EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PUNCH2: Explore the strategy for intrinsically disordered protein predictor

Di Meng iD, Gianluca Pollastri

PLOS ONE · 26.03.2025 · 20 (3) · e0319208

DOI: 10.1371/journal.pone.0319208 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 26.03.2025. Verfasst von Di Meng und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, University College Dublin, Dublin, Ireland. Hauptthemen laut MEDLINE: Intrinsically Disordered Proteins, Computational Biology, Software. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science Foundation Ireland.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Intrinsically disordered proteins (IDPs) and their intrinsically disordered regions (IDRs) lack stable three-dimensional structures, posing significant challenges for computational prediction. This study introduces PUNCH2 and PUNCH2-light , advanced predictors designed to address these challenges through curated datasets, innovative feature extraction, and optimized neural architectures. By integrating experimental datasets from PDB ( PDB_missing ) and fully disordered sequences from DisProt ( DisProt_FD ), we enhanced model performance and robustness. Three embedding strategies—One-Hot, MSA-based, and PLM-based embeddings—were evaluated, with ProtTrans emerging as the most effective single embedding and combined embeddings achieving the best results. The predictors employ a 12-layer convolutional network (CNN_L12_narrow), offering a balance between accuracy and computational efficiency. PUNCH2 combines One-Hot, ProtTrans, and MSA-Transformer embeddings, while PUNCH2-light provides a faster alternative excluding MSA-based embeddings. PUNCH2 and its streamlined variant, PUNCH2-light , are competitive with other predictors on the CAID2 benchmark and rank as the top two predictors in the CAID3 competition. These tools provide efficient, accurate solutions to advance IDP research and understanding.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Intrinsically Disordered ProteinsComputational BiologySoftwareDatabases, ProteinNeural Networks, ComputerAlgorithmsProtein Conformation

Substanzen

Intrinsically Disordered Proteins

Autor:innen und Institutionen

  • School of Computer Science, University College Dublin, Dublin, Ireland.

ORCID-Profile: Di Meng

Förderung

  • Science Foundation Ireland

Zitieren

APA

Meng, D., & Pollastri, G. (2025). PUNCH2: Explore the strategy for intrinsically disordered protein predictor. PLOS ONE, 20(3), e0319208. https://doi.org/10.1371/journal.pone.0319208

Vancouver

Meng D, Pollastri G. PUNCH2: Explore the strategy for intrinsically disordered protein predictor. PLOS ONE. 2025;20(3):e0319208. doi:10.1371/journal.pone.0319208

BibTeX
@article{Meng2025,
  author = {Meng, Di and Pollastri, Gianluca},
  title = {PUNCH2: Explore the strategy for intrinsically disordered protein predictor},
  journal = {PLOS ONE},
  year = {2025},
  volume = {20},
  number = {3},
  pages = {e0319208},
  doi = {10.1371/journal.pone.0319208}
}
Kostenlos starten →