EUVIMEDEUVIMED entdecken
Crossref

SynerDTI: a synergistic deep learning framework for drug-target interaction prediction via global feature coordinated attention mechanism

Yuxuan Liao, Mugang Lin, Jia Peng, Yu Peng, Jiajia Liu

Molecular Diversity · 25.02.2026 · 30 (2) · 2749-2771

DOI: 10.1007/s11030-026-11491-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular Diversity, online erschienen am 25.02.2026. Verfasst von Yuxuan Liao und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Hengyang Normal University, Hengyang, 421002, China. Hauptthemen laut MEDLINE: Deep Learning, Drug Discovery. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: the Scientific Research Fund of Hunan Provincial Education Department, the National Natural Science Foundation of China, the 14th Five-Year Plan Key Disciplines and Application-oriented Special Disciplines of Hunan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To accelerate drug discovery and repurposing, many studies increasingly rely on computational methods to predict Drug-Target Interactions (DTIs). However, existing models often face challenges related to deep feature fusion and accurate interaction modeling between drugs and targets, which limit their predictive performance. To solve these problems, this paper proposes a novel deep neural network framework referred to as SynerDTI. It incorporates an Inception Convolutional Neural Network, which employs multi-scale convolutional techniques to efficiently extract local and global features, allowing to increase the modeling capabilities of multi-scale protein structures. In addition, a Residual Graph Convolutional Network is used to accurately capture complex topological features within drug molecular graphs by propagating and aggregating information from neighboring nodes. Moreover, a Global Feature Collaborative Attention mechanism is designed for feature fusion. It combines residual connections with attention operations in a parallel architecture. This synergistic mechanism allows the model to focus on key structural regions and learn richer interactive representations of drug and target features. Furthermore, the Kolmogorov-Arnold Network is introduced in the prediction phase to increase the nonlinear modeling capacity of the framework, which allows to increase its prediction accuracy and generalization ability. Experiments are finally conducted to compare SynerDTI with fifteen state-of-the-art models. The obtained results show that it consistently outperforms them on many benchmark datasets. These results demonstrate the high prediction efficiency of SynerDTI, highlighting its potential as a significant advancement in the computational drug discovery domain.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningDrug DiscoveryGraph Neural NetworksProteinsConvolutional Neural NetworksComputational BiologyNeural Networks, Computer

Stichwörter der Autor:innen

Attention mechanismDrug-target interaction predictionInception convolutional neural networkKolmogorov–Arnold networkResidual graph convolutional network

Substanzen

Proteins

Autor:innen und Institutionen

  • College of Computer Science and Technology, Hengyang Normal University, Hengyang, 421002, China.
  • College of Computer Science and Technology, Hengyang Normal University, Hengyang, 421002, China. mglin@hynu.edu.cn.
  • Hunan Engineering Research Center of Cyberspace Security Technology and Applications, Hengyang Normal University, Hengyang, 421002, China. mglin@hynu.edu.cn.
  • Hunan Provincial Key Laboratory of Intelligent Information Processing and Application, Hengyang, 421002, China. mglin@hynu.edu.cn.

Förderung

  • the Scientific Research Fund of Hunan Provincial Education Department
  • the National Natural Science Foundation of China
  • the 14th Five-Year Plan Key Disciplines and Application-oriented Special Disciplines of Hunan Province
  • the Science and Technology Plan Project of Hunan Province
  • the Hunan Provincial Natural Science Foundation of China

Zitieren

APA

Liao, Y., Lin, M., Peng, J., Peng, Y., & Liu, J. (2026). SynerDTI: a synergistic deep learning framework for drug-target interaction prediction via global feature coordinated attention mechanism. Molecular Diversity, 30(2), 2749-2771. https://doi.org/10.1007/s11030-026-11491-9

Vancouver

Liao Y, Lin M, Peng J, Peng Y, Liu J. SynerDTI: a synergistic deep learning framework for drug-target interaction prediction via global feature coordinated attention mechanism. Molecular Diversity. 2026;30(2):2749-2771. doi:10.1007/s11030-026-11491-9

BibTeX
@article{Liao2026,
  author = {Liao, Yuxuan and Lin, Mugang and Peng, Jia and Peng, Yu and Liu, Jiajia},
  title = {SynerDTI: a synergistic deep learning framework for drug-target interaction prediction via global feature coordinated attention mechanism},
  journal = {Molecular Diversity},
  year = {2026},
  volume = {30},
  number = {2},
  pages = {2749--2771},
  doi = {10.1007/s11030-026-11491-9}
}
Kostenlos starten →