Supervised fine-tuning enhances unsupervised learning from 45 million amino acids in TCR and peptide sequences
Bioinformatics · 03.05.2026 · 42 (5)
DOI: 10.1093/bioinformatics/btag200 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 24.04.2026. Verfasst von Kewei Zhou und 5 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Rua de Luís Gonzaga Gomes, Macao…. Hauptthemen laut MEDLINE: Receptors, Antigen, T-Cell, Peptides, Amino Acids, Unsupervised Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Macao Science and Technology Development Fund, Macao Polytechnic University.
Abstract (Originalsprache)
Motivation T cell receptor (TCR) and peptide interactions (TPI) are one of the most important parts of T cell immunity. Experimental identification of TPI is time-consuming and labor-intensive; therefore, it is necessary to develop computational prediction method that exploit existing data to predict TPI. Results We use huge TCR and peptide sequences to pre-train two language models (∼152M parameters), respectively, and integrate them into a sequence-based only prediction framework (i.e. RoBERTcr) with supervised fine-tuning (SFT). Visualization of amino acids embedding from pre-trained language model (PLM) shows biochemical clusters based on different properties, and our PLMs outperform existing protein language models (i.e. ESM and ProtTrans) under the same condition. RoBERTcr achieved higher performance than other state-of-the-art methods based on structures or sequences without dataset bias. The visualization of attention from our framework implies valuable spatial information that residues in TCR contacting peptides are the key to their interaction. Availability RoBERTcr is free available at https://fca_icdb.mpu.edu.mo/robertcr/ and https://doi.org/10.5281/zenodo.18043054.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Rua de Luís Gonzaga Gomes, Macao, 999078, China.
ORCID-Profile: Huanxiang Liu, Xiaojun Yao
Förderung
- Macao Science and Technology Development Fund
- Macao Polytechnic University
Zitieren
APA
Zhou, K., Xu, K., Lin, S., Zhai, S., Liu, H., & Yao, X. (2026). Supervised fine-tuning enhances unsupervised learning from 45 million amino acids in TCR and peptide sequences. Bioinformatics, 42(5). https://doi.org/10.1093/bioinformatics/btag200
Vancouver
Zhou K, Xu K, Lin S, Zhai S, Liu H, Yao X. Supervised fine-tuning enhances unsupervised learning from 45 million amino acids in TCR and peptide sequences. Bioinformatics. 2026;42(5). doi:10.1093/bioinformatics/btag200
BibTeX
@article{Zhou2026,
author = {Zhou, Kewei and Xu, Kai and Lin, Shaolong and Zhai, Silong and Liu, Huanxiang and Yao, Xiaojun},
title = {Supervised fine-tuning enhances unsupervised learning from 45 million amino acids in TCR and peptide sequences},
journal = {Bioinformatics},
year = {2026},
volume = {42},
number = {5},
doi = {10.1093/bioinformatics/btag200}
}
EUVIMED