Coarse-graining auto-encoders for molecular dynamics
Molecular dynamics simulations provide theoretical insight into the microscopic behavior of condensed-phase materials and, as a predictive tool, enable computational design of new compounds. However, because of the large spatial and temporal scales of thermodynamic and kinetic phenomena in materials...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer Science and Business Media LLC
2020
|
| Online Access: | https://hdl.handle.net/1721.1/127224 |
| _version_ | 1826194362499858432 |
|---|---|
| author | Wang, Wujie Gomez-Bombarelli, Rafael |
| author2 | Massachusetts Institute of Technology. Department of Materials Science and Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Materials Science and Engineering Wang, Wujie Gomez-Bombarelli, Rafael |
| author_sort | Wang, Wujie |
| collection | MIT |
| description | Molecular dynamics simulations provide theoretical insight into the microscopic behavior of condensed-phase materials and, as a predictive tool, enable computational design of new compounds. However, because of the large spatial and temporal scales of thermodynamic and kinetic phenomena in materials, atomistic simulations are often computationally infeasible. Coarse-graining methods allow larger systems to be simulated by reducing their dimensionality, propagating longer timesteps, and averaging out fast motions. Coarse-graining involves two coupled learning problems: defining the mapping from an all-atom representation to a reduced representation, and parameterizing a Hamiltonian over coarse-grained coordinates. We propose a generative modeling framework based on variational auto-encoders to unify the tasks of learning discrete coarse-grained variables, decoding back to atomistic detail, and parameterizing coarse-grained force fields. The framework is tested on a number of model systems including single molecules and bulk-phase periodic simulations. |
| first_indexed | 2024-09-23T09:54:50Z |
| format | Article |
| id | mit-1721.1/127224 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T09:54:50Z |
| publishDate | 2020 |
| publisher | Springer Science and Business Media LLC |
| record_format | dspace |
| spelling | mit-1721.1/1272242022-09-26T14:32:02Z Coarse-graining auto-encoders for molecular dynamics Wang, Wujie Gomez-Bombarelli, Rafael Massachusetts Institute of Technology. Department of Materials Science and Engineering Molecular dynamics simulations provide theoretical insight into the microscopic behavior of condensed-phase materials and, as a predictive tool, enable computational design of new compounds. However, because of the large spatial and temporal scales of thermodynamic and kinetic phenomena in materials, atomistic simulations are often computationally infeasible. Coarse-graining methods allow larger systems to be simulated by reducing their dimensionality, propagating longer timesteps, and averaging out fast motions. Coarse-graining involves two coupled learning problems: defining the mapping from an all-atom representation to a reduced representation, and parameterizing a Hamiltonian over coarse-grained coordinates. We propose a generative modeling framework based on variational auto-encoders to unify the tasks of learning discrete coarse-grained variables, decoding back to atomistic detail, and parameterizing coarse-grained force fields. The framework is tested on a number of model systems including single molecules and bulk-phase periodic simulations. 2020-09-10T12:36:58Z 2020-09-10T12:36:58Z 2019-12 2020-09-09T18:20:39Z Article http://purl.org/eprint/type/JournalArticle 2057-3960 https://hdl.handle.net/1721.1/127224 Wang, Wujie and Rafael Gómez-Bombarelli. “Coarse-graining auto-encoders for molecular dynamics.” npj Computational Materials, 5, 1 (December 2019): 125 © 2019 The Author(s) en 10.1038/S41524-019-0261-5 npj Computational Materials Creative Commons Attribution 4.0 International license https://creativecommons.org/licenses/by/4.0/ application/pdf Springer Science and Business Media LLC Nature |
| spellingShingle | Wang, Wujie Gomez-Bombarelli, Rafael Coarse-graining auto-encoders for molecular dynamics |
| title | Coarse-graining auto-encoders for molecular dynamics |
| title_full | Coarse-graining auto-encoders for molecular dynamics |
| title_fullStr | Coarse-graining auto-encoders for molecular dynamics |
| title_full_unstemmed | Coarse-graining auto-encoders for molecular dynamics |
| title_short | Coarse-graining auto-encoders for molecular dynamics |
| title_sort | coarse graining auto encoders for molecular dynamics |
| url | https://hdl.handle.net/1721.1/127224 |
| work_keys_str_mv | AT wangwujie coarsegrainingautoencodersformoleculardynamics AT gomezbombarellirafael coarsegrainingautoencodersformoleculardynamics |