In silico prediction of pK a values using explainable deep learning methods.

Abstract

Negative logarithm of the acid dissociation constant (pK _a) significantly influences the absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties of molecules and is a crucial indicator in drug research. Given the rapid and accurate characteristics of computational methods, their role in predicting drug properties is increasingly important. Although many pK _a prediction models currently exist, they often focus on enhancing model precision while neglecting interpretability. In this study, we present GraFpK _a, a pK _a prediction model using graph neural networks (GNNs) and molecular fingerprints. The results show that our acidic and basic models achieved mean absolute errors (MAEs) of 0.621 and 0.402, respectively, on the test set, demonstrating good predictive performance. Notably, to improve interpretability, GraFpK _a also incorporates Integrated Gradients (IGs), providing a clearer visual description of the atoms significantly affecting the pK _a values. The high reliability and interpretability of GraFpK _a ensure accurate pK _a predictions while also facilitating a deeper understanding of the relationship between molecular structure and pK _a values, making it a valuable tool in the field of pK _a prediction.