workbench 0.8.172__py3-none-any.whl → 0.8.173__py3-none-any.whl

workbench/model_scripts/custom_models/uq_models/generated_model_script.py

@@ -1,7 +1,7 @@
-# Model: XGBoost for point predictions + LightGBM with MAPIE for conformalized intervals
-from mapie.regression import ConformalizedQuantileRegressor
-from lightgbm import LGBMRegressor
-from xgboost import XGBRegressor
+# Model: NGBoost Regressor with Distribution output
+from ngboost import NGBRegressor
+from ngboost.distns import Cauchy, T
+from xgboost import XGBRegressor  # Point Estimator
 from sklearn.model_selection import train_test_split
 
 # Model Performance Scores
@@ -20,12 +20,19 @@ import numpy as np
 import pandas as pd
 from typing import List, Tuple
 
+# Local Imports
+from proximity import Proximity
+
+
+
 # Template Placeholders
 TEMPLATE_PARAMS = {
+    "id_column": "udm_mol_id",
     "target": "udm_asy_res_value",
     "features": ['bcut2d_logplow', 'numradicalelectrons', 'smr_vsa5', 'fr_lactam', 'fr_morpholine', 'fr_aldehyde', 'slogp_vsa1', 'fr_amidine', 'bpol', 'fr_ester', 'fr_azo', 'kappa3', 'peoe_vsa5', 'fr_ketone_topliss', 'vsa_estate9', 'estate_vsa9', 'bcut2d_mrhi', 'fr_ndealkylation1', 'numrotatablebonds', 'minestateindex', 'fr_quatn', 'peoe_vsa3', 'fr_epoxide', 'fr_aniline', 'minpartialcharge', 'fr_nitroso', 'fpdensitymorgan2', 'fr_oxime', 'fr_sulfone', 'smr_vsa1', 'kappa1', 'fr_pyridine', 'numaromaticrings', 'vsa_estate6', 'molmr', 'estate_vsa1', 'fr_dihydropyridine', 'vsa_estate10', 'fr_alkyl_halide', 'chi2n', 'fr_thiocyan', 'fpdensitymorgan1', 'fr_unbrch_alkane', 'slogp_vsa9', 'chi4n', 'fr_nitro_arom', 'fr_al_oh', 'fr_furan', 'fr_c_s', 'peoe_vsa8', 'peoe_vsa14', 'numheteroatoms', 'fr_ndealkylation2', 'maxabspartialcharge', 'vsa_estate2', 'peoe_vsa7', 'apol', 'numhacceptors', 'fr_tetrazole', 'vsa_estate1', 'peoe_vsa9', 'naromatom', 'bcut2d_chghi', 'fr_sh', 'fr_halogen', 'slogp_vsa4', 'fr_benzodiazepine', 'molwt', 'fr_isocyan', 'fr_prisulfonamd', 'maxabsestateindex', 'minabsestateindex', 'peoe_vsa11', 'slogp_vsa12', 'estate_vsa5', 'numaliphaticcarbocycles', 'bcut2d_mwlow', 'slogp_vsa7', 'fr_allylic_oxid', 'fr_methoxy', 'fr_nh0', 'fr_coo2', 'fr_phenol', 'nacid', 'nbase', 'chi3v', 'fr_ar_nh', 'fr_nitrile', 'fr_imidazole', 'fr_urea', 'bcut2d_mrlow', 'chi1', 'smr_vsa6', 'fr_aryl_methyl', 'narombond', 'fr_alkyl_carbamate', 'fr_piperzine', 'exactmolwt', 'qed', 'chi0n', 'fr_sulfonamd', 'fr_thiazole', 'numvalenceelectrons', 'fr_phos_acid', 'peoe_vsa12', 'fr_nh1', 'fr_hdrzine', 'fr_c_o_nocoo', 'fr_lactone', 'estate_vsa6', 'bcut2d_logphi', 'vsa_estate7', 'peoe_vsa13', 'numsaturatedcarbocycles', 'fr_nitro', 'fr_phenol_noorthohbond', 'rotratio', 'fr_barbitur', 'fr_isothiocyan', 'balabanj', 'fr_arn', 'fr_imine', 'maxpartialcharge', 'fr_sulfide', 'slogp_vsa11', 'fr_hoccn', 'fr_n_o', 'peoe_vsa1', 'slogp_vsa6', 'heavyatommolwt', 'fractioncsp3', 'estate_vsa8', 'peoe_vsa10', 'numaliphaticrings', 'fr_thiophene', 'maxestateindex', 'smr_vsa10', 'labuteasa', 'smr_vsa2', 'fpdensitymorgan3', 'smr_vsa9', 'slogp_vsa10', 'numaromaticheterocycles', 'fr_nh2', 'fr_diazo', 'chi3n', 'fr_ar_coo', 'slogp_vsa5', 'fr_bicyclic', 'fr_amide', 'estate_vsa10', 'fr_guanido', 'chi1n', 'numsaturatedrings', 'fr_piperdine', 'fr_term_acetylene', 'estate_vsa4', 'slogp_vsa3', 'fr_coo', 'fr_ether', 'estate_vsa7', 'bcut2d_chglo', 'fr_oxazole', 'peoe_vsa6', 'hallkieralpha', 'peoe_vsa2', 'chi2v', 'nocount', 'vsa_estate5', 'fr_nhpyrrole', 'fr_al_coo', 'bertzct', 'estate_vsa11', 'minabspartialcharge', 'slogp_vsa8', 'fr_imide', 'kappa2', 'numaliphaticheterocycles', 'numsaturatedheterocycles', 'fr_hdrzone', 'smr_vsa4', 'fr_ar_n', 'nrot', 'smr_vsa8', 'slogp_vsa2', 'chi4v', 'fr_phos_ester', 'fr_para_hydroxylation', 'smr_vsa3', 'nhohcount', 'estate_vsa2', 'mollogp', 'tpsa', 'fr_azide', 'peoe_vsa4', 'numhdonors', 'fr_al_oh_notert', 'fr_c_o', 'chi0', 'fr_nitro_arom_nonortho', 'vsa_estate3', 'fr_benzene', 'fr_ketone', 'vsa_estate8', 'smr_vsa7', 'fr_ar_oh', 'fr_priamide', 'ringcount', 'estate_vsa3', 'numaromaticcarbocycles', 'bcut2d_mwhi', 'chi1v', 'heavyatomcount', 'vsa_estate4', 'chi0v', 'chiral_centers', 'r_cnt', 's_cnt', 'db_stereo', 'e_cnt', 'z_cnt', 'chiral_fp', 'db_fp'],
     "compressed_features": [],
-    "train_all_data": True
+    "train_all_data": False,
+    "track_columns": "udm_asy_res_value"
 }
 
