Chemical structure-aware molecular image representation learning
Briefings in Bioinformatics · 22.09.2023 · 24 (6)
DOI: 10.1093/bib/bbad404 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 16.11.2023. Verfasst von Hongxin Xiang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Engineering, Hunan University, Hunan, 410082, China. Hauptthemen laut MEDLINE: Learning, Benchmarking. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Hunan Provincial Natural Science Outstanding Youth Fund, Postgraduate Scientific Research Innovation Project of Hunan Province.
Abstract (Originalsprache)
Current methods of molecular image-based drug discovery face two major challenges: (1) work effectively in absence of labels, and (2) capture chemical structure from implicitly encoded images. Given that chemical structures are explicitly encoded by molecular graphs (such as nitrogen, benzene rings and double bonds), we leverage self-supervised contrastive learning to transfer chemical knowledge from graphs to images. Specifically, we propose a novel Contrastive Graph-Image Pre-training (CGIP) framework for molecular representation learning, which learns explicit information in graphs and implicit information in images from large-scale unlabeled molecules via carefully designed intra- and inter-modal contrastive learning. We evaluate the performance of CGIP on multiple experimental settings (molecular property prediction, cross-modal retrieval and distribution similarity), and the results show that CGIP can achieve state-of-the-art performance on all 12 benchmark datasets and demonstrate that CGIP transfers chemical knowledge in graphs to molecular images, enabling image encoder to perceive chemical structures in images. We hope this simple and effective framework will inspire people to think about the value of image for molecular representation learning.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information Science and Engineering, Hunan University, Hunan, 410082, China.
- Department of AIDD, Shanghai Yuyao Biotechnology Co., Ltd., Shanghai, 201109, China.
- School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, 430065, China.
- School of Informatics, Xiamen University, Xiamen, 361005, China.
- Zhejiang Lab, Hangzhou, 310013, China.
Förderung
- National Natural Science Foundation of China
- Hunan Provincial Natural Science Outstanding Youth Fund
- Postgraduate Scientific Research Innovation Project of Hunan Province
Zitieren
APA
Xiang, H., Jin, S., Liu, X., Zeng, X., & Zeng, L. (2023). Chemical structure-aware molecular image representation learning. Briefings in Bioinformatics, 24(6). https://doi.org/10.1093/bib/bbad404
Vancouver
Xiang H, Jin S, Liu X, Zeng X, Zeng L. Chemical structure-aware molecular image representation learning. Briefings in Bioinformatics. 2023;24(6). doi:10.1093/bib/bbad404
BibTeX
@article{Xiang2023,
author = {Xiang, Hongxin and Jin, Shuting and Liu, Xiangrong and Zeng, Xiangxiang and Zeng, Li},
title = {Chemical structure-aware molecular image representation learning},
journal = {Briefings in Bioinformatics},
year = {2023},
volume = {24},
number = {6},
doi = {10.1093/bib/bbad404}
}
EUVIMED