Zhang_2025_J.Chem.Inf.Model__

Developing enzymes with desired thermal properties is crucial for a wide range of industrial and research applications, and determining temperature stability is an essential step in this process. Experimental determination of thermal parameters is labor-intensive, time-consuming, and costly. Moreover, existing computational approaches are often hindered by limited data availability and imbalanced distributions. To address these challenges, we introduce a curated temperature stability data set designed for model development and benchmarking in enzyme thermal modeling. Leveraging this data set, we present the Segment Transformer, a novel deep learning framework that enables efficient and accurate prediction of enzyme temperature stability. The model achieves state-of-the-art performance with RMSE of 23.29, MAE of 17.37, Pearson correlation of 0.35, and Spearman correlation of 0.34, respectively. These results highlight the effectiveness of incorporating segment-level representations, grounded in the biological observation that different regions of a protein sequence contribute unequally to thermal behavior. As a proof of concept, we applied the Segment Transformer to guide the engineering of a cutinase enzyme. Experimental validation demonstrated a 1.64-fold improvement in relative activity following heat treatment, achieved through only 17 mutations and without compromising catalytic function.