EUVIMEDEUVIMED entdecken
Open Access

Discovery of TYR inhibitors from de novo molecular generation to dual-track lead optimization: “Competition” between AI and chemists

Yinyan Sun iD, Jiahui Wang iD, Wenchao Chen iD, Xiaoying Jiang iD, Shan Wang, Jia Zhi, Feifan Li iD, Meiling Feng, Xiaotian Niu, Bin Ju iD, Jianan Guo iD, Renren Bai iD

Science Advances · 19.06.2026 · 12 (25)

DOI: 10.1126/sciadv.aeg0376 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 19.06.2026. Verfasst von Yinyan Sun und 11 weiteren Autor:innen. Beteiligte Einrichtung: School of Pharmacy, Hangzhou Normal University, Hangzhou 311121, PR China. Hauptthemen laut MEDLINE: Monophenol Monooxygenase, Drug Discovery, Artificial Intelligence, Enzyme Inhibitors. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study introduces a unified framework combining artificial intelligence (AI)–directed de novo molecular generation with dual-track lead optimization—comprising expert-guided strategies and AI-driven pathways—to discover tyrosinase (TYR) inhibitors for hyperpigmentation disorders. Using a reinforcement learning (RL)–based generative model, the lead compound AI10 was identified. Subsequent optimization followed two parallel routes. The expert-guided approach yielded AI10-m15 as the most potent TYR inhibitor, with notable antipigmentation activity and excellent cellular safety profiles. In contrast, the AI-driven pathway explored broader chemical spaces, generating unconventional chemotypes, exemplified by the potent TYR inhibitor AI10-a2 , highlighting AI’s capacity to uncover nonintuitive activity cliffs despite greater output variability. Systematic comparison revealed that the AI model offers exploratory diversity, whereas expert-guided optimization provides predictable improvements in activity and developability. In summary, starting from an AI-generated lead and subsequently integrating both expert-guided and AI-driven structural optimization strategies, these findings further underscore that combining AI technologies with experts’ medicinal chemistry insights can substantially accelerate the discovery of viable candidate compounds.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Monophenol MonooxygenaseDrug DiscoveryArtificial IntelligenceEnzyme InhibitorsHumansStructure-Activity RelationshipGenerative Artificial IntelligenceReinforcement Machine Learning

Substanzen

Monophenol MonooxygenaseEnzyme Inhibitors

Autor:innen und Institutionen

  • School of Pharmacy, Hangzhou Normal University, Hangzhou 311121, PR China.
  • Key Laboratory of Elemene Class Anti-Cancer Chinese Medicines; Engineering Laboratory of Development and Application of Traditional Chinese Medicines; Collaborative Innovation Center of Traditional Chinese Medicines of…
  • Zhejiang Angel Medical AI Technology Co., Ltd., Hangzhou 311103, PR China.
  • Department of Pharmacy, Jinhua Municipal Central Hospital, Jinhua 321000, PR China.

ORCID-Profile: Yinyan Sun, Jiahui Wang, Wenchao Chen, Xiaoying Jiang, Feifan Li, Bin Ju, Jianan Guo, Renren Bai

Zitieren

APA

Sun, Y., Wang, J., Chen, W., Jiang, X., Wang, S., Zhi, J., Li, F., Feng, M., Niu, X., Ju, B., Guo, J., & Bai, R. (2026). Discovery of TYR inhibitors from de novo molecular generation to dual-track lead optimization: “Competition” between AI and chemists. Science Advances, 12(25). https://doi.org/10.1126/sciadv.aeg0376

Vancouver

Sun Y, Wang J, Chen W, Jiang X, Wang S, Zhi J, et al. Discovery of TYR inhibitors from de novo molecular generation to dual-track lead optimization: “Competition” between AI and chemists. Science Advances. 2026;12(25). doi:10.1126/sciadv.aeg0376

BibTeX
@article{Sun2026,
  author = {Sun, Yinyan and Wang, Jiahui and Chen, Wenchao and Jiang, Xiaoying and Wang, Shan and Zhi, Jia and Li, Feifan and Feng, Meiling and Niu, Xiaotian and Ju, Bin and Guo, Jianan and Bai, Renren},
  title = {Discovery of TYR inhibitors from de novo molecular generation to dual-track lead optimization: “Competition” between AI and chemists},
  journal = {Science Advances},
  year = {2026},
  volume = {12},
  number = {25},
  doi = {10.1126/sciadv.aeg0376}
}
Kostenlos starten →