Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Sep 30;24(1):367.
doi: 10.1186/s12859-023-05497-5.

DGDTA: dynamic graph attention network for predicting drug-target binding affinity

Haixia Zhai  1 , Hongli Hou  1 , Junwei Luo  2 , Xiaoyan Liu  1 , Zhengjiang Wu  1 , Junfeng Wang  1
Affiliations

DGDTA: dynamic graph attention network for predicting drug-target binding affinity

Haixia Zhai et al. BMC Bioinformatics. .

Abstract

Background: Obtaining accurate drug-target binding affinity (DTA) information is significant for drug discovery and drug repositioning. Although some methods have been proposed for predicting DTA, the features of proteins and drugs still need to be further analyzed. Recently, deep learning has been successfully used in many fields. Hence, designing a more effective deep learning method for predicting DTA remains attractive.

Results: Dynamic graph DTA (DGDTA), which uses a dynamic graph attention network combined with a bidirectional long short-term memory (Bi-LSTM) network to predict DTA is proposed in this paper. DGDTA adopts drug compound as input according to its corresponding simplified molecular input line entry system (SMILES) and protein amino acid sequence. First, each drug is considered a graph of interactions between atoms and edges, and dynamic attention scores are used to consider which atoms and edges in the drug are most important for predicting DTA. Then, Bi-LSTM is used to better extract the contextual information features of protein amino acid sequences. Finally, after combining the obtained drug and protein feature vectors, the DTA is predicted by a fully connected layer. The source code is available from GitHub at https://github.com/luojunwei/DGDTA .

Conclusions: The experimental results show that DGDTA can predict DTA more accurately than some other methods.

Keywords: Drug discovery; Drug–target binding affinity; Dynamic graph attention network; Long short-term memory.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
General architecture of DGDTA
Fig. 2
Fig. 2
Comparison between baseline1 and different models at 200 and 1000 epochs
Fig. 3
Fig. 3
Comparison between baseline2 and different models at 200 and 1000 epochs
Fig. 4
Fig. 4
CI comparison among the experimental methods on the Davis and KIBA datasets
Fig. 5
Fig. 5
Attention coefficients of the GAT and GATv2
Fig. 6
Fig. 6
MSE trend
Fig. 7
Fig. 7
Visualization of the binding of a drug ‘DB5329102’ and a target ‘ITK’
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Strittmatter SM. Old drugs learn new tricks. Nat Med. 2014;20(6):590. doi: 10.1038/nm.3595. - DOI - PMC - PubMed
    1. Affinity2Vec drug–target binding affinity prediction through representation learning, graph mining, and machine learning. Sci Rep. 2022;12(1):1–18. - PMC - PubMed
    1. Wan S, Kumar D, Ilyin V, Homsi UA, Coveney PV. The effect of protein mutations on drug binding suggests ensuing personalised drug selection. Sci Rep. 2021;11(1):13452. doi: 10.1038/s41598-021-92785-w. - DOI - PMC - PubMed
    1. Ashburn TT, Thor KB. Drug repositioning: identifying and developing new uses for existing drugs. Nat Rev Drug Discov. 2004;3(8):673–683. doi: 10.1038/nrd1468. - DOI - PubMed
    1. Guan J, Tian K, Wang Y, Shao M, Zhou S. Boosting compound-protein interaction prediction by deep learning. Methods Companion Methods Enzymol. 2016;110:64–72. doi: 10.1016/j.ymeth.2016.06.024. - DOI - PubMed

LinkOut - more resources

-