Avoid full node index load for filters

backend/app/protein/api/routes/protein.py

@@ -62,7 +62,7 @@ async def get_filters():
     """Get available filter options and ranges."""
     try:
         manager = _require_data_manager()
-        chains = sorted(list(manager.get_all_chains()))
+        chains = sorted(manager.get_chain_sample())
         fd = manager.get_filters_data()
 
         return FilterOptions(

backend/app/protein/data_loader.py

@@ -66,11 +66,22 @@ class DataManager:
             raise RuntimeError("Call load_data() first.")
         return connect_readonly(self.db_path)
 
-    def get_all_chains(self) -> Set[str]:
-        """Return unique A-side chain identifiers as 'PDBID_ChainID' from node table."""
-        from app.protein import tsv_loader
-        index = tsv_loader._get_index()
-        return {f"{pdb.upper()}_{chain}" for pdb, chain in index.keys()}
+    def get_chain_sample(self, limit: int = 500) -> Set[str]:
+        """Return a small chain sample without loading the full node index."""
+        conn = self._connect()
+        try:
+            cur = conn.cursor()
+            cur.execute(
+                "SELECT pdb_id, auth_asym_id FROM node "
+                "WHERE pdb_id IS NOT NULL AND auth_asym_id IS NOT NULL LIMIT ?",
+                (limit,),
+            )
+            return {
+                f"{str(pdb).upper()}_{str(chain).upper()}"
+                for pdb, chain in cur.fetchall()
+            }
+        finally:
+            conn.close()
 
     def get_filters_data(self) -> Dict[str, Any]:
         """Return aggregated ranges for filter UI."""