EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Pocket contrastive learning and conformation fusion for robust structure-conditioned 3D molecular generation under receptor conformational variation

Huan Liu, Yijie Ding iD, Xiaoyi Guo, Hongjie Wu iD

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag740 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Huan Liu und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou, 215009, China. Hauptthemen laut MEDLINE: Proteins, Molecular Docking Simulation, Machine Learning, Computational Biology. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Pocket-conditioned molecular generation incorporates the three-dimensional (3D) geometry and chemical environment of protein binding sites into molecular design. However, receptor conformational variation can introduce distribution shifts between training and inference, particularly under cross-docking conditions. Existing approaches often do not fully exploit the correspondence between related receptor conformations during training. Results We propose a structure-conditioned 3D molecular generation framework that combines pocket-level contrastive learning with reference-conformation feature fusion. Built on a stepwise constructive generative model, these training-stage components encourage stable pocket representations across related conformations while preserving single-pocket inference without requiring a reference conformation. Evaluation on CrossDocked2020 and three external datasets, ASB-E, DUD-E, and APObind, demonstrates improvements in generation success, structural validity, and docking-related performance, particularly under cross-dock evaluation. These results support improved robustness of pocket-conditioned molecular generation under receptor conformational variation. Availability and Implementation The source code and reproduction instructions are available at https://github.com/LHHHHuan/MTMGen. Pretrained models and an archival code snapshot are available at https://doi.org/10.5281/zenodo.21944857.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsMolecular Docking SimulationMachine LearningComputational BiologyProtein ConformationBinding SitesModels, Molecular

Substanzen

Proteins

Autor:innen und Institutionen

  • College of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou, 215009, China.
  • Faculty of Computing, Harbin Institute of Technology, Harbin, 150001, China.
  • Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong SAR, China.

ORCID-Profile: Yijie Ding, Hongjie Wu

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Liu, H., Ding, Y., Guo, X., & Wu, H. (2026). Pocket contrastive learning and conformation fusion for robust structure-conditioned 3D molecular generation under receptor conformational variation. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag740

Vancouver

Liu H, Ding Y, Guo X, Wu H. Pocket contrastive learning and conformation fusion for robust structure-conditioned 3D molecular generation under receptor conformational variation. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag740

BibTeX
@article{Liu2026,
  author = {Liu, Huan and Ding, Yijie and Guo, Xiaoyi and Wu, Hongjie},
  title = {Pocket contrastive learning and conformation fusion for robust structure-conditioned 3D molecular generation under receptor conformational variation},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag740}
}
Kostenlos starten →