Predicting recognition between T cell receptors and epitopes with TCRGP
Предсказание распознавания эпитопов рецепторами T-клеток с помощью TCRGP
2021-03-25
SCID: 54.1/4sdatc27
Discuss with AI
Gaussian processT cell receptorsTCRGPepitope specificity predictionscRNA+TCRαβ sequencing
Figures from the paper
Abstract (AI)
Adaptive immune system uses T cell receptors (TCRs) to recognize pathogens and to consequently initiate immune responses. TCRs can be sequenced from individuals and methods analyzing the specificity of the TCRs can help us better understand individuals' immune status in different disorders. For this task, we have developed TCRGP, a novel Gaussian process method that predicts if TCRs recognize specified epitopes. TCRGP can utilize the amino acid sequences of the complementarity determining regions (CDRs) from TCRα and TCRβ chains and learn which CDRs are important in recognizing different epitopes. Our comprehensive evaluation with epitope-specific TCR sequencing data shows that TCRGP achieves on average higher prediction accuracy in terms of AUROC score than existing state-of-the-art methods in epitope-specificity predictions. We also propose a novel analysis approach for combined single-cell RNA and TCRαβ (scRNA+TCRαβ) sequencing data by quantifying epitope-specific TCRs with TCRGP and identify HBV-epitope specific T cells and their transcriptomic states in hepatocellular carcinoma patients.
Key Findings
1
Across comprehensive evaluations on epitope-specific TCR sequencing data, TCRGP achieved higher average AUROC than existing state-of-the-art specificity-prediction methods.
2
Applying this approach identified HBV-epitope-specific T cells and their transcriptomic states in patients with hepatocellular carcinoma.
3
TCRGP enables analysis of combined single-cell RNA and paired TCRαβ sequencing data by quantifying epitope-specific TCRs.
4
TCRGP is a Gaussian process method that predicts whether T-cell receptors recognize specified epitopes.
5
The method uses amino acid sequences from TCRα and TCRβ complementarity-determining regions and learns which CDRs contribute to recognition of each epitope.
Research Object
T cell receptors (TCRs) recognizing specified epitopes, including TCRα and TCRβ complementarity-determining regions
Research Subject
Epitope-specific recognition and prediction performance of TCRs, including the CDR sequence features important for recognition
Publication Details
Publication Date
2021-03-25
Journal
PLoS Computational Biology
Publisher
Public Library of Science
ISSN
1553-734X
Cited by
157
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
Cited by5
TITAN: T-cell receptor specificity prediction with bimodal attention networks2021
Deep learning predictions of TCR-epitope interactions reveal epitope-specific chains in dual alpha T cells2024
epiTCR: a highly sensitive predictor for TCR–peptide binding2023
EPIC-TRACE: predicting TCR binding to unseen epitopes using attention and contextualized embeddings2023
tcrBLOSUM: an amino acid substitution matrix for sensitive alignment of distant epitope-specific TCRs2024