-->

The critical step of T cell-mediated immunity is the interaction between T-cell receptor (TCR) and epitope peptide-major histocompatibility complex (pMHC) molecules. The ability to use TCR sequences to infer antigen-specificity could greatly aid potential diagnostics and therapeutics. Here, we build a user-friendly web service named DeepTR for T cell response predicion by modeling TCR binding specificities of the neoantigens. DeepTR implements comprehensive featurization strategies in a biologically meaningful way followed with multimodal deep learning network to numerically embed sequences of MHC, antigens and six loops of TCR (α- and β-chain of CDR1-3) for predicting the pMHC-TCR interactions. Through DeepTR, we hope to serve the community to push forward our understandings of mechanism of T cell-mediated immunity and yield new insight in both personalized immune treatment and development of targeted vaccines.

DeepTR workflow

Deep learning framework of DeepTR models and web server. A. A deep generative model for learning TCR embeddings by LSTM autoencoder. We encoded >20,000 paired α/β TCR sequence data and their six complementary determining regions (CDRs) into high-dimensional physicalchemical feature representations to improved TCR repertoires featurization. B. For embedding of pMHCs, based on over based on more than 200, 000 quantitative binding affinity measurements, we constructed a new pan-allele MHC class I predictor through the deep neural network. The input of this model is the MHC class I sequences and the antigen peptides. The layers before output should contain important information regarding the overall structure of the pMHC complex, which could provide high-quality MHC-antigen co-embedding. C. We leveraged the trained numeric vector encodings of TCRs and pMHCs for learning the pairing between them. We constructed a fully connected deep-learning network based on the output of these two submodels, leading to a final layer with a single neuron for predicting the pairing. D. The web portal implemented by DeepTR models.

Updates
6/10/2022: Some bugs have been fixed.
3/15/2022: DeepTR 1.0 was released for T cell response prediction by deep learning.
01/26/2022: The pan TCR-epitope prediction model is implemented and evaluated through the co-embedding of TCR, epitope and MHC.
10/21/2021: The performance of TCR repertoires featurization is evaluated at multiple levels.
05/15/2021: A new pan-allele MHC class I predictor was constructed through the CNN-LSTM neural network..
01/26/2021: We have collected more than 200, 000 quantitative binding affinity measurements.
11/21/2020: We have performed multiple sequence alignments for >10,000 major histocompatibility complex (MHC) class I alleles to construct a unique pseudo-label for each MHC.
09/12/2020: Deep generative neural network (LSTM Autoencoders) was developed for embedding six CDRs and peptide.
05/17/2020: Complementarity-determining regions (CDRs) were xtracted from TCRα and β sequence and V genes.
04/09/2020: >20,000 paired TCRα and β sequence data are processed.
01/26/2020: T-cell receptor repertoires were collected from VDJdb database.
Developers


* DeepTR is free and open to all users and there is no login requirement.