 
@@ -101,7 +108,7 @@ def convert_categorical_types(df: pd.DataFrame, features: list, category_mapping
 
 
 def decompress_features(
-        df: pd.DataFrame, features: List[str], compressed_features: List[str]
+    df: pd.DataFrame, features: List[str], compressed_features: List[str]
 ) -> Tuple[pd.DataFrame, List[str]]:
     """Prepare features for the model by decompressing bitstring features
 
@@ -157,11 +164,13 @@ def decompress_features(
 
 if __name__ == "__main__":
     # Template Parameters
+    id_column = TEMPLATE_PARAMS["id_column"]
     target = TEMPLATE_PARAMS["target"]
     features = TEMPLATE_PARAMS["features"]
     orig_features = features.copy()
     compressed_features = TEMPLATE_PARAMS["compressed_features"]
     train_all_data = TEMPLATE_PARAMS["train_all_data"]
+    track_columns = TEMPLATE_PARAMS["track_columns"]  # Can be None
     validation_split = 0.2
 
     # Script arguments for input/output directories
@@ -219,175 +228,78 @@ if __name__ == "__main__":
     print(f"FIT/TRAIN: {df_train.shape}")
     print(f"VALIDATION: {df_val.shape}")
 
+    # We're using XGBoost for point predictions and NGBoost for uncertainty quantification
+    xgb_model = XGBRegressor()
+    ngb_model = NGBRegressor()  # Dist=Cauchy) Seems to give HUGE prediction intervals
+    ngb_model = NGBRegressor(
+        Dist=T,
+        learning_rate=0.005,
+        minibatch_frac=0.1,  # Very small batches
+        col_sample=0.8  # This parameter DOES exist
+    ) # Testing this out
+    print("NGBoost using T distribution for uncertainty quantification")
+
     # Prepare features and targets for training
     X_train = df_train[features]
     X_validate = df_val[features]
     y_train = df_train[target]
     y_validate = df_val[target]
 
-    # Train XGBoost for point predictions
-    print("\nTraining XGBoost for point predictions...")
-    xgb_model = XGBRegressor(
-        n_estimators=1000,
-        max_depth=6,
-        learning_rate=0.01,
-        subsample=0.8,
-        colsample_bytree=0.8,
-        random_state=42,
-        verbosity=0
-    )
+    # Train both models using the training data
     xgb_model.fit(X_train, y_train)
-
-    # Evaluate XGBoost performance
-    y_pred_xgb = xgb_model.predict(X_validate)
-    xgb_rmse = root_mean_squared_error(y_validate, y_pred_xgb)
-    xgb_mae = mean_absolute_error(y_validate, y_pred_xgb)
-    xgb_r2 = r2_score(y_validate, y_pred_xgb)
-
-    print(f"\nXGBoost Point Prediction Performance:")
-    print(f"RMSE: {xgb_rmse:.3f}")
-    print(f"MAE: {xgb_mae:.3f}")
-    print(f"R2: {xgb_r2:.3f}")
-
-    # Define confidence levels we want to model
-    confidence_levels = [0.50, 0.80, 0.90, 0.95]  # 50%, 80%, 90%, 95% confidence intervals
-
-    # Store MAPIE models for each confidence level
-    mapie_models = {}
-
-    # Train models for each confidence level
-    for confidence_level in confidence_levels:
-        alpha = 1 - confidence_level
-        lower_q = alpha / 2
-        upper_q = 1 - alpha / 2
-
-        print(f"\nTraining quantile models for {confidence_level * 100:.0f}% confidence interval...")
-        print(f"  Quantiles: {lower_q:.3f}, {upper_q:.3f}, 0.500")
-
-        # Train three models for this confidence level
-        quantile_estimators = []
-        for q in [lower_q, upper_q, 0.5]:
-            print(f"    Training model for quantile {q:.3f}...")
-            est = LGBMRegressor(
-                objective="quantile",
-                alpha=q,
-                n_estimators=1000,
-                max_depth=6,
-                learning_rate=0.01,
-                num_leaves=31,
-                min_child_samples=20,
-                subsample=0.8,
-                colsample_bytree=0.8,
-                random_state=42,
-                verbose=-1,
-                force_col_wise=True
-            )
-            est.fit(X_train, y_train)
-            quantile_estimators.append(est)
-
-        # Create MAPIE CQR model for this confidence level
-        print(f"  Setting up MAPIE CQR for {confidence_level * 100:.0f}% confidence...")
-        mapie_model = ConformalizedQuantileRegressor(
-            quantile_estimators,
-            confidence_level=confidence_level,
-            prefit=True
-        )
-
-        # Conformalize the model
-        print(f"  Conformalizing with validation data...")
-        mapie_model.conformalize(X_validate, y_validate)
-
-        # Store the model
-        mapie_models[f"mapie_{confidence_level:.2f}"] = mapie_model
-
-        # Validate coverage for this confidence level
-        y_pred, y_pis = mapie_model.predict_interval(X_validate)
-        coverage = np.mean((y_validate >= y_pis[:, 0, 0]) & (y_validate <= y_pis[:, 1, 0]))
-        print(f"  Coverage: Target={confidence_level * 100:.0f}%, Empirical={coverage * 100:.1f}%")
-
-    print(f"\nOverall Model Performance Summary:")
-    print(f"XGBoost RMSE: {xgb_rmse:.3f}")
-    print(f"XGBoost MAE: {xgb_mae:.3f}")
-    print(f"XGBoost R2: {xgb_r2:.3f}")
+    ngb_model.fit(X_train, y_train, X_val=X_validate, Y_val=y_validate)
+
+    # Make Predictions on the Validation Set
+    print(f"Making Predictions on Validation Set...")
+    preds = xgb_model.predict(X_validate)
+
+    # Calculate various model performance metrics (regression)
+    rmse = root_mean_squared_error(y_validate, preds)
+    mae = mean_absolute_error(y_validate, preds)
+    r2 = r2_score(y_validate, preds)
+    print(f"RMSE: {rmse:.3f}")
+    print(f"MAE: {mae:.3f}")
+    print(f"R2: {r2:.3f}")
     print(f"NumRows: {len(df_val)}")
 
