Discriminator‐Guided Inverse Folding for Multi‐Property Protein Design
Advanced Science · 2026
DOI: 10.1002/advs.75988 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Science, 2026. Verfasst von Yuchuan Zheng und 7 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Advanced Study in Physics, Zhejiang University, Hangzhou, China. Hauptthemen laut MEDLINE: Protein Folding, Proteins, Protein Engineering. Die Arbeit nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Beijing Natural Science Foundation.
Abstract (Originalsprache)
Designing proteins for real‐world applications requires the simultaneous satisfaction of multiple physicochemical properties. Structure‐based de novo protein design has become the prominent design paradigm, successfully creating numerous proteins. Property optimization is commonly introduced during the sequence generation stage of protein design, i.e., inverse folding. Existing methods primarily rely on fine‐tuning inverse folding models to design sequences with desired characteristics. However, multi‐property optimization through fine‐tuning demands datasets annotated with multiple properties—resources that remain extremely limited. Consequently, structure‐based protein design has not yet achieved joint optimization of multiple properties. Here, we present Discriminator‐Guided Inverse Folding (DGIF), a framework that guides the inverse folding model by adjusting its internal history states through an auxiliary discriminator module. The discriminator integrates multiple property predictors, each trained independently on a single‐property dataset, thereby enabling multi‐property optimization in the absence of datasets annotated with multiple properties. In addition to substantial improvements in key traits like thermostability and solubility, DGIF can generate protein sequences optimized for both properties simultaneously, with the designed proteins shifting markedly toward the Pareto front that represents optimal trade‐offs. Experimental results validate the effectiveness of DGIF for multi‐property protein design.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Institute for Advanced Study in Physics, Zhejiang University, Hangzhou, China.
- School of Physics, Zhejiang University, Hangzhou, China.
- The Sixth Laboratory, National Vaccine and Serum Institute (NVSI), Beijing, China.
- National Engineering Research Center for Novel Vaccines, Beijing, China.
- Shanghai Artificial Intelligence Laboratory, Shanghai, China.
- Laboratoire International Associé Centre National de la Recherche Scientifique et University of Illinois at Urbana-Champaign, Unité Mixte de Recherche n°7019, Université de Lorraine, B.P. 70239, Vandœuvre-lès-Nancy cede…
ORCID-Profile: Jingyuan Li
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Beijing Natural Science Foundation
- Natural Science Foundation of Beijing Municipality
Zitieren
APA
Zheng, Y., Liu, C., Liu, Z., Su, M., Tang, C., Zheng, X., Zhang, H., & Li, J. (2026). Discriminator‐Guided Inverse Folding for Multi‐Property Protein Design. Advanced Science. https://doi.org/10.1002/advs.75988
Vancouver
Zheng Y, Liu C, Liu Z, Su M, Tang C, Zheng X, et al. Discriminator‐Guided Inverse Folding for Multi‐Property Protein Design. Advanced Science. 2026. doi:10.1002/advs.75988
BibTeX
@article{Zheng2026,
author = {Zheng, Yuchuan and Liu, Chuyi and Liu, Zhaoming and Su, Mao and Tang, Chenyu and Zheng, Xiang and Zhang, Hao and Li, Jingyuan},
title = {Discriminator‐Guided Inverse Folding for Multi‐Property Protein Design},
journal = {Advanced Science},
year = {2026},
doi = {10.1002/advs.75988}
}
EUVIMED