Physics-Informed Bayesian Optimization for Conformational Ensemble Augmentation

Physics-Informed Bayesian Optimization for Conformational Ensemble Augmentation Full article

Journal

Journal of Chemical Information and Modeling
ISSN: 1549-960X , E-ISSN: 1549-9596

Output data

Year: 2025, Volume: 65, Number: 12, Pages: 6048–6056 Pages count : DOI: 10.1021/acs.jcim.5c00522

Authors

Bespalov Ivan A. ^1,2 , Krivoshchapov Nikolai V. ² , Lisov Alexey A. ² , Chaliy Vasiliy A. ² , Medvedev Michael G. ²

Affiliations

1	Lomonosov Moscow State University, Leninskie Gory 1 (3), 119991 Moscow, Russian Federation
2	N.D. Zelinsky Institute of Organic Chemistry, Russian Academy of Sciences, Leninsky Prospect 29, 119991 Moscow, Russian Federation

Conformational search is a key part of reaction modeling, molecular docking, and other fields of computational chemistry, where it is important to take molecules’ flexibility into account. However, modern conformational search approaches provide no guarantee that they did not miss any important conformation. Thus, identifying missing conformations from an existing ensemble is of broad importance for computational chemistry. In this paper, we introduce a Bayesian optimization algorithm for conformational ensemble augmentation, that is, locating missing conformers in an existing ensemble, which employs Bayesian optimization with physics-informed torsion-potential-based kernel function and a novel acquisition function that prioritizes potential energy surface exploration for increased conformer diversity. The devised method demonstrates high efficiency on a test set of biologically relevant molecules.

Bespalov I.A. , Krivoshchapov N.V. , Lisov A.A. , Chaliy V.A. , Medvedev M.G.
Physics-Informed Bayesian Optimization for Conformational Ensemble Augmentation
Journal of Chemical Information and Modeling. 2025. V.65. N12. P.6048–6056. DOI: 10.1021/acs.jcim.5c00522 WOS Scopus OpenAlex

≡ Web of science:	WOS:001503524100001
≡ Scopus:	2-s2.0-105007497689
≡ OpenAlex:	W4411058142