-    # Analyze interval widths across confidence levels
-    print(f"\nInterval Width Analysis:")
-    for conf_level in confidence_levels:
-        model = mapie_models[f"mapie_{conf_level:.2f}"]
-        _, y_pis = model.predict_interval(X_validate)
-        widths = y_pis[:, 1, 0] - y_pis[:, 0, 0]
-        print(f"  {conf_level * 100:.0f}% CI: Mean width={np.mean(widths):.3f}, Std={np.std(widths):.3f}")
-
     # Save the trained XGBoost model
     xgb_model.save_model(os.path.join(args.model_dir, "xgb_model.json"))
 
-    # Save all MAPIE models
-    for model_name, model in mapie_models.items():
-        joblib.dump(model, os.path.join(args.model_dir, f"{model_name}.joblib"))
+    # Save the trained NGBoost model
+    joblib.dump(ngb_model, os.path.join(args.model_dir, "ngb_model.joblib"))
 
-    # Save the feature list
+    # Save the features (this will validate input during predictions)
     with open(os.path.join(args.model_dir, "feature_columns.json"), "w") as fp:
-        json.dump(features, fp)
-
-    # Save category mappings if any
-    if category_mappings:
-        with open(os.path.join(args.model_dir, "category_mappings.json"), "w") as fp:
-            json.dump(category_mappings, fp)
-
-    # Save model configuration
-    model_config = {
-        "model_type": "XGBoost_MAPIE_CQR_LightGBM",
-        "confidence_levels": confidence_levels,
-        "n_features": len(features),
-        "target": target,
-        "validation_metrics": {
-            "xgb_rmse": float(xgb_rmse),
-            "xgb_mae": float(xgb_mae),
-            "xgb_r2": float(xgb_r2),
-            "n_validation": len(df_val)
-        }
-    }
-    with open(os.path.join(args.model_dir, "model_config.json"), "w") as fp:
-        json.dump(model_config, fp, indent=2)
+        json.dump(orig_features, fp)  # We save the original features, not the decompressed ones
+
+    # Now the Proximity model
+    model = Proximity(df_train, id_column, features, target, track_columns=track_columns)
 
-    print(f"\nModel training complete!")
-    print(f"Saved 1 XGBoost model and {len(mapie_models)} MAPIE models to {args.model_dir}")
+    # Now serialize the model
+    model.serialize(args.model_dir)
 
 
 #
 # Inference Section
 #
 def model_fn(model_dir) -> dict:
-    """Load XGBoost and all MAPIE models from the specified directory."""
-
-    # Load model configuration to know which models to load
-    with open(os.path.join(model_dir, "model_config.json")) as fp:
-        config = json.load(fp)
+    """Load and return XGBoost, NGBoost, and Prox Model from model directory."""
 
