Skip to content

HGKAN: Hypergraph Kolmogorov-Arnold Networks for Interpretable Prediction of Herb–Symptom Associations

Aug 2026 · IEEE journal of biomedical and health informatics · Vol 30, pp. 8467-8478 · 0 citations · 46 references
Medicine Computer Science

Abstract

With the increasing availability of large-scale traditional Chinese medicine (TCM) data, accurate prediction of herb–symptom associations (HSAs) has become a crucial task in natural drug discovery. Existing computational approaches mainly employ graph neural networks (GNNs) to model herb–symptom relationships in biological information networks. However, these methods are limited to low-order pairwise associations, failing to capture herbs’ high-order effects and providing limited interpretability. To address these challenges, we model HSAs as a hierarchical hypergraph, where ingredients and targets form two distinct node layers, herbs and symptoms are represented as hyperedges connecting multiple nodes, and inter-layer edges capture ingredient–target interactions. Based on this structure, we propose hypergraph Kolmogorov-Arnold networks (HGKAN) comprising two modules: a binary interaction KAN (BiKAN) with bidirectional cross-attention for encoding pairwise ingredient–target interactions, and two high-order interaction KAN (HiKAN) branches for node-hyperedge message passing and selective high-order feature aggregation. Extensive experiments on two public TCM datasets show that HGKAN significantly outperforms 6 state-of-the-art baselines. Case studies further highlight the model’s interpretability and provide mechanistic insights into herbal treatment.

View source

Similar papers

Open access Oct 2026

Dual-stream decoupled hypergraph learning for compound-target interaction prediction in traditional Chinese medicine.

Experiments demonstrate that DSDHG outperforms existing state-of-the-art methods across multiple evaluation metrics, and case studies show that the proposed framework can effectively identify potential therapeutic targets of natural compounds and facilitate target discovery in TCM.

Le-Ying Chen, Min Luo, Liu-Yin Wang et al. · 0 citations
Oct 2026

UCEC: A Knowledge Graph-Assisted Machine Learning for Molecular-Mechanism-Interpretable Natural Product-Disease Association Prioritization.

A knowledge graph-assisted machine learning model: Uncertainty-Calibrated Evidence-Chains (UCEC) for prioritizing NP-disease associations and generating traceable mechanistic hypotheses for subsequent validation is proposed.

Wen-Yu Lu, Yi-Hui Cai, Xiao-Qian Peng et al. · 0 citations
Nov 2026

HyperDFI: Cross-View Hypergraph-Graph Contrastive Learning for Drug-Food Interaction Prediction

Drug-food interactions (DFIs) are one of the major factors that trigger adverse drug events and have important research and clinical application value. However, experimental identification of DFIs remains costly and limited in scalability, leading to insufficient coverage of known interactions. Existing computational...

Lan Huang, Zhi-Yao Han, Jia-Na Ding et al. · 0 citations
Conference Open access Oct 2026

Lightweight Graph Network for Efficient and Interpretable Cancer Drug Response Prediction

Accurate prediction of cancer drug response is essential for advancing precision oncology; however, existing deep learning approaches, particularly graph neural networks (GNNs), often rely on computationally intensive architectures and lack interpretability, limiting their applicability in real-world clinical settings....

A. Rangesh, G. Devika · 0 citations
Review Open access Oct 2026

Explainable AI for Network Pharmacology: A Critical Framework for Interpreting Multi-Target Drug Discovery on Biological Graphs

Network pharmacology examines drug action across interacting targets, pathways, and disease modules. Increasingly, however, the graph neural networks and knowledge-graph models used for this purpose are difficult to inspect. This critical narrative review considers feature attribution, attention, counterfactual and rul...

Khaled S. Allemailem, A. Almatroudi, Abdullah M. Alnajim · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.