File(s) under permanent embargo
GraphDTA: Predicting drug target binding affinity with graph neural networks
journal contribution
posted on 2021-04-15, 00:00 authored by Thin NguyenThin Nguyen, H Le, Thomas Quinn, T Nguyen, T D Le, Svetha VenkateshSvetha VenkateshAbstract
Summary
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 implementation
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.
Supplementary information
Supplementary data are available at Bioinformatics online.
Summary
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 implementation
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.
Supplementary information
Supplementary data are available at Bioinformatics online.
History
Journal
BioinformaticsVolume
37Issue
8Pagination
1140 - 1147Publisher
OXFORD UNIV PRESSLocation
EnglandPublisher DOI
ISSN
1367-4803eISSN
1460-2059Language
EnglishPublication classification
C1.1 Refereed article in a scholarly journalUsage metrics
Categories
No categories selectedKeywords
Science & TechnologyLife Sciences & BiomedicineTechnologyPhysical SciencesBiochemical Research MethodsBiotechnology & Applied MicrobiologyComputer Science, Interdisciplinary ApplicationsMathematical & Computational BiologyStatistics & ProbabilityBiochemistry & Molecular BiologyComputer ScienceMathematicsINHIBITORSSMILES
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC