Biobridge: Bridging Biomedical Foundation Models Via Knowledge Graphs

Abstract

Foundation models (FMs) are able to leverage large volumes of unlabeled data to demonstrate superior performance across a wide range of tasks. However, FMs developed for biomedical domains have largely remained unimodal, i.e., independently trained and used for tasks on protein sequences alone, small molecule structures alone, or clinical data alone. To overcome this limitation of biomedical FMs, we present BioBridge, a novel parameter-efficient learning framework, to bridge independently trained unimodal FMs to establish multimodal behavior. BioBridge achieves it by utilizing Knowledge Graphs (KG) to learn transformations between one unimodal FM and another without fine-tuning any underlying unimodal FMs. Our empirical results demonstrate that BioBridge can beat the best baseline KG embedding methods (on average by around 76.3%) in cross-modal retrieval tasks. We also identify BioBridge demonstrates out-of-domain generalization ability by extrapolating to unseen modalities or relation

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2023biobridge

Related papers

• Thin Bridges For Drug Text Alignment: Lightweight Contrastive Learning For Target Specific Drug Retrieval (2025)0.00
• Unigraph2: Learning A Unified Embedding Space To Bind Multimodal Graphs (2025)6.77
• Medgraph: An Experimental Semantic Information Retrieval Method Using Knowledge Graph Embedding For The Biomedical Citations Indexed In Pubmed (2021)0.00
• RAG-GFM: Overcoming In-memory Bottlenecks In Graph Foundation Models Via Retrieval-augmented Generation (2026)0.00
• Interfacing Foundation Models' Embeddings (2023)0.00
• Honeybee: A Scalable Modular Framework For Creating Multimodal Oncology Datasets With Foundational Embedding Models (2024)0.00
• Graph-based Retriever Captures The Long Tail Of Biomedical Knowledge (2024)0.00
• Multimodal Learning For Scalable Representation Of High-dimensional Medical Data (2024)0.00