EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ActivityDiff: a diffusion model with positive and negative activity guidance for de novo drug design

Huimin Zhu, Renyi Zhou, Jing Tang iD, Min Li iD

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag564 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Huimin Zhu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Central South University, Changsha 410083, China. Hauptthemen laut MEDLINE: Drug Design, Software, Computational Biology. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Hunan Provincial Natural Science Foundation of China, European Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation De novo drug design requires not only promoting desired target activity, but also avoiding undesired target interactions that compromise selectivity and safety. However, existing generative models largely focus on optimizing positive activity, while overlooking negative activity information that could help suppress off-target effects during molecular design. Results We present ActivityDiff, a classifier-guided diffusion framework for activity-controlled molecular generation. Unlike conventional approaches that rely primarily on positive activity optimization, ActivityDiff explicitly incorporates both positive and negative guidance through separately trained drug–target classifiers. This design enables the model not only to promote desired target activities, but also to suppress harmful off-target interactions during generation. Experiments show that ActivityDiff effectively supports various drug design tasks, including single- and dual-target generation, fragment-constrained dual-target design, selective generation for improved target specificity, and reduction of off-target effects. These results demonstrate that classifier-guided diffusion with explicit negative guidance provides an effective strategy for jointly optimizing efficacy and safety in molecular design. Availability and implementation The source code can be obtained from https://github.com/e-yi/ActivityDiff.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug DesignSoftwareComputational BiologyAlgorithms

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Central South University, Changsha 410083, China.
  • Research Program in Systems Oncology, University of Helsinki, Helsinki 00290, Finland.

ORCID-Profile: Jing Tang, Min Li

Förderung

  • National Natural Science Foundation of China
  • Hunan Provincial Natural Science Foundation of China
  • European Research Council
  • the China Postdoctoral Science Foundation
  • the High Performance Computing Center of Central South University

Zitieren

APA

Zhu, H., Zhou, R., Tang, J., & Li, M. (2026). ActivityDiff: a diffusion model with positive and negative activity guidance for de novo drug design. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag564

Vancouver

Zhu H, Zhou R, Tang J, Li M. ActivityDiff: a diffusion model with positive and negative activity guidance for de novo drug design. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag564

BibTeX
@article{Zhu2026,
  author = {Zhu, Huimin and Zhou, Renyi and Tang, Jing and Li, Min},
  title = {ActivityDiff: a diffusion model with positive and negative activity guidance for de novo drug design},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag564}
}
Kostenlos starten →