GraphDTA: predicting drug–target binding affinity with graph neural networks

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.

DeepPurpose: a deep learning library for drug–target interaction prediction

“…To demonstrate the use of DeepPurpose, we compare DeepPurpose with KronRLS ( Pahikkala et al , 2015 ), a popular DTI method, and GraphDTA ( Nguyen et al , 2020 ) and DeepDTA ( Öztürk et al , 2018 ), state-of-the-art DL methods. We find that many DeepPurpose models achieve comparable prediction performance on two benchmark datasets, DAVIS ( Davis et al , 2011 ) and KIBA ( He et al , 2017 ) ( Fig.…”

“…Deep learning (DL) has advanced traditional computational modeling of compounds by offering an increased expressive power in identifying, processing and extrapolating complex patterns in molecular data ( Lee et al , 2019 ; Öztürk et al , 2018 ). There are many DL models designed for DTI prediction (Lee et al , 2019; Nguyen et al , 2020 ; Öztürk et al , 2018 ). However, to generate predictions, deploy DL models in practice, test and evaluate model performance, one needs considerable programming skills and extensive biochemical knowledge.…”

Graph Neural Networks and Their Current Applications in Bioinformatics

“…This study realized the prediction of the real-valued interaction strength between drugs and targets and solved the cold-target problem. There are also some studies similar to the general thinking of the above-mentioned method but differ in data processing ( Gao et al, 2018 ; Nguyen et al, 2021 ). Miyazaki et al (2020) provided a drug–target interaction prediction model that ligands were specifically targeting toward proteins without using true negative interaction information.…”

MSA-Regularized Protein Sequence Transformer toward Predicting Genome-Wide Chemical-Protein Interactions: Application to GPCRome Deorphanization

“…End-to-end deep learning approaches have recently gained momentum. 10 11 Various neural network architectures, including Convolutional Neural Network (CNN), 12 13 seq2seq, 14 15 and Transformer, 16 have been applied to represent protein sequences. These works mainly focused on filling in missing CPIs for the existing drug targets.…”