EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CONTRA-IL6: an interpretable hybrid convolutional neural network and Transformer framework for accurate prediction of interleukin-6-inducing peptides using protein language models

Duong Thanh Tran, Nhat Truong Pham, Gwang Lee iD, Shaherin Basith iD, Balachandran Manavalan iD

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag250 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Duong Thanh Tran und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon 16419, Gyeonggi-do, Republic of …. Hauptthemen laut MEDLINE: Interleukin-6, Peptides. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sungkyunkwan University and the BK21 FOUR, Ministry of Education, National Research Foundation of Korea.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Interleukin-6 (IL-6) is a key immunomodulatory cytokine implicated in diverse physiological processes and pathological conditions, including autoimmune diseases, cancers, and cytokine storms. Immunogenic peptides capable of inducing IL-6 expression are key modulators of host immune responses and represent promising candidates for therapeutic design and epitope-based vaccine development. However, experimental identification of IL-6-inducing peptides remains laborious and unsuitable for large-scale screening. Although existing computational approaches show promise, many often struggle to capture both global contextual semantics and local motif-level features essential for peptide immunogenicity. To address these limitations, we present CONTRA-IL6, a novel deep learning framework that integrates Transformer fusion and convolutional localization modules with stacked pretrained protein language model embeddings to predict IL-6-inducing peptides. Comprehensive benchmarking on an independent dataset demonstrates that CONTRA-IL6 achieves superior predictive performance over six state-of-the-art predictors. Notably, it achieves the highest Matthews correlation coefficient (MCC, 0.504) and F1 (0.549) and improves over the best-performing existing method by 3.2% in MCC and 4.3% in F1, demonstrating balanced and robust performance. Feature space visualizations (uniform manifold approximation and projection, kernel density estimation) showed clear class separation, while 1D gradient-weighted class activation mapping++ highlighted strong attention to specific C-terminal regions. Crucially, we moved beyond these attribution methods by employing in silico mutagenesis, which causally confirmed the functional importance and physicochemical constraints. Ablation studies further confirmed the synergistic contribution of global and local modules to model performance. CONTRA-IL6 offers a robust, scalable, and interpretable solution for immunoinformatics research. The standalone package is freely available at https://pypi.org/project/contra-il6/ to facilitate broader community use.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Interleukin-6PeptidesHumansComputational BiologyConvolutional Neural NetworksDeep LearningImmunoinformaticsPrediction Algorithms

Stichwörter der Autor:innen

IL-6-inducing peptidesTransformerconvolutional neural networksdeep learningimmunotherapyprotein language model

Substanzen

Interleukin-6Peptides

Autor:innen und Institutionen

  • Department of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon 16419, Gyeonggi-do, Republic of Korea.
  • Department of Physiology, Ajou University School of Medicine, Suwon 16499, Republic of Korea.
  • Department of Molecular Science and Technology, Ajou University, Suwon 16499, Republic of Korea.

ORCID-Profile: Gwang Lee, Shaherin Basith, Balachandran Manavalan

Förderung

  • Sungkyunkwan University and the BK21 FOUR
  • Ministry of Education
  • National Research Foundation of Korea
  • Ministry of Science and ICT
  • Department of Integrative Biotechnology, Sungkyunkwan University
  • BK21 FOUR Project, Republic of Korea
  • Commercialization Promotion Agency for R&D Outcomes
  • MSIT, Republic of Korea

Zitieren

APA

Tran, D. T., Pham, N. T., Lee, G., Basith, S., & Manavalan, B. (2026). CONTRA-IL6: an interpretable hybrid convolutional neural network and Transformer framework for accurate prediction of interleukin-6-inducing peptides using protein language models. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag250

Vancouver

Tran DT, Pham NT, Lee G, Basith S, Manavalan B. CONTRA-IL6: an interpretable hybrid convolutional neural network and Transformer framework for accurate prediction of interleukin-6-inducing peptides using protein language models. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag250

BibTeX
@article{Tran2026,
  author = {Tran, Duong Thanh and Pham, Nhat Truong and Lee, Gwang and Basith, Shaherin and Manavalan, Balachandran},
  title = {CONTRA-IL6: an interpretable hybrid convolutional neural network and Transformer framework for accurate prediction of interleukin-6-inducing peptides using protein language models},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag250}
}
Kostenlos starten →