Updated imports

README.md

@@ -14,7 +14,6 @@ pipeline_tag: tabular-regression
 
 An XGBoost regressor that predicts the **heavy-atom-count weighted synthesizability
 score** (`hac_weighted_score`) of PROTAC molecules from SMILES.
-
 Nested 5×5 scaffold cross-validation, Optuna tuning. **Mean CV R² = 0.565.**
 
 ## Files
@@ -29,22 +28,43 @@ Nested 5×5 scaffold cross-validation, Optuna tuning. **Mean CV R² = 0.565.**
 
 Requires the project code: https://github.com/ribesstefano/PROTAC-Synthesizability
 
+Install the package (editable) so `protac_synth` is importable, then:
+
 ```python
-from xgb.model import XGBoostRegressor
-from mol_utils import compute_fingerprints, compute_descriptors
+from protac_synth.models.xgb.model import XGBoostRegressor
+from protac_synth.chem_utils import (
+    standardize_all, compute_fingerprints, compute_descriptors,
+)
 
 model  = XGBoostRegressor.load("xgb_v3_final")   # base path, no extension
 smiles = ["O=C(O)c1ccccc1"]
-preds  = model.predict(smiles,
-                       X_fp=compute_fingerprints(smiles, 512, 2),
-                       X_desc=compute_descriptors(smiles))
+
+# featurization consumes standardized RDKit Mols, not raw SMILES
+mols  = standardize_all(smiles)
+preds = model.predict(
+    smiles,
+    X_fp=compute_fingerprints(mols, model.fp_size, model.fp_radius),
+    X_desc=compute_descriptors(mols),
+)
 ```
 
+Notes:
+- `compute_fingerprints` / `compute_descriptors` take pre-standardized Mols
+  (from `standardize_all`), so each molecule is parsed and standardized once.
+- Using `model.fp_size` / `model.fp_radius` guarantees the fingerprint settings
+  match those the model was trained with.
+
 ## Dependencies
 
-Pin these for reproducible loading (`.skops` and RDKit are version-sensitive):
-`rdkit`, `scikit-learn`, `skops`, `xgboost`, `numpy`.
+The `.skops` preprocessor and the RDKit descriptor set are **version-sensitive** —
+loading under a different version can raise `InconsistentVersionWarning` or produce
+a feature-count mismatch. Pin the versions the model was exported with:
+
+- `scikit-learn==1.6.1` (the version the `.skops` pipeline was saved with)
+- `rdkit` — pin the exact version used at training; the RDKit descriptor list
+  changes across releases, and a mismatch changes the descriptor column count.
+- `skops`, `xgboost`, `numpy` — pin to the training environment.
 
 ## License
 
-MIT
+MIT