workbench 0.8.217__py3-none-any.whl → 0.8.219__py3-none-any.whl

workbench/algorithms/sql/outliers.py

@@ -209,9 +209,9 @@ class Outliers:
             else:
                 return group.nlargest(n, col)
 
-        # Group by 'outlier_group' and apply the helper function, explicitly selecting columns
-        top_outliers = outlier_df.groupby("outlier_group", group_keys=False).apply(
-            get_extreme_values, include_groups=True
+        # Group by 'outlier_group' and apply the helper function, explicitly selecting columns to silence warning
+        top_outliers = outlier_df.groupby("outlier_group", group_keys=False)[outlier_df.columns].apply(
+            get_extreme_values
         )
         return top_outliers.reset_index(drop=True)
 

workbench/core/artifacts/endpoint_core.py

@@ -410,7 +410,7 @@ class EndpointCore(Artifact):
             primary_target = targets
 
         # Sanity Check that the target column is present
-        if primary_target and (primary_target not in prediction_df.columns):
+        if primary_target not in prediction_df.columns:
             self.log.important(f"Target Column {primary_target} not found in prediction_df!")
             self.log.important("In order to compute metrics, the target column must be present!")
             metrics = pd.DataFrame()
@@ -432,7 +432,7 @@ class EndpointCore(Artifact):
         print(metrics.head())
 
         # Capture the inference results and metrics
-        if capture_name is not None:
+        if primary_target and capture_name:
 
             # If we don't have an id_column, we'll pull it from the model's FeatureSet
             if id_column is None:

workbench/core/artifacts/feature_set_core.py

@@ -247,7 +247,7 @@ class FeatureSetCore(Artifact):
 
         # Set the compressed features in our FeatureSet metadata
         self.log.important(f"Setting Compressed Columns...{compressed_columns}")
-        self.upsert_workbench_meta({"comp_features": compressed_columns})
+        self.upsert_workbench_meta({"compressed_features": compressed_columns})
 
     def get_compressed_features(self) -> list[str]:
         """Get the compressed features for this FeatureSet
@@ -256,7 +256,7 @@ class FeatureSetCore(Artifact):
             list[str]: The compressed columns for this FeatureSet
         """
         # Get the compressed features from our FeatureSet metadata
-        return self.workbench_meta().get("comp_features", [])
+        return self.workbench_meta().get("compressed_features", [])
 
     def num_columns(self) -> int:
         """Return the number of columns of the Feature Set"""

workbench/model_script_utils/model_script_utils.py

@@ -148,12 +148,16 @@ def convert_categorical_types(
 def decompress_features(
     df: pd.DataFrame, features: list[str], compressed_features: list[str]
 ) -> tuple[pd.DataFrame, list[str]]:
-    """Decompress bitstring features into individual bit columns.
+    """Decompress compressed features (bitstrings or count vectors) into individual columns.
+
+    Supports two formats (auto-detected):
+        - Bitstrings: "10110010..." → individual uint8 columns (0 or 1)
+        - Count vectors: "0,3,0,1,5,..." → individual uint8 columns (0-255)
 
     Args:
         df: The features DataFrame
         features: Full list of feature names
-        compressed_features: List of feature names to decompress (bitstrings)
+        compressed_features: List of feature names to decompress
 
     Returns:
         Tuple of (DataFrame with decompressed features, updated feature list)
@@ -178,18 +182,18 @@ def decompress_features(
         # Remove the feature from the list to avoid duplication
         decompressed_features.remove(feature)
 
-        # Handle all compressed features as bitstrings
-        bit_matrix = np.array([list(bitstring) for bitstring in df[feature]], dtype=np.uint8)
-        prefix = feature[:3]
+        # Auto-detect format and parse: comma-separated counts or bitstring
+        sample = str(df[feature].dropna().iloc[0]) if not df[feature].dropna().empty else ""
+        parse_fn = (lambda s: list(map(int, s.split(",")))) if "," in sample else list
+        feature_matrix = np.array([parse_fn(s) for s in df[feature]], dtype=np.uint8)
 
