Predicting antigen specificity of single T cells based on TCR CDR3 regions
Abstract It has recently become possible to simultaneously assay T‐cell specificity with respect to large sets of antigens and the T‐cell receptor sequence in high‐throughput single‐cell experiments. Leveraging this new type of data, we propose and benchmark a collection of deep learning architectur...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2020-08-01
|
Series: | Molecular Systems Biology |
Subjects: | |
Online Access: | https://doi.org/10.15252/msb.20199416 |
id |
doaj-c1e080fe74514040907d1c15f461e086 |
---|---|
record_format |
Article |
spelling |
doaj-c1e080fe74514040907d1c15f461e0862021-08-02T15:28:47ZengWileyMolecular Systems Biology1744-42922020-08-01168n/an/a10.15252/msb.20199416Predicting antigen specificity of single T cells based on TCR CDR3 regionsDavid S Fischer0Yihan Wu1Benjamin Schubert2Fabian J Theis3Institute of Computational Biology Helmholtz Zentrum München Neuherberg GermanyInstitute of Computational Biology Helmholtz Zentrum München Neuherberg GermanyInstitute of Computational Biology Helmholtz Zentrum München Neuherberg GermanyInstitute of Computational Biology Helmholtz Zentrum München Neuherberg GermanyAbstract It has recently become possible to simultaneously assay T‐cell specificity with respect to large sets of antigens and the T‐cell receptor sequence in high‐throughput single‐cell experiments. Leveraging this new type of data, we propose and benchmark a collection of deep learning architectures to model T‐cell specificity in single cells. In agreement with previous results, we found that models that treat antigens as categorical outcome variables outperform those that model the TCR and antigen sequence jointly. Moreover, we show that variability in single‐cell immune repertoire screens can be mitigated by modeling cell‐specific covariates. Lastly, we demonstrate that the number of bound pMHC complexes can be predicted in a continuous fashion providing a gateway to disentangle cell‐to‐dextramer binding strength and receptor‐to‐pMHC affinity. We provide these models in the Python package TcellMatch to allow imputation of antigen specificities in single‐cell RNA‐seq studies on T cells without the need for MHC staining.https://doi.org/10.15252/msb.20199416antigen specificitymultimodalsingle cellsupervised learningT‐cell receptors |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
David S Fischer Yihan Wu Benjamin Schubert Fabian J Theis |
spellingShingle |
David S Fischer Yihan Wu Benjamin Schubert Fabian J Theis Predicting antigen specificity of single T cells based on TCR CDR3 regions Molecular Systems Biology antigen specificity multimodal single cell supervised learning T‐cell receptors |
author_facet |
David S Fischer Yihan Wu Benjamin Schubert Fabian J Theis |
author_sort |
David S Fischer |
title |
Predicting antigen specificity of single T cells based on TCR CDR3 regions |
title_short |
Predicting antigen specificity of single T cells based on TCR CDR3 regions |
title_full |
Predicting antigen specificity of single T cells based on TCR CDR3 regions |
title_fullStr |
Predicting antigen specificity of single T cells based on TCR CDR3 regions |
title_full_unstemmed |
Predicting antigen specificity of single T cells based on TCR CDR3 regions |
title_sort |
predicting antigen specificity of single t cells based on tcr cdr3 regions |
publisher |
Wiley |
series |
Molecular Systems Biology |
issn |
1744-4292 |
publishDate |
2020-08-01 |
description |
Abstract It has recently become possible to simultaneously assay T‐cell specificity with respect to large sets of antigens and the T‐cell receptor sequence in high‐throughput single‐cell experiments. Leveraging this new type of data, we propose and benchmark a collection of deep learning architectures to model T‐cell specificity in single cells. In agreement with previous results, we found that models that treat antigens as categorical outcome variables outperform those that model the TCR and antigen sequence jointly. Moreover, we show that variability in single‐cell immune repertoire screens can be mitigated by modeling cell‐specific covariates. Lastly, we demonstrate that the number of bound pMHC complexes can be predicted in a continuous fashion providing a gateway to disentangle cell‐to‐dextramer binding strength and receptor‐to‐pMHC affinity. We provide these models in the Python package TcellMatch to allow imputation of antigen specificities in single‐cell RNA‐seq studies on T cells without the need for MHC staining. |
topic |
antigen specificity multimodal single cell supervised learning T‐cell receptors |
url |
https://doi.org/10.15252/msb.20199416 |
work_keys_str_mv |
AT davidsfischer predictingantigenspecificityofsingletcellsbasedontcrcdr3regions AT yihanwu predictingantigenspecificityofsingletcellsbasedontcrcdr3regions AT benjaminschubert predictingantigenspecificityofsingletcellsbasedontcrcdr3regions AT fabianjtheis predictingantigenspecificityofsingletcellsbasedontcrcdr3regions |
_version_ |
1721230616638259200 |