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

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.