-        # Create all new columns at once - avoids fragmentation
-        new_col_names = [f"{prefix}_{i}" for i in range(bit_matrix.shape[1])]
-        new_df = pd.DataFrame(bit_matrix, columns=new_col_names, index=df.index)
+        # Create new columns with prefix from feature name
+        prefix = feature[:3]
+        new_col_names = [f"{prefix}_{i}" for i in range(feature_matrix.shape[1])]
+        new_df = pd.DataFrame(feature_matrix, columns=new_col_names, index=df.index)
 
-        # Add to features list
+        # Update features list and dataframe
         decompressed_features.extend(new_col_names)
-
-        # Drop original column and concatenate new ones
         df = df.drop(columns=[feature])
         df = pd.concat([df, new_df], axis=1)
 

workbench/model_scripts/chemprop/chemprop.template

@@ -481,8 +481,8 @@ if __name__ == "__main__":
             val_dataset.normalize_targets(target_scaler)
             output_transform = nn.UnscaleTransform.from_standard_scaler(target_scaler)
 
-        train_loader = data.build_dataloader(train_dataset, batch_size=batch_size, shuffle=True)
-        val_loader = data.build_dataloader(val_dataset, batch_size=batch_size, shuffle=False)
+        train_loader = data.build_dataloader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=3)
+        val_loader = data.build_dataloader(val_dataset, batch_size=batch_size, shuffle=False, num_workers=3)
 
         # Build and train model
         pl.seed_everything(hyperparameters["seed"] + fold_idx)

workbench/model_scripts/chemprop/generated_model_script.py

@@ -50,10 +50,10 @@ DEFAULT_HYPERPARAMETERS = {
 # Template parameters (filled in by Workbench)
 TEMPLATE_PARAMS = {
     "model_type": "uq_regressor",
-    "targets": ['udm_asy_res_efflux_ratio'],
-    "feature_list": ['smiles'],
-    "id_column": "udm_mol_bat_id",
-    "model_metrics_s3_path": "s3://ideaya-sageworks-bucket/models/caco2-er-reg-chemprop/training",
+    "targets": ['logd'],
+    "feature_list": ['smiles', 'mollogp', 'fr_halogen', 'nbase', 'peoe_vsa6', 'bcut2d_mrlow', 'peoe_vsa7', 'peoe_vsa9', 'vsa_estate1', 'peoe_vsa1', 'numhdonors', 'vsa_estate5', 'smr_vsa3', 'slogp_vsa1', 'vsa_estate7', 'bcut2d_mwhi', 'axp_2dv', 'axp_3dv', 'mi', 'smr_vsa9', 'vsa_estate3', 'estate_vsa9', 'bcut2d_mwlow', 'tpsa', 'vsa_estate10', 'xch_5dv', 'slogp_vsa2', 'nhohcount', 'bcut2d_logplow', 'hallkieralpha', 'c2sp2', 'bcut2d_chglo', 'smr_vsa4', 'maxabspartialcharge', 'estate_vsa6', 'qed', 'slogp_vsa6', 'vsa_estate2', 'bcut2d_logphi', 'vsa_estate8', 'xch_7dv', 'fpdensitymorgan3', 'xpc_6d', 'smr_vsa10', 'axp_0d', 'fr_nh1', 'axp_4dv', 'peoe_vsa2', 'estate_vsa8', 'peoe_vsa5', 'vsa_estate6'],
+    "id_column": "molecule_name",
+    "model_metrics_s3_path": "s3://sandbox-sageworks-artifacts/models/logd-reg-chemprop-hybrid/training",
     "hyperparameters": {},
 }
 
@@ -481,8 +481,8 @@ if __name__ == "__main__":
             val_dataset.normalize_targets(target_scaler)
             output_transform = nn.UnscaleTransform.from_standard_scaler(target_scaler)
 
