EUVIMEDEUVIMED entdecken
Crossref

Predicting Protein Thermostability with Equivariant Graph Neural Networks and Contrastive Learning

Kai Han iD, Kai Zhong, Xiaoping Song, Weihua Wang, Yannan Bin iD, Ruifen Cao

Journal of Chemical Information and Modeling · 2026

DOI: 10.1021/acs.jcim.6c01926 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, 2026. Verfasst von Kai Han und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institutes of Physical Science and Information Technology, Anhui University, Hefei230601, China. Hauptthemen laut MEDLINE: Graph Neural Networks, Proteins, Temperature, Machine Learning. Die Arbeit nennt 57 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Graph Neural NetworksProteinsTemperatureMachine LearningComputational BiologyProtein StabilityModels, Molecular

Substanzen

Proteins

Autor:innen und Institutionen

  • Institutes of Physical Science and Information Technology, Anhui University, Hefei230601, China.
  • College of Pharmacy, Anhui Institute of Medicine, Hefei230061, China.
  • School of Computer Science and Technology, Anhui University, Hefei230601, China.

ORCID-Profile: Kai Han, Yannan Bin

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Han, K., Zhong, K., Song, X., Wang, W., Bin, Y., & Cao, R. (2026). Predicting Protein Thermostability with Equivariant Graph Neural Networks and Contrastive Learning. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.6c01926

Vancouver

Han K, Zhong K, Song X, Wang W, Bin Y, Cao R. Predicting Protein Thermostability with Equivariant Graph Neural Networks and Contrastive Learning. Journal of Chemical Information and Modeling. 2026. doi:10.1021/acs.jcim.6c01926

BibTeX
@article{Han2026,
  author = {Han, Kai and Zhong, Kai and Song, Xiaoping and Wang, Weihua and Bin, Yannan and Cao, Ruifen},
  title = {Predicting Protein Thermostability with Equivariant Graph Neural Networks and Contrastive Learning},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  doi = {10.1021/acs.jcim.6c01926}
}
Kostenlos starten →