Datasets S1–S4: Supporting Information for Automated Reaction Transition State Search for Neutral Hydrolysis

Dataset S1: tanimoto_matrix_study.csv - Pairwise Tanimoto similarity matrix between study-case molecules (ECFP4 fingerprints, radius 2). - Rows and columns correspond to molecule IDs in Table S7. Values range from 0 (no similarity) to 1 (identical). Dataset S2: descriptor_pca_study.csv - RDKit descriptors for PCA analysis: MolWt, TPSA, LogP, HBD, HBA, RotatableBonds, RingCount, HeavyAtoms, FractionCSP3. - Includes standardized values and PCA scores (PC1, PC2). Dataset S3: tanimoto_matrix_validation.csv - Pairwise Tanimoto similarity matrix for validation cases (same structure as S1). Dataset S4: descriptor_pca_validation.csv - RDKit descriptors for validation dataset (same columns as S2). - Units: molecular weight in amu; TPSA in Ų; logP unitless.