Enhancing protein-ligand binding affinity predictions using neural network potentials Research Letter
| Authors: | Sabanés Zariquiey, F.; Galvelis, R.; Gallicchio, E.; Chodera, J. D.; Markland, T. E.; De Fabritiis, G. |
| Title: | Enhancing protein-ligand binding affinity predictions using neural network potentials |
| Abstract: | This letter gives results on improving protein-ligand binding affinity predictions based on molecular dynamics simulations using machine learning potentials with a hybrid neural network potential and molecular mechanics methodology (NNP/MM). We compute relative binding free energies with the Alchemical Transfer Method and validate its performance against established benchmarks and find significant enhancements compared with conventional MM force fields like GAFF2. © 2024 American Chemical Society. |
| Keywords: | proteins; molecular dynamics; protein; protein binding; chemistry; ligand; ligands; benchmarking; thermodynamics; binding energy; artificial neural network; molecular dynamics simulation; neural-networks; machine-learning; binding free energy; protein-ligand binding affinities; neural networks, computer; dynamics simulation; learning potential; hybrid neural networks; prediction-based; relative binding; transfer method |
| Journal Title: | Journal of Chemical Information and Modeling |
| Volume: | 64 |
| Issue: | 5 |
| ISSN: | 1549-9596 |
| Publisher: | American Chemical Society |
| Date Published: | 2024-03-11 |
| Start Page: | 1481 |
| End Page: | 1485 |
| Language: | English |
| DOI: | 10.1021/acs.jcim.3c02031 |
| PUBMED: | 38376463 |
| PROVIDER: | scopus |
| DOI/URL: | |
| Notes: | Article -- MSK Cancer Center Support Grant (P30 CA008748) acknowledged in PDF -- Source: Scopus |