     # Load XGBoost regressor
     xgb_path = os.path.join(model_dir, "xgb_model.json")
     xgb_model = XGBRegressor(enable_categorical=True)
     xgb_model.load_model(xgb_path)
 
-    # Load all MAPIE models
-    mapie_models = {}
-    for conf_level in config["confidence_levels"]:
-        model_name = f"mapie_{conf_level:.2f}"
-        mapie_models[model_name] = joblib.load(os.path.join(model_dir, f"{model_name}.joblib"))
+    # Load NGBoost regressor
+    ngb_model = joblib.load(os.path.join(model_dir, "ngb_model.joblib"))
 
-    # Load category mappings if they exist
-    category_mappings = {}
-    category_path = os.path.join(model_dir, "category_mappings.json")
-    if os.path.exists(category_path):
-        with open(category_path) as fp:
-            category_mappings = json.load(fp)
+    # Deserialize the proximity model
+    prox_model = Proximity.deserialize(model_dir)
 
     return {
-        "xgb_model": xgb_model,
-        "mapie_models": mapie_models,
-        "confidence_levels": config["confidence_levels"],
-        "category_mappings": category_mappings
+        "xgboost": xgb_model,
+        "ngboost": ngb_model,
+        "proximity": prox_model
     }
 
 
@@ -403,7 +315,7 @@ def input_fn(input_data, content_type):
     if "text/csv" in content_type:
         return pd.read_csv(StringIO(input_data))
     elif "application/json" in content_type:
-        return pd.DataFrame(json.loads(input_data))
+        return pd.DataFrame(json.loads(input_data))  # Assumes JSON array of records
     else:
         raise ValueError(f"{content_type} not supported!")
 
@@ -411,26 +323,23 @@ def input_fn(input_data, content_type):
 def output_fn(output_df, accept_type):
     """Supports both CSV and JSON output formats."""
     if "text/csv" in accept_type:
-        # Convert categorical columns to string to avoid fillna issues
-        for col in output_df.select_dtypes(include=['category']).columns:
-            output_df[col] = output_df[col].astype(str)
-        csv_output = output_df.fillna("N/A").to_csv(index=False)
+        csv_output = output_df.fillna("N/A").to_csv(index=False)  # CSV with N/A for missing values
         return csv_output, "text/csv"
     elif "application/json" in accept_type:
-        return output_df.to_json(orient="records"), "application/json"
+        return output_df.to_json(orient="records"), "application/json"  # JSON array of records (NaNs -> null)
     else:
         raise RuntimeError(f"{accept_type} accept type is not supported by this script.")
 
 
 def predict_fn(df, models) -> pd.DataFrame:
-    """Make predictions using XGBoost for point estimates and MAPIE for conformalized intervals
+    """Make Predictions with our XGB Quantile Regression Model
 
     Args:
         df (pd.DataFrame): The input DataFrame
-        models (dict): Dictionary containing XGBoost and MAPIE models
+        models (dict): The dictionary of models to use for predictions
 
     Returns:
-        pd.DataFrame: DataFrame with XGBoost predictions and conformalized intervals
+        pd.DataFrame: The DataFrame with the predictions added
     """
 
     # Grab our feature columns (from training)
@@ -441,62 +350,44 @@ def predict_fn(df, models) -> pd.DataFrame:
     # Match features in a case-insensitive manner
     matched_df = match_features_case_insensitive(df, model_features)
 
-    # Apply categorical mappings if they exist
-    if models.get("category_mappings"):
-        matched_df, _ = convert_categorical_types(
-            matched_df,
-            model_features,
-            models["category_mappings"]
-        )
+    # Use XGBoost for point predictions
+    df["prediction"] = models["xgboost"].predict(matched_df[model_features])
+
+    # NGBoost predict returns distribution objects
+    y_dists = models["ngboost"].pred_dist(matched_df[model_features])
+
+    # Extract parameters from distribution
+    dist_params = y_dists.params
 
-    # Get features for prediction
-    X = matched_df[model_features]
-
-    # Get XGBoost point predictions
-    df["prediction"] = models["xgb_model"].predict(X)
-
-    # Get predictions from each MAPIE model for conformalized intervals
-    for conf_level in models["confidence_levels"]:
-        model_name = f"mapie_{conf_level:.2f}"
-        model = models["mapie_models"][model_name]
-
-        # Get conformalized predictions
-        y_pred, y_pis = model.predict_interval(X)
-
-        # Map confidence levels to quantile names
-        if conf_level == 0.50:  # 50% CI
-            df["q_25"] = y_pis[:, 0, 0]
-            df["q_75"] = y_pis[:, 1, 0]
-        elif conf_level == 0.80:  # 80% CI
-            df["q_10"] = y_pis[:, 0, 0]
-            df["q_90"] = y_pis[:, 1, 0]
-        elif conf_level == 0.90:  # 90% CI
-            df["q_05"] = y_pis[:, 0, 0]
-            df["q_95"] = y_pis[:, 1, 0]
-        elif conf_level == 0.95:  # 95% CI
-            df["q_025"] = y_pis[:, 0, 0]
-            df["q_975"] = y_pis[:, 1, 0]
-
-    # Add median (q_50) from XGBoost prediction
-    df["q_50"] = df["prediction"]
-
-    # Calculate uncertainty metrics based on 95% interval
-    interval_width = df["q_975"] - df["q_025"]
-    df["prediction_std"] = interval_width / 3.92
+    # Extract mean and std from distribution parameters
+    df["prediction_uq"] = dist_params['loc']  # mean
+    df["prediction_std"] = dist_params['scale']  # standard deviation
+
+    # Add 95% prediction intervals using ppf (percent point function)
+    # Note: Our hybrid model uses XGB point prediction and NGBoost UQ
+    #  so we need to adjust the bounds to include the point prediction
+    df["q_025"] = np.minimum(y_dists.ppf(0.025), df["prediction"])
+    df["q_975"] = np.maximum(y_dists.ppf(0.975), df["prediction"])
+
+    # Add 90% prediction intervals
+    df["q_05"] = y_dists.ppf(0.05)  # 5th percentile
+    df["q_95"] = y_dists.ppf(0.95)  # 95th percentile
+
+    # Add 80% prediction intervals
+    df["q_10"] = y_dists.ppf(0.10)  # 10th percentile
+    df["q_90"] = y_dists.ppf(0.90)  # 90th percentile
+
+    # Add 50% prediction intervals
+    df["q_25"] = y_dists.ppf(0.25)  # 25th percentile
+    df["q_75"] = y_dists.ppf(0.75)  # 75th percentile
 
