PSTP: accurate residue-level phase separation prediction using protein conformational and language model embeddings
Briefings in Bioinformatics · 2025
DOI: 10.1093/bib/bbaf171 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Mofan Feng und 8 weiteren Autor:innen. Beteiligte Einrichtung: Bio-X Institutes, Key Laboratory for the Genetics of Developmental and Neuropsychiatric Disorders, Shanghai Jiao Tong University, No. 1954 Huashan Ro…. Hauptthemen laut MEDLINE: Proteins, Software, Computational Biology. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Key Research and Development Program, Innovation Program of Shanghai Municipal Education Commission, National Natural Science Foundation of China.
Abstract (Originalsprache)
Phase separation (PS) is essential in cellular processes and disease mechanisms, highlighting the need for predictive algorithms to analyze uncharacterized sequences and accelerate experimental validation. Current high-accuracy methods often rely on extensive annotations or handcrafted features, limiting their generalizability to sequences lacking such annotations and making it difficult to identify key protein regions involved in PS. We introduce Phase Separation’s Transfer-learning Prediction (PSTP), which combines conformational embeddings with large language model embeddings, enabling state-of-the-art PS predictions from protein sequences alone. PSTP performs well across various prediction scenarios and shows potential for predicting novel-designed artificial proteins. Additionally, PSTP provides residue-level predictions that are highly correlated with experimentally validated PS regions. By analyzing 160 000+ variants, PSTP characterizes the strong link between the incidence of pathogenic variants and residue-level PS propensities in unconserved intrinsically disordered regions, offering insights into underexplored mutation effects. PSTP’s sliding-window optimization reduces its memory usage to a few hundred megabytes, facilitating rapid execution on typical CPUs and GPUs. Offered via both a web server and an installable Python package, PSTP provides a versatile tool for decoding protein PS behavior and supporting disease-focused research.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Bio-X Institutes, Key Laboratory for the Genetics of Developmental and Neuropsychiatric Disorders, Shanghai Jiao Tong University, No. 1954 Huashan Road, Xuhui District, Shanghai 200030, China.
- Shanghai Institute of Medical Genetics, Shanghai Children's Hospital, Shanghai Jiao Tong University School of Medicine, No. 24 Lane 1400 West Beijing Road, Jing'an District, Shanghai 200040, China.
- School of Environmental Science & Engineering, Shanghai Jiao Tong University, No. 800 Dongchuan Road, Minhang District, Shanghai 200240, China.
Förderung
- National Key Research and Development Program
- Innovation Program of Shanghai Municipal Education Commission
- National Natural Science Foundation of China
- Shanghai Municipal Science and Technology Major Project
- China Postdoctoral Science Foundation
- Key Technology Breakthrough Program of Ningbo Sci-Tech Innovation YONGJIANG 2035
- Municipal Public Welfare Project
- Shanghai Jiao Tong University STAR Grant
Zitieren
APA
Feng, M., Liu, L., Xian, Z. N., Wei, X., Li, K., Yan, W., Lu, Q., Shi, Y., & He, G. (2025). PSTP: accurate residue-level phase separation prediction using protein conformational and language model embeddings. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf171
Vancouver
Feng M, Liu L, Xian ZN, Wei X, Li K, Yan W, et al. PSTP: accurate residue-level phase separation prediction using protein conformational and language model embeddings. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf171
BibTeX
@article{Feng2025,
author = {Feng, Mofan and Liu, Liangjie and Xian, Zhuo-Ning and Wei, Xiaoxi and Li, Keyi and Yan, Wenqian and Lu, Qing and Shi, Yi and He, Guang},
title = {PSTP: accurate residue-level phase separation prediction using protein conformational and language model embeddings},
journal = {Briefings in Bioinformatics},
year = {2025},
doi = {10.1093/bib/bbaf171}
}
EUVIMED