ReLMole: Molecular Representation Learning Based on Two-Level Graph Similarities
- 27 October 2022
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 62 (22) , 5361-5372
Abstract
Molecular representation is a critical part of various prediction tasks for physicochemical properties of molecules and drug design. As graph notations are common in expressing the structural information of chemical compounds, graph neural networks (GNNs) have become the mainstream backbone model for learning molecular representation. However, the scarcity of task-specific labels in the biomedical domain limits the power of GNNs. Recently, self-supervised pretraining for GNNs has been leveraged to deal with this issue, while the existing pretraining methods are mainly designed for graph data in general domains without considering the specific data properties of molecules. In this paper, we propose a representation learning method for molecular graphs, called ReLMole, which is featured by a hierarchical graph modeling of molecules and a contrastive learning scheme based on two-level graph similarities. We assess the performance of ReLMole on two types of downstream tasks, namely, the prediction of molecular properties (MPs) and drug-drug interaction (DDIs). ReLMole achieves promising results for all the tasks. It outperforms the baseline models by over 2.6% on ROC-AUC averaged across six MP prediction tasks, and it improves the F1 value by 7-18% in DDI prediction for unseen drugs compared with other self-supervised models.Keywords
Funding Information
- National Natural Science Foundation of China (61972251, 62272300)
This publication has 35 references indexed in Scilit:
- Maximum Common Substructure-Based Data Fusion in Similarity SearchingJournal of Chemical Information and Modeling, 2015
- Similarity-based modeling in large-scale prediction of drug-drug interactionsNature Protocols, 2014
- SWEETLEAD: an In Silico Database of Approved Drugs, Regulated Chemicals, and Herbal Isolates for Computer-Aided Drug DiscoveryPLOS ONE, 2013
- Drug—drug interaction through molecular structure similarity analysisJournal of the American Medical Informatics Association, 2012
- A Bayesian Approach to in Silico Blood-Brain Barrier Penetration ModelingJournal of Chemical Information and Modeling, 2012
- Extended-Connectivity FingerprintsJournal of Chemical Information and Modeling, 2010
- On the Art of Compiling and Using 'Drug‐Like' Chemical Fragment SpacesChemMedChem, 2008
- A maximum common substructure-based algorithm for searching and predicting drug-like compoundsBioinformatics, 2008
- DrugBank: a knowledgebase for drugs, drug actions and drug targetsNucleic Acids Research, 2007
- The Properties of Known Drugs. 1. Molecular FrameworksJournal of Medicinal Chemistry, 1996