-        train_loader = data.build_dataloader(train_dataset, batch_size=batch_size, shuffle=True)
-        val_loader = data.build_dataloader(val_dataset, batch_size=batch_size, shuffle=False)
+        train_loader = data.build_dataloader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=3)
+        val_loader = data.build_dataloader(val_dataset, batch_size=batch_size, shuffle=False, num_workers=3)
 
         # Build and train model
         pl.seed_everything(hyperparameters["seed"] + fold_idx)

workbench/model_scripts/chemprop/model_script_utils.py

@@ -148,12 +148,16 @@ def convert_categorical_types(
 def decompress_features(
     df: pd.DataFrame, features: list[str], compressed_features: list[str]
 ) -> tuple[pd.DataFrame, list[str]]:
-    """Decompress bitstring features into individual bit columns.
+    """Decompress compressed features (bitstrings or count vectors) into individual columns.
+
+    Supports two formats (auto-detected):
+        - Bitstrings: "10110010..." → individual uint8 columns (0 or 1)
+        - Count vectors: "0,3,0,1,5,..." → individual uint8 columns (0-255)
 
     Args:
         df: The features DataFrame
         features: Full list of feature names
-        compressed_features: List of feature names to decompress (bitstrings)
+        compressed_features: List of feature names to decompress
 
     Returns:
         Tuple of (DataFrame with decompressed features, updated feature list)
@@ -178,18 +182,18 @@ def decompress_features(
         # Remove the feature from the list to avoid duplication
         decompressed_features.remove(feature)
 
-        # Handle all compressed features as bitstrings
-        bit_matrix = np.array([list(bitstring) for bitstring in df[feature]], dtype=np.uint8)
-        prefix = feature[:3]
+        # Auto-detect format and parse: comma-separated counts or bitstring
+        sample = str(df[feature].dropna().iloc[0]) if not df[feature].dropna().empty else ""
+        parse_fn = (lambda s: list(map(int, s.split(",")))) if "," in sample else list
+        feature_matrix = np.array([parse_fn(s) for s in df[feature]], dtype=np.uint8)
 
-        # Create all new columns at once - avoids fragmentation
-        new_col_names = [f"{prefix}_{i}" for i in range(bit_matrix.shape[1])]
-        new_df = pd.DataFrame(bit_matrix, columns=new_col_names, index=df.index)
+        # Create new columns with prefix from feature name
+        prefix = feature[:3]
+        new_col_names = [f"{prefix}_{i}" for i in range(feature_matrix.shape[1])]
+        new_df = pd.DataFrame(feature_matrix, columns=new_col_names, index=df.index)
 
-        # Add to features list
+        # Update features list and dataframe
         decompressed_features.extend(new_col_names)
-
-        # Drop original column and concatenate new ones
         df = df.drop(columns=[feature])
         df = pd.concat([df, new_df], axis=1)
 

workbench/model_scripts/custom_models/chem_info/fingerprints.py

@@ -1,11 +1,19 @@
-"""Molecular fingerprint computation utilities"""
+"""Molecular fingerprint computation utilities for ADMET modeling.
+
+This module provides Morgan count fingerprints, the standard for ADMET prediction.
+Count fingerprints outperform binary fingerprints for molecular property prediction.
+
+References:
+    - Count vs Binary: https://pubs.acs.org/doi/10.1021/acs.est.3c02198
+    - ECFP/Morgan: https://pubs.acs.org/doi/10.1021/ci100050t
+"""
 
 import logging
-import pandas as pd
 
-# Molecular Descriptor Imports
+import numpy as np
+import pandas as pd
 from rdkit import Chem, RDLogger
-from rdkit.Chem import rdFingerprintGenerator
+from rdkit.Chem import AllChem
 from rdkit.Chem.MolStandardize import rdMolStandardize
 
 # Suppress RDKit warnings (e.g., "not removing hydrogen atom without neighbors")
@@ -16,20 +24,25 @@ RDLogger.DisableLog("rdApp.warning")
 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.
+def compute_morgan_fingerprints(df: pd.DataFrame, radius: int = 2, n_bits: int = 2048) -> pd.DataFrame:
+    """Compute Morgan count fingerprints for ADMET modeling.
+
+    Generates true count fingerprints where each bit position contains the
+    number of times that substructure appears in the molecule (clamped to 0-255).
+    This is the recommended approach for ADMET prediction per 2025 research.
 