     # Reorder the quantile columns for easier reading
     quantile_cols = ["q_025", "q_05", "q_10", "q_25", "q_75", "q_90", "q_95", "q_975"]
     other_cols = [col for col in df.columns if col not in quantile_cols]
     df = df[other_cols + quantile_cols]
 
-    # Uncertainty score
-    df["uncertainty_score"] = interval_width / (np.abs(df["prediction"]) + 1e-6)
-
-    # Confidence bands
-    df["confidence_band"] = pd.cut(
-        df["uncertainty_score"],
-        bins=[0, 0.5, 1.0, 2.0, np.inf],
-        labels=["high", "medium", "low", "very_low"]
-    )
+    # Compute Nearest neighbors with Proximity model
+    models["proximity"].neighbors(df)
 
+    # Return the modified DataFrame
     return df

workbench/model_scripts/xgb_model/generated_model_script.py

@@ -28,12 +28,12 @@ from typing import List, Tuple
 
 # Template Parameters
 TEMPLATE_PARAMS = {
-    "model_type": "regressor",
-    "target": "udm_asy_res_intrinsic_clearance_ul_per_min_per_mg_protein",
-    "features": ['bcut2d_logplow', 'numradicalelectrons', 'smr_vsa5', 'fr_lactam', 'fr_morpholine', 'fr_aldehyde', 'slogp_vsa1', 'fr_amidine', 'bpol', 'fr_ester', 'fr_azo', 'kappa3', 'peoe_vsa5', 'fr_ketone_topliss', 'vsa_estate9', 'estate_vsa9', 'bcut2d_mrhi', 'fr_ndealkylation1', 'numrotatablebonds', 'minestateindex', 'fr_quatn', 'peoe_vsa3', 'fr_epoxide', 'fr_aniline', 'minpartialcharge', 'fr_nitroso', 'fpdensitymorgan2', 'fr_oxime', 'fr_sulfone', 'smr_vsa1', 'kappa1', 'fr_pyridine', 'numaromaticrings', 'vsa_estate6', 'molmr', 'estate_vsa1', 'fr_dihydropyridine', 'vsa_estate10', 'fr_alkyl_halide', 'chi2n', 'fr_thiocyan', 'fpdensitymorgan1', 'fr_unbrch_alkane', 'slogp_vsa9', 'chi4n', 'fr_nitro_arom', 'fr_al_oh', 'fr_furan', 'fr_c_s', 'peoe_vsa8', 'peoe_vsa14', 'numheteroatoms', 'fr_ndealkylation2', 'maxabspartialcharge', 'vsa_estate2', 'peoe_vsa7', 'apol', 'numhacceptors', 'fr_tetrazole', 'vsa_estate1', 'peoe_vsa9', 'naromatom', 'bcut2d_chghi', 'fr_sh', 'fr_halogen', 'slogp_vsa4', 'fr_benzodiazepine', 'molwt', 'fr_isocyan', 'fr_prisulfonamd', 'maxabsestateindex', 'minabsestateindex', 'peoe_vsa11', 'slogp_vsa12', 'estate_vsa5', 'numaliphaticcarbocycles', 'bcut2d_mwlow', 'slogp_vsa7', 'fr_allylic_oxid', 'fr_methoxy', 'fr_nh0', 'fr_coo2', 'fr_phenol', 'nacid', 'nbase', 'chi3v', 'fr_ar_nh', 'fr_nitrile', 'fr_imidazole', 'fr_urea', 'bcut2d_mrlow', 'chi1', 'smr_vsa6', 'fr_aryl_methyl', 'narombond', 'fr_alkyl_carbamate', 'fr_piperzine', 'exactmolwt', 'qed', 'chi0n', 'fr_sulfonamd', 'fr_thiazole', 'numvalenceelectrons', 'fr_phos_acid', 'peoe_vsa12', 'fr_nh1', 'fr_hdrzine', 'fr_c_o_nocoo', 'fr_lactone', 'estate_vsa6', 'bcut2d_logphi', 'vsa_estate7', 'peoe_vsa13', 'numsaturatedcarbocycles', 'fr_nitro', 'fr_phenol_noorthohbond', 'rotratio', 'fr_barbitur', 'fr_isothiocyan', 'balabanj', 'fr_arn', 'fr_imine', 'maxpartialcharge', 'fr_sulfide', 'slogp_vsa11', 'fr_hoccn', 'fr_n_o', 'peoe_vsa1', 'slogp_vsa6', 'heavyatommolwt', 