Probing T-cell response by sequence-based probabilistic modeling.

With the increasing ability to use high-throughput next-generation sequencing to quantify the diversity of the human T cell receptor (TCR) repertoire, the ability to use TCR sequences to infer antigen-specificity could greatly aid potential diagnostics and therapeutics. Here, we use a machine-learni...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Barbara Bravi, Vinod P Balachandran, Benjamin D Greenbaum, Aleksandra M Walczak, Thierry Mora, Rémi Monasson, Simona Cocco
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/1b09e79bd3cc42a9a6d184af909b44d9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1b09e79bd3cc42a9a6d184af909b44d9
record_format	dspace
spelling	oai:doaj.org-article:1b09e79bd3cc42a9a6d184af909b44d92021-12-02T19:57:52ZProbing T-cell response by sequence-based probabilistic modeling.1553-734X1553-735810.1371/journal.pcbi.1009297https://doaj.org/article/1b09e79bd3cc42a9a6d184af909b44d92021-09-01T00:00:00Zhttps://doi.org/10.1371/journal.pcbi.1009297https://doaj.org/toc/1553-734Xhttps://doaj.org/toc/1553-7358With the increasing ability to use high-throughput next-generation sequencing to quantify the diversity of the human T cell receptor (TCR) repertoire, the ability to use TCR sequences to infer antigen-specificity could greatly aid potential diagnostics and therapeutics. Here, we use a machine-learning approach known as Restricted Boltzmann Machine to develop a sequence-based inference approach to identify antigen-specific TCRs. Our approach combines probabilistic models of TCR sequences with clone abundance information to extract TCR sequence motifs central to an antigen-specific response. We use this model to identify patient personalized TCR motifs that respond to individual tumor and infectious disease antigens, and to accurately discriminate specific from non-specific responses. Furthermore, the hidden structure of the model results in an interpretable representation space where TCRs responding to the same antigen cluster, correctly discriminating the response of TCR to different viral epitopes. The model can be used to identify condition specific responding TCRs. We focus on the examples of TCRs reactive to candidate neoantigens and selected epitopes in experiments of stimulated TCR clone expansion.Barbara BraviVinod P BalachandranBenjamin D GreenbaumAleksandra M WalczakThierry MoraRémi MonassonSimona CoccoPublic Library of Science (PLoS)articleBiology (General)QH301-705.5ENPLoS Computational Biology, Vol 17, Iss 9, p e1009297 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Biology (General) QH301-705.5
spellingShingle	Biology (General) QH301-705.5 Barbara Bravi Vinod P Balachandran Benjamin D Greenbaum Aleksandra M Walczak Thierry Mora Rémi Monasson Simona Cocco Probing T-cell response by sequence-based probabilistic modeling.
description	With the increasing ability to use high-throughput next-generation sequencing to quantify the diversity of the human T cell receptor (TCR) repertoire, the ability to use TCR sequences to infer antigen-specificity could greatly aid potential diagnostics and therapeutics. Here, we use a machine-learning approach known as Restricted Boltzmann Machine to develop a sequence-based inference approach to identify antigen-specific TCRs. Our approach combines probabilistic models of TCR sequences with clone abundance information to extract TCR sequence motifs central to an antigen-specific response. We use this model to identify patient personalized TCR motifs that respond to individual tumor and infectious disease antigens, and to accurately discriminate specific from non-specific responses. Furthermore, the hidden structure of the model results in an interpretable representation space where TCRs responding to the same antigen cluster, correctly discriminating the response of TCR to different viral epitopes. The model can be used to identify condition specific responding TCRs. We focus on the examples of TCRs reactive to candidate neoantigens and selected epitopes in experiments of stimulated TCR clone expansion.
format	article
author	Barbara Bravi Vinod P Balachandran Benjamin D Greenbaum Aleksandra M Walczak Thierry Mora Rémi Monasson Simona Cocco
author_facet	Barbara Bravi Vinod P Balachandran Benjamin D Greenbaum Aleksandra M Walczak Thierry Mora Rémi Monasson Simona Cocco
author_sort	Barbara Bravi
title	Probing T-cell response by sequence-based probabilistic modeling.
title_short	Probing T-cell response by sequence-based probabilistic modeling.
title_full	Probing T-cell response by sequence-based probabilistic modeling.
title_fullStr	Probing T-cell response by sequence-based probabilistic modeling.
title_full_unstemmed	Probing T-cell response by sequence-based probabilistic modeling.
title_sort	probing t-cell response by sequence-based probabilistic modeling.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/1b09e79bd3cc42a9a6d184af909b44d9
work_keys_str_mv	AT barbarabravi probingtcellresponsebysequencebasedprobabilisticmodeling AT vinodpbalachandran probingtcellresponsebysequencebasedprobabilisticmodeling AT benjamindgreenbaum probingtcellresponsebysequencebasedprobabilisticmodeling AT aleksandramwalczak probingtcellresponsebysequencebasedprobabilisticmodeling AT thierrymora probingtcellresponsebysequencebasedprobabilisticmodeling AT remimonasson probingtcellresponsebysequencebasedprobabilisticmodeling AT simonacocco probingtcellresponsebysequencebasedprobabilisticmodeling
_version_	1718375765938012160

Probing T-cell response by sequence-based probabilistic modeling.

Ejemplares similares