workbench 0.8.213__py3-none-any.whl → 0.8.219__py3-none-any.whl

workbench/model_scripts/custom_models/chem_info/fingerprints.py

@@ -1,31 +1,48 @@
-"""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
-from rdkit import Chem
-from rdkit.Chem import rdFingerprintGenerator
+import numpy as np
+import pandas as pd
+from rdkit import Chem, RDLogger
+from rdkit.Chem import AllChem
 from rdkit.Chem.MolStandardize import rdMolStandardize
 
+# Suppress RDKit warnings (e.g., "not removing hydrogen atom without neighbors")
+# Keep errors enabled so we see actual problems
+RDLogger.DisableLog("rdApp.warning")
+
 # 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.
+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
 
@@ -39,7 +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
@@ -47,23 +64,32 @@ def compute_morgan_fingerprints(df: pd.DataFrame, radius=2, n_bits=2048, counts=
         # 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"])
+            log.warning(f"Failed to convert {len(failed_smiles)} SMILES to molecules ({failed_smiles})")
+        df = df.dropna(subset=["molecule"]).copy()
 
     # 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)
+    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
@@ -71,59 +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()
@@ -131,4 +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/custom_models/proximity/feature_space_proximity.py

@@ -0,0 +1,194 @@
+import pandas as pd
+import numpy as np
+from sklearn.preprocessing import StandardScaler
+from sklearn.neighbors import NearestNeighbors
+from typing import List, Optional
+import logging
+
+# Workbench Imports
+from workbench.algorithms.dataframe.proximity import Proximity
+from workbench.algorithms.dataframe.projection_2d import Projection2D
+
+# Set up logging
+log = logging.getLogger("workbench")
+
+
+class FeatureSpaceProximity(Proximity):
+    """Proximity computations for numeric feature spaces using Euclidean distance."""
+
+    def __init__(
+        self,
+        df: pd.DataFrame,
+        id_column: str,
+        features: List[str],
+        target: Optional[str] = None,
+        include_all_columns: bool = False,
+    ):
+        """
+        Initialize the FeatureSpaceProximity class.
+
+        Args:
+            df: DataFrame containing data for neighbor computations.
+            id_column: Name of the column used as the identifier.
+            features: List of feature column names to be used for neighbor computations.
+            target: Name of the target column. Defaults to None.
+            include_all_columns: Include all DataFrame columns in neighbor results. Defaults to False.
+        """
+        # Validate and filter features before calling parent init
+        self._raw_features = features
+        super().__init__(
+            df, id_column=id_column, features=features, target=target, include_all_columns=include_all_columns
+        )
+
+    def _prepare_data(self) -> None:
+        """Filter out non-numeric features and drop NaN rows."""
+        # Validate features
+        self.features = self._validate_features(self.df, self._raw_features)
+
+        # Drop NaN rows for the features we're using
+        self.df = self.df.dropna(subset=self.features).copy()
+
+    def _validate_features(self, df: pd.DataFrame, features: List[str]) -> List[str]:
+        """Remove non-numeric features and log warnings."""
+        non_numeric = [f for f in features if f not in df.select_dtypes(include=["number"]).columns]
+        if non_numeric:
+            log.warning(f"Non-numeric features {non_numeric} aren't currently supported, excluding them")
+        return [f for f in features if f not in non_numeric]
+
+    def _build_model(self) -> None:
+        """Standardize features and fit Nearest Neighbors model."""
+        self.scaler = StandardScaler()
+        X = self.scaler.fit_transform(self.df[self.features])
+        self.nn = NearestNeighbors().fit(X)
+
+    def _transform_features(self, df: pd.DataFrame) -> np.ndarray:
+        """Transform features using the fitted scaler."""
+        return self.scaler.transform(df[self.features])
+
+    def _project_2d(self) -> None:
+        """Project the numeric features to 2D for visualization."""
+        if len(self.features) >= 2:
+            self.df = Projection2D().fit_transform(self.df, features=self.features)
+
+
+# Testing the FeatureSpaceProximity class
+if __name__ == "__main__":
+
+    pd.set_option("display.max_columns", None)
+    pd.set_option("display.width", 1000)
+
+    # Create a sample DataFrame
+    data = {
+        "ID": [1, 2, 3, 4, 5],
+        "Feature1": [0.1, 0.2, 0.3, 0.4, 0.5],
+        "Feature2": [0.5, 0.4, 0.3, 0.2, 0.1],
+        "Feature3": [2.5, 2.4, 2.3, 2.3, np.nan],
