Determining epitope specificity of T cell receptors with TCRGP

Abstract

T cell receptors (TCRs) can recognize various pathogens and consequently start immune responses. TCRs can be sequenced from individuals and methods that can analyze the specificity of the TCRs can help us better understand the individual's immune status in different diseases. We have developed TCRGP, a novel Gaussian process (GP) method that can predict if TCRs recognize certain epitopes. This method can utilize different CDR sequences from both TCRα and TCRβ chains from single-cell data and learn which CDRs are important in recognizing the different epitopes. We have experimented with one previously presented and one new data set and show that TCRGP outperforms other state-of-the-art methods in predicting the epitope specificity of TCRs on both data sets. The software implementation and data sets are available at https://github.com/emmijokinen/TCRGP.

Current challenges for epitope-agnostic TCR interaction prediction and a new perspective derived from image classification

“…Despite the advent of single cell TCR paired chain sequencing, currently available TCR-epitope binding data mostly consists of single-chain, often beta-chain, data, while in reality both the alpha-and beta-chains are thought to contribute to binding specificity. Indeed, recent studies have concluded that utilising both chains could increase the accuracy of predictive TCR-epitope models (14,15).…”

“…Previous work has tackled this problem from an epitopespecific angle, and demonstrated that the amino acid sequences of the TCR CDR3 region contain sufficient information to predict epitope recognition using epitope-specific models (10,11,14,(16)(17)(18). These types of predictive models have now been made accessible to immunology researchers via web tools such as TCRex (19).…”

Prediction of specific TCR-peptide binding from large dictionaries of TCR-peptide pairs

“…In order to show that ERGO outperforms all current approaches, we tested its precision on previous attempts to predict TCR-peptide binding. We first compared it to the work of Jokinen et al (17) who compared TCRs found by Dash et al (16) to bind three human epitopes and seven mice epitopes with TCRs from VDJdb database (21), which bind additional 22 epitopes. These peptide-TCR pairs were compared with naïve TCRs not expected to recognize the epitopes.…”

“…Important steps have been made in this direction by Glanville et al (4) and Dash et al (16), who detected the clear signature of short amino acid motifs in the CDR3 region of TCRβ and TCRα in response to specific peptides presented by specific MHC molecules. This work was then extended by two more recent efforts that combined such motifs with machine learning approaches (17,18) to predict peptide specific TCRs vs. naïve TCRs, using either Convolutional Neural Networks (18), or Gaussian Processes (17). These methods significantly outperform random classification in practically all tested datasets.…”

TCRex: detection of enriched T cell epitope specificity in full T cell receptor sequence repertoires

“…Training of epitope-specific prediction models was based on the method established in (12). This method was shown to perform comparably to other state-of-the-art classifiers in a recent independent study (22). In brief, the amino acid sequences of the CDR3 regions of the TCR beta chains were converted into physicochemical features and the beta chain's V/J genes and families were one-hot encoded.…”