EUVIMEDEUVIMED entdecken
Crossref

Artificial Intelligence for Generating Drug-like Molecules: A Taxonomy of Methods and Evaluation Strategies

Chia-Chu Fan iD, Emily Wittrup iD, Morgen Henry, Gilbert S Omenn iD, Kayvan Najarian

Journal of Chemical Information and Modeling · 18.11.2026

DOI: 10.1021/acs.jcim.6c02793 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 18.11.2026. Verfasst von Chia-Chu Fan und 4 weiteren Autor:innen. Beteiligte Einrichtung: Gilbert S. Omenn Department of Computational Medicine and Bioinformatics, University of Michigan Medical School, Ann Arbor, Michigan48109, United Sta…. Die Arbeit nennt 217 Literaturangaben. Gefördert von: NCI NIH HHS, NIEHS NIH HHS, Institute for Healthcare Policy and Innovation, University of Michigan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generative artificial intelligence (AI) is increasingly used for de novo small-molecule design, but the practical and translational utility of generated candidates depends on the configuration of the entire discovery workflow rather than on generative model architecture alone. This review adopts a workflow-based perspective on generative molecular design, tracing the process from existing molecular data sets, preprocessing and representation, to molecule generation, conditioning, candidate prioritization, evaluation, and iterative refinement. It examines how generative AI model families, constraints, and predictive oracles interact within this pipeline, and evaluates generated candidates using intrinsic metrics, computational assessments, and experimental and translational evidence. Active learning, computational and experimental feedback, and human expert input are further discussed as mechanisms for closed-loop refinement. Across these stages, we identify data construction and representation choices, oracle quality, evaluation protocols, and the availability of informative feedback as major determinants of how model performance should be interpreted and whether generated structures progress toward biologically and translationally meaningful candidates, with selected examples. In conclusion, reliable generative drug discovery requires coordinated design across the entire workflow rather than isolated advances in individual components.

Schlagwörter

Stichwörter der Autor:innen

Generative artificial intelligenceclosed-loop learningde novo molecular designevaluation and validationmolecular representationsoracle-guided optimizationsmall-molecule drug discovery

Autor:innen und Institutionen

  • Gilbert S. Omenn Department of Computational Medicine and Bioinformatics, University of Michigan Medical School, Ann Arbor, Michigan48109, United States.
  • College of Pharmacy, University of Michigan, Ann Arbor, Michigan48104, United States.
  • Department of Internal Medicine, University of Michigan Medical School, Ann Arbor, Michigan48109, United States.
  • Department of Human Genetics, University of Michigan Medical School, Ann Arbor, Michigan48109, United States.
  • Department of Environmental Health Sciences, University of Michigan School of Public Health, Ann Arbor, Michigan48109, United States.
  • Department of Emergency Medicine, University of Michigan Medical School, Ann Arbor, Michigan48109, United States.

ORCID-Profile: Chia-Chu Fan, Emily Wittrup, Gilbert S Omenn

Förderung

  • NCI NIH HHS
  • NIEHS NIH HHS
  • Institute for Healthcare Policy and Innovation, University of Michigan
  • National Institute of Environmental Health Sciences
  • National Cancer Institute

Zitieren

APA

Fan, C. C., Wittrup, E., Henry, M., Omenn, G. S., & Najarian, K. (2026). Artificial Intelligence for Generating Drug-like Molecules: A Taxonomy of Methods and Evaluation Strategies. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.6c02793

Vancouver

Fan CC, Wittrup E, Henry M, Omenn GS, Najarian K. Artificial Intelligence for Generating Drug-like Molecules: A Taxonomy of Methods and Evaluation Strategies. Journal of Chemical Information and Modeling. 2026. doi:10.1021/acs.jcim.6c02793

BibTeX
@article{Fan2026,
  author = {Fan, Chia-Chu and Wittrup, Emily and Henry, Morgen and Omenn, Gilbert S and Najarian, Kayvan},
  title = {Artificial Intelligence for Generating Drug-like Molecules: A Taxonomy of Methods and Evaluation Strategies},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  doi = {10.1021/acs.jcim.6c02793}
}
Kostenlos starten →