EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GPSD: a hybrid learning framework for the prediction of phosphatase-specific dephosphorylation sites

Cheng Han, Shanshan Fu, Miaomiao Chen, Yujie Gou, Dan Liu, Chi Zhang, Xinhe Huang, Leming Xiao, Miaoying Zhao, Jiayi Zhang, Qiang Xiao, Di Peng iD und 1 weitere

Briefings in Bioinformatics · 2024

DOI: 10.1093/bib/bbae694 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2024. Verfasst von Cheng Han und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bioinformatics and Systems Biology, MOE Key Laboratory of Molecular Biophysics, Hubei Bioinformatics and Molecular Imaging Key Laborato…. Hauptthemen laut MEDLINE: Computational Biology. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Natural Science Foundation of China, Hubei Innovation Group Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Protein phosphorylation is dynamically and reversibly regulated by protein kinases and protein phosphatases, and plays an essential role in orchestrating a wide range of biological processes. Although a number of tools have been developed for predicting kinase-specific phosphorylation sites (p-sites), computational prediction of phosphatase-specific dephosphorylation sites remains to be a great challenge. In this study, we manually curated 4393 experimentally identified site-specific phosphatase–substrate relationships for 3463 dephosphorylation sites occurring on phosphoserine, phosphothreonine, and/or phosphotyrosine residues, from the literature and public databases. Then, we developed a hybrid learning framework, the group-based prediction system for the prediction of phosphatase-specific dephosphorylation sites (GPSD). For model training, we integrated 10 types of sequence features and utilized three types of machine learning methods, including penalized logistic regression, deep neural networks, and transformer neural networks. First, a pretrained model was constructed using 561 416 nonredundant p-sites and then fine-tuned to generate computational models for predicting general dephosphorylation sites. In addition, 103 individual phosphatase-specific predictors were constructed via transfer learning and meta-learning. For site prediction, one or multiple protein sequences in FASTA format could be inputted, and the prediction results will be shown together with additional annotations, such as protein–protein interactions, structural information, and disorder propensity. The online service of GPSD is freely available at https://gpsd.biocuckoo.cn/. We believe that GPSD can serve as a valuable tool for further analysis of dephosphorylation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computational BiologyPhosphorylationMachine LearningNeural Networks, ComputerPhosphoric Monoester HydrolasesSoftwareDatabases, ProteinSubstrate Specificity

Stichwörter der Autor:innen

dephosphorylation sitemachine learningposttranslational modificationprotein phosphatasetransfer learning

Substanzen

Phosphoric Monoester Hydrolases

Autor:innen und Institutionen

  • Department of Bioinformatics and Systems Biology, MOE Key Laboratory of Molecular Biophysics, Hubei Bioinformatics and Molecular Imaging Key Laboratory, Center for Artificial Intelligence Biology, College of Life Scienc…
  • School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Luoyu Road 1037, Wuhan, Hubei 430074, China.

ORCID-Profile: Di Peng, Yu Xue

Förderung

  • National Key Research and Development Program of China
  • Natural Science Foundation of China
  • Hubei Innovation Group Project
  • Hubei Province Postdoctoral Outstanding Talent Tracking Support Program
  • Interdisciplinary Research Program of Hust
  • Research Core Facilities for Life Science

Zitieren

APA

Han, C., Fu, S., Chen, M., Gou, Y., Liu, D., Zhang, C., Huang, X., Xiao, L., Zhao, M., Zhang, J., Xiao, Q., Peng, D., & Xue, Y. (2024). GPSD: a hybrid learning framework for the prediction of phosphatase-specific dephosphorylation sites. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbae694

Vancouver

Han C, Fu S, Chen M, Gou Y, Liu D, Zhang C, et al. GPSD: a hybrid learning framework for the prediction of phosphatase-specific dephosphorylation sites. Briefings in Bioinformatics. 2024. doi:10.1093/bib/bbae694

BibTeX
@article{Han2024,
  author = {Han, Cheng and Fu, Shanshan and Chen, Miaomiao and Gou, Yujie and Liu, Dan and Zhang, Chi and Huang, Xinhe and Xiao, Leming and Zhao, Miaoying and Zhang, Jiayi and Xiao, Qiang and Peng, Di and Xue, Yu},
  title = {GPSD: a hybrid learning framework for the prediction of phosphatase-specific dephosphorylation sites},
  journal = {Briefings in Bioinformatics},
  year = {2024},
  doi = {10.1093/bib/bbae694}
}
Kostenlos starten →