'fractioncsp3', 'estate_vsa8', 'peoe_vsa10', 'numaliphaticrings', 'fr_thiophene', 'maxestateindex', 'smr_vsa10', 'labuteasa', 'smr_vsa2', 'fpdensitymorgan3', 'smr_vsa9', 'slogp_vsa10', 'numaromaticheterocycles', 'fr_nh2', 'fr_diazo', 'chi3n', 'fr_ar_coo', 'slogp_vsa5', 'fr_bicyclic', 'fr_amide', 'estate_vsa10', 'fr_guanido', 'chi1n', 'numsaturatedrings', 'fr_piperdine', 'fr_term_acetylene', 'estate_vsa4', 'slogp_vsa3', 'fr_coo', 'fr_ether', 'estate_vsa7', 'bcut2d_chglo', 'fr_oxazole', 'peoe_vsa6', 'hallkieralpha', 'peoe_vsa2', 'chi2v', 'nocount', 'vsa_estate5', 'fr_nhpyrrole', 'fr_al_coo', 'bertzct', 'estate_vsa11', 'minabspartialcharge', 'slogp_vsa8', 'fr_imide', 'kappa2', 'numaliphaticheterocycles', 'numsaturatedheterocycles', 'fr_hdrzone', 'smr_vsa4', 'fr_ar_n', 'nrot', 'smr_vsa8', 'slogp_vsa2', 'chi4v', 'fr_phos_ester', 'fr_para_hydroxylation', 'smr_vsa3', 'nhohcount', 'estate_vsa2', 'mollogp', 'tpsa', 'fr_azide', 'peoe_vsa4', 'numhdonors', 'fr_al_oh_notert', 'fr_c_o', 'chi0', 'fr_nitro_arom_nonortho', 'vsa_estate3', 'fr_benzene', 'fr_ketone', 'vsa_estate8', 'smr_vsa7', 'fr_ar_oh', 'fr_priamide', 'ringcount', 'estate_vsa3', 'numaromaticcarbocycles', 'bcut2d_mwhi', 'chi1v', 'heavyatomcount', 'vsa_estate4', 'chi0v'],
+    "model_type": "classifier",
+    "target": "class",
+    "features": ['chi2v', 'fr_sulfone', 'chi1v', 'bcut2d_logplow', 'fr_piperzine', 'kappa3', 'smr_vsa1', 'slogp_vsa5', 'fr_ketone_topliss', 'fr_sulfonamd', 'fr_imine', 'fr_benzene', 'fr_ester', 'chi2n', 'labuteasa', 'peoe_vsa2', 'smr_vsa6', 'bcut2d_chglo', 'fr_sh', 'peoe_vsa1', 'fr_allylic_oxid', 'chi4n', 'fr_ar_oh', 'fr_nh0', 'fr_term_acetylene', 'slogp_vsa7', 'slogp_vsa4', 'estate_vsa1', 'vsa_estate4', 'numbridgeheadatoms', 'numheterocycles', 'fr_ketone', 'fr_morpholine', 'fr_guanido', 'estate_vsa2', 'numheteroatoms', 'fr_nitro_arom_nonortho', 'fr_piperdine', 'nocount', 'numspiroatoms', 'fr_aniline', 'fr_thiophene', 'slogp_vsa10', 'fr_amide', 'slogp_vsa2', 'fr_epoxide', 'vsa_estate7', 'fr_ar_coo', 'fr_imidazole', 'fr_nitrile', 'fr_oxazole', 'numsaturatedrings', 'fr_pyridine', 'fr_hoccn', 'fr_ndealkylation1', 'numaliphaticheterocycles', 'fr_phenol', 'maxpartialcharge', 'vsa_estate5', 'peoe_vsa13', 'minpartialcharge', 'qed', 'fr_al_oh', 'slogp_vsa11', 'chi0n', 'fr_bicyclic', 'peoe_vsa12', 'fpdensitymorgan1', 'fr_oxime', 'molwt', 'fr_dihydropyridine', 'smr_vsa5', 'peoe_vsa5', 'fr_nitro', 'hallkieralpha', 'heavyatommolwt', 'fr_alkyl_halide', 'peoe_vsa8', 'fr_nhpyrrole', 'fr_isocyan', 'bcut2d_chghi', 'fr_lactam', 'peoe_vsa11', 'smr_vsa9', 'tpsa', 'chi4v', 'slogp_vsa1', 'phi', 'bcut2d_logphi', 'avgipc', 'estate_vsa11', 'fr_coo', 'bcut2d_mwhi', 'numunspecifiedatomstereocenters', 'vsa_estate10', 'estate_vsa8', 'numvalenceelectrons', 'fr_nh2', 'fr_lactone', 'vsa_estate1', 'estate_vsa4', 'numatomstereocenters', 'vsa_estate8', 'fr_para_hydroxylation', 'peoe_vsa3', 'fr_thiazole', 'peoe_vsa10', 'fr_ndealkylation2', 'slogp_vsa12', 