Probing T cell response by improved TCR repertoires featurization with deep generative model


Cellular immunity is orchestrated by T cells through their immense T-cell receptors (TCRs) repertoire, which interact with antigenic peptides presented by major histocompatibility complex (pMHC) molecules. Here, we release DeepTR, a one-stop collection of unsupervised and supervised deep learning approaches for pan peptide-MHC class I binding prediction, antigen-specific TCR clustering, and T cell response specificity prediction achieved by mimicking crucial steps of the antigen presentation pathway. This online tool requires TCR repertoires through bulk or single-cell methods, including CDR sequences and TRV genes from the paired TCRα & β chains. Each row should contain a TCR record (CDR3α sequence, TRAV gene, CDR3β sequence, TRBV gene) and all inputs are separated by commas. Candidate antigens and HLA alleles also need to be specified. The DeepTR server predicts pMHC-TCR binding to over 100 well studied human HLA molecules. We constructed a classification tree of HLAs. Users can quickly retrieve and submit candidate HLA alleles through the search box and tree map. A few minutes after submitting the job, the top ranked interaction between TCR and pMHC in each HLA allele would be visualized in an interactive way on the output page.

Important note: Each job may take 1-10 minutes to finish. You may retrive the results anytime using the Job Identifier (JID e.g., JOB1234_1234567890). Please do keep a record of the JID.

Example result: A quick example result page can be checked here.


Input parameters


Please input TCR repertoires below. Each row contains a TCR record (CDR3a, TRAV gene, CDR3b, TRBV gene) and separated by commas. A head line is required. (Load the example data to check.)

Please input antigen below. The length of the antigens should be 8-15 mer.

    Check HLA allele (n = 0; clear all)