An ensemble learning framework for protein stability prediction with enhanced recognition of stabilizing mutations
Protein Science · 2026
DOI: 10.1002/pro.70728 ↗Kurz gefasst
Fachartikel in der Zeitschrift Protein Science, 2026. Verfasst von Yang Liu und 2 weiteren Autor:innen. Beteiligte Einrichtung: Jiangsu Key Laboratory of Drug Discovery and Translational Research for Brain Diseases, School of Basic Medical Sciences, Soochow University, Suzhou,…. Hauptthemen laut MEDLINE: Mutation, Proteins, Computational Biology. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Basic Research Program of Jiangsu, Priority Academic Program Development of Jiangsu Higher Education Institutions.
Abstract (Originalsprache)
Accurately predicting mutation‐induced protein stability changes remains a central challenge in structural bioinformatics. Existing methods exhibit a strong bias toward destabilizing mutations, leading to limited performance for stabilizing mutations and constraining their utility in protein engineering. Here, we address this limitation through two complementary strategies: balanced dataset construction and integrative modeling. To mitigate the severe class imbalance in current stability datasets, we constructed undersampling‐based balanced datasets and further evaluated reverse‐mutation augmentation as a comparative strategy. Building on the rapid development of high‐performing predictors, we hypothesized that integrating their outputs could exploit complementary strengths and improve predictive accuracy. Accordingly, we developed three modeling frameworks, including models based on handcrafted features, models using embedding representations extracted from ProteinMPNN, and ensemble models integrating a diverse set of state‐of‐the‐art predictors. Across multiple independent test sets, ensemble models consistently outperformed individual approaches, with particularly pronounced gains in identifying stabilizing mutations. These findings demonstrate that combining undersampling‐based balanced data construction with systematic predictor integration provides an effective and practical strategy for achieving more balanced and accurate protein stability prediction, and offers a useful framework for identifying stabilizing mutations in protein engineering and related applications. StaMutAble is freely available at: https://github.com/minghuilab/StaMutAble .
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Jiangsu Key Laboratory of Drug Discovery and Translational Research for Brain Diseases, School of Basic Medical Sciences, Soochow University, Suzhou, Jiangsu, China.
- Biomedical Basic Research Center (BBRC) of Jiangsu, Soochow University, Suzhou, Jiangsu, China.
- MOE Key Laboratory of Geriatric Diseases and Immunology, School of Basic Medical Sciences, Suzhou Medical College of Soochow University, Suzhou, Jiangsu, China.
Förderung
- Basic Research Program of Jiangsu
- Priority Academic Program Development of Jiangsu Higher Education Institutions
Zitieren
APA
Liu, Y., Zhang, J., & Li, M. (2026). An ensemble learning framework for protein stability prediction with enhanced recognition of stabilizing mutations. Protein Science. https://doi.org/10.1002/pro.70728
Vancouver
Liu Y, Zhang J, Li M. An ensemble learning framework for protein stability prediction with enhanced recognition of stabilizing mutations. Protein Science. 2026. doi:10.1002/pro.70728
BibTeX
@article{Liu2026,
author = {Liu, Yang and Zhang, Jian and Li, Minghui},
title = {An ensemble learning framework for protein stability prediction with enhanced recognition of stabilizing mutations},
journal = {Protein Science},
year = {2026},
doi = {10.1002/pro.70728}
}
EUVIMED