QupKake: Integrating Machine Learning and Quantum Chemistry for micro-pKa Predictions

2023/12/04 by Omri Abarbanel, Geoffrey Hutchison · 1 voice
Computer Science · Materials Science · Environmental Science · #Computational Drug Discovery Methods #Machine Learning in Materials Science #Chemistry and Chemical Engineering

paper · pdf · doi:10.26434/chemrxiv-2023-gxplb

Abstract

Accurate prediction of micro-pKa values is crucial for understanding and modulating the acidity and basicity of organic molecules, with applications in drug discovery, materials science, and environmental chemistry. This work introduces QupKake, a novel workflow that combines graph neural network (GNN) models with semiempirical quantum mechanical (QM) features to achieve exceptional accu- racy and generalization in micro-pKa prediction. QupKake outperforms state-of-the-art models on a variety of benchmark datasets, with root mean square errors (RMSEs) between 0.5-0.8 pKa units on five external test sets. Feature importance analysis reveals the crucial role of QM features in both the reaction site enumeration and micro-pKa prediction models. QupKake represents a significant advancement in micro-pKa prediction, offering a powerful tool for various applications in chemistry and beyond.

Discussions

• Thrilled to post the latest work by Omri Abarbanel - a *major* step forward for micro-pKa prediction models: QupKake has prediction errors ~0.5-0.7 by combining ML and QM 🧪 #compchem Omri beat comme [bsky, 10 points, 1 comments]

Related

• QupKake: Integrating Machine Learning and Quantum Chemistry for Micro-p K a Predictions
• PlayMolecule pKAce: Small Molecule Protonation through Equivariant Neural Networks
• PointGAT: A quantum chemical property prediction model integrating graph attention and 3D geometry
• High-throughput quantum theory of atoms in molecules (QTAIM) for geometric deep learning of molecular and reaction properties
• High Througput pKa Prediction Using Semi Empirical Methods