Prediction of p K a Using Machine Learning Methods with Rooted Topological Torsion Fingerprints: Application to Aliphatic Amines.

The acid-base dissociation constant, p K _a , is a key parameter to define the ionization state of a compound and directly affects its biopharmaceutical profile. In this study, we developed a novel approach for p K _a prediction using rooted topological torsion fingerprints in combination with five machine learning (ML) methods: random forest, partial least squares, extreme gradient boosting, lasso regression, and support vector regression. With a large and diverse set of 14 499 experimental p K _a values, p K _a models were developed for aliphatic amines. The models demonstrated consistently good prediction statistics and were able to generate accurate prospective predictions as validated with an external test set of 726 p K _a values (RMSE 0.45, MAE 0.33, and R ² 0.84 by the top model). The factors that may affect prediction accuracy and model applicability were carefully assessed. The results demonstrated that rooted topological torsion fingerprints coupled with ML methods provide a promising approach for developing accurate p K _a prediction models.