Attention-aware contrastive learning for predicting T cell receptor-antigen binding specificity

@article{Fang2022AttentionawareCL,
  title={Attention-aware contrastive learning for predicting T cell receptor-antigen binding specificity},
  author={Yiming Fang and Xuejun Liu and Hui Liu},
  journal={bioRxiv},
  year={2022}
}
It has been verified that only a small fraction of the neoantigens presented by MHC class I molecules on the cell surface can elicit T cells. The limitation can be attributed to the binding specificity of T cell receptor (TCR) to peptide-MHC complex (pMHC). Computational prediction of T cell binding to neoantigens is an challenging and unresolved task. In this paper, we propose an attentive-mask contrastive learning model, ATMTCR, for inferring TCR-antigen binding specificity. For each input… 

References

SHOWING 1-10 OF 40 REFERENCES

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

TLDR
A k-nearest-neighbor (K-NN) classifier is established as a strong baseline and a bimodal neural network is proposed that explicitly encodes both TCR sequences and epitopes to enable the independent study of generalization capabilities to unseen TCRs and/or epitopes.

Deep learning-based prediction of the T cell receptor-antigen binding specificity

TLDR
A transfer learning-based model is built, named pMHC-TCR binding prediction network (pMTnet), to predict TCR-binding specificities of neoantigens, and T cell antigens in general, presented by class I major histocompatibility complexes (pMHCs).

NetTCR: sequence-based prediction of TCR binding to peptide-MHC complexes using convolutional neural networks

TLDR
This work trains a sequence-based predictor of the interaction between TCRs and peptides presented by the most common human MHCI allele, HLA-A*02:01, based on convolutional neural networks, which is especially designed to meet the challenges posed by the large length variations of T CRs.

BERTMHC: improved MHC–peptide class II interaction prediction with transformer and multiple instance learning

TLDR
A transformer neural network model which leverages self-supervised pretraining from a large corpus of protein sequences and a multiple instance learning (MIL) framework to deconvolve mass spectrometry data where multiple potential MHC alleles may have presented each peptide is presented.

TCR-BERT: learning the grammar of T-cell receptors for flexible antigen-xbinding analyses

TLDR
TCR-BERT can be a useful tool for T-cell scientists, enabling greater understanding and more diverse applications, and provides a conceptual framework for leveraging unlabeled data to improve machine learning on biological sequences.

NetMHCpan-3.0; improved prediction of binding to MHC class I molecules integrating information from multiple receptor and peptide length datasets

TLDR
A neural network-based machine-learning algorithm leveraging information across multiple receptor specificities and ligand length scales is developed and demonstrated how this approach significantly improves the accuracy for prediction of peptide binding and identification of MHC ligands.

Prediction of Specific TCR-Peptide Binding From Large Dictionaries of TCR-Peptide Pairs

TLDR
It is shown that ERGO significantly outperforms all current methods for classification of TCRs that bind peptides, but more importantly can distinguish the specific target of a TCR among a large set of peptides.

Rapid Assessment of T-Cell Receptor Specificity of the Immune Repertoire

TLDR
A pairwise energy model, RACER, is introduced, a supervised, physics-based machine learning algorithm trained on deposited TCR-p-MHCs sequences and structures, capable of estimating T CR-peptide binding affinity at a rate of 0.02 seconds per pair, thus enabling large-scale evaluations of TCR epitope recognition.

Predicting recognition between T cell receptors and epitopes with TCRGP

TLDR
TCRGP is developed, a novel Gaussian process method that predicts if TCRs recognize specified epitopes and achieves on average higher prediction accuracy in terms of AUROC score than existing state-of-the-art methods in epitope-specificity predictions.

Machine Learning for Cancer Immunotherapies Based on Epitope Recognition by T Cell Receptors

TLDR
This review is focused on T cell receptor-mediated therapies and finds that breakthrough computational methods for predicting antigen presentation and TCR binding are urgently required to facilitate highly personalized therapies that can simultaneously target multiple patient-specific antigens.