EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Diffusion‐Based Generative Model With Scaffold‐Hopping Strategy Yields Highly Potent Bioactive Molecules

Yuwei Yang, Xiaoqing Gong, Shukai Gu, Jing Li, Bo Liu, Yanan Tian, Qianqian Zhang iD, Xiaojun Yao, Huanxiang Liu iD

Advanced Science · 2026-08 · 13 (44)

DOI: 10.1002/advs.75674 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 15.05.2026. Verfasst von Yuwei Yang und 8 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Applied Sciences, Macao Polytechnic University, Macao SAR, China. Hauptthemen laut MEDLINE: Drug Discovery, Drug Design. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Development Fund of Macao SAR.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As a critical step in drug discovery, lead optimization is a profoundly complex endeavor with a notoriously high failure rate, as it necessitates the simultaneous optimization of multiple, often conflicting parameters, including physicochemical properties, drug‐likeness, synthetic accessibility, and target binding affinity. While several generative models have been proposed for lead optimization under multi‐property constraints, they still struggle to balance multi‐objective optimization with sufficient scaffold‐level exploration. To address this challenge, we present SMarT‐Diff (Scaffold‐based Multi‐property Tuning Diffusion), a generative diffusion model that achieves this balance by reinventing scaffold hopping—enabling both property optimization and structural novelty. SMarT‐Diff achieved superior performance across diverse molecular generation and optimization metrics. Notably, across both single‐target (LRRK2, HPK1, GLP‐1R) and dual‐target (GSK3β/JNK3) molecular optimization tasks, the model consistently generated drug‐like molecules exhibiting enhanced structural diversity, preserved pharmacophoric features, and high synthetic accessibility. Furthermore, wet‐lab validation of our model‐generated compounds against LRRK2 identified a highly promising candidate with an IC 50 of 1.544 nM, which surpasses even the positive control LRRK2‐IN‐1. This result not only confirms the compound's exceptional potency but also demonstrates the strong real‐world potential of our model to drive the design and optimization of novel, highly effective drug candidates.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug DiscoveryDrug DesignGenerative Artificial IntelligenceHumans

Stichwörter der Autor:innen

deep learningdiffusion modeldrug discoverymolecular generationmulti‐objective optimization

Autor:innen und Institutionen

  • Faculty of Applied Sciences, Macao Polytechnic University, Macao SAR, China.

ORCID-Profile: Qianqian Zhang, Huanxiang Liu

Förderung

  • Science and Technology Development Fund of Macao SAR

Zitieren

APA

Yang, Y., Gong, X., Gu, S., Li, J., Liu, B., Tian, Y., Zhang, Q., Yao, X., & Liu, H. (2026). Diffusion‐Based Generative Model With Scaffold‐Hopping Strategy Yields Highly Potent Bioactive Molecules. Advanced Science, 13(44). https://doi.org/10.1002/advs.75674

Vancouver

Yang Y, Gong X, Gu S, Li J, Liu B, Tian Y, et al. Diffusion‐Based Generative Model With Scaffold‐Hopping Strategy Yields Highly Potent Bioactive Molecules. Advanced Science. 2026;13(44). doi:10.1002/advs.75674

BibTeX
@article{Yang2026,
  author = {Yang, Yuwei and Gong, Xiaoqing and Gu, Shukai and Li, Jing and Liu, Bo and Tian, Yanan and Zhang, Qianqian and Yao, Xiaojun and Liu, Huanxiang},
  title = {Diffusion‐Based Generative Model With Scaffold‐Hopping Strategy Yields Highly Potent Bioactive Molecules},
  journal = {Advanced Science},
  year = {2026},
  volume = {13},
  number = {44},
  doi = {10.1002/advs.75674}
}
Kostenlos starten →