     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.
+        df: Input DataFrame containing SMILES strings.
+        radius: Radius for the Morgan fingerprint (default 2 = ECFP4 equivalent).
+        n_bits: Number of bits for the fingerprint (default 2048).
 
     Returns:
-        pd.DataFrame: The input DataFrame with the Morgan fingerprints added as bit strings.
+        pd.DataFrame: Input DataFrame with 'fingerprint' column added.
+                      Values are comma-separated uint8 counts.
 
     Note:
-        See: https://greglandrum.github.io/rdkit-blog/posts/2021-07-06-simulating-counts.html
+        Count fingerprints outperform binary for ADMET prediction.
+        See: https://pubs.acs.org/doi/10.1021/acs.est.3c02198
     """
     delete_mol_column = False
 
@@ -43,7 +56,7 @@ def compute_morgan_fingerprints(df: pd.DataFrame, radius=2, n_bits=2048, counts=
         log.warning("Detected serialized molecules in 'molecule' column. Removing...")
         del df["molecule"]
 
-    # Convert SMILES to RDKit molecule objects (vectorized)
+    # Convert SMILES to RDKit molecule objects
     if "molecule" not in df.columns:
         log.info("Converting SMILES to RDKit Molecules...")
         delete_mol_column = True
@@ -59,15 +72,24 @@ def compute_morgan_fingerprints(df: pd.DataFrame, radius=2, n_bits=2048, counts=
         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)
+    def mol_to_count_string(mol):
+        """Convert molecule to comma-separated count fingerprint string."""
+        if mol is None:
+            return pd.NA
 
-    # Compute Morgan fingerprints (vectorized)
-    fingerprints = largest_frags.apply(
-        lambda mol: (morgan_generator.GetFingerprint(mol).ToBitString() if mol else pd.NA)
-    )
+        # Get hashed Morgan fingerprint with counts
+        fp = AllChem.GetHashedMorganFingerprint(mol, radius, nBits=n_bits)
+
+        # Initialize array and populate with counts (clamped to uint8 range)
+        counts = np.zeros(n_bits, dtype=np.uint8)
+        for idx, count in fp.GetNonzeroElements().items():
+            counts[idx] = min(count, 255)
+
+        # Return as comma-separated string
+        return ",".join(map(str, counts))
+
+    # Compute Morgan count fingerprints
+    fingerprints = largest_frags.apply(mol_to_count_string)
 
     # Add the fingerprints to the DataFrame
     df["fingerprint"] = fingerprints
@@ -75,59 +97,62 @@ def compute_morgan_fingerprints(df: pd.DataFrame, radius=2, n_bits=2048, counts=
     # 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")
+    print("Running Morgan count fingerprint tests...")
 
     # 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
+        "sodium_acetate": "CC(=O)[O-].[Na+]",  # Salt (largest fragment used)
         "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 1: Morgan Count Fingerprints (default parameters)
+    print("\n1. Testing Morgan fingerprint generation (radius=2, n_bits=2048)...")
 
     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)
+    fp_df = compute_morgan_fingerprints(test_df.copy())
 
     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")
+        if pd.notna(fp):
+            counts = [int(x) for x in fp.split(",")]
+            non_zero = sum(1 for c in counts if c > 0)
+            max_count = max(counts)
+            print(f"   {row['name']:15} → {len(counts)} features, {non_zero} non-zero, max={max_count}")
+        else:
+            print(f"   {row['name']:15} → N/A")
 
-    # Test 2: Different fingerprint parameters
-    print("\n2. Testing different fingerprint parameters...")
+    # Test 2: Different parameters
+    print("\n2. Testing with different parameters (radius=3, n_bits=1024)...")
 
