Multitask Machine Learning of Collective Variables for Enhanced Sampling of Rare Events
| Autor: | Lixin Sun, Jonathan Vandermause, Simon Batzner, Yu Xie, David Clark, Wei Chen, Boris Kozinsky |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
Chemical Physics (physics.chem-ph)
FOS: Computer and information sciences Computer Science - Machine Learning Entropy FOS: Physical sciences Computational Physics (physics.comp-ph) Molecular Dynamics Simulation Computer Science Applications Machine Learning (cs.LG) Machine Learning Physics - Chemical Physics Neural Networks Computer Physical and Theoretical Chemistry Physics - Computational Physics Algorithms |
| Zdroj: | Journal of chemical theory and computation. 18(4) |
| ISSN: | 1549-9626 |
| Popis: | Computing accurate reaction rates is a central challenge in computational chemistry and biology because of the high cost of free energy estimation with unbiased molecular dynamics. In this work, a data-driven machine learning algorithm is devised to learn collective variables with a multitask neural network, where a common upstream part reduces the high dimensionality of atomic configurations to a low dimensional latent space, and separate downstream parts map the latent space to predictions of basin class labels and potential energies. The resulting latent space is shown to be an effective low-dimensional representation, capturing the reaction progress and guiding effective umbrella sampling to obtain accurate free energy landscapes. This approach is successfully applied to model systems including a 5D M\"uller Brown model, a 5D three-well model, and alanine dipeptide in vacuum. This approach enables automated dimensionality reduction for energy controlled reactions in complex systems, offers a unified framework that can be trained with limited data, and outperforms single-task learning approaches, including autoencoders. Comment: 10 pages, 8 figures, presented in MRS 2020 Fall |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|