GraphDTA: Predicting drug–target binding affinity with graph neural networks
Authors:
- Thin NguyenTNThin Nguyen
- Thomas P. QuinnTQThomas P. Quinn
- Tri NguyenTNTri Nguyen
- Thuc Duy LeTLThuc Duy Le
Preprint
Abstract
The development of new drugs is costly, time consuming, and often accompanied with safety issues. Drug repurposing can avoid the expensive and lengthy process of drug development by finding new uses for already approved drugs. In order to repurpose drugs effectively, it is useful to know which proteins are targeted by which drugs. Computational models that estimate the interaction strength of new drug--target pairs have the potential to expedite drug repurposing. Several models have been proposed for this task. However, these models represent the drugs as strings, which is not a natural way to represent molecules. We propose a new model called GraphDTA that represents drugs as graphs and uses graph neural networks to predict drug--target affinity. We show that graph neural networks not only predict drug--target affinity better than non-deep learning models, but also outperform competing deep learning methods. Our results confirm that deep learning models are appropriate for drug--target binding affinity prediction, and that representing drugs as graphs can lead to further improvements. Availability of data and materials: The proposed models are implemented in Python. Related data, pre-trained models, and source code are publicly available at https://github.com/thinng/GraphDTA . All scripts and data needed to reproduce the post-hoc statistical analysis are available from https://doi.org/10.5281/zenodo.3603523 . Contact: Thin.Nguyen@deakin.edu.auKeywords
All Related Versions
- Published version: Bioinformatics, 37 (8), 1140.
This publication has 33 references indexed in Scilit:
- Comprehensive analysis of kinase inhibitor selectivityNature Biotechnology, 2011
- ChemMine tools: an online service for analyzing and clustering small moleculesNucleic Acids Research, 2011
- A Machine Learning-Based Method To Improve Docking Scoring Functions and Its Application to Drug RepurposingJournal of Chemical Information and Modeling, 2011
- Pharmacogenetics in drug discovery and development: a translational perspectiveNature Reviews Drug Discovery, 2008
- Drug repositioning: identifying and developing new uses for existing drugsNature Reviews Drug Discovery, 2004
- Protein Kinase Inhibitors: Insights into Drug Design from StructureScience, 2004
- Feature Selection for Descriptor Based Classification Models. 2. Human Intestinal Absorption (HIA)Journal of Chemical Information and Computer Sciences, 2004
- The Protein Kinase Complement of the Human GenomeScience, 2002
- Protein kinases — the major drug targets of the twenty-first century?Nature Reviews Drug Discovery, 2002
- SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rulesJournal of Chemical Information and Computer Sciences, 1988