skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Deep learning for computational chemistry

Abstract

The rise and fall of artificial neural networks is well documented in the scientific literature of both the fields of computer science and computational chemistry. Yet almost two decades later, we are now seeing a resurgence of interest in deep learning, a machine learning algorithm based on “deep” neural networks. Within the last few years, we have seen the transformative impact of deep learning the computer science domain, notably in speech recognition and computer vision, to the extent that the majority of practitioners in those field are now regularly eschewing prior established models in favor of deep learning models. In this review, we provide an introductory overview into the theory of deep neural networks and their unique properties as compared to traditional machine learning algorithms used in cheminformatics. By providing an overview of the variety of emerging applications of deep neural networks, we highlight its ubiquity and broad applicability to a wide range of challenges in the field, including QSAR, virtual screening, protein structure modeling, QM calculations, materials synthesis and property prediction. In reviewing the performance of deep neural networks, we observed a consistent outperformance against non neural networks state-of-the-art models across disparate research topics, and deep neural network basedmore » models often exceeded the “glass ceiling” expectations of their respective tasks. Coupled with the maturity of GPU-accelerated computing for training deep neural networks and the exponential growth of chemical data on which to train these networks on, we anticipate that deep learning algorithms will be a useful tool and may grow into a pivotal role for various challenges in the computational chemistry field.« less

Authors:
ORCiD logo [1];  [1];  [1]
  1. Advanced Computing, Mathematics, and Data Division, Pacific Northwest National Laboratory, 902 Battelle Blvd Richland Washington 99354
Publication Date:
Research Org.:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1406688
Report Number(s):
PNNL-SA-121040
Journal ID: ISSN 0192-8651
DOE Contract Number:  
AC05-76RL01830
Resource Type:
Journal Article
Resource Relation:
Journal Name: Journal of Computational Chemistry; Journal Volume: 38; Journal Issue: 16
Country of Publication:
United States
Language:
English
Subject:
Deep Learning; Computational Chemistry; Materials Genome; Quantum Chemistry; molecular modeling

Citation Formats

Goh, Garrett B., Hodas, Nathan O., and Vishnu, Abhinav. Deep learning for computational chemistry. United States: N. p., 2017. Web. doi:10.1002/jcc.24764.
Goh, Garrett B., Hodas, Nathan O., & Vishnu, Abhinav. Deep learning for computational chemistry. United States. doi:10.1002/jcc.24764.
Goh, Garrett B., Hodas, Nathan O., and Vishnu, Abhinav. Wed . "Deep learning for computational chemistry". United States. doi:10.1002/jcc.24764.
@article{osti_1406688,
title = {Deep learning for computational chemistry},
author = {Goh, Garrett B. and Hodas, Nathan O. and Vishnu, Abhinav},
abstractNote = {The rise and fall of artificial neural networks is well documented in the scientific literature of both the fields of computer science and computational chemistry. Yet almost two decades later, we are now seeing a resurgence of interest in deep learning, a machine learning algorithm based on “deep” neural networks. Within the last few years, we have seen the transformative impact of deep learning the computer science domain, notably in speech recognition and computer vision, to the extent that the majority of practitioners in those field are now regularly eschewing prior established models in favor of deep learning models. In this review, we provide an introductory overview into the theory of deep neural networks and their unique properties as compared to traditional machine learning algorithms used in cheminformatics. By providing an overview of the variety of emerging applications of deep neural networks, we highlight its ubiquity and broad applicability to a wide range of challenges in the field, including QSAR, virtual screening, protein structure modeling, QM calculations, materials synthesis and property prediction. In reviewing the performance of deep neural networks, we observed a consistent outperformance against non neural networks state-of-the-art models across disparate research topics, and deep neural network based models often exceeded the “glass ceiling” expectations of their respective tasks. Coupled with the maturity of GPU-accelerated computing for training deep neural networks and the exponential growth of chemical data on which to train these networks on, we anticipate that deep learning algorithms will be a useful tool and may grow into a pivotal role for various challenges in the computational chemistry field.},
doi = {10.1002/jcc.24764},
journal = {Journal of Computational Chemistry},
number = 16,
volume = 38,
place = {United States},
year = {Wed Mar 08 00:00:00 EST 2017},
month = {Wed Mar 08 00:00:00 EST 2017}
}