Large Language and Protein Assistant for Protein-Protein Interactions prediction

Peng Zhou, Pengsen Ma, Jianmin Wang, Xibao Cai, Haitao Huang, Wei Liu, Longyue Wang, Lai Hou Tim, xiangxiang Zeng

Keywords: Multimodal;LLM;Protein-Protein Interaction;Binding Affinity Prediction

TL;DR: We've developed LLaPA, a large multimodal model that overcomes limitations of existing PPI network-based models by integrating proteins, PPI networks, and natural language.

Abstract: Predicting the types and affinities of protein-protein interactions (PPIs) is crucial for understanding biological processes and discovering macromolecular drugs. While encoding proteins themselves is essential, PPI networks can also provide rich prior knowledge for these predictive tasks. However, existing methods oversimplify the problem of PPI prediction in a semi-supervised manner when utilizing PPI networks, limiting their practical application. Furthermore, how to effectively use the rich prior knowledge of PPI networks for novel proteins not present in the network remains an unexplored issue. Additionally, due to inflexible architectures, existing methods cannot handle complexes containing an arbitrary number of proteins. To overcome these limitations, we introduce LLaPA (Large Language and Protein Assistant), a multimodal large language model that integrates proteins and PPI networks. LLaPA offers a more rational approach to utilizing PPI networks for PPI prediction and can fully exploit the information of PPI networks for unseen proteins. Through natural language instructions, LLaPA can accept any number of protein sequences and has the potential to perform various protein tasks. Experiments show that LLaPA achieves state-of-the-art performance in multi-label PPI type prediction and is capable of predicting the binding affinity between multiple interacting proteins based on sequence data.

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

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.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

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.

Submission Number: 6318