EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Generative Multiobjective Bayesian Optimization with Scalable Batch Evaluations for Sample-Efficient De Novo Molecular Design

Madhav R Muthyala iD, Farshud Sorourifar, Tianhong Tan, You Peng iD, Joel A Paulson iD

Industrial & Engineering Chemistry Research · 14.01.2026 · 65 (1) · 628-642

DOI: 10.1021/acs.iecr.5c03166 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Industrial & Engineering Chemistry Research, online erschienen am 21.12.2025. Verfasst von Madhav R Muthyala und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemical and Biological Engineering, University of Wisconsin-Madison, Madison, Wisconsin 53706, United States. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 94 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Designing molecules that must satisfy multiple, often conflicting, objectives is a central challenge in molecular discovery. The enormous size of the chemical space and the cost of high-fidelity simulations have driven the development of machine learning-guided strategies for accelerating design with limited data. Among these, Bayesian optimization (BO) offers a principled framework for sample-efficient search, while generative models provide a mechanism to propose novel, diverse candidates beyond fixed libraries. However, existing methods that couple the two often rely on continuous latent spaces, which introduce both architectural entanglement and scalability challenges. This work introduces an alternative, modular "generate-then-optimize" framework for de novo multiobjective molecular design/discovery. At each iteration, a generative model is used to construct a large, diverse pool of candidate molecules, after which a novel acquisition function, qPMHI (multipoint Probability of Maximum Hypervolume Improvement), is used to optimally select a batch of candidates most likely to induce the largest Pareto front expansion. The key insight is that qPMHI decomposes additively, enabling exact, scalable batch selection via only a simple ranking of probabilities that can be easily estimated with Monte Carlo sampling. We benchmark the framework against state-of-the-art latent-space and discrete molecular optimization methods, demonstrating significant improvements across synthetic benchmarks and application-driven tasks. Specifically, in a case study related to sustainable energy storage, we show that our approach quickly uncovers novel, diverse, and high-performing organic (quinone-based) cathode materials for aqueous redox flow battery applications.

Autor:innen und Institutionen

  • Department of Chemical and Biological Engineering, University of Wisconsin-Madison, Madison, Wisconsin 53706, United States.
  • Department of Chemical and Biomolecular Engineering, The Ohio State University, Columbus, Ohio 43210, United States.
  • Chemometrics, AI and Statistics, Technical Expertise and Support, The Dow Chemical Company, Lake Jackson, Texas 77566, United States.

ORCID-Profile: Madhav R Muthyala, You Peng, Joel A Paulson

Förderung

  • National Science Foundation

Zitieren

APA

Muthyala, M. R., Sorourifar, F., Tan, T., Peng, Y., & Paulson, J. A. (2026). Generative Multiobjective Bayesian Optimization with Scalable Batch Evaluations for Sample-Efficient De Novo Molecular Design. Industrial & Engineering Chemistry Research, 65(1), 628-642. https://doi.org/10.1021/acs.iecr.5c03166

Vancouver

Muthyala MR, Sorourifar F, Tan T, Peng Y, Paulson JA. Generative Multiobjective Bayesian Optimization with Scalable Batch Evaluations for Sample-Efficient De Novo Molecular Design. Industrial & Engineering Chemistry Research. 2026;65(1):628-642. doi:10.1021/acs.iecr.5c03166

BibTeX
@article{Muthyala2026,
  author = {Muthyala, Madhav R and Sorourifar, Farshud and Tan, Tianhong and Peng, You and Paulson, Joel A},
  title = {Generative Multiobjective Bayesian Optimization with Scalable Batch Evaluations for Sample-Efficient De Novo Molecular Design},
  journal = {Industrial & Engineering Chemistry Research},
  year = {2026},
  volume = {65},
  number = {1},
  pages = {628--642},
  doi = {10.1021/acs.iecr.5c03166}
}
Kostenlos starten →