-    # Test with counts enabled
-    fp_counts_df = compute_morgan_fingerprints(test_df.copy(), radius=3, n_bits=256, counts=True)
+    fp_df_custom = compute_morgan_fingerprints(test_df.copy(), radius=3, n_bits=1024)
 
-    print("   With count simulation (256 bits * 4):")
-    for _, row in fp_counts_df.iterrows():
+    for _, row in fp_df_custom.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")
+        if pd.notna(fp):
+            counts = [int(x) for x in fp.split(",")]
+            non_zero = sum(1 for c in counts if c > 0)
+            print(f"   {row['name']:15} → {len(counts)} features, {non_zero} non-zero")
+        else:
+            print(f"   {row['name']:15} → N/A")
 
     # 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__}")
+    fp_invalid = compute_morgan_fingerprints(invalid_df.copy())
+    print(f"   ✓ Invalid SMILES handled: {len(fp_invalid)} rows returned")
 
     # Test with pre-existing molecule column
     mol_df = test_df.copy()
@@ -135,4 +160,16 @@ if __name__ == "__main__":
     fp_with_mol = compute_morgan_fingerprints(mol_df)
     print(f"   ✓ Pre-existing molecule column handled: {len(fp_with_mol)} fingerprints generated")
 
+    # Test 4: Verify count values are reasonable
+    print("\n4. Verifying count distribution...")
+    all_counts = []
+    for _, row in fp_df.iterrows():
+        fp = row.get("fingerprint", "N/A")
+        if pd.notna(fp):
+            counts = [int(x) for x in fp.split(",")]
+            all_counts.extend([c for c in counts if c > 0])
+
+    if all_counts:
+        print(f"   Non-zero counts: min={min(all_counts)}, max={max(all_counts)}, mean={np.mean(all_counts):.2f}")
+
     print("\n✅ All fingerprint tests completed!")

