Co-design protein sequence and structure in discrete space via generative flow
Bioinformatics · 2025
DOI: 10.1093/bioinformatics/btaf248 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2025. Verfasst von Sen Yang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Bioinformatics Center of AMMS, Beijing, 100039, China. Hauptthemen laut MEDLINE: Proteins, Software, Computational Biology, Protein Engineering. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Motivation Generative models have demonstrated considerable promise in de novo protein design. Traditional approaches typically focus on either sequence or structure in isolation, limiting the capacity to explore the intricate sequence–structure landscape and achieve optimal designs. However, joint protein sequence and structure co-design remains a largely underexplored challenge. Results We present CoFlow, a discrete model for protein co-design from scratch or given constraints. CoFlow employs a joint discrete flow and integrates a multi-modal protein masked language model to facilitate co-design in the discrete space. Comprehensive experiments demonstrate that CoFlow outperforms previous design methods across multiple evaluation metrics. Notably, CoFlow achieves a consistency approximately eight times higher than that of ESM3 in unconditional generation. Moreover, CoFlow exhibits competitive performance in conditional generation tasks, including motif-scaffolding, protein folding, and inverse folding. Availability and implementation The source code of CoFlow, including data preprocessing and model, is available at https://github.com/LtECoD/CoFlow and https://zenodo.org/records/14842367. (DOI: 10.5281/zenodo.14842367).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Bioinformatics Center of AMMS, Beijing, 100039, China.
- The 921st Hospital of Chinese PLA, Changsha, 410073, China.
- Computer College, National University of Defense Technology, Changsha, 410073, China.
ORCID-Profile: Sen Yang
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Yang, S., Ju, L., Cheng, P., Zhou, J., Cai, Y., & Feng, D. (2025). Co-design protein sequence and structure in discrete space via generative flow. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf248
Vancouver
Yang S, Ju L, Cheng P, Zhou J, Cai Y, Feng D. Co-design protein sequence and structure in discrete space via generative flow. Bioinformatics. 2025. doi:10.1093/bioinformatics/btaf248
BibTeX
@article{Yang2025,
author = {Yang, Sen and Ju, Lingli and Cheng, Peng and Zhou, JiangLin and Cai, Yamin and Feng, Dawei},
title = {Co-design protein sequence and structure in discrete space via generative flow},
journal = {Bioinformatics},
year = {2025},
doi = {10.1093/bioinformatics/btaf248}
}
EUVIMED