chore(training): modernize fingerprints to MorganGenerator

Shared rdFingerprintGenerator.GetMorganGenerator across train/predict/app; identical bits, AUROCs unchanged; clears the deprecation warning.

Author: rvnminers-A-and-N

training/app.py

@@ -28,13 +28,14 @@
 from fastapi.responses import HTMLResponse
 from pydantic import BaseModel
 from rdkit import Chem
-from rdkit.Chem import AllChem, DataStructs
+from rdkit.Chem import DataStructs, rdFingerprintGenerator
 
 import predict as P  # reuse the unified flavor read
 
 app = FastAPI(title="Flavor Workbench (demo)")
 
 _FPS, _SMI, _KNOWN = [], [], []
+_MORGAN = rdFingerprintGenerator.GetMorganGenerator(radius=2, fpSize=2048)
 
 
 def _build_index():
@@ -48,7 +49,7 @@ def _build_index():
         mol = Chem.MolFromSmiles(r["smiles"])
         if mol is None:
             continue
-        _FPS.append(AllChem.GetMorganFingerprintAsBitVect(mol, 2, nBits=2048))
+        _FPS.append(_MORGAN.GetFingerprint(mol))
         _SMI.append(r["smiles"])
         _KNOWN.append([t for t in basic if r[t] == 1])
     print(f"substitution index built: {len(_FPS)} molecules")
@@ -92,7 +93,7 @@ def api_neighbors(q: Query):
     if not smi or not _FPS:
         return {"neighbors": []}
     mol = Chem.MolFromSmiles(smi)
-    fp = AllChem.GetMorganFingerprintAsBitVect(mol, 2, nBits=2048)
+    fp = _MORGAN.GetFingerprint(mol)
     sims = DataStructs.BulkTanimotoSimilarity(fp, _FPS)
     self_smi = Chem.MolToSmiles(mol)
     ranked = sorted(range(len(sims)), key=lambda i: sims[i], reverse=True)

training/predict.py

@@ -48,9 +48,10 @@
 import joblib
 import numpy as np
 from rdkit import Chem
-from rdkit.Chem import AllChem, Crippen, DataStructs, Descriptors, rdMolDescriptors
+from rdkit.Chem import Crippen, DataStructs, Descriptors, rdFingerprintGenerator, rdMolDescriptors
 
 FP_BITS, FP_RADIUS = 2048, 2
+_MORGAN = rdFingerprintGenerator.GetMorganGenerator(radius=FP_RADIUS, fpSize=FP_BITS)
 TASTE = Path("taste_models")
 
 ACID_SMARTS = {
@@ -234,7 +235,7 @@ def _measured(mol):
 
 
 def _fp(mol):
-    bv = AllChem.GetMorganFingerprintAsBitVect(mol, FP_RADIUS, nBits=FP_BITS)
+    bv = _MORGAN.GetFingerprint(mol)
     arr = np.zeros((FP_BITS,), dtype=np.int8)
     DataStructs.ConvertToNumpyArray(bv, arr)
     return arr.reshape(1, -1)

training/train_taste.py

@@ -21,7 +21,7 @@
 import numpy as np
 import pandas as pd
 from rdkit import Chem
-from rdkit.Chem import AllChem, DataStructs
+from rdkit.Chem import DataStructs, rdFingerprintGenerator
 from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import roc_auc_score, r2_score
@@ -31,6 +31,7 @@
 # handled in predict.py and never trained — regardless of how much data accrues.
 RULE_TASTES = {"sour", "salty"}
 FP_BITS, FP_RADIUS = 2048, 2
+_MORGAN = rdFingerprintGenerator.GetMorganGenerator(radius=FP_RADIUS, fpSize=FP_BITS)
 # Below this, a taste is too thin for an HONEST head, so it's skipped and
 # handled by rule/flag instead. It's not a hard exclusion: add more data (more
 # sources) and the taste crosses the line and trains itself on the next run.
@@ -55,7 +56,7 @@ def fp(smiles):
     mol = Chem.MolFromSmiles(smiles)
     if mol is None:
         return None
-    bv = AllChem.GetMorganFingerprintAsBitVect(mol, FP_RADIUS, nBits=FP_BITS)
+    bv = _MORGAN.GetFingerprint(mol)
     arr = np.zeros((FP_BITS,), dtype=np.int8)
     DataStructs.ConvertToNumpyArray(bv, arr)
     return arr