BAND NN: A Deep Learning Framework for Energy Prediction and Geometry Optimization of Organic Small Molecules. Issue 8 (17th December 2019)

• Record Type: Journal Article
• Authors: Laghuvarapu, Siddhartha; Pathak, Yashaswi; Priyakumar, U. Deva
• Is Part Of: Journal of computational chemistry. Volume 41:Issue 8(2020)
• Page Start: 790
• Page End: 799
• Publication Date: 2019-12-17
• Subjects: machine learning -- atomization energy -- geometry optimization -- conformational analysis -- neural network; Chemistry -- Data processing -- Periodicals; 542.85
• DOI: 10.1002/jcc.26128
• Languages: English
• ISSNs: 0192-8651

Abstract

Abstract : Recent advances in artificial intelligence along with the development of large data sets of energies calculated using quantum mechanical (QM)/density functional theory (DFT) methods have enabled prediction of accurate molecular energies at reasonably low computational cost. However, machine learning models that have been reported so far require the atomic positions obtained from geometry optimizations using high‐level QM/DFT methods as input in order to predict the energies and do not allow for geometry optimization. In this study, a transferable and molecule size‐independent machine learning model bonds (B), angles (A), nonbonded (N) interactions, and dihedrals (D) neural network (BAND NN) based on a chemically intuitive representation inspired by molecular mechanics force fields is presented. The model predicts the atomization energies of equilibrium and nonequilibrium structures as sum of energy contributions from bonds (B), angles (A), nonbonds (N), and dihedrals (D) at remarkable accuracy. The robustness of the proposed model is further validated by calculations that span over the conformational, configurational, and reaction space. The transferability of this model on systems larger than the ones in the data set is demonstrated by performing calculations on selected large molecules. Importantly, employing the BAND NN model, it is possible to perform geometry optimizations starting from nonequilibrium structures along with predicting their energies. © 2019 Wiley Periodicals, Inc. Abstract : Calculating energies of molecular systems using density functional theory is compute intensive, and hence approximate methods are desirable in high‐throughput applications. In this study, the authors propose a machine learning model, bonds (B), angles (A), nonbonded (N) interactions, and dihedrals (D) neural network (BAND NN), using deep neural networks employing a feature vector inspired by additive force field equations. The authors show that reliable energies can be obtained from BAND NN model and can be applied for energy minimization of organic molecules.