A Reinforcement Learning-Guided Genetic Algorithm Integrating Medicinal Chemistry-Inspired Molecular Transformations
Journal of Chemical Information and Modeling · 27.04.2026 · 66 (8) · 4576-4591
DOI: 10.1021/acs.jcim.6c00397 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 16.04.2026. Verfasst von Domenico Alberga und 5 weiteren Autor:innen. Beteiligte Einrichtung: CNR - Institute of Crystallography, Via Amendola 122/o, Bari 70126, Italy. Hauptthemen laut MEDLINE: Genetic Algorithms, Reinforcement Machine Learning, Chemistry, Pharmaceutical. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 87 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministero dell?Istruzione, dell?Universit? e della Ricerca.
Abstract (Originalsprache)
Achieving optimal target activity while maintaining synthetic accessibility and drug-likeness represents a major challenge in computational drug discovery. Existing de novo generative models often yield chemically invalid or synthetically intractable structures and struggle to optimize multiple objectives simultaneously. Here, we introduce ALCHIMIA, an interpretable hybrid framework combining reinforcement learning (RL) and a genetic algorithm (GA), built based on a vocabulary of 33 medicinal chemistry-inspired molecular transformations. The RL component trains a policy network to prioritize transformation sequences that improve synthetic accessibility (SA) and the quantitative estimate of drug-likeness (QED) scores, embedding these constraints directly into molecular generation. The GA component applies the learned policy as a mutational operator within population-based optimization guided by molecular docking, enabling the exploration of diverse chemical lineages while converging toward high-affinity ligands. ALCHIMIA was applied to two different pharmacologically relevant targets: human Cannabinoid Receptor 2 (CB2R) and human Sigma nonopioid intracellular Receptor 1 (S1R). We considered three different scenarios: (i) unconstrained hit identification; (ii) scaffold-constrained lead optimization; and (iii) design of dual modulators. The framework generated chemically valid molecules with QED and SA scores comparable to or better than those obtained with random baselines and selected de novo design methods. By codifying typical medicinal chemistry actions as learnable transformations and coupling multiobjective optimization with GA-based diversity maintenance, ALCHIMIA, freely available as a GitHub repository (https://github.com/alberdom88/ALCHIMIA), provides a practical, interpretable, and scalable framework for molecular de novo design.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- CNR - Institute of Crystallography, Via Amendola 122/o, Bari 70126, Italy.
- Department of Biotechnology, Chemistry and Pharmacy, University of Siena, Siena 53100, Italy.
- Dipartimento di Medicina di Precisione e Rigenerativa e Area Jonica (DiMePRe-J), Università Degli Studi di Bari Aldo Moro, Piazza Giulio Cesare, 11, Policlinico, Bari 70124, Italy.
ORCID-Profile: Domenico Alberga, Vittoria Nanna, Maria Giovanna Eva Papadopoulos, Giuseppe Felice Mangiatordi
Förderung
- Ministero dell?Istruzione, dell?Universit? e della Ricerca
Zitieren
APA
Alberga, D., Nanna, V., Papadopoulos, M. G. E., Ancona, A., Lomuscio, M. C., & Mangiatordi, G. F. (2026). A Reinforcement Learning-Guided Genetic Algorithm Integrating Medicinal Chemistry-Inspired Molecular Transformations. Journal of Chemical Information and Modeling, 66(8), 4576-4591. https://doi.org/10.1021/acs.jcim.6c00397
Vancouver
Alberga D, Nanna V, Papadopoulos MGE, Ancona A, Lomuscio MC, Mangiatordi GF. A Reinforcement Learning-Guided Genetic Algorithm Integrating Medicinal Chemistry-Inspired Molecular Transformations. Journal of Chemical Information and Modeling. 2026;66(8):4576-4591. doi:10.1021/acs.jcim.6c00397
BibTeX
@article{Alberga2026,
author = {Alberga, Domenico and Nanna, Vittoria and Papadopoulos, Maria Giovanna Eva and Ancona, Adolfo and Lomuscio, Maria Cristina and Mangiatordi, Giuseppe Felice},
title = {A Reinforcement Learning-Guided Genetic Algorithm Integrating Medicinal Chemistry-Inspired Molecular Transformations},
journal = {Journal of Chemical Information and Modeling},
year = {2026},
volume = {66},
number = {8},
pages = {4576--4591},
doi = {10.1021/acs.jcim.6c00397}
}
EUVIMED