QupKake: Integrating Machine Learning and Quantum Chemistry for Micro-p K a Predictions

2024/06/04 by Omri Abarbanel, Geoffrey Hutchison · 1 voice · 32 citations
Biochemistry, Genetics and Molecular Biology · Chemistry · Computer Science · Materials Science · #Chemistry #Computational Drug Discovery Methods #Computer science #Machine Learning in Materials Science #Machine learning #Metabolomics and Mass Spectrometry Studies #Molecule #Organic chemistry #Physical chemistry #Physics #Quantum #Quantum chemical #Quantum chemistry #Quantum mechanics

paper · pdf · doi:10.1021/acs.jctc.4c00328

published in Journal of Chemical Theory and Computation 20(15), 6946-6956 (American Chemical Society)

openalex publication_date 2024/06/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06

Abstract

High Resolution Image Download MS PowerPoint Slide Accurate prediction of micro-p K a 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 method that combines graph neural network models with semiempirical quantum mechanical (QM) features to achieve exceptional accuracy and generalization in micro-p K a prediction. QupKake outperforms state-of-the-art models on a variety of benchmark data sets, with root-mean-square errors between 0.5 and 0.8 p K a units on five external test sets. Feature importance analysis reveals the crucial role of QM features in both the reaction site enumeration and micro-p K a prediction models. QupKake represents a significant advancement in micro-p K a prediction, offering a powerful tool for various applications in chemistry and beyond.

Citations

• Quantum-chemical insights from deep tensor neural networks

Cited by

• Digitized dataset of aqueous acid dissociation constants
• Assessing the performance of quantum-mechanical descriptors in physicochemical and biological property prediction

Discussions

• My student, Omri Abarbanel finally published his #openaccess paper on QupKake, an ML+quantum model for accurately predicting pKa of a wide range of organic molecules. doi.org/10.1021/acs.... We've r [bsky, 17 points, 3 comments]

Related

• QupKake: Integrating Machine Learning and Quantum Chemistry for micro-pKa Predictions
• PlayMolecule pKAce: Small Molecule Protonation through Equivariant Neural Networks
• PointGAT: A quantum chemical property prediction model integrating graph attention and 3D geometry
• PM6-ML: The Synergy of Semiempirical Quantum Chemistry and Machine Learning Transformed into a Practical Computational Method
• High-throughput quantum theory of atoms in molecules (QTAIM) for geometric deep learning of molecular and reaction properties