USP-ddG: a unified structural paradigm with data efficacy and mixture-of-experts for predicting mutational effects on protein–protein interactions
Bioinformatics · 01.07.2026 · 42 (Supplement_1)
DOI: 10.1093/bioinformatics/btag249 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 07.07.2026. Verfasst von Guanglei Yu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Central South University, Changsha 410083, China. Hauptthemen laut MEDLINE: Proteins, Mutation, Computational Biology, Protein Interaction Mapping. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Xiangjiang Laboratory, High Performance Computing Center of Central South University.
Abstract (Originalsprache)
Motivation Accurately estimating changes in binding free energy (ΔΔG) is critical for understanding protein–protein interactions (PPIs) and guiding rational protein design. Recent deep learning methods have achieved notable progress by pre-training on large-scale structural data. While some approaches explore structural flexibility through energy-based sampling or generative modeling, these strategies typically involve substantial computational cost and overlook data efficacy in terms of training data organization. Results We present USP-ddG, a unified structural paradigm for ΔΔG prediction built on a dual-channel architecture. The model incorporates three complementary components: (i) an inverse folding-based log-odds ratio, (ii) the empirical force field FoldX capturing side-chain packing energetics, and (iii) a geometric encoder that leverages Gaussian coordinate perturbation as a regularization strategy to improve robustness. To enhance representation capacity, we introduce a framework that integrates feed-forward network (FFN) and Mixture-of-Experts (MoE) to model domain-invariant and -specific features, respectively. We further propose CATH-guided Folding Ordering (CFO), a data efficacy strategy that organizes samples to mitigate catastrophic forgetting and data distribution bias. USP-ddG consistently outperforms existing state-of-the-art methods on the SKEMPI v2.0 benchmark, including the challenging hold-out CATH test set. It achieves superior accuracy on both single- and multi-point mutations and demonstrates strong performance in antibody affinity optimization against H1N1 and HER2, and in predicting the impact of SARS-CoV-2 variants on hACE2 binding. Ablation studies confirm the contribution of each component. These results highlight USP-ddG as a robust and data-efficient framework for modeling mutational effects on PPIs. Availability and implementation USP-ddG is available at https://github.com/ak422/USP-ddG.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Computer Science and Engineering, Central South University, Changsha 410083, China.
- Hunan Provincial Key Lab on Bioinformatics, Central South University, Changsha 410083, China.
- College of Medical Engineering and Technology, Xinjiang Medical University, Urumqi 830017, China.
ORCID-Profile: Qichang Zhao, Jianxin Wang
Förderung
- National Natural Science Foundation of China
- Xiangjiang Laboratory
- High Performance Computing Center of Central South University
Zitieren
APA
Yu, G., Bi, X., Zhao, Q., & Wang, J. (2026). USP-ddG: a unified structural paradigm with data efficacy and mixture-of-experts for predicting mutational effects on protein–protein interactions. Bioinformatics, 42(Supplement_1). https://doi.org/10.1093/bioinformatics/btag249
Vancouver
Yu G, Bi X, Zhao Q, Wang J. USP-ddG: a unified structural paradigm with data efficacy and mixture-of-experts for predicting mutational effects on protein–protein interactions. Bioinformatics. 2026;42(Supplement_1). doi:10.1093/bioinformatics/btag249
BibTeX
@article{Yu2026,
author = {Yu, Guanglei and Bi, Xuehua and Zhao, Qichang and Wang, Jianxin},
title = {USP-ddG: a unified structural paradigm with data efficacy and mixture-of-experts for predicting mutational effects on protein–protein interactions},
journal = {Bioinformatics},
year = {2026},
volume = {42},
number = {Supplement_1},
doi = {10.1093/bioinformatics/btag249}
}
EUVIMED