PlayMolecule pKAce: Small Molecule Protonation through Equivariant Neural Networks

TL;DR

This paper introduces pKAce, a web tool using equivariant neural networks to accurately predict micro-pKa values of small molecules, improving efficiency with less training data.

Contribution

The work adapts a state-of-the-art equivariant neural network model for pKa prediction, achieving high accuracy with reduced training data requirements.

Findings

Achieves state-of-the-art performance in pKa prediction.

Uses significantly less training data than existing models.

Provides a user-friendly web application for chemists.

Abstract

Small molecule protonation is an important part of the preparation of small molecules for many types of computational chemistry protocols. For this, a correct estimation of the pKa values of the protonation sites of molecules is required. In this work, we present pKAce, a new web application for the prediction of micro-pKa values of the molecules' protonation sites. We adapt the state-of-the-art, equivariant, TensorNet model originally developed for quantum mechanics energy and force predictions to the prediction of micro-pKa values. We show that an adapted version of this model can achieve state-of-the-art performance comparable with established models while trained on just a fraction of their training data.