EUVIMEDEUVIMED entdecken
Crossref

An Attention-Gated Graph Spiking Neural Membrane System for Structure-Activity Relationship Prediction

Jun Fu iD, Jianyi Zhang iD, Hong Peng iD, Wenxuan Zhang iD, Kaiying Han iD, Xiali Hei iD

International Journal of Neural Systems · 2026-08 · 36 (08)

DOI: 10.1142/s0129065726500231 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Neural Systems, online erschienen am 28.02.2026. Verfasst von Jun Fu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Beijing Electronic Science and Technology Institute, Beijing 100070, P. R. China. Hauptthemen laut MEDLINE: Action Potentials, Neurons, Attention, Models, Neurological. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 51 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spiking Neural P (SNP) systems have attracted increasing attention due to their biologically inspired, event-driven computation and inherent capability for temporal modeling. However, most existing SNP variants rely on fixed or purely local information propagation mechanisms, which limits their ability to capture long-range dependencies and contextual interactions in complex structured data. To address this limitation, we propose an Attention-Gated Spiking Neural membrane system (AGSNP), which incorporates an attention-guided gating mechanism directly into the spiking neuron dynamics. Unlike prior SNP models that treat attention as an external aggregation operation, AGSNP embeds attention signals into the nonlinear spiking update and memory regulation process. This design enables adaptive information propagation across distant structural components while preserving biologically inspired spiking behavior. To evaluate the effectiveness of the proposed architecture, AGSNP is instantiated within a graph-based learning framework and applied to Structure Activity Relationship (SAR) prediction. Experiments on three publicly available benchmark datasets demonstrate that AGSNP consistently outperforms representative baseline methods. Notably, under limited data availability and severe class imbalance, the proposed model achieves improvements of approximately 2.0–5.7% in AUC and related metrics on the Tox21 dataset, and 3.5–17.0% on the MUV dataset.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Action PotentialsNeuronsAttentionModels, NeurologicalStructure-Activity RelationshipHumansAnimalsGraph Neural Networks

Stichwörter der Autor:innen

Spiking neural membrane systemgraph attention mechanismstructure activity relationship

Autor:innen und Institutionen

  • Beijing Electronic Science and Technology Institute, Beijing 100070, P. R. China.
  • Xihua University, Chengdu 610039, P. R. China.
  • Institute of Materia Medica, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 10050, P. R. China.
  • SWJTU-LEEDS Joint School Southwest Jiaotong University, Chengdu 611756, P. R. China.
  • University of Louisiana at Lafayette, Lafayette 70503, USA.

ORCID-Profile: Jun Fu, Jianyi Zhang, Hong Peng, Wenxuan Zhang, Kaiying Han, Xiali Hei

Zitieren

APA

Fu, J., Zhang, J., Peng, H., Zhang, W., Han, K., & Hei, X. (2026). An Attention-Gated Graph Spiking Neural Membrane System for Structure-Activity Relationship Prediction. International Journal of Neural Systems, 36(08). https://doi.org/10.1142/s0129065726500231

Vancouver

Fu J, Zhang J, Peng H, Zhang W, Han K, Hei X. An Attention-Gated Graph Spiking Neural Membrane System for Structure-Activity Relationship Prediction. International Journal of Neural Systems. 2026;36(08). doi:10.1142/s0129065726500231

BibTeX
@article{Fu2026,
  author = {Fu, Jun and Zhang, Jianyi and Peng, Hong and Zhang, Wenxuan and Han, Kaiying and Hei, Xiali},
  title = {An Attention-Gated Graph Spiking Neural Membrane System for Structure-Activity Relationship Prediction},
  journal = {International Journal of Neural Systems},
  year = {2026},
  volume = {36},
  number = {08},
  doi = {10.1142/s0129065726500231}
}
Kostenlos starten →