Machine Learning-Enhanced Calculation of Quantum-Classical Binding Free Energies
Saved in:
| Title: | Machine Learning-Enhanced Calculation of Quantum-Classical Binding Free Energies |
|---|---|
| Authors: | Moritz Bensberg, Marco Eckhoff, F. Emil Thomasen, William Bro-Jørgensen, Matthew S. Teynor, Valentina Sora, Thomas Weymuth, Raphael T. Husistein, Frederik E. Knudsen, Anders Krogh, Kresten Lindorff-Larsen, Markus Reiher, Gemma C. Solomon |
| Source: | Bensberg, M, Eckhoff, M, Thomasen, F E, Bro-Jørgensen, W, Teynor, M S, Sora, V, Weymuth, T, Husistein, R T, Knudsen, F E, Krogh, A, Lindorff-Larsen, K, Reiher, M & Solomon, G C 2025, ' Machine Learning-Enhanced Calculation of Quantum-Classical Binding Free Energies ', Journal of Chemical Theory and Computation, vol. 21, no. 16, pp. 8182-8198 . https://doi.org/10.1021/acs.jctc.5c00388 |
| Publication Status: | Preprint |
| Publisher Information: | American Chemical Society (ACS), 2025. |
| Publication Year: | 2025 |
| Subject Terms: | Chemical Physics (physics.chem-ph), Biological Physics (physics.bio-ph), Physics - Chemical Physics, FOS: Physical sciences, Physics - Biological Physics, Disordered Systems and Neural Networks (cond-mat.dis-nn), Condensed Matter - Disordered Systems and Neural Networks, Computational Physics (physics.comp-ph), Physics - Computational Physics |
| Description: | Binding free energies are a key element in understanding and predicting the strength of protein--drug interactions. While classical free energy simulations yield good results for many purely organic ligands, drugs including transition metal atoms often require quantum chemical methods for an accurate description. We propose a general and automated workflow that samples the potential energy surface with hybrid quantum mechanics/molecular mechanics (QM/MM) calculations and trains a machine learning (ML) potential on the QM energies and forces to enable efficient alchemical free energy simulations. To represent systems including many different chemical elements efficiently and to account for the different description of QM and MM atoms, we propose an extension of element-embracing atom-centered symmetry functions for QM/MM data as an ML descriptor. The ML potential approach takes electrostatic embedding and long-range electrostatics into account. We demonstrate the applicability of the workflow on the well-studied protein--ligand complex of myeloid cell leukemia 1 and the inhibitor 19G and on the anti-cancer drug NKP1339 acting on the glucose-regulated protein 78. |
| Document Type: | Article |
| File Description: | application/pdf |
| Language: | English |
| ISSN: | 1549-9626 1549-9618 |
| DOI: | 10.1021/acs.jctc.5c00388 |
| DOI: | 10.48550/arxiv.2503.03955 |
| Access URL: | http://arxiv.org/abs/2503.03955 https://curis.ku.dk/ws/files/463565292/Machine_Learning-Enhanced_Calculation.pdf |
| Rights: | CC BY arXiv Non-Exclusive Distribution |
| Accession Number: | edsair.doi.dedup.....24f7d7f0ae0abbd798436d405739019d |
| Database: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstract: | Binding free energies are a key element in understanding and predicting the strength of protein--drug interactions. While classical free energy simulations yield good results for many purely organic ligands, drugs including transition metal atoms often require quantum chemical methods for an accurate description. We propose a general and automated workflow that samples the potential energy surface with hybrid quantum mechanics/molecular mechanics (QM/MM) calculations and trains a machine learning (ML) potential on the QM energies and forces to enable efficient alchemical free energy simulations. To represent systems including many different chemical elements efficiently and to account for the different description of QM and MM atoms, we propose an extension of element-embracing atom-centered symmetry functions for QM/MM data as an ML descriptor. The ML potential approach takes electrostatic embedding and long-range electrostatics into account. We demonstrate the applicability of the workflow on the well-studied protein--ligand complex of myeloid cell leukemia 1 and the inhibitor 19G and on the anti-cancer drug NKP1339 acting on the glucose-regulated protein 78. |
|---|---|
| ISSN: | 15499626 15499618 |
| DOI: | 10.1021/acs.jctc.5c00388 |