BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs

Zifeng Wang, Zichen Wang, Balasubramaniam Srinivasan, Vassilis N. Ioannidis, Huzefa Rangwala, RISHITA ANUBHAI

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: drug discovery, foundation model, multi-modal learning, knowledge graph

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We developed a parameter-efficient method to bridge multiple unimodal biomedical foundation models using a knowledge graph to enable multi-modal functionalities.

Abstract:

Foundation models (FMs) learn from 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, we present BioBridge, a 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 results demonstrate that BioBridge can
beat the best baseline KG embedding methods (on average by ~ 76.3%) in cross-modal retrieval tasks. We also identify BioBridge demonstrates out-of-domain generalization ability by extrapolating to unseen modalities or relations. Additionally, we also show that BioBridge presents itself as a general-purpose retriever that can aid biomedical multimodal question answering as well as enhance the guided generation of novel drugs. Code is at https://github.com/RyanWangZf/BioBridge.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 989