EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

PSTP: accurate residue-level phase separation prediction using protein conformational and language model embeddings

Mofan Feng, Liangjie Liu, Zhuo-Ning Xian, Xiaoxi Wei, Keyi Li, Wenqian Yan, Qing Lu, Yi Shi, Guang He

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.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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)

ProteinsSoftwareComputational BiologyProtein ConformationAlgorithmsMachine LearningHumansPhase Separation

Stichwörter der Autor:innen

conformation-aware embeddingsintrinsically disordered regionslanguage modelprotein phase separationresidue-level phase separation prediction

Substanzen

Proteins

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}
}
Kostenlos starten →