A Caltech Library Service

Accurate Molecular-Orbital-Based Machine Learning Energies via Unsupervised Clustering of Chemical Space

Cheng, Lixue and Sun, Jiace and Miller, Thomas F., III (2022) Accurate Molecular-Orbital-Based Machine Learning Energies via Unsupervised Clustering of Chemical Space. Journal of Chemical Theory and Computation, 18 (8). pp. 4826-4835. ISSN 1549-9618. doi:10.1021/acs.jctc.2c00396.

[img] PDF - Submitted Version
See Usage Policy.

[img] PDF - Supplemental Material
See Usage Policy.


Use this Persistent URL to link to this item:


We introduce an unsupervised clustering algorithm to improve training efficiency and accuracy in predicting energies using molecular-orbital-based machine learning (MOB-ML). This work determines clusters via the Gaussian mixture model (GMM) in an entirely automatic manner and simplifies an earlier supervised clustering approach [ J. Chem. Theory Comput. 2019, 15, 6668] by eliminating both the necessity for user-specified parameters and the training of an additional classifier. Unsupervised clustering results from GMM have the advantages of accurately reproducing chemically intuitive groupings of frontier molecular orbitals and exhibiting improved performance with an increasing number of training examples. The resulting clusters from supervised or unsupervised clustering are further combined with scalable Gaussian process regression (GPR) or linear regression (LR) to learn molecular energies accurately by generating a local regression model in each cluster. Among all four combinations of regressors and clustering methods, GMM combined with scalable exact GPR (GMM/GPR) is the most efficient training protocol for MOB-ML. The numerical tests of molecular energy learning on thermalized data sets of drug-like molecules demonstrate the improved accuracy, transferability, and learning efficiency of GMM/GPR over other training protocols for MOB-ML, i.e., supervised regression clustering combined with GPR (RC/GPR) and GPR without clustering. GMM/GPR also provides the best molecular energy predictions compared with ones from the literature on the same benchmark data sets. With a lower scaling, GMM/GPR has a 10.4-fold speedup in wall-clock training time compared with scalable exact GPR with a training size of 6500 QM7b-T molecules.

Item Type:Article
Related URLs:
URLURL TypeDescription Paper
Cheng, Lixue0000-0002-7329-0585
Miller, Thomas F., III0000-0002-1882-5380
Additional Information:© 2022 American Chemical Society. Received: April 20, 2022. We thank Dr. Tamara Husch for the guidance on the improved feature generation protocol and Vignesh Bhethanabotla for his help to improve the quality of this manuscript. T.F.M. acknowledges support from the U.S. Army Research Laboratory (W911NF-12-2-0023), the U.S. Department of Energy (DOE) (DE-SC0019390), the Caltech DeLogi Fund, and the Camille and Henry Dreyfus Foundation (Award ML-20-196). Computational resources were provided by the National Energy Research Scientific Computing Center (NERSC), a DOE Office of Science User Facility supported by the DOE Office of Science under Contract DE-AC02-05CH11231. The authors declare no competing financial interest.
Funding AgencyGrant Number
Army Research Office (ARO)W911NF-12-2-0023
Department of Energy (DOE)DE-SC0019390
Caltech De Logi FundUNSPECIFIED
Camille and Henry Dreyfus FoundationML-20-196
Department of Energy (DOE)DE-AC02-05CH11231
Subject Keywords:Cluster chemistry, Energy, Layers, Molecular modeling, Molecules
Issue or Number:8
Record Number:CaltechAUTHORS:20220517-214308613
Persistent URL:
Official Citation:Accurate Molecular-Orbital-Based Machine Learning Energies via Unsupervised Clustering of Chemical Space. Lixue Cheng, Jiace Sun, and Thomas F. Miller III. Journal of Chemical Theory and Computation 2022 18 (8), 4826-4835; DOI: 10.1021/acs.jctc.2c00396
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:114790
Deposited By: George Porter
Deposited On:18 May 2022 15:29
Last Modified:04 Oct 2022 17:34

Repository Staff Only: item control page