
+    return build(df[keep]), y[keep].astype(int)
+
+
+def main() -> None:
+    p = argparse.ArgumentParser()
+    p.add_argument("--tsv", required=True)
+    p.add_argument("--register", action="store_true")
+    a = p.parse_args()
+
+    X, y = load(a.tsv)
+    Xtr, Xte, ytr, yte = train_test_split(X, y, test_size=0.2, stratify=y, random_state=42)
+
+    mlflow.set_experiment("rarelens-pathogenicity")
+    with mlflow.start_run():
+        params = {"n_estimators": 400, "learning_rate": 0.05, "num_leaves": 31, "class_weight": "balanced"}
+        mlflow.log_params(params)
+        model = lgb.LGBMClassifier(**params).fit(Xtr, ytr)
+        proba = model.predict_proba(Xte)[:, 1]
+        mlflow.log_metrics({"auroc": roc_auc_score(yte, proba), "auprc": average_precision_score(yte, proba)})
+        mlflow.lightgbm.log_model(
+            model, "model",
+            registered_model_name="rarelens-pathogenicity" if a.register else None,
+        )
+
+
+if __name__ == "__main__":
+    main()