An effective self-supervised framework for learning expressive molecular global representations to drug discovery. Issue 6 (3rd May 2021)

• Record Type: Journal Article
• Authors: Li, Pengyong; Wang, Jun; Qiao, Yixuan; Chen, Hao; Yu, Yihuan; Yao, Xiaojun; Gao, Peng; Xie, Guotong; Song, Sen
• Is Part Of: Briefings in bioinformatics. Volume 22:Issue 6(2021)
• Publication Date: 2021-05-03
• Subjects: molecular representation -- deep learning -- graph neural network -- self-supervised learning; Genetics -- Data processing -- Periodicals; Molecular biology -- Data processing -- Periodicals; Genomes -- Data processing -- Periodicals; 572.80285
• DOI: 10.1093/bib/bbab109
• Languages: English
• ISSNs: 1467-5463

Abstract

Abstract: How to produce expressive molecular representations is a fundamental challenge in artificial intelligence-driven drug discovery. Graph neural network (GNN) has emerged as a powerful technique for modeling molecular data. However, previous supervised approaches usually suffer from the scarcity of labeled data and poor generalization capability. Here, we propose a novel molecular pre-training graph-based deep learning framework, named MPG, that learns molecular representations from large-scale unlabeled molecules. In MPG, we proposed a powerful GNN for modelling molecular graph named MolGNet, and designed an effective self-supervised strategy for pre-training the model at both the node and graph-level. After pre-training on 11 million unlabeled molecules, we revealed that MolGNet can capture valuable chemical insights to produce interpretable representation. The pre-trained MolGNet can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of drug discovery tasks, including molecular properties prediction, drug-drug interaction and drug-target interaction, on 14 benchmark datasets. The pre-trained MolGNet in MPG has the potential to become an advanced molecular encoder in the drug discovery pipeline.