EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Guided diffusion for molecular generation with interaction prompt

Peng Wu, Huabin Du, Yingchao Yan, Tzong-Yi Lee iD, Chen Bai, Song Wu iD

Briefings in Bioinformatics · 27.03.2024 · 25 (3)

DOI: 10.1093/bib/bbae174 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 21.04.2024. Verfasst von Peng Wu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Urology, South China Hospital, Medical School, Shenzhen University, Fuxin Road, Longgang District, Shenzhen, 518116, China. Tel.: +86 0…. Hauptthemen laut MEDLINE: Proteins. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Shenzhen Engineering Research Center, Shenzhen Science and Technology Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Molecular generative models have exhibited promising capabilities in designing molecules from scratch with high binding affinities in a predetermined protein pocket, offering potential synergies with traditional structural-based drug design strategy. However, the generative processes of such models are random and the atomic interaction information between ligand and protein are ignored. On the other hand, the ligand has high propensity to bind with residues called hotspots. Hotspot residues contribute to the majority of the binding free energies and have been recognized as appealing targets for designed molecules. In this work, we develop an interaction prompt guided diffusion model, InterDiff to deal with the challenges. Four kinds of atomic interactions are involved in our model and represented as learnable vector embeddings. These embeddings serve as conditions for individual residue to guide the molecular generative process. Comprehensive in silico experiments evince that our model could generate molecules with desired ligand–protein interactions in a guidable way. Furthermore, we validate InterDiff on two realistic protein-based therapeutic agents. Results show that InterDiff could generate molecules with better or similar binding mode compared to known targeted drugs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsLigandsProtein BindingDrug DesignModels, MolecularAlgorithmsBinding SitesComputer Simulation

Stichwörter der Autor:innen

atomic interactiondiffusion modelmolecular generative modelprompt learning

Substanzen

ProteinsLigands

Autor:innen und Institutionen

  • Department of Urology, South China Hospital, Medical School, Shenzhen University, Fuxin Road, Longgang District, Shenzhen, 518116, China. Tel.: +86 0755 89798999.
  • MoMed Biotechnology Co., Ltd., Hangzhou 310005, China.
  • Institute of Bioinformatics and Systems Biology, National Yang Ming Chiao Tung University, Hsinchu 300, Taiwan, China. Tel.:+886 0928 560313.
  • Warshel Institute for Computational Biology, School of Life and Health Sciences, School of Medicine, The Chinese University of Hong Kong, Shenzhen, Shenzhen, 518172, Guangdong, China. Tel.:+86 0755 84273118.
  • South China Hospital, Health Science Center, Shenzhen University, Shenzhen 518116, China.

ORCID-Profile: Tzong-Yi Lee, Song Wu

Förderung

  • National Natural Science Foundation of China
  • Shenzhen Engineering Research Center
  • Shenzhen Science and Technology Program

Zitieren

APA

Wu, P., Du, H., Yan, Y., Lee, T. Y., Bai, C., & Wu, S. (2024). Guided diffusion for molecular generation with interaction prompt. Briefings in Bioinformatics, 25(3). https://doi.org/10.1093/bib/bbae174

Vancouver

Wu P, Du H, Yan Y, Lee TY, Bai C, Wu S. Guided diffusion for molecular generation with interaction prompt. Briefings in Bioinformatics. 2024;25(3). doi:10.1093/bib/bbae174

BibTeX
@article{Wu2024,
  author = {Wu, Peng and Du, Huabin and Yan, Yingchao and Lee, Tzong-Yi and Bai, Chen and Wu, Song},
  title = {Guided diffusion for molecular generation with interaction prompt},
  journal = {Briefings in Bioinformatics},
  year = {2024},
  volume = {25},
  number = {3},
  doi = {10.1093/bib/bbae174}
}
Kostenlos starten →