EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CLASPP: A unified model for predicting post-translational modifications

Nathan Gravel, Zhongliang Zhou iD, Ruili Fang, Austin Downes, Saber Soleymani, Natarajan Kannan iD

PLOS Computational Biology · 14.08.2026 · 22 (8) · e1014616

DOI: 10.1371/journal.pcbi.1014616 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 14.08.2026. Verfasst von Nathan Gravel und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Bioinformatics, University of Georgia, Atlanta, Georgia, United States of America. Hauptthemen laut MEDLINE: Protein Processing, Post-Translational, Computational Biology. Die Arbeit nennt 91 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, National Science Foundation, National Institute of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Post-Translational Modifications (PTMs) are a fundamental mechanism for regulating cellular pathways and increasing the functional diversity of the proteome. Accurately predicting the PTM types that are likely to occur at a given site in the primary sequence is a key challenge in functional proteomics. Existing PTM prediction models predominantly focus on either single PTM types or employ ensemble methods that combine multiple models to predict different PTM types. This fragmentation is largely driven by the vast imbalance in data availability across PTM types, making it difficult to predict multiple PTM types with a single model. To address this limitation, we present the C ontrastively L earned A ttention-based S tratified P TM P redictor (CLASPP), a unified PTM prediction model. CLASPP addresses imbalance challenges by leveraging unsupervised clustering-based undersampling and a novel contrastive learning framework tailored to PTM data. Additionally, our hierarchical data organization and curation are shown to improve CLASPP’s performance by balancing the representation of individual PTM types and provides a standardized dataset to train and validate future model designs. Drawing inspiration from advancements in image and natural language processing, the CLASPP model employs a multi-stage training strategy and a high-quality, curated training dataset to improve PTM prediction performance. To uncover what is learned during the contrastive learning stage, the CLASPP model is shown to distinguish known protein kinase substrate specificity profiles as a form of explainability. Finally, we evaluate the application of CLASPP in predicting PTMs in different model organisms and experimentally validated ubiquitination sites in the understudied DCLK3 kinase. Overall, CLASPP represents a unified model for PTM prediction that addresses key bottlenecks in data imbalance and offers new strategies for biological data curation, thereby improving PTM-type prediction performance across diverse organisms.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Protein Processing, Post-TranslationalComputational BiologyPrediction AlgorithmsProteomicsHumansDatabases, ProteinPredictive Learning ModelsAnimalsProteome

Substanzen

Proteome

Autor:innen und Institutionen

  • Institute of Bioinformatics, University of Georgia, Atlanta, Georgia, United States of America.
  • School of Computing, University of Georgia, Atlanta, Georgia, United States of America.
  • Institute for Insight, Georgia State University, Atlanta, Georgia, United States of America.
  • Department of Biochemistry and Molecular Biology, University of Georgia, Atlanta, Georgia, United States of America.

ORCID-Profile: Zhongliang Zhou, Natarajan Kannan

Förderung

  • NIGMS NIH HHS
  • National Science Foundation
  • National Institute of Health

Zitieren

APA

Gravel, N., Zhou, Z., Fang, R., Downes, A., Soleymani, S., & Kannan, N. (2026). CLASPP: A unified model for predicting post-translational modifications. PLOS Computational Biology, 22(8), e1014616. https://doi.org/10.1371/journal.pcbi.1014616

Vancouver

Gravel N, Zhou Z, Fang R, Downes A, Soleymani S, Kannan N. CLASPP: A unified model for predicting post-translational modifications. PLOS Computational Biology. 2026;22(8):e1014616. doi:10.1371/journal.pcbi.1014616

BibTeX
@article{Gravel2026,
  author = {Gravel, Nathan and Zhou, Zhongliang and Fang, Ruili and Downes, Austin and Soleymani, Saber and Kannan, Natarajan},
  title = {CLASPP: A unified model for predicting post-translational modifications},
  journal = {PLOS Computational Biology},
  year = {2026},
  volume = {22},
  number = {8},
  pages = {e1014616},
  doi = {10.1371/journal.pcbi.1014616}
}
Kostenlos starten →