'peoe_vsa9', 'maxestateindex', 'fr_quatn', 'smr_vsa7', 'minestateindex', 'numaromaticheterocycles', 'numrotatablebonds', 'fr_ar_nh', 'fr_ether', 'exactmolwt', 'fr_phenol_noorthohbond', 'slogp_vsa3', 'fr_ar_n', 'sps', 'fr_c_o_nocoo', 'bertzct', 'peoe_vsa7', 'slogp_vsa8', 'numradicalelectrons', 'molmr', 'fr_tetrazole', 'numsaturatedcarbocycles', 'bcut2d_mrhi', 'kappa1', 'numamidebonds', 'fpdensitymorgan2', 'smr_vsa8', 'chi1n', 'estate_vsa6', 'fr_barbitur', 'fr_diazo', 'kappa2', 'chi0', 'bcut2d_mrlow', 'balabanj', 'peoe_vsa4', 'numhacceptors', 'fr_sulfide', 'chi3n', 'smr_vsa2', 'fr_al_oh_notert', 'fr_benzodiazepine', 'fr_phos_ester', 'fr_aldehyde', 'fr_coo2', 'estate_vsa5', 'fr_prisulfonamd', 'numaromaticcarbocycles', 'fr_unbrch_alkane', 'fr_urea', 'fr_nitroso', 'smr_vsa10', 'fr_c_s', 'smr_vsa3', 'fr_methoxy', 'maxabspartialcharge', 'slogp_vsa9', 'heavyatomcount', 'fr_azide', 'chi3v', 'smr_vsa4', 'mollogp', 'chi0v', 'fr_aryl_methyl', 'fr_nh1', 'fpdensitymorgan3', 'fr_furan', 'fr_hdrzine', 'fr_arn', 'numaromaticrings', 'vsa_estate3', 'fr_azo', 'fr_halogen', 'estate_vsa9', 'fr_hdrzone', 'numhdonors', 'fr_alkyl_carbamate', 'fr_isothiocyan', 'minabspartialcharge', 'fr_al_coo', 'ringcount', 'chi1', 'estate_vsa7', 'fr_nitro_arom', 'vsa_estate9', 'minabsestateindex', 'maxabsestateindex', 'vsa_estate6', 'estate_vsa10', 'estate_vsa3', 'fr_n_o', 'fr_amidine', 'fr_thiocyan', 'fr_phos_acid', 'fr_c_o', 'fr_imide', 'numaliphaticrings', 'peoe_vsa6', 'vsa_estate2', 'nhohcount', 'numsaturatedheterocycles', 'slogp_vsa6', 'peoe_vsa14', 'fractioncsp3', 'bcut2d_mwlow', 'numaliphaticcarbocycles', 'fr_priamide', 'nacid', 'nbase', 'naromatom', 'narombond', 'sz', 'sm', 'sv', 'sse', 'spe', 'sare', 'sp', 'si', 'mz', 'mm', 'mv', 'mse', 'mpe', 'mare', 'mp', 'mi', 'xch_3d', 'xch_4d', 'xch_5d', 'xch_6d', 'xch_7d', 'xch_3dv', 'xch_4dv', 'xch_5dv', 'xch_6dv', 'xch_7dv', 'xc_3d', 'xc_4d', 'xc_5d', 'xc_6d', 'xc_3dv', 'xc_4dv', 'xc_5dv', 'xc_6dv', 'xpc_4d', 'xpc_5d', 'xpc_6d', 'xpc_4dv', 'xpc_5dv', 'xpc_6dv', 'xp_0d', 'xp_1d', 'xp_2d', 'xp_3d', 'xp_4d', 'xp_5d', 'xp_6d', 'xp_7d', 'axp_0d', 'axp_1d', 'axp_2d', 'axp_3d', 'axp_4d', 'axp_5d', 'axp_6d', 'axp_7d', 'xp_0dv', 'xp_1dv', 'xp_2dv', 'xp_3dv', 'xp_4dv', 'xp_5dv', 'xp_6dv', 'xp_7dv', 'axp_0dv', 'axp_1dv', 'axp_2dv', 'axp_3dv', 'axp_4dv', 'axp_5dv', 'axp_6dv', 'axp_7dv', 'c1sp1', 'c2sp1', 'c1sp2', 'c2sp2', 'c3sp2', 'c1sp3', 'c2sp3', 'c3sp3', 'c4sp3', 'hybratio', 'fcsp3', 'num_stereocenters', 'num_unspecified_stereocenters', 'num_defined_stereocenters', 'num_r_centers', 'num_s_centers', 'num_stereobonds', 'num_e_bonds', 'num_z_bonds', 'stereo_complexity', 'frac_defined_stereo'],
     "compressed_features": [],
-    "model_metrics_s3_path": "s3://ideaya-sageworks-bucket/models/temp-hlm-phase1-reg-0-80/training",
-    "train_all_data": False
+    "model_metrics_s3_path": "s3://ideaya-sageworks-bucket/models/sol-class-f1-100/training",
+    "train_all_data": True
 }
 
