A Domain Adaptive Interpretable Substructure-Aware Graph Attention Network for Drug–Drug Interaction Prediction
Interdisciplinary Sciences: Computational Life Sciences · 2025-12 · 17 (4) · 773-790
DOI: 10.1007/s12539-024-00680-5 ↗Kurz gefasst
Fachartikel in der Zeitschrift Interdisciplinary Sciences: Computational Life Sciences, online erschienen am 07.01.2025. Verfasst von Qi Zhang und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Science, Dalian Jiaotong University, Dalian, 116028, China. Hauptthemen laut MEDLINE: Drug Interactions, Neural Networks, Computer. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: Key Laboratory of Computational Science and Application of Hainan Province, the Fundamental Research Funds for the Provincial Universities of Liaoning.
Abstract (Originalsprache)
Accurate prediction of drug-drug interaction (DDI) is essential to improve clinical efficacy, avoid adverse effects of drug combination therapy, and enhance drug safety. Recently researchers have developed several computer-aided methods for DDI prediction. However, these methods lack the substructural features that are critical to drug interactions and are not effective in generalizing across domains and different distribution data. In this work, we present SAGAN, a domain adaptive interpretable substructure-aware graph attention network for DDI prediction. Based on attention mechanism and unsupervised clustering algorithm, we propose a new substructure segmentation method, which segments the drug molecule into multiple substructures, learns the mechanism of drug interaction from the perspective of interaction, and identifies important interaction regions between drugs. To enhance the generalization ability of the model, we improve and apply a conditional domain adversarial network to achieve cross-domain generalization by alternately optimizing the cross-entropy loss on the source domain and the adversarial loss of the domain discriminator. We evaluate and compare SAGAN with the state-of-the-art DDI prediction model on four real-world datasets for both in-domain and cross-domain scenarios, and show that SAGAN achieves the best overall performance. Moreover, the visualization results of the model show that SAGAN has achieved pharmacologically significant substructure extraction, which can help drug developers screen for some undiscovered local interaction sites, and provide important information for further drug structure optimization. The codes and datasets are available online at https://github.com/wyx2012/SAGAN .
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Science, Dalian Jiaotong University, Dalian, 116028, China.
- College of Software, Dalian Jiaotong University, Dalian, 116028, China.
- College of Science, Dalian Jiaotong University, Dalian, 116028, China. liutree80@163.com.
Förderung
- Key Laboratory of Computational Science and Application of Hainan Province
- the Fundamental Research Funds for the Provincial Universities of Liaoning
Zitieren
APA
Zhang, Q., Wei, Y., & Liu, L. (2025). A Domain Adaptive Interpretable Substructure-Aware Graph Attention Network for Drug–Drug Interaction Prediction. Interdisciplinary Sciences: Computational Life Sciences, 17(4), 773-790. https://doi.org/10.1007/s12539-024-00680-5
Vancouver
Zhang Q, Wei Y, Liu L. A Domain Adaptive Interpretable Substructure-Aware Graph Attention Network for Drug–Drug Interaction Prediction. Interdisciplinary Sciences: Computational Life Sciences. 2025;17(4):773-790. doi:10.1007/s12539-024-00680-5
BibTeX
@article{Zhang2025,
author = {Zhang, Qi and Wei, Yuxiao and Liu, Liwei},
title = {A Domain Adaptive Interpretable Substructure-Aware Graph Attention Network for Drug–Drug Interaction Prediction},
journal = {Interdisciplinary Sciences: Computational Life Sciences},
year = {2025},
volume = {17},
number = {4},
pages = {773--790},
doi = {10.1007/s12539-024-00680-5}
}
EUVIMED