A variational deep-learning approach to modeling memory T cell dynamics.

Mechanistic models of dynamic, interacting cell populations have yielded many insights into the growth and resolution of immune responses. Historically these models have described the behavior of pre-defined cell types based on small numbers of phenotypic markers. The ubiquity of deep phenotyping th...

Full description

Saved in:
Bibliographic Details
Main Authors: Christiaan H van Dorp, Joshua I Gray, Daniel H Paik, Donna L Farber, Andrew J Yates
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-07-01
Series:PLoS Computational Biology
Online Access:https://doi.org/10.1371/journal.pcbi.1013242
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849228218056310784
author Christiaan H van Dorp
Joshua I Gray
Daniel H Paik
Donna L Farber
Andrew J Yates
author_facet Christiaan H van Dorp
Joshua I Gray
Daniel H Paik
Donna L Farber
Andrew J Yates
author_sort Christiaan H van Dorp
collection DOAJ
description Mechanistic models of dynamic, interacting cell populations have yielded many insights into the growth and resolution of immune responses. Historically these models have described the behavior of pre-defined cell types based on small numbers of phenotypic markers. The ubiquity of deep phenotyping therefore presents a new challenge; how do we confront tractable and interpretable mathematical models with high-dimensional data? To tackle this problem, we studied the development and persistence of lung tissue-resident memory CD4 and CD8 T cells ([Formula: see text]) in mice infected with influenza virus. We developed an approach in which dynamical model parameters and the population structure are inferred simultaneously. This method uses deep learning and stochastic variational inference and is trained on the single-cell flow-cytometry data directly, rather than on the kinetics of pre-identified clusters. We show that during the resolution phase of the immune response, memory CD4 and CD8 T cells within the lung are phenotypically diverse, with subsets exhibiting highly distinct and time-dependent dynamics. [Formula: see text] heterogeneity is maintained long-term by ongoing differentiation of relatively persistent Bcl-2hi CD4 and CD8 