AttentionMGT-DTA: A multi-modal drug-target affinity prediction using graph transformer and attention mechanism

AttentionMGT-DTA : A multi-modal drug-target affinity prediction using graph transformer and attention mechanism

Wu, Hongjie (author): Suzhou University of Science and Technology, Suzhou, China

Liu, Junkai (author): Suzhou University of Science and Technology, Suzhou, China; University of Electronic Science and Technology of China, Quzhou, China

Zou, Quan (author): University of Electronic Science and Technology of China, Quzhou, China

Qi, Shujie (author): Suzhou University of Science and Technology, Suzhou, China

Cui, Zhiming (author): Suzhou University of Science and Technology, Suzhou, China

Tiwari, Prayag, 1991- (author): Högskolan i Halmstad,Akademin för informationsteknologi

Ding, Yijie (author): University of Electronic Science and Technology of China, Quzhou, China

(creator_code:org_t)

Oxford : Elsevier, 2024
2024
English.
In: Neural Networks. - Oxford : Elsevier. - 0893-6080 .- 1879-2782. ; 169, s. 623-636

Related links:: https://doi.org/10.1...; show more...; https://urn.kb.se/re...; https://doi.org/10.1...; show less...

Abstract Subject headings

The accurate prediction of drug-target affinity (DTA) is a crucial step in drug discovery and design. Traditional experiments are very expensive and time-consuming. Recently, deep learning methods have achieved notable performance improvements in DTA prediction. However, one challenge for deep learning-based models is appropriate and accurate representations of drugs and targets, especially the lack of effective exploration of target representations. Another challenge is how to comprehensively capture the interaction information between different instances, which is also important for predicting DTA. In this study, we propose AttentionMGT-DTA, a multi-modal attention-based model for DTA prediction. AttentionMGT-DTA represents drugs and targets by a molecular graph and binding pocket graph, respectively. Two attention mechanisms are adopted to integrate and interact information between different protein modalities and drug-target pairs. The experimental results showed that our proposed model outperformed state-of-the-art baselines on two benchmark datasets. In addition, AttentionMGT-DTA also had high interpretability by modeling the interaction strength between drug atoms and protein residues. Our code is available at https://github.com/JK-Liu7/AttentionMGT-DTA. © 2023 The Author(s)

By the author/editor: Wu, Hongjie; Liu, Junkai; Jiang, Tengsheng; Zou, Quan; Qi, Shujie; Cui, Zhiming; show more...; Tiwari, Prayag, ...; Ding, Yijie; show less...

About the subject

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Computer Science ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.