EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting protein–carbohydrate binding sites: a deep learning approach integrating protein language model embeddings and structural features

Md Muhaiminul Islam Nafi iD, M Saifur Rahman iD

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag008 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Md Muhaiminul Islam Nafi und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of CSE, BUET, Palashi Road, Dhaka 1000, Dhaka District, Bangladesh. Hauptthemen laut MEDLINE: Deep Learning, Proteins, Computational Biology, Carbohydrates. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: RISE Student Research Grant, BUET.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Protein–carbohydrate interactions play an important role in many biological processes and functions, like inflammation, signal transduction, and cell adhesion. In our work, we will study non-covalent carbohydrate binding sites. In this paper, we aim to build a deep-learning model to predict non-covalent protein–carbohydrate binding sites. We were motivated by the fact that experimental approaches for predicting these sites are expensive. So, computational tools are necessary for identifying these interactions. We explored several sequence-based features as well as structural features. We also leveraged protein language model embeddings. We analyzed different architectures and selected the most suitable deep learning architecture for our finalized prediction model, DeepCPBSite. DeepCPBSite is an ensemble model that combines three separate models with three approaches (random undersampling, weighted oversampling, and class-weighted loss) built on the ResNet+FNN architecture. We made separate datasets from three sources: RCSB, UniProt, and CASP. We also compared the structural features extracted from the structures predicted by AlphaFold and ESMFold in the context of our prediction tasks. We employed three different feature selection techniques and finally did a SHAP (SHapley Additive exPlanations) analysis on the structural features after categorizing the proteins based on their organism information. DeepCPBSite achieved 78.7% balanced accuracy and 59.6% sensitivity on the TS53 set, outperforming the second-best competitor, DeepGlycanSite, by 1.16% and 2.94%, respectively. Additionally, its F1, MCC, and AUPR scores outperformed other state-of-the-art methods, with improvements ranging from 3.77%–47.6%, 3.84%–32.7%, and 8.18%–60.21%, respectively.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningProteinsComputational BiologyCarbohydratesBinding SitesProtein BindingDatabases, Protein

Stichwörter der Autor:innen

computational biologymachine learningpredictionproteinsstructural bioinformatics

Substanzen

ProteinsCarbohydrates

Autor:innen und Institutionen

  • Department of CSE, BUET, Palashi Road, Dhaka 1000, Dhaka District, Bangladesh.
  • Department of CSE, United International University (UIU), United City, Madani Avenue, Badda, Dhaka 1212, Dhaka District, Bangladesh.

ORCID-Profile: Md Muhaiminul Islam Nafi, M Saifur Rahman

Förderung

  • RISE Student Research Grant
  • BUET

Zitieren

APA

Muhaiminul Islam Nafi, M., & Saifur Rahman, M. (2026). Predicting protein–carbohydrate binding sites: a deep learning approach integrating protein language model embeddings and structural features. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag008

Vancouver

Muhaiminul Islam Nafi M, Saifur Rahman M. Predicting protein–carbohydrate binding sites: a deep learning approach integrating protein language model embeddings and structural features. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag008

BibTeX
@article{MuhaiminulIslamNafi2026,
  author = {Muhaiminul Islam Nafi, Md and Saifur Rahman, M},
  title = {Predicting protein–carbohydrate binding sites: a deep learning approach integrating protein language model embeddings and structural features},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag008}
}
Kostenlos starten →