+    }
+    df = pd.DataFrame(data)
+
+    # Test the FeatureSpaceProximity class
+    features = ["Feature1", "Feature2", "Feature3"]
+    prox = FeatureSpaceProximity(df, id_column="ID", features=features)
+    print(prox.neighbors(1, n_neighbors=2))
+
+    # Test the neighbors method with radius
+    print(prox.neighbors(1, radius=2.0))
+
+    # Test with Features list
+    prox = FeatureSpaceProximity(df, id_column="ID", features=["Feature1"])
+    print(prox.neighbors(1))
+
+    # Create a sample DataFrame
+    data = {
+        "id": ["a", "b", "c", "d", "e"],  # Testing string IDs
+        "Feature1": [0.1, 0.2, 0.3, 0.4, 0.5],
+        "Feature2": [0.5, 0.4, 0.3, 0.2, 0.1],
+        "target": [1, 0, 1, 0, 5],
+    }
+    df = pd.DataFrame(data)
+
+    # Test with String Ids
+    prox = FeatureSpaceProximity(
+        df,
+        id_column="id",
+        features=["Feature1", "Feature2"],
+        target="target",
+        include_all_columns=True,
+    )
+    print(prox.neighbors(["a", "b"]))
+
+    # Test duplicate IDs
+    data = {
+        "id": ["a", "b", "c", "d", "d"],  # Duplicate ID (d)
+        "Feature1": [0.1, 0.2, 0.3, 0.4, 0.5],
+        "Feature2": [0.5, 0.4, 0.3, 0.2, 0.1],
+        "target": [1, 0, 1, 0, 5],
+    }
+    df = pd.DataFrame(data)
+    prox = FeatureSpaceProximity(df, id_column="id", features=["Feature1", "Feature2"], target="target")
+    print(df.equals(prox.df))
+
+    # Test on real data from Workbench
+    from workbench.api import FeatureSet, Model
+
+    fs = FeatureSet("aqsol_features")
+    model = Model("aqsol-regression")
+    features = model.features()
+    df = fs.pull_dataframe()
+    prox = FeatureSpaceProximity(df, id_column=fs.id_column, features=model.features(), target=model.target())
+    print("\n" + "=" * 80)
+    print("Testing Neighbors...")
+    print("=" * 80)
+    test_id = df[fs.id_column].tolist()[0]
+    print(f"\nNeighbors for ID {test_id}:")
+    print(prox.neighbors(test_id))
+
+    print("\n" + "=" * 80)
+    print("Testing isolated_compounds...")
+    print("=" * 80)
+
+    # Test isolated data in the top 1%
+    isolated_1pct = prox.isolated(top_percent=1.0)
+    print(f"\nTop 1% most isolated compounds (n={len(isolated_1pct)}):")
+    print(isolated_1pct)
+
+    # Test isolated data in the top 5%
+    isolated_5pct = prox.isolated(top_percent=5.0)
+    print(f"\nTop 5% most isolated compounds (n={len(isolated_5pct)}):")
+    print(isolated_5pct)
+
+    print("\n" + "=" * 80)
+    print("Testing target_gradients...")
+    print("=" * 80)
+
+    # Test with different parameters
+    gradients_1pct = prox.target_gradients(top_percent=1.0, min_delta=1.0)
+    print(f"\nTop 1% target gradients (min_delta=5.0) (n={len(gradients_1pct)}):")
+    print(gradients_1pct)
+
+    gradients_5pct = prox.target_gradients(top_percent=5.0, min_delta=5.0)
+    print(f"\nTop 5% target gradients (min_delta=5.0) (n={len(gradients_5pct)}):")
+    print(gradients_5pct)
+
+    # Test proximity_stats
+    print("\n" + "=" * 80)
+    print("Testing proximity_stats...")
+    print("=" * 80)
+    stats = prox.proximity_stats()
+    print(stats)
+
+    # Plot the distance distribution using pandas
+    print("\n" + "=" * 80)
+    print("Plotting distance distribution...")
+    print("=" * 80)
+    prox.df["nn_distance"].hist(bins=50, figsize=(10, 6), edgecolor="black")
+
+    # Visualize the 2D projection
+    print("\n" + "=" * 80)
+    print("Visualizing 2D Projection...")
+    print("=" * 80)
+    from workbench.web_interface.components.plugin_unit_test import PluginUnitTest
+    from workbench.web_interface.components.plugins.scatter_plot import ScatterPlot
+
+    unit_test = PluginUnitTest(ScatterPlot, input_data=prox.df[:1000], x="x", y="y", color=model.target())
+    unit_test.run()

workbench/model_scripts/custom_models/proximity/feature_space_proximity.template

@@ -8,7 +8,7 @@ TEMPLATE_PARAMS = {
     "id_column": "{{id_column}}",
     "features": "{{feature_list}}",
     "target": "{{target_column}}",
-    "track_columns": "{{track_columns}}",
+    "include_all_columns": "{{include_all_columns}}",
 }
 
 from io import StringIO
@@ -18,7 +18,7 @@ import os
 import pandas as pd
 
 # Local Imports
-from proximity import Proximity
+from feature_space_proximity import FeatureSpaceProximity
 
 
 # Function to check if dataframe is empty
@@ -61,7 +61,7 @@ if __name__ == "__main__":
     id_column = TEMPLATE_PARAMS["id_column"]
     features = TEMPLATE_PARAMS["features"]
     target = TEMPLATE_PARAMS["target"]  # Can be None for unsupervised models
-    track_columns = TEMPLATE_PARAMS["track_columns"]  # Can be None
+    include_all_columns = TEMPLATE_PARAMS["include_all_columns"]  # Defaults to False
 