 # Function to check if dataframe is empty

workbench/repl/workbench_shell.py

@@ -41,7 +41,7 @@ from workbench.cached.cached_meta import CachedMeta
 try:
     import rdkit  # noqa
     import mordred  # noqa
-    from workbench.utils import chem_utils
+    from workbench.utils.chem_utils import vis
 
     HAVE_CHEM_UTILS = True
 except ImportError:
@@ -178,12 +178,12 @@ class WorkbenchShell:
 
         # Add cheminformatics utils if available
         if HAVE_CHEM_UTILS:
-            self.commands["show"] = chem_utils.show
+            self.commands["show"] = vis.show
 
     def start(self):
         """Start the Workbench IPython shell"""
         cprint("magenta", "\nWelcome to Workbench!")
-        if self.aws_status is False:
+        if not self.aws_status:
             cprint("red", "AWS Account Connection Failed...Review/Fix the Workbench Config:")
             cprint("red", f"Path: {self.cm.site_config_path}")
             self.show_config()

workbench/utils/chem_utils/fingerprints.py

@@ -0,0 +1,134 @@
+"""Molecular fingerprint computation utilities"""
+
+import logging
+import pandas as pd
+
+# Molecular Descriptor Imports
+from rdkit import Chem
+from rdkit.Chem import rdFingerprintGenerator
+from rdkit.Chem.MolStandardize import rdMolStandardize
+
+# Set up the logger
+log = logging.getLogger("workbench")
+
+
+def compute_morgan_fingerprints(df: pd.DataFrame, radius=2, n_bits=2048, counts=True) -> pd.DataFrame:
+    """Compute and add Morgan fingerprints to the DataFrame.
+
+    Args:
+        df (pd.DataFrame): Input DataFrame containing SMILES strings.
+        radius (int): Radius for the Morgan fingerprint.
+        n_bits (int): Number of bits for the fingerprint.
+        counts (bool): Count simulation for the fingerprint.
+
+    Returns:
+        pd.DataFrame: The input DataFrame with the Morgan fingerprints added as bit strings.
+
+    Note:
+        See: https://greglandrum.github.io/rdkit-blog/posts/2021-07-06-simulating-counts.html
+    """
+    delete_mol_column = False
+
+    # Check for the SMILES column (case-insensitive)
+    smiles_column = next((col for col in df.columns if col.lower() == "smiles"), None)
+    if smiles_column is None:
+        raise ValueError("Input DataFrame must have a 'smiles' column")
+
+    # Sanity check the molecule column (sometimes it gets serialized, which doesn't work)
+    if "molecule" in df.columns and df["molecule"].dtype == "string":
+        log.warning("Detected serialized molecules in 'molecule' column. Removing...")
+        del df["molecule"]
+
+    # Convert SMILES to RDKit molecule objects (vectorized)
+    if "molecule" not in df.columns:
+        log.info("Converting SMILES to RDKit Molecules...")
+        delete_mol_column = True
+        df["molecule"] = df[smiles_column].apply(Chem.MolFromSmiles)
+        # Make sure our molecules are not None
+        failed_smiles = df[df["molecule"].isnull()][smiles_column].tolist()
+        if failed_smiles:
+            log.error(f"Failed to convert the following SMILES to molecules: {failed_smiles}")
+        df = df.dropna(subset=["molecule"])
+
+    # If we have fragments in our compounds, get the largest fragment before computing fingerprints
+    largest_frags = df["molecule"].apply(
+        lambda mol: rdMolStandardize.LargestFragmentChooser().choose(mol) if mol else None
+    )
+
+    # Create a Morgan fingerprint generator
+    if counts:
+        n_bits *= 4  # Multiply by 4 to simulate counts
+    morgan_generator = rdFingerprintGenerator.GetMorganGenerator(radius=radius, fpSize=n_bits, countSimulation=counts)
+
+    # Compute Morgan fingerprints (vectorized)
+    fingerprints = largest_frags.apply(
+        lambda mol: (morgan_generator.GetFingerprint(mol).ToBitString() if mol else pd.NA)
+    )
+
+    # Add the fingerprints to the DataFrame
+    df["fingerprint"] = fingerprints
+
+    # Drop the intermediate 'molecule' column if it was added
+    if delete_mol_column:
+        del df["molecule"]
+    return df
+
+
+if __name__ == "__main__":
+    print("Running molecular fingerprint tests...")
+    print("Note: This requires molecular_screening module to be available")
+
+    # Test molecules
+    test_molecules = {
+        "aspirin": "CC(=O)OC1=CC=CC=C1C(=O)O",
+        "caffeine": "CN1C=NC2=C1C(=O)N(C(=O)N2C)C",
+        "glucose": "C([C@@H]1[C@H]([C@@H]([C@H](C(O1)O)O)O)O)O",  # With stereochemistry
+        "sodium_acetate": "CC(=O)[O-].[Na+]",  # Salt
+        "benzene": "c1ccccc1",
+        "butene_e": "C/C=C/C",  # E-butene
+        "butene_z": "C/C=C\\C",  # Z-butene
+    }
+
+    # Test 1: Morgan Fingerprints
+    print("\n1. Testing Morgan fingerprint generation...")
+
+    test_df = pd.DataFrame({"SMILES": list(test_molecules.values()), "name": list(test_molecules.keys())})
+
+    fp_df = compute_morgan_fingerprints(test_df.copy(), radius=2, n_bits=512, counts=False)
+
+    print("   Fingerprint generation results:")
+    for _, row in fp_df.iterrows():
+        fp = row.get("fingerprint", "N/A")
+        fp_len = len(fp) if fp != "N/A" else 0
+        print(f"   {row['name']:15} → {fp_len} bits")
+
+    # Test 2: Different fingerprint parameters
+    print("\n2. Testing different fingerprint parameters...")
+
+    # Test with counts enabled
+    fp_counts_df = compute_morgan_fingerprints(test_df.copy(), radius=3, n_bits=256, counts=True)
+
+    print("   With count simulation (256 bits * 4):")
+    for _, row in fp_counts_df.iterrows():
+        fp = row.get("fingerprint", "N/A")
+        fp_len = len(fp) if fp != "N/A" else 0
+        print(f"   {row['name']:15} → {fp_len} bits")
+
+    # Test 3: Edge cases
+    print("\n3. Testing edge cases...")
+
+    # Invalid SMILES
+    invalid_df = pd.DataFrame({"SMILES": ["INVALID", ""]})
+    try:
+        fp_invalid = compute_morgan_fingerprints(invalid_df.copy())
+        print(f"   ✓ Invalid SMILES handled: {len(fp_invalid)} valid molecules")
+    except Exception as e:
+        print(f"   ✓ Invalid SMILES properly raised error: {type(e).__name__}")
+
+    # Test with pre-existing molecule column
+    mol_df = test_df.copy()
+    mol_df["molecule"] = mol_df["SMILES"].apply(Chem.MolFromSmiles)
+    fp_with_mol = compute_morgan_fingerprints(mol_df)
+    print(f"   ✓ Pre-existing molecule column handled: {len(fp_with_mol)} fingerprints generated")
+
+    print("\n✅ All fingerprint tests completed!")