MGKAN: Predicting Asymmetric Drug-Drug Interactions via a Multimodal Graph Kolmogorov-Arnold Network

2026-02-02

AI Summary

This work addresses the challenge of modeling nonlinear and asymmetric relationships in drug–drug interaction (DDI) prediction by proposing MGKAN, a novel framework that integrates Kolmogorov–Arnold Networks (KANs) into graph neural networks for the first time. Replacing conventional MLPs with learnable KAN basis functions, MGKAN incorporates multi-view pharmacological network fusion, role-aware embeddings, and a linear attention mechanism to effectively capture the directional nature and high-order nonlinear semantics of DDIs. Experimental results on two benchmark datasets demonstrate that MGKAN significantly outperforms seven state-of-the-art methods. Ablation studies and case analyses further confirm its superior performance in both prediction accuracy and directional modeling of drug interactions.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Multiagent Systems: Other Foundations of Multi Agent Systems

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Predicting drug-drug interactions (DDIs) is essential for safe pharmacological treatments. Previous graph neural network (GNN) models leverage molecular structures and interaction networks but mostly rely on linear aggregation and symmetric assumptions, limiting their ability to capture nonlinear and heterogeneous patterns. We propose MGKAN, a Graph Kolmogorov-Arnold Network that introduces learnable basis functions into asymmetric DDI prediction. MGKAN replaces conventional MLP transformations with KAN-driven basis functions, enabling more expressive and nonlinear modeling of drug relationships. To capture pharmacological dependencies, MGKAN integrates three network views-an asymmetric DDI network, a co-interaction network, and a biochemical similarity network-with role-specific embeddings to preserve directional semantics. A fusion module combines linear attention and nonlinear transformation to enhance representational capacity. On two benchmark datasets, MGKAN outperforms seven state-of-the-art baselines. Ablation studies and case studies confirm its predictive accuracy and effectiveness in modeling directional drug effects.

Problem

• drug-drug interactions
• asymmetric prediction
• nonlinear modeling
• graph neural networks
• pharmacological dependencies

Innovation

• Graph Kolmogorov-Arnold Network
• asymmetric drug-drug interactions
• multimodal graph fusion
• learnable basis functions
• directional semantics