articleNature CommunicationsJul 1, 2019GOLD OA

Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning

JSJustin S. SmithBNBenjamin NebgenRZR.I. ZubatyukNLNicholas LubbersCDChristian Devereux

Los Alamos National Laboratory · University of Florida · +4 more institutions

PubMed
Indexed incrossrefdoajpubmed

Abstract

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…

Citation impact

652
total citations
FWCI
30.28
Percentile
100%
References
71
Citations per year

Authors

9

Topics & keywords

Topics
Keywords
  • Computer science
  • Scalability
  • Thermochemistry
  • Coupled cluster
  • Artificial neural network
  • Transferability
  • Computational science
  • Chemical space
No related works found for this paper.

Funding