Journal
NATURE COMMUNICATIONS
Volume 10, Issue -, Pages -Publisher
NATURE PORTFOLIO
DOI: 10.1038/s41467-019-10827-4
Keywords
-
Categories
Funding
- University of Florida
- National Science Foundation (NSF) [1456638, 1338192]
- NVIDIA Corporation
- U.S. Department of Energy (DOE) through the LANL LDRD Program
- DOD-ONR [N00014-16-1-2311]
- Eshelman Institute for Innovation award
- National Science Foundation [DMR110088, ACI-1053575, 1148698]
- NSF [CHE-1802831, CHE-1802789]
- U.S. DOE Office of Science
- Direct For Computer & Info Scie & Enginr
- Division Of Computer and Network Systems [1456638] Funding Source: National Science Foundation
- Division Of Computer and Network Systems
- Direct For Computer & Info Scie & Enginr [1338192] Funding Source: National Science Foundation
Ask authors/readers for more resources
Computational modeling of chemical and biological systems at atomic resolution is a crucial tool in the chemist's toolset. The use of computer simulations requires a balance between cost and accuracy: quantum-mechanical methods provide high accuracy but are computationally expensive and scale poorly to large systems, while classical force fields are cheap and scalable, but lack transferability to new systems. Machine learning can be used to achieve the best of both approaches. Here we train a general-purpose neural network potential (ANI-1ccx) that approaches CCSD(T)/CBS accuracy on benchmarks for reaction thermochemistry, isomerization, and drug-like molecular torsions. This is achieved by training a network to DFT data then using transfer learning techniques to retrain on a dataset of gold standard QM calculations (CCSD(T)/CBS) that optimally spans chemical space. The resulting potential is broadly applicable to materials science, biology, and chemistry, and billions of times faster than CCSD(T)/CBS calculations.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available