EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

GLDM: hit molecule generation with constrained graph latent diffusion model

Conghao Wang, Hiok Hian Ong, Shunsuke Chiba, Jagath C Rajapakse

Briefings in Bioinformatics · 27.03.2024 · 25 (3)

DOI: 10.1093/bib/bbae142 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 04.04.2024. Verfasst von Conghao Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Nanyang Technological University, 50 Nanyang Ave, 639798, Singapore. Hauptthemen laut MEDLINE: Drug Discovery. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Ministry of Education.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Discovering hit molecules with desired biological activity in a directed manner is a promising but profound task in computer-aided drug discovery. Inspired by recent generative AI approaches, particularly Diffusion Models (DM), we propose Graph Latent Diffusion Model (GLDM)—a latent DM that preserves both the effectiveness of autoencoders of compressing complex chemical data and the DM’s capabilities of generating novel molecules. Specifically, we first develop an autoencoder to encode the molecular data into low-dimensional latent representations and then train the DM on the latent space to generate molecules inducing targeted biological activity defined by gene expression profiles. Manipulating DM in the latent space rather than the input space avoids complicated operations to map molecule decomposition and reconstruction to diffusion processes, and thus improves training efficiency. Experiments show that GLDM not only achieves outstanding performances on molecular generation benchmarks, but also generates samples with optimal chemical properties and potentials to induce desired biological activity.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug DiscoveryDiffusion

Stichwörter der Autor:innen

Diffusion Modelsdeep generative modelsdrug designhit molecule discovery

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Nanyang Technological University, 50 Nanyang Ave, 639798, Singapore.
  • School of Chemistry, Chemical Engineering and Biotechnology, Nanyang Technological University, 21 Nanyang Link, 637371, Singapore.

Förderung

  • Ministry of Education

Zitieren

APA

Wang, C., Ong, H. H., Chiba, S., & Rajapakse, J. C. (2024). GLDM: hit molecule generation with constrained graph latent diffusion model. Briefings in Bioinformatics, 25(3). https://doi.org/10.1093/bib/bbae142

Vancouver

Wang C, Ong HH, Chiba S, Rajapakse JC. GLDM: hit molecule generation with constrained graph latent diffusion model. Briefings in Bioinformatics. 2024;25(3). doi:10.1093/bib/bbae142

BibTeX
@article{Wang2024,
  author = {Wang, Conghao and Ong, Hiok Hian and Chiba, Shunsuke and Rajapakse, Jagath C},
  title = {GLDM: hit molecule generation with constrained graph latent diffusion model},
  journal = {Briefings in Bioinformatics},
  year = {2024},
  volume = {25},
  number = {3},
  doi = {10.1093/bib/bbae142}
}
Kostenlos starten →