Journal
JOURNAL OF CHEMICAL INFORMATION AND MODELING
Volume 61, Issue 1, Pages 115-122Publisher
AMER CHEMICAL SOC
DOI: 10.1021/acs.jcim.0c01071
Keywords
-
Categories
Funding
- Bristol Myers Squibb
- U.S. National Science Foundation [CHE-1955940]
- U.S. National Science Foundation through a Graduate Rsearch Fellowship [DGE-1650044]
- Georgia Tech Hive Cluster - U.S. National Science Foundation [MRI-1828187]
Ask authors/readers for more resources
EPNN is a fast and accurate neural network atomic charge partitioning model that conserves total molecular charge at a fraction of the cost of traditional quantum mechanical computations. It can be easily applied to large biomolecules, making it highly practical for various applications.
Atomic charges are critical quantities in molecular mechanics and molecular dynamics, but obtaining these quantities requires heuristic choices based on atom typing or relatively expensive quantum mechanical computations to generate a density to be partitioned. Most machine learning efforts in this domain ignore total molecular charges, relying on overfitting and arbitrary rescaling in order to match the total system charge. Here, we introduce the electron-passing neural network (EPNN), a fast, accurate neural network atomic charge partitioning model that conserves total molecular charge by construction. EPNNs predict atomic charges very similar to those obtained by partitioning quantum mechanical densities but at such a small fraction of the cost that they can be easily computed for large biomolecules. Charges from this method may be used directly for molecular mechanics, as features for cheminformatics, or as input to any neural network potential.
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