EUVIMEDObjevte EUVIMED
Crossref

HAGGNN : Hydration‐Aware Geometric Graph Neural Network for Protein Thermal Stability Prediction

Yingying Jiang, Lingzhi Liu, Yanrui Ding iD

Proteins: Structure, Function, and Bioinformatics · 2026-08 · 94 (8) · 1485-1499

DOI: 10.1002/prot.70133 ↗

At a glance

Journal article in Proteins: Structure, Function, and Bioinformatics, published online on 2026-03-17. Written by Yingying Jiang and 2 co-authors. Institution: School of Science, Jiangnan University, Wuxi, China. Major MEDLINE topics: Proteins, Water. 47 references.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Water plays a fundamental thermodynamic role in determining protein structure, function, and stability. Rather than merely acting as a passive solvent, water actively participates in entropy‐driven free energy changes, which are crucial for stabilizing protein conformations. However, existing deep learning models for predicting protein thermal stability primarily focus on internal geometric and topological features, while neglecting the hierarchical hydration environment and its coupling with protein structure. To address this limitation, we propose a Hydration‐Aware Geometric Graph Neural Network (HAGGNN), which explicitly integrates hydration environment into geometric deep learning. HAGGNN introduces a unified Hydration‐Geometry Co‐Modeling framework that combines invariant and equivariant GNNs. HAGGNN enables the joint capture of geometric dependencies and hydration effects, providing a more comprehensive understanding of protein‐water interactions. Experiments on a large‐scale protein dataset demonstrate that HAGGNN achieves superior predictive performance compared with models that do not incorporate hydration thermodynamics. Ablation studies further confirm the essential contributions of each module. HAGGNN provides a new computational paradigm that integrates geometric learning with hydration environment, offering mechanistic insights into protein thermal stability prediction.

Subjects

MeSH terms (MEDLINE)

ProteinsWaterGraph Neural NetworksProtein StabilityThermodynamicsProtein ConformationDeep LearningComputational Biology

Author keywords

equivariant graph neural networkhydration environmentinvariant graph neural networkprotein thermostability prediction

Substances

ProteinsWater

Authors and institutions

  • School of Science, Jiangnan University, Wuxi, China.

ORCID profiles: Yanrui Ding

Cite

APA

Jiang, Y., Liu, L., & Ding, Y. (2026). HAGGNN : Hydration‐Aware Geometric Graph Neural Network for Protein Thermal Stability Prediction. Proteins: Structure, Function, and Bioinformatics, 94(8), 1485-1499. https://doi.org/10.1002/prot.70133

Vancouver

Jiang Y, Liu L, Ding Y. HAGGNN : Hydration‐Aware Geometric Graph Neural Network for Protein Thermal Stability Prediction. Proteins: Structure, Function, and Bioinformatics. 2026;94(8):1485-1499. doi:10.1002/prot.70133

BibTeX
@article{Jiang2026,
  author = {Jiang, Yingying and Liu, Lingzhi and Ding, Yanrui},
  title = {HAGGNN : Hydration‐Aware Geometric Graph Neural Network for Protein Thermal Stability Prediction},
  journal = {Proteins: Structure, Function, and Bioinformatics},
  year = {2026},
  volume = {94},
  number = {8},
  pages = {1485--1499},
  doi = {10.1002/prot.70133}
}
Start for free →