EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Geometry-Complete Latent Diffusion Model for 3D Molecule Generation

Qunhao Zhang iD, Jun Xiao, Dongjiang Niu, Zhixin Zhang, Shanyang Ding, Zhen Li iD

Bioinformatics · 30.07.2025

DOI: 10.1093/bioinformatics/btaf426 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 30.07.2025. Verfasst von Qunhao Zhang und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Qingdao University, Shandong 266071, China. Hauptthemen laut MEDLINE: Models, Molecular. Die Arbeit wurde bisher 7-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Nature Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Generative models, especially diffusion models, have recently made remarkable progress in fields such as graph generation and drug design. However, current diffusion-based 3D molecule generation models still struggle with adequately modeling the true data distribution. Results We designed the Geometry-Complete Latent Diffusion Model (GCLDM) to enhance the modeling capacity of diffusion models. A geometry-complete autoencoder for feature mapping between atom space and latent space is introduced. In addition, the latent space diffusion model can model continuous latent representations, which is helpful in learning to fit multi-modal feature distributions for the diffusion model. The comparative experimental results demonstrate that GCLDM could fit the true distribution well of molecules and outperform other state-of-art methods. Availability and Implementation Our codes and data are all provided at: [ https://github.com/charlotte0104/GCLDM-for-3d-molucule-generation], and [ https://zenodo.org/records/15773195].

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Models, MolecularDiffusionAlgorithmsSoftware

Autor:innen und Institutionen

  • College of Computer Science and Technology, Qingdao University, Shandong 266071, China.

ORCID-Profile: Qunhao Zhang, Zhen Li

Förderung

  • National Nature Science Foundation of China

Zitieren

APA

Zhang, Q., Xiao, J., Niu, D., Zhang, Z., Ding, S., & Li, Z. (2025). Geometry-Complete Latent Diffusion Model for 3D Molecule Generation. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf426

Vancouver

Zhang Q, Xiao J, Niu D, Zhang Z, Ding S, Li Z. Geometry-Complete Latent Diffusion Model for 3D Molecule Generation. Bioinformatics. 2025. doi:10.1093/bioinformatics/btaf426

BibTeX
@article{Zhang2025,
  author = {Zhang, Qunhao and Xiao, Jun and Niu, Dongjiang and Zhang, Zhixin and Ding, Shanyang and Li, Zhen},
  title = {Geometry-Complete Latent Diffusion Model for 3D Molecule Generation},
  journal = {Bioinformatics},
  year = {2025},
  doi = {10.1093/bioinformatics/btaf426}
}
Kostenlos starten →