workbench/model_scripts/pytorch_model/generated_model_script.py

@@ -61,10 +61,10 @@ DEFAULT_HYPERPARAMETERS = {
 TEMPLATE_PARAMS = {
     "model_type": "uq_regressor",
     "target": "udm_asy_res_efflux_ratio",
-    "features": ['smr_vsa4', 'tpsa', 'numhdonors', 'nhohcount', 'nbase', 'vsa_estate3', 'fr_guanido', 'mollogp', 'peoe_vsa8', 'peoe_vsa1', 'fr_imine', 'vsa_estate2', 'estate_vsa10', 'asphericity', 'xc_3dv', 'smr_vsa3', 'charge_centroid_distance', 'c3sp3', 'nitrogen_span', 'estate_vsa2', 'minpartialcharge', 'hba_hbd_ratio', 'slogp_vsa1', 'axp_7d', 'nocount', 'vsa_estate4', 'vsa_estate6', 'estate_vsa4', 'xc_4dv', 'xc_4d', 'num_s_centers', 'vsa_estate9', 'chi2v', 'axp_5d', 'mi', 'mse', 'bcut2d_mrhi', 'smr_vsa6', 'hallkieralpha', 'balabanj', 'amphiphilic_moment', 'type_ii_pattern_count', 'minabsestateindex', 'bcut2d_mwlow', 'axp_0dv', 'slogp_vsa5', 'axp_2d', 'axp_1dv', 'xch_5d', 'peoe_vsa10', 'molecular_asymmetry', 'kappa3', 'estate_vsa3', 'sse', 'bcut2d_logphi', 'fr_imidazole', 'molecular_volume_3d', 'bertzct', 'maxestateindex', 'aromatic_interaction_score', 'axp_3d', 'radius_of_gyration', 'vsa_estate7', 'si', 'axp_5dv', 'molecular_axis_length', 'estate_vsa6', 'fpdensitymorgan1', 'axp_6d', 'estate_vsa9', 'fpdensitymorgan2', 'xp_0dv', 'xp_6dv', 'molmr', 'qed', 'estate_vsa8', 'peoe_vsa9', 'xch_6dv', 'xp_7d', 'slogp_vsa2', 'xp_5dv', 'bcut2d_chghi', 'xch_6d', 'chi0n', 'slogp_vsa3', 'chi1v', 'chi3v', 'bcut2d_chglo', 'axp_1d', 'mp', 'num_defined_stereocenters', 'xp_3dv', 'bcut2d_mrlow', 'fr_al_oh', 'peoe_vsa7', 'chi2n', 'axp_6dv', 'axp_2dv', 'chi4n', 'xc_3d', 'axp_7dv', 'vsa_estate8', 'xch_7d', 'maxpartialcharge', 'chi1n', 'peoe_vsa2', 'axp_3dv', 'bcut2d_logplow', 'mv', 'xpc_5dv', 'kappa2', 'vsa_estate5', 'xp_5d', 'mm', 'maxabspartialcharge', 'axp_4dv', 'maxabsestateindex', 'axp_4d', 'xch_4dv', 'xp_2dv', 'heavyatommolwt', 'numatomstereocenters', 'xp_7dv', 'numsaturatedheterocycles', 'xp_3d', 'kappa1', 'mz', 'axp_0d', 'chi1', 'xch_4d', 'smr_vsa1', 'xp_2d', 'estate_vsa5', 'phi', 'fr_ether', 'xc_5d', 'c1sp3', 'estate_vsa7', 'estate_vsa1', 'vsa_estate1', 'slogp_vsa4', 'avgipc', 'smr_vsa10', 'numvalenceelectrons', 'xc_5dv', 'peoe_vsa12', 'peoe_vsa6', 'xpc_5d', 'xpc_6d', 'minestateindex', 'chi3n', 'smr_vsa5', 'xp_4d', 'numheteroatoms', 'fpdensitymorgan3', 'xpc_4d', 'sps', 'xp_1d', 'sv', 'fr_ar_n', 'slogp_vsa10', 'c2sp3', 'xpc_4dv', 'chi0v', 'xpc_6dv', 'xp_1dv', 'vsa_estate10', 'sare', 'c2sp2', 'mpe', 'xch_7dv', 'chi4v', 'type_i_pattern_count', 'sp', 'slogp_vsa8', 'amide_count', 'num_stereocenters', 'num_r_centers', 'tertiary_amine_count', 'spe', 'xp_4dv', 'numsaturatedrings', 'mare', 'numhacceptors', 'chi0', 'fractioncsp3', 'fr_nh0', 'xch_5dv', 'fr_aniline', 'smr_vsa7', 'labuteasa', 'c3sp2', 'xp_0d', 'xp_6d', 'peoe_vsa11', 'fr_ar_nh', 'molwt', 'intramolecular_hbond_potential', 'peoe_vsa3', 'fr_nhpyrrole', 'numaliphaticrings', 'hybratio', 'smr_vsa9', 'peoe_vsa13', 'bcut2d_mwhi', 'c1sp2', 'slogp_vsa11', 'numrotatablebonds', 'numaliphaticcarbocycles', 'slogp_vsa6', 'peoe_vsa4', 'numunspecifiedatomstereocenters', 'xc_6d', 'xc_6dv', 'num_unspecified_stereocenters', 'sz', 'minabspartialcharge', 'fcsp3', 'c1sp1', 'fr_piperzine', 'numaliphaticheterocycles', 'numamidebonds', 'fr_benzene', 'numaromaticheterocycles', 'sm', 'fr_priamide', 'fr_piperdine', 'fr_methoxy', 'c4sp3', 'fr_c_o_nocoo', 'exactmolwt', 'stereo_complexity', 'fr_hoccn', 'numaromaticcarbocycles', 'fr_nh2', 'numheterocycles', 'fr_morpholine', 'fr_ketone', 'fr_nh1', 'frac_defined_stereo', 'fr_aryl_methyl', 'fr_alkyl_halide', 'fr_phenol', 'fr_al_oh_notert', 'fr_ar_oh', 'fr_pyridine', 'fr_amide', 'slogp_vsa7', 'fr_halogen', 'numsaturatedcarbocycles', 'slogp_vsa12', 'fr_ndealkylation1', 'xch_3d', 'fr_bicyclic', 'naromatom', 'narombond'],
+    "features": ['fingerprint'],
     "id_column": "udm_mol_bat_id",
-    "compressed_features": [],
-    "model_metrics_s3_path": "s3://ideaya-sageworks-bucket/models/caco2-er-reg-pytorch/training",
+    "compressed_features": ['fingerprint'],
+    "model_metrics_s3_path": "s3://ideaya-sageworks-bucket/models/caco2-er-reg-fp-pytorch/training",
     "hyperparameters": {},
 }
 

