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/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