Drug-target interaction prediction via hierarchical gated attention and information bottleneck
Complex Engineering Systems · 28.05.2026 · 6 (2)
DOI: 10.20517/ces.2025.88 ↗Kurz gefasst
Fachartikel in der Zeitschrift Complex Engineering Systems, online erschienen am 28.05.2026. Verfasst von Shengli Song und 4 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben.
Abstract (Originalsprache)
Accurate drug-target interaction (DTI) prediction is essential for drug repositioning and accelerating drug discovery. Deep learning methods have made remarkable progress over traditional biological experiments, yet existing models often fail to capture local node topologies and multi-view semantic dependencies simultaneously. Moreover, most methods rely on basic loss functions that cannot filter out redundant noise, hindering the learning of compact and discriminative node representations. In this work, we propose a DTI prediction framework that integrates a hierarchical gated multi-head attention (HGMA) mechanism with an information bottleneck (IB) strategy. HGMA adopts a two-layer architecture: the first layer performs weighted aggregation over semantic meta-paths, and the second layer fuses attention heads via an adaptive gating mechanism, enhancing drug and target representations. The IB module compresses inputs by removing task-irrelevant redundancy while preserving predictive information, improving discriminability and generalization. Extensive experiments show that our model consistently outperforms state-of-the-art methods in both accuracy and robustness.
Zitieren
APA
Song, S., Chen, Z., Wang, Y., Guo, Q., & Guo, Y. (2026). Drug-target interaction prediction via hierarchical gated attention and information bottleneck. Complex Engineering Systems, 6(2). https://doi.org/10.20517/ces.2025.88
Vancouver
Song S, Chen Z, Wang Y, Guo Q, Guo Y. Drug-target interaction prediction via hierarchical gated attention and information bottleneck. Complex Engineering Systems. 2026;6(2). doi:10.20517/ces.2025.88
BibTeX
@article{Song2026,
author = {Song, Shengli and Chen, Zihao and Wang, Yihan and Guo, Quanming and Guo, Yanbu},
title = {Drug-target interaction prediction via hierarchical gated attention and information bottleneck},
journal = {Complex Engineering Systems},
year = {2026},
volume = {6},
number = {2},
doi = {10.20517/ces.2025.88}
}
EUVIMED