OneProt: Towards Multi-Modal Protein Foundation Models

TL;DR

OneProt is a multi-modal protein AI model integrating structural, sequence, text, and binding site data, demonstrating improved retrieval and downstream task performance, and enabling transfer learning across protein representations.

Contribution

It introduces a novel multi-modal protein modeling approach using ImageBind and combines GNNs and transformers, highlighting the importance of binding site data and transfer capabilities.

Findings

Strong performance in retrieval tasks

Enhanced downstream task accuracy

Binding site encoder is crucial for performance

Abstract

Recent advances in Artificial Intelligence have enabled multi-modal systems to model and translate diverse information spaces. Extending beyond text and vision, we introduce OneProt, a multi-modal AI for proteins that integrates structural, sequence, text, and binding site data. Using the ImageBind framework, OneProt aligns the latent spaces of protein modality encoders in a lightweight fine-tuning scheme that focuses on pairwise alignment with sequence data rather than requiring full matches. This novel approach comprises a mix of Graph Neural Networks and transformer architectures. It demonstrates strong performance in retrieval tasks and showcases the efficacy of multi-modal systems in Protein Machine Learning through a broad spectrum of downstream baselines, including enzyme function prediction and binding site analysis. Furthermore, OneProt enables the transfer of representational information from specialized encoders to the sequence encoder, enhancing capabilities for distinguishing evolutionarily related and unrelated sequences and exhibiting representational properties where evolutionarily related proteins align in similar directions within the latent space. In addition, we extensively investigate modality ablations to identify the encoders that contribute most to predictive performance, highlighting the significance of the binding site encoder, which has not been used in similar models previously. This work expands the horizons of multi-modal protein models, paving the way for transformative applications in drug discovery, biocatalytic reaction planning, and protein engineering.