LLM-H2G provides an effective framework for integrating biomedical semantics with heterogeneous hypergraph structure and may support interpretable discovery of biologically plausible herb–disease associations.
Abstract
Herb–disease association prediction is central to computational traditional medicine, but existing graph and hypergraph methods mainly rely on observed topology and underuse biomedical textual semantics, especially in heterogeneous or sparse association networks.
We propose LLM-H2G, a biomedical semantic-enhanced hypergraph contrastive learning framework that integrates herbs, compounds, proteins and diseases through an enhanced heterogeneous hypergraph. Entity names are encoded as large language model-derived semantic representations, injected into compound and protein propagation, and aligned with herb and disease structural readouts through an InfoNCE objective. Across TCM-suite and Ethnobotany benchmarks, LLM-H2G consistently outperforms representative network embedding, graph neural network, graph contrastive learning and hypergraph baselines, with the largest performance gaps observed for sparsely connected herbs. Ablation and parameter analyses show that both semantic enrichment and enhanced hypergraph construction are necessary for the observed gains. Case studies further show two complementary uses of the model: attribution and docking recover plausible compound–protein mediators for known associations, while literature-supported
de novo
predictions reveal candidate unannotated therapeutic paths.
LLM-H2G provides an effective framework for integrating biomedical semantics with heterogeneous hypergraph structure and may support interpretable discovery of biologically plausible herb–disease associations. As a representative new path, the
Ginkgo biloba
–Radiation Injuries prediction is supported by a coherent radiation-related MeSH cluster and PubMed-indexed experimental evidence.
BackgroundEfficient organization and retrieval of rapidly growing biomedical literature require representations that capture contextual semantics and explicit biomedical relationships. However, existing methods typically model text and ontology structure separately, producing incomplete representations with limited clu...
Mei-Jing Li, Jia-Shun Guo, Run-Qing Huang· Technology and Health Care· 0 citations
In drug-disease association prediction, graph neural networks (GNNs) offer a powerful means to maintain linear complexity without compromising high predictive accuracy. Our framework operates on a drug–Gene Ontology (GO)–disease tripartite graph, where GO terms serve as a functional bridge connecting drugs and diseases...
The rapid emergence of antimicrobial resistance necessitates AI-driven computational strategies to navigate the molecular diversity landscape of microbe-drug interactions. While graph neural networks have shown promise in predicting such associations, existing methods struggle with the intertwined challenges of process...
Yan-Bu Guo, Quan-Ming Guo, Jin-De Cao et al.· Journal of Biomedical Inform...· 0 citations
CDVGL-PDA’s strong predictive performance across balanced, imbalanced, and low-similarity datasets is demonstrated, while case studies highlight its ability to uncover potential PDAs, illustrating its promise for advancing disease mechanism research and therapeutic target discovery.
Xiang Chen, Li-Jun Quan, Ye-Xuan Mao et al.· Bioinform.· 0 citations
The proposed M2G-LLM (Multimodal MedGraph-LLM), a novel framework that enhances LLMs with multimodal integration and alignment via Graph Neural Networks (GNNs), highlights the promise of combining the language understanding of LLMs with the relational reasoning capabilities of GNNs for comprehensive, multimodal healthc...
Drug-drug interactions (DDIs) are critical in pharmacology, as synergistic or antagonistic effects between co-administered drugs can enhance therapeutic outcomes or cause toxicity, posing major challenges for drug safety assessment and new drug development. Current molecular representation methods often fail to capture...
Li Zhou, Yun Zuo, Wen-Ying He et al.· PLoS Computational Biology· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.