workbench/model_scripts/pytorch_model/model_script_utils.py

@@ -148,12 +148,16 @@ def convert_categorical_types(
 def decompress_features(
     df: pd.DataFrame, features: list[str], compressed_features: list[str]
 ) -> tuple[pd.DataFrame, list[str]]:
-    """Decompress bitstring features into individual bit columns.
+    """Decompress compressed features (bitstrings or count vectors) into individual columns.
+
+    Supports two formats (auto-detected):
+        - Bitstrings: "10110010..." → individual uint8 columns (0 or 1)
+        - Count vectors: "0,3,0,1,5,..." → individual uint8 columns (0-255)
 
     Args:
         df: The features DataFrame
         features: Full list of feature names
-        compressed_features: List of feature names to decompress (bitstrings)
+        compressed_features: List of feature names to decompress
 
     Returns:
         Tuple of (DataFrame with decompressed features, updated feature list)
@@ -178,18 +182,18 @@ def decompress_features(
         # Remove the feature from the list to avoid duplication
         decompressed_features.remove(feature)
 
-        # Handle all compressed features as bitstrings
-        bit_matrix = np.array([list(bitstring) for bitstring in df[feature]], dtype=np.uint8)
-        prefix = feature[:3]
+        # Auto-detect format and parse: comma-separated counts or bitstring
+        sample = str(df[feature].dropna().iloc[0]) if not df[feature].dropna().empty else ""
+        parse_fn = (lambda s: list(map(int, s.split(",")))) if "," in sample else list
+        feature_matrix = np.array([parse_fn(s) for s in df[feature]], dtype=np.uint8)
 
-        # Create all new columns at once - avoids fragmentation
-        new_col_names = [f"{prefix}_{i}" for i in range(bit_matrix.shape[1])]
-        new_df = pd.DataFrame(bit_matrix, columns=new_col_names, index=df.index)
+        # Create new columns with prefix from feature name
+        prefix = feature[:3]
+        new_col_names = [f"{prefix}_{i}" for i in range(feature_matrix.shape[1])]
+        new_df = pd.DataFrame(feature_matrix, columns=new_col_names, index=df.index)
 
-        # Add to features list
+        # Update features list and dataframe
         decompressed_features.extend(new_col_names)
-
-        # Drop original column and concatenate new ones
         df = df.drop(columns=[feature])
         df = pd.concat([df, new_df], axis=1)
 

workbench/model_scripts/xgb_model/generated_model_script.py

@@ -63,12 +63,12 @@ REGRESSION_ONLY_PARAMS = {"objective"}
 
 # Template parameters (filled in by Workbench)
 TEMPLATE_PARAMS = {
-    "model_type": "classifier",
-    "target": "solubility_class",
-    "features": ['molwt', 'mollogp', 'molmr', 'heavyatomcount', 'numhacceptors', 'numhdonors', 'numheteroatoms', 'numrotatablebonds', 'numvalenceelectrons', 'numaromaticrings', 'numsaturatedrings', 'numaliphaticrings', 'ringcount', 'tpsa', 'labuteasa', 'balabanj', 'bertzct'],
-    "id_column": "id",
-    "compressed_features": [],
-    "model_metrics_s3_path": "s3://sandbox-sageworks-artifacts/models/aqsol-class/training",
+    "model_type": "uq_regressor",
+    "target": "udm_asy_res_efflux_ratio",
+    "features": ['fingerprint'],
+    "id_column": "udm_mol_bat_id",
+    "compressed_features": ['fingerprint'],
+    "model_metrics_s3_path": "s3://ideaya-sageworks-bucket/models/caco2-er-reg-fp/training",
     "hyperparameters": {},
 }
 

