Leveraging Multi-modal Representations to Predict Protein Melting Temperatures

TL;DR

This paper develops multi-modal protein models combining sequence, structure, and function data to improve the accuracy of predicting protein melting temperatures, achieving state-of-the-art results.

Contribution

It introduces a novel approach using multiple protein language models and feature extraction methods to enhance Delta Tm prediction accuracy.

Findings

ESM-3 model achieves PCC of 0.50 on s571 dataset

Multi-modal representations outperform single-modal models

Integration of sequence, structure, and function data improves predictions

Abstract

Accurately predicting protein melting temperature changes (Delta Tm) is fundamental for assessing protein stability and guiding protein engineering. Leveraging multi-modal protein representations has shown great promise in capturing the complex relationships among protein sequences, structures, and functions. In this study, we develop models based on powerful protein language models, including ESM-2, ESM-3 and AlphaFold, using various feature extraction methods to enhance prediction accuracy. By utilizing the ESM-3 model, we achieve a new state-of-the-art performance on the s571 test dataset, obtaining a Pearson correlation coefficient (PCC) of 0.50. Furthermore, we conduct a fair evaluation to compare the performance of different protein language models in the Delta Tm prediction task. Our results demonstrate that integrating multi-modal protein representations could advance the prediction of protein melting temperatures.