Make chain search use lazy node lookups

backend/app/protein/tsv_loader.py

@@ -8,6 +8,7 @@ key the first occurrence is kept.
 import ast
 import sqlite3
 import logging
+from functools import lru_cache
 from typing import Dict, List, Optional, Tuple, Any
 
 from app.protein.config import get_database_path
@@ -74,6 +75,27 @@ def reset_index() -> None:
     """Force reload of node index."""
     global _index
     _index = None
+    _lookup_node_row.cache_clear()
+
+
+@lru_cache(maxsize=4096)
+def _lookup_node_row(pdb_id: str, auth_asym_id: str) -> Optional[_Row]:
+    """Read one node row without blocking on a full-table in-memory index."""
+    conn = connect_readonly(get_database_path())
+    try:
+        conn.row_factory = sqlite3.Row
+        row = conn.execute(
+            'SELECT base_label, sequence, sequence_length, CATH_ID, cath_superfamily,'
+            '       Rosetta, FoldX, EvoEF2, RM, "RM+", ranked_functions,'
+            '       state_id, experimental_method, pH, temp_K'
+            ' FROM node WHERE LOWER(pdb_id) = ? AND UPPER(auth_asym_id) = ? LIMIT 1',
+            (pdb_id.lower(), auth_asym_id.upper()),
+        ).fetchone()
+        if row is None:
+            return None
+        return {key: row[key] or "" for key in row.keys()}
+    finally:
+        conn.close()
 
 
 def _parse_functions(raw: str) -> List[str]:
@@ -90,7 +112,7 @@ def _parse_functions(raw: str) -> List[str]:
 
 
 def _parse_float(val: str) -> Optional[float]:
-    val = val.strip()
+    val = str(val).strip()
     if not val:
         return None
     try:
@@ -101,8 +123,7 @@ def _parse_float(val: str) -> Optional[float]:
 
 def get_energy_scores(pdb_id: str, auth_asym_id: str) -> Optional[Dict[str, Any]]:
     """Return energy scores (Rosetta, FoldX, EvoEF2, RM, RM+) or None if not found."""
-    key = (pdb_id.lower(), auth_asym_id.upper())
-    row = _get_index().get(key)
+    row = get_node_row(pdb_id, auth_asym_id)
     if row is None:
         return None
     return {
@@ -116,13 +137,13 @@ def get_energy_scores(pdb_id: str, auth_asym_id: str) -> Optional[Dict[str, Any]
 
 def get_node_row(pdb_id: str, auth_asym_id: str) -> Optional[_Row]:
     """Return the cached node row for a chain."""
-    return _get_index().get((pdb_id.lower(), auth_asym_id.upper()))
+    key = (pdb_id.lower(), auth_asym_id.upper())
+    return _index.get(key) if _index is not None else _lookup_node_row(*key)
 
 
 def get_binding_status(pdb_id: str, auth_asym_id: str) -> Optional[str]:
     """Return binding status (base_label: apo/holo) or None if not found."""
-    key = (pdb_id.lower(), auth_asym_id.upper())
-    row = _get_index().get(key)
+    row = get_node_row(pdb_id, auth_asym_id)
     if row is None:
         return None
     return row.get("base_label") or None
@@ -130,8 +151,7 @@ def get_binding_status(pdb_id: str, auth_asym_id: str) -> Optional[str]:
 
 def get_cath_id(pdb_id: str, auth_asym_id: str) -> Optional[str]:
     """Return CATH_ID or 'uncategorized' if not found."""
-    key = (pdb_id.lower(), auth_asym_id.upper())
-    row = _get_index().get(key)
+    row = get_node_row(pdb_id, auth_asym_id)
     if row is None:
         return "uncategorized"
     val = row.get("CATH_ID", "").strip()
@@ -140,8 +160,7 @@ def get_cath_id(pdb_id: str, auth_asym_id: str) -> Optional[str]:
 
 def get_cath_superfamily(pdb_id: str, auth_asym_id: str) -> Optional[str]:
     """Return CATH superfamily code (e.g. '3.40.190.10') or None if not found."""
-    key = (pdb_id.lower(), auth_asym_id.upper())
-    row = _get_index().get(key)
+    row = get_node_row(pdb_id, auth_asym_id)
     if row is None:
         return None
     val = row.get("cath_superfamily", "").strip()
@@ -150,8 +169,7 @@ def get_cath_superfamily(pdb_id: str, auth_asym_id: str) -> Optional[str]:
 
 def get_sequence(pdb_id: str, auth_asym_id: str) -> Tuple[Optional[str], Optional[int]]:
     """Return (seq_can, sequence_length) from node table, or (None, None) if not found."""
-    key = (pdb_id.lower(), auth_asym_id.upper())
-    row = _get_index().get(key)
+    row = get_node_row(pdb_id, auth_asym_id)
     if row is None:
         return None, None
     seq = row["sequence"] or None
@@ -164,8 +182,7 @@ def get_sequence(pdb_id: str, auth_asym_id: str) -> Tuple[Optional[str], Optiona
 
 def get_functions(pdb_id: str, auth_asym_id: str) -> Optional[List[str]]:
     """Return ranked function list for a chain, or None if not in node table."""
-    key = (pdb_id.lower(), auth_asym_id.upper())
-    row = _get_index().get(key)
+    row = get_node_row(pdb_id, auth_asym_id)
     if row is None:
         return None
     return _parse_functions(row["ranked_functions"])
@@ -173,8 +190,7 @@ def get_functions(pdb_id: str, auth_asym_id: str) -> Optional[List[str]]:
 
 def get_state_id(pdb_id: str, auth_asym_id: str) -> Optional[str]:
     """Return state_id for a chain, or None if not found."""
-    key = (pdb_id.lower(), auth_asym_id.upper())
-    row = _get_index().get(key)
+    row = get_node_row(pdb_id, auth_asym_id)
     if row is None:
         return None
     val = row.get("state_id", "").strip()