2026-10-13T16:42:08Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34046871 2026-10-01T16:04:37Z category_1 category_4 category_14 category_734 category_931 portal_63 item_type_6 month_year_10_2026

Predicting Protein Thermostability with Equivariant Graph Neural Networks and Contrastive Learning Kai Han (1499161) Kai Zhong (423362) Xiaoping Song (525486) Weihua Wang (196992) Yannan Bin (6286199) Ruifen Cao (25157379) Biophysics Biochemistry Molecular Biology Biological Sciences not elsewhere classified Information Systems not elsewhere classified thermostability changes induced structure representation strategy residue interaction networks presenting obvious limitations industrial enzyme modification predicting protein thermostability robust feature representations experimental results demonstrate protein language models guiding protein engineering protein engineering feature propagation experimental outcomes language model three mutants structural modeling structural context potential applicability point mutations paper proposes method employs local microenvironments local microenvironment joint sequence core challenge building upon attention mechanism Accurately predicting the thermostability changes induced by single-point mutations is a core challenge in protein engineering and industrial enzyme modification. However, current computational methods often struggle to jointly integrate evolutionary information, structural context, and the interactions between mutation sites and their local microenvironments, presenting obvious limitations in guiding protein modification practice. To this end, this paper proposes the Equivariant Contrastive Learning Network (ECL-Net) for effectively predicting protein thermostability changes. Firstly, this method employs a joint sequence-structure representation strategy, deeply integrating sequence embeddings extracted by protein language models (PLMs) with spatial structural information captured by residue interaction networks, while an Equivariant Graph Neural Network (EGNN) is utilized for feature propagation and structural modeling. Furthermore, the self-attention mechanism of the language model is utilized to determine critical residues highly correlated with the mutation, thereby introducing structural microenvironment information. Building upon this, a contrastive learning method jointly guided by the mutation site and local microenvironment is designed, aiming to guide the model to learn more robust feature representations. Experimental results demonstrate that ECL-Net outperforms existing baseline models. Among the four predicted transglutaminase mutants, the model’s predictions for three mutants were consistent with the experimental outcomes, demonstrating the potential applicability of ECL-Net in guiding protein engineering. 2026-10-01T00:00:00Z Text Journal contribution 10.1021/acs.jcim.6c01926.s001 https://figshare.com/articles/journal_contribution/Predicting_Protein_Thermostability_with_Equivariant_Graph_Neural_Networks_and_Contrastive_Learning/34046871 CC BY-NC 4.0