Ukai, K.; Fujita, S.; Terada, T.

The rapid advancement of genome sequencing technologies has led to the accumulation of a vast number of protein sequences in public databases. However, a significant proportion of these proteins remain functionally uncharacterized. Concurrently, the expansion of protein sequence data has enabled the development of protein language models (pLMs). By distilling billions of years of evolutionary history into a latent representational space, these models have acquired an unprecedented capacity to predict both the tertiary structures and functions of proteins. In this study, we developed a deep learning-based method to predict whether two proteins catalyze the same enzymatic reaction. Our approach leverages latent representations generated by ESM Cambrian (ESM C), a state-of-the-art pLM, which are then processed through a neural network architecture integrating an attention mechanism. Our method outperformed existing approaches, including those based solely on full-length sequence similarity. Notably, it also surpassed our previous LightGBM-based model, which relied on structural similarity scores derived from AlphaFold-predicted models. Analysis of the attention weights reveals that our model autonomously highlights biologically significant sites, such as catalytic and binding residues. This demonstrates that integrating pLMs with attention mechanisms can enhance the accuracy and interpretability of protein function prediction while eliminating the need for manual feature engineering.