Reinforcement Learning-Driven Multiproperty Optimization in Molecular Design Using Multicontext Transcriptome Data
Journal of Chemical Information and Modeling · 27.07.2026 · 66 (14) · 7972-7983
DOI: 10.1021/acs.jcim.6c00809 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 06.07.2026. Verfasst von Yuki Matsukiyo und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Complex Systems Science, Graduate School of Informatics, Nagoya University, Chikusa, Nagoya, Aichi464-8601, Japan. Hauptthemen laut MEDLINE: Drug Design, Transcriptome. Die Arbeit nennt 46 Literaturangaben. Gefördert von: Japan Agency for Medical Research and Development, Japan Society for the Promotion of Science, Japan Science and Technology Agency.
Abstract (Originalsprache)
Drug discovery inherently involves multiparameter optimization in the molecular design because drug candidate molecules must meet diverse properties such as bioactivity, synthesizability, and pharmacokinetic properties. This optimization has traditionally relied on iterative manual design and experimental testing, which are labor-intensive and time-consuming. There is therefore a strong incentive to develop computational methods that efficiently design drug-like molecules with multiple favorable properties using chemical and biological data on therapeutic targets. This study proposes a novel computational method for multiproperty optimization in the molecular structure design of bioactive molecules using multicontext (i.e., chemically and genetically perturbed) transcriptome data on human cells. We integrate a molecular generative model conditioned on a transcriptome profile observed with the target gene knockdown or overexpression into a reinforcement learning framework, enabling simultaneous optimization of a quantitative estimate of drug-likeness, synthetic accessibility score, and water/octanol partition coefficient, while accounting for system-level biological effects on a therapeutic target. Using comprehensive benchmarking against established baselines and rigorous validation across multiple metrics, we demonstrate that the proposed method consistently yields molecules with more favorable drug-like characteristics than existing methods. This proposed method can help achieve more efficient identification of novel drug candidates.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Complex Systems Science, Graduate School of Informatics, Nagoya University, Chikusa, Nagoya, Aichi464-8601, Japan.
- D3 center, The University of Osaka, Ibaraki, Osaka567-0047, Japan.
- Division of Interdisciplinary Research and Development (R&D), Aichi Cancer Center Research Institute, Chikusa, Nagoya, Aichi464-8681, Japan.
ORCID-Profile: Yuki Matsukiyo, Yoshihiro Yamanishi
Förderung
- Japan Agency for Medical Research and Development
- Japan Society for the Promotion of Science
- Japan Science and Technology Agency
Zitieren
APA
Matsukiyo, Y., Li, C., & Yamanishi, Y. (2026). Reinforcement Learning-Driven Multiproperty Optimization in Molecular Design Using Multicontext Transcriptome Data. Journal of Chemical Information and Modeling, 66(14), 7972-7983. https://doi.org/10.1021/acs.jcim.6c00809
Vancouver
Matsukiyo Y, Li C, Yamanishi Y. Reinforcement Learning-Driven Multiproperty Optimization in Molecular Design Using Multicontext Transcriptome Data. Journal of Chemical Information and Modeling. 2026;66(14):7972-7983. doi:10.1021/acs.jcim.6c00809
BibTeX
@article{Matsukiyo2026,
author = {Matsukiyo, Yuki and Li, Chen and Yamanishi, Yoshihiro},
title = {Reinforcement Learning-Driven Multiproperty Optimization in Molecular Design Using Multicontext Transcriptome Data},
journal = {Journal of Chemical Information and Modeling},
year = {2026},
volume = {66},
number = {14},
pages = {7972--7983},
doi = {10.1021/acs.jcim.6c00809}
}
EUVIMED