MutPPI+: a multimodal framework for predicting mutation effects on protein–protein interactions via mutation-path-based data augmentation
Briefings in Bioinformatics · 01.03.2026 · 27 (2)
DOI: 10.1093/bib/bbag105 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 08.03.2026. Verfasst von Juntao Deng und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Automation, Tsinghua University, Shuangqing Road 30, Haidian District, Beijing, 100084, China. Hauptthemen laut MEDLINE: Mutation, Computational Biology, Deep Learning, Proteins. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Fundamental Research Funds for the Central Universities, China, National Science Foundation of China.
Abstract (Originalsprache)
Protein–protein interactions (PPIs) are central to cellular signaling and regulation, and their dysregulation underlies many diseases. Predicting the impact of mutations on PPI stability, quantified as ΔΔG, is essential for understanding disease mechanisms and guiding protein engineering. Here, we first present MutPPI, a graph-based deep-learning model that encodes full-residue structural features of protein–protein complexes and employs a shared GIN-GAT feature extractor for wild-type and mutant complexes. MutPPI outperforms 12 existing methods on an antibody–antigen single-point mutation dataset (S645). By integrating evolutionary information from protein language models, we further develop MutPPI-plus, achieving enhanced predictive performance. Second, we proposed a mutation-path-based data augmentation strategy, which enriches input modalities and improves generalization of both MutPPI and MutPPI-plus. After data augmentation, MutPPI-plus demonstrates state-of-the-art performance on S645 and three additional multi-point mutation datasets (SM_ZEMu, SM595, SM1124), substantially surpassing DDMut-PPI. Our analyses highlight the benefits of the multimodal framework and the physically informed data augmentation method. Together, these results provide a versatile computational tool for accurate ΔΔG prediction, advancing rational protein design.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Automation, Tsinghua University, Shuangqing Road 30, Haidian District, Beijing, 100084, China.
- Institute for Healthcare Artificial Intelligence Application, Guangdong Second Provincial General Hospital, Xingang Middle Road 466, Haizhu District, Guangzhou, 510317, China.
- Department of Nuclear Medicine, Jinan University, Huangpu Avenue West 601, Tianhe District, Guangzhou, 510632, China.
- College of Information Science & Technology, Beijing University of Chemical Technology, Beisanhuan East Road 15, Chaoyang District, Beijing, 100029, China.
ORCID-Profile: Juntao Deng, Min Liu, Weibin Cheng
Förderung
- Fundamental Research Funds for the Central Universities, China
- National Science Foundation of China
Zitieren
APA
Deng, J., Gu, M., Zhang, P., Liu, T., Hu, G., Dong, M., Zhang, Y., Song, Y., Zhang, Y., Liu, M., Tian, J., & Cheng, W. (2026). MutPPI+: a multimodal framework for predicting mutation effects on protein–protein interactions via mutation-path-based data augmentation. Briefings in Bioinformatics, 27(2). https://doi.org/10.1093/bib/bbag105
Vancouver
Deng J, Gu M, Zhang P, Liu T, Hu G, Dong M, et al. MutPPI+: a multimodal framework for predicting mutation effects on protein–protein interactions via mutation-path-based data augmentation. Briefings in Bioinformatics. 2026;27(2). doi:10.1093/bib/bbag105
BibTeX
@article{Deng2026,
author = {Deng, Juntao and Gu, Miao and Zhang, Pengyan and Liu, Tao and Hu, Guansong and Dong, Mingyu and Zhang, Yabin and Song, Yizhen and Zhang, Yunfan and Liu, Min and Tian, Junzhang and Cheng, Weibin},
title = {MutPPI+: a multimodal framework for predicting mutation effects on protein–protein interactions via mutation-path-based data augmentation},
journal = {Briefings in Bioinformatics},
year = {2026},
volume = {27},
number = {2},
doi = {10.1093/bib/bbag105}
}
EUVIMED