AUTHOR=Dang Tien , Nguyen Viet Thanh Duy , Le Minh Tuan , Hy Truong-Son 

TITLE=BioMedKG: multimodal contrastive representation learning in augmented BioMedical knowledge graphs

JOURNAL=Frontiers in Systems Biology

VOLUME=Volume 5 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/systems-biology/articles/10.3389/fsysb.2025.1651930

DOI=10.3389/fsysb.2025.1651930

ISSN=2674-0702

ABSTRACT=Biomedical Knowledge Graphs (BKGs) integrate diverse datasets to elucidate complex relationships within the biomedical field. Effective link prediction on these graphs can uncover valuable connections, such as potential new drug-disease relations. We introduce a novel multimodal approach that unifies embeddings from specialized Language Models (LMs) with Graph Contrastive Learning (GCL) to enhance intra-entity relationships while employing a Knowledge Graph Embedding (KGE) model to capture inter-entity relationships for effective link prediction. To address limitations in existing BKGs, we present PrimeKG++, an enriched knowledge graph incorporating multimodal data, including biological sequences and textual descriptions for each entity type. By combining semantic and relational information in a unified representation, our approach demonstrates strong generalizability, enabling accurate link predictions even for unseen nodes. Experimental results in PrimeKG++ and the DrugBank drug-target interaction dataset demonstrate the effectiveness and robustness of our method in diverse biomedical datasets. Our source code, pre-trained models, and data are publicly available at https://github.com/HySonLab/BioMedKG.