     # Script arguments for input/output directories
     parser = argparse.ArgumentParser()
@@ -79,8 +79,8 @@ if __name__ == "__main__":
     # Check if the DataFrame is empty
     check_dataframe(all_df, "training_df")
 
-    # Create the Proximity model
-    model = Proximity(all_df, id_column, features, target, track_columns=track_columns)
+    # Create the FeatureSpaceProximity model
+    model = FeatureSpaceProximity(all_df, id_column=id_column, features=features, target=target, include_all_columns=include_all_columns)
 
     # Now serialize the model
     model.serialize(args.model_dir)
@@ -90,7 +90,7 @@ if __name__ == "__main__":
 def model_fn(model_dir):
 
     # Deserialize the model
-    model = Proximity.deserialize(model_dir)
+    model = FeatureSpaceProximity.deserialize(model_dir)
     return model
 
 

workbench/model_scripts/custom_models/uq_models/feature_space_proximity.py

@@ -0,0 +1,194 @@
+import pandas as pd
+import numpy as np
+from sklearn.preprocessing import StandardScaler
+from sklearn.neighbors import NearestNeighbors
+from typing import List, Optional
+import logging
+
+# Workbench Imports
+from workbench.algorithms.dataframe.proximity import Proximity
+from workbench.algorithms.dataframe.projection_2d import Projection2D
+
+# Set up logging
+log = logging.getLogger("workbench")
+
+
+class FeatureSpaceProximity(Proximity):
+    """Proximity computations for numeric feature spaces using Euclidean distance."""
+
+    def __init__(
+        self,
+        df: pd.DataFrame,
+        id_column: str,
+        features: List[str],
+        target: Optional[str] = None,
+        include_all_columns: bool = False,
+    ):
+        """
+        Initialize the FeatureSpaceProximity class.
+
+        Args:
+            df: DataFrame containing data for neighbor computations.
+            id_column: Name of the column used as the identifier.
+            features: List of feature column names to be used for neighbor computations.
+            target: Name of the target column. Defaults to None.
+            include_all_columns: Include all DataFrame columns in neighbor results. Defaults to False.
+        """
+        # Validate and filter features before calling parent init
+        self._raw_features = features
+        super().__init__(
+            df, id_column=id_column, features=features, target=target, include_all_columns=include_all_columns
+        )
+
+    def _prepare_data(self) -> None:
+        """Filter out non-numeric features and drop NaN rows."""
+        # Validate features
+        self.features = self._validate_features(self.df, self._raw_features)
+
+        # Drop NaN rows for the features we're using
+        self.df = self.df.dropna(subset=self.features).copy()
+
+    def _validate_features(self, df: pd.DataFrame, features: List[str]) -> List[str]:
+        """Remove non-numeric features and log warnings."""
+        non_numeric = [f for f in features if f not in df.select_dtypes(include=["number"]).columns]
+        if non_numeric:
+            log.warning(f"Non-numeric features {non_numeric} aren't currently supported, excluding them")
+        return [f for f in features if f not in non_numeric]
+
+    def _build_model(self) -> None:
+        """Standardize features and fit Nearest Neighbors model."""
+        self.scaler = StandardScaler()
+        X = self.scaler.fit_transform(self.df[self.features])
+        self.nn = NearestNeighbors().fit(X)
+
+    def _transform_features(self, df: pd.DataFrame) -> np.ndarray:
+        """Transform features using the fitted scaler."""
+        return self.scaler.transform(df[self.features])
+
+    def _project_2d(self) -> None:
+        """Project the numeric features to 2D for visualization."""
+        if len(self.features) >= 2:
+            self.df = Projection2D().fit_transform(self.df, features=self.features)
+
+
+# Testing the FeatureSpaceProximity class
+if __name__ == "__main__":
+
+    pd.set_option("display.max_columns", None)
+    pd.set_option("display.width", 1000)
