No retraction, correction or concern found when last checked on Oct 29, 2026.

TITAN: T-cell receptor specificity prediction with bimodal attention networks

Anna Weber, Jannis Born, María Rodriguez Martínez

Bioinformatics · 2021 · CC BY

Abstract

Motivation. The activity of the adaptive immune system is governed by T-cells and their specific T-cell receptors (TCR), which selectively recognize foreign antigens. Recent advances in experimental techniques have enabled sequencing of TCRs and their antigenic targets (epitopes), allowing to research the missing link between TCR sequence and epitope binding specificity. Scarcity of data and a large sequence space make this task challenging, and to date only models limited to a small set of epitopes have achieved good performance. Here, we establish a k-nearest-neighbor (K-NN) classifier as a strong baseline and then propose Tcr epITope bimodal Attention Networks (TITAN), a bimodal neural network that explicitly encodes both TCR sequences and epitopes to enable the independent study of generalization capabilities to unseen TCRs and/or epitopes.

Results. By encoding epitopes at the atomic level with SMILES sequences, we leverage transfer learning and data augmentation to enrich the input data space and boost performance. TITAN achieves high performance in the prediction of specificity of unseen TCRs (ROC-AUC 0.87 in 10-fold CV) and surpasses the results of the current state-of-the-art (ImRex) by a large margin. Notably, our Levenshtein-based K-NN classifier also exhibits competitive performance on unseen TCRs. While the generalization to unseen epitopes remains challenging, we report two major breakthroughs. First, by dissecting the attention heatmaps, we demonstrate that the sparsity of available epitope data favors an implicit treatment of epitopes as classes. This may be a general problem that limits unseen epitope performance for sufficiently complex models. Second, we show that TITAN nevertheless exhibits significantly improved performance on unseen epitopes and is capable of focusing attention on chemically meaningful molecular structures.

Availability and implementation. The code as well as the dataset used in this study is publicly available at https://github.com/PaccMann/TITAN.

Supplementary information. Supplementary data are available at Bioinformatics online.

References 34

1.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
2.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
3.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
4.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
5.
Estimating T-cell repertoire diversity: limitations of classical estimators and a new approach · 2015
No notice
6.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
7.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
8.
The ChEMBL database in 2017 · 2016
No notice
9.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
10.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
11.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
12.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
13.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
14.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
15.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
16.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
17.
VDJdb in 2019: database extension, new analysis infrastructure and a T-cell receptor motif compendium · 2019
No notice
18.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
19.
Detection of Enriched T Cell Epitope Specificity in Full T Cell Receptor Sequence Repertoires · 2019
No notice
20.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
21.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
22.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
23.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
24.
Prediction of Specific TCR-Peptide Binding From Large Dictionaries of TCR-Peptide Pairs · 2020
No notice
25.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
26.
UniProt: the universal protein knowledgebase in 2021 · 2020
No notice
27.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
28.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
29.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
30.
TCRMatch: Predicting T-Cell Receptor Specificity Based on Sequence Similarity to Previously Characterized Receptors · 2021
No notice
31.
DeepTCR is a deep learning framework for revealing sequence concepts within T-cell repertoires · 2021
Corrected
32.
Predicting recognition between T cell receptors and epitopes with TCRGP · 2021
No notice
33.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library
34.
This reference’s wording can’t be shown under the paper’s licence.
Not in our library

Cited by papers we hold 1

Therapeutic cancer vaccines: advancements, challenges and prospects · 2023
No notice

Reads

Read by people on this page

None yet.

Checked or read by AI through naulon

None yet.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.

Are you an author?

Is this your paper?

Claim it to add your note and be paid when agents cite it. Free.