removed logging

predict.py

@@ -17,73 +17,67 @@ def predict(smiles_list):
     Returns:
         dict: {smiles: {target_name: prediction_prob}}
     """
-    logging.basicConfig(level=logging.INFO)
-    try:
-        # clean smiles
-        clean_smiles, valid_mask = create_clean_smiles(smiles_list)
-
-        # Mapping from cleaned to original for valid ones
-        originals_valid = [orig for orig, ok in zip(smiles_list, valid_mask) if ok]
-
-        # sanity check (optional but nice to have)
-        if len(originals_valid) != len(clean_smiles):
-            raise ValueError(
-                f"Mismatch: {len(originals_valid)} valid originals vs {len(clean_smiles)} cleaned SMILES"
-            )
-
-        # map cleaned → original
-        cleaned_to_original = dict(zip(clean_smiles, originals_valid))
-        print(len(cleaned_to_original.keys()))
-
-        # tox21 targets
-        TARGET_NAMES = [
-                "NR-AhR","NR-AR","NR-AR-LBD","NR-Aromatase","NR-ER","NR-ER-LBD","NR-PPAR-gamma","SR-ARE","SR-ATAD5","SR-HSE","SR-MMP","SR-p53"
-            ]
-        DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-        print(f"Received {len(smiles_list)} SMILES strings")
-
-        # put smiles into csv
-        with open("./src/smiles.csv", "w", newline="") as f:
-            writer = csv.writer(f)
-            writer.writerow(["smiles"])  # header
-            for smi in clean_smiles:
-                writer.writerow([smi])
-        logging.info("here")
-        # predict
-        command = [
-            "chemprop", "predict",
-            "--test-path", "src/smiles.csv",
-            "--model-path", "assets/best1.pt",
-            "--smiles-columns", "smiles",
-            "--preds-path", "src/preds.csv"
-        ]
-
-        # Run the command
-        subprocess.run(command, check=True)
+    # clean smiles
+    clean_smiles, valid_mask = create_clean_smiles(smiles_list)
 
-        # create results dictionary from predictions
+    # Mapping from cleaned to original for valid ones
+    originals_valid = [orig for orig, ok in zip(smiles_list, valid_mask) if ok]
 
-        csv_path = "./src/preds.csv"
+    # sanity check (optional but nice to have)
+    if len(originals_valid) != len(clean_smiles):
+        raise ValueError(
+            f"Mismatch: {len(originals_valid)} valid originals vs {len(clean_smiles)} cleaned SMILES"
+        )
 
-        predictions = {}
-        with open("./src/preds.csv", "r", newline="") as f:
-            reader = csv.DictReader(f)
-            rows = list(reader)
-            target_names = [col for col in reader.fieldnames if col != "smiles"]
+    # map cleaned → original
+    cleaned_to_original = dict(zip(clean_smiles, originals_valid))
 
-            for row in rows:
-                clean_smi = row["smiles"]
-                original_smi = cleaned_to_original.get(clean_smi, clean_smi)
-                pred_dict = {t: float(row[t]) for t in target_names}
-                predictions[original_smi] = pred_dict
-
-        # Add placeholder predictions for invalid SMILES
-        for smi, is_valid in zip(smiles_list, valid_mask):
-            if not is_valid:
-                predictions[smi] = {t: 0.0 for t in TARGET_NAMES}
+    # tox21 targets
+    TARGET_NAMES = [
+            "NR-AhR","NR-AR","NR-AR-LBD","NR-Aromatase","NR-ER","NR-ER-LBD","NR-PPAR-gamma","SR-ARE","SR-ATAD5","SR-HSE","SR-MMP","SR-p53"
+        ]
+    DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    print(f"Received {len(smiles_list)} SMILES strings")
+
+    # put smiles into csv
+    with open("./src/smiles.csv", "w", newline="") as f:
+        writer = csv.writer(f)
+        writer.writerow(["smiles"])  # header
+        for smi in clean_smiles:
+            writer.writerow([smi])
+    logging.info("here")
+    # predict
+    command = [
+        "chemprop", "predict",
+        "--test-path", "src/smiles.csv",
+        "--model-path", "assets/best1.pt",
+        "--smiles-columns", "smiles",
+        "--preds-path", "src/preds.csv"
+    ]
+
+    # Run the command
+    subprocess.run(command, check=True)
+
+    # create results dictionary from predictions
+
+    csv_path = "./src/preds.csv"
+
+    predictions = {}
+    with open("./src/preds.csv", "r", newline="") as f:
+        reader = csv.DictReader(f)
+        rows = list(reader)
+        target_names = [col for col in reader.fieldnames if col != "smiles"]
+
+        for row in rows:
+            clean_smi = row["smiles"]
+            original_smi = cleaned_to_original.get(clean_smi, clean_smi)
+            pred_dict = {t: float(row[t]) for t in target_names}
+            predictions[original_smi] = pred_dict
+
+    # Add placeholder predictions for invalid SMILES
+    for smi, is_valid in zip(smiles_list, valid_mask):
+        if not is_valid:
+            predictions[smi] = {t: 0.0 for t in TARGET_NAMES}
         
-    except Exception as e:
-        logging.error(f"Error: {e}")
-        return
 
     return predictions