workbench/model_scripts/xgb_model/model_script_utils.py

@@ -148,12 +148,16 @@ def convert_categorical_types(
 def decompress_features(
     df: pd.DataFrame, features: list[str], compressed_features: list[str]
 ) -> tuple[pd.DataFrame, list[str]]:
-    """Decompress bitstring features into individual bit columns.
+    """Decompress compressed features (bitstrings or count vectors) into individual columns.
+
+    Supports two formats (auto-detected):
+        - Bitstrings: "10110010..." → individual uint8 columns (0 or 1)
+        - Count vectors: "0,3,0,1,5,..." → individual uint8 columns (0-255)
 
     Args:
         df: The features DataFrame
         features: Full list of feature names
-        compressed_features: List of feature names to decompress (bitstrings)
+        compressed_features: List of feature names to decompress
 
     Returns:
         Tuple of (DataFrame with decompressed features, updated feature list)
@@ -178,18 +182,18 @@ def decompress_features(
         # Remove the feature from the list to avoid duplication
         decompressed_features.remove(feature)
 
-        # Handle all compressed features as bitstrings
-        bit_matrix = np.array([list(bitstring) for bitstring in df[feature]], dtype=np.uint8)
-        prefix = feature[:3]
+        # Auto-detect format and parse: comma-separated counts or bitstring
+        sample = str(df[feature].dropna().iloc[0]) if not df[feature].dropna().empty else ""
+        parse_fn = (lambda s: list(map(int, s.split(",")))) if "," in sample else list
+        feature_matrix = np.array([parse_fn(s) for s in df[feature]], dtype=np.uint8)
 
-        # Create all new columns at once - avoids fragmentation
-        new_col_names = [f"{prefix}_{i}" for i in range(bit_matrix.shape[1])]
-        new_df = pd.DataFrame(bit_matrix, columns=new_col_names, index=df.index)
+        # Create new columns with prefix from feature name
+        prefix = feature[:3]
+        new_col_names = [f"{prefix}_{i}" for i in range(feature_matrix.shape[1])]
+        new_df = pd.DataFrame(feature_matrix, columns=new_col_names, index=df.index)
 
-        # Add to features list
+        # Update features list and dataframe
         decompressed_features.extend(new_col_names)
-
-        # Drop original column and concatenate new ones
         df = df.drop(columns=[feature])
         df = pd.concat([df, new_df], axis=1)
 

workbench/scripts/meta_model_sim.py

@@ -0,0 +1,35 @@
+"""MetaModelSimulator: Simulate and analyze ensemble model performance.
+
+This class helps evaluate whether a meta model (ensemble) would outperform
+individual child models by analyzing endpoint inference predictions.
+"""
+
+import argparse
+from workbench.utils.meta_model_simulator import MetaModelSimulator
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Simulate and analyze ensemble model performance using MetaModelSimulator."
+    )
+    parser.add_argument(
+        "models",
+        nargs="+",
+        help="List of model endpoint names to include in the ensemble simulation.",
+    )
+    parser.add_argument(
+        "--id-column",
+        default="molecule_name",
+        help="Name of the ID column (default: molecule_name)",
+    )
+    args = parser.parse_args()
+    models = args.models
+    id_column = args.id_column
+
+    # Create MetaModelSimulator instance and generate report
+    sim = MetaModelSimulator(models, id_column=id_column)
+    sim.report()
+
+
+if __name__ == "__main__":
+    main()