MoleMCL: a multi-level contrastive learning framework for molecular pre-training
Bioinformatics · 29.03.2024 · 40 (4)
DOI: 10.1093/bioinformatics/btae164 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 26.03.2024. Verfasst von Xinyi Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Technology, Xiamen University, Xiamen 361005, China. Hauptthemen laut MEDLINE: Drug Design, Semantics. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Motivation Molecular representation learning plays an indispensable role in crucial tasks such as property prediction and drug design. Despite the notable achievements of molecular pre-training models, current methods often fail to capture both the structural and feature semantics of molecular graphs. Moreover, while graph contrastive learning has unveiled new prospects, existing augmentation techniques often struggle to retain their core semantics. To overcome these limitations, we propose a gradient-compensated encoder parameter perturbation approach, ensuring efficient and stable feature augmentation. By merging enhancement strategies grounded in attribute masking and parameter perturbation, we introduce MoleMCL, a new MOLEcular pre-training model based on multi-level contrastive learning. Results Experimental results demonstrate that MoleMCL adeptly dissects the structure and feature semantics of molecular graphs, surpassing current state-of-the-art models in molecular prediction tasks, paving a novel avenue for molecular modeling. Availability and implementation The code and data underlying this work are available in GitHub at https://github.com/BioSequenceAnalysis/MoleMCL.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer Science and Technology, Xiamen University, Xiamen 361005, China.
- National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen 361005, China.
ORCID-Profile: Xinyi Zhang, Xiangrong Liu
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhang, X., Xu, Y., Jiang, C., Shen, L., & Liu, X. (2024). MoleMCL: a multi-level contrastive learning framework for molecular pre-training. Bioinformatics, 40(4). https://doi.org/10.1093/bioinformatics/btae164
Vancouver
Zhang X, Xu Y, Jiang C, Shen L, Liu X. MoleMCL: a multi-level contrastive learning framework for molecular pre-training. Bioinformatics. 2024;40(4). doi:10.1093/bioinformatics/btae164
BibTeX
@article{Zhang2024,
author = {Zhang, Xinyi and Xu, Yanni and Jiang, Changzhi and Shen, Lian and Liu, Xiangrong},
title = {MoleMCL: a multi-level contrastive learning framework for molecular pre-training},
journal = {Bioinformatics},
year = {2024},
volume = {40},
number = {4},
doi = {10.1093/bioinformatics/btae164}
}
EUVIMED