+
+    # Create a sample DataFrame
+    data = {
+        "ID": [1, 2, 3, 4, 5],
+        "Feature1": [0.1, 0.2, 0.3, 0.4, 0.5],
+        "Feature2": [0.5, 0.4, 0.3, 0.2, 0.1],
+        "Feature3": [2.5, 2.4, 2.3, 2.3, np.nan],
+    }
+    df = pd.DataFrame(data)
+
+    # Test the FeatureSpaceProximity class
+    features = ["Feature1", "Feature2", "Feature3"]
+    prox = FeatureSpaceProximity(df, id_column="ID", features=features)
+    print(prox.neighbors(1, n_neighbors=2))
+
+    # Test the neighbors method with radius
+    print(prox.neighbors(1, radius=2.0))
+
+    # Test with Features list
+    prox = FeatureSpaceProximity(df, id_column="ID", features=["Feature1"])
+    print(prox.neighbors(1))
+
+    # Create a sample DataFrame
+    data = {
+        "id": ["a", "b", "c", "d", "e"],  # Testing string IDs
+        "Feature1": [0.1, 0.2, 0.3, 0.4, 0.5],
+        "Feature2": [0.5, 0.4, 0.3, 0.2, 0.1],
+        "target": [1, 0, 1, 0, 5],
+    }
+    df = pd.DataFrame(data)
+
+    # Test with String Ids
+    prox = FeatureSpaceProximity(
+        df,
+        id_column="id",
+        features=["Feature1", "Feature2"],
+        target="target",
+        include_all_columns=True,
+    )
+    print(prox.neighbors(["a", "b"]))
+
+    # Test duplicate IDs
+    data = {
+        "id": ["a", "b", "c", "d", "d"],  # Duplicate ID (d)
+        "Feature1": [0.1, 0.2, 0.3, 0.4, 0.5],
+        "Feature2": [0.5, 0.4, 0.3, 0.2, 0.1],
+        "target": [1, 0, 1, 0, 5],
+    }
+    df = pd.DataFrame(data)
+    prox = FeatureSpaceProximity(df, id_column="id", features=["Feature1", "Feature2"], target="target")
+    print(df.equals(prox.df))
+
+    # Test on real data from Workbench
+    from workbench.api import FeatureSet, Model
+
+    fs = FeatureSet("aqsol_features")
+    model = Model("aqsol-regression")
+    features = model.features()
+    df = fs.pull_dataframe()
+    prox = FeatureSpaceProximity(df, id_column=fs.id_column, features=model.features(), target=model.target())
+    print("\n" + "=" * 80)
+    print("Testing Neighbors...")
+    print("=" * 80)
+    test_id = df[fs.id_column].tolist()[0]
+    print(f"\nNeighbors for ID {test_id}:")
+    print(prox.neighbors(test_id))
+
+    print("\n" + "=" * 80)
+    print("Testing isolated_compounds...")
+    print("=" * 80)
+
+    # Test isolated data in the top 1%
+    isolated_1pct = prox.isolated(top_percent=1.0)
+    print(f"\nTop 1% most isolated compounds (n={len(isolated_1pct)}):")
+    print(isolated_1pct)
+
+    # Test isolated data in the top 5%
+    isolated_5pct = prox.isolated(top_percent=5.0)
+    print(f"\nTop 5% most isolated compounds (n={len(isolated_5pct)}):")
+    print(isolated_5pct)
+
+    print("\n" + "=" * 80)
+    print("Testing target_gradients...")
+    print("=" * 80)
+
+    # Test with different parameters
+    gradients_1pct = prox.target_gradients(top_percent=1.0, min_delta=1.0)
+    print(f"\nTop 1% target gradients (min_delta=5.0) (n={len(gradients_1pct)}):")
+    print(gradients_1pct)
+
+    gradients_5pct = prox.target_gradients(top_percent=5.0, min_delta=5.0)
+    print(f"\nTop 5% target gradients (min_delta=5.0) (n={len(gradients_5pct)}):")
+    print(gradients_5pct)
+
+    # Test proximity_stats
+    print("\n" + "=" * 80)
+    print("Testing proximity_stats...")
+    print("=" * 80)
+    stats = prox.proximity_stats()
+    print(stats)
+
+    # Plot the distance distribution using pandas
+    print("\n" + "=" * 80)
+    print("Plotting distance distribution...")
+    print("=" * 80)
+    prox.df["nn_distance"].hist(bins=50, figsize=(10, 6), edgecolor="black")
+
+    # Visualize the 2D projection
+    print("\n" + "=" * 80)
+    print("Visualizing 2D Projection...")
+    print("=" * 80)
+    from workbench.web_interface.components.plugin_unit_test import PluginUnitTest
+    from workbench.web_interface.components.plugins.scatter_plot import ScatterPlot
+
+    unit_test = PluginUnitTest(ScatterPlot, input_data=prox.df[:1000], x="x", y="y", color=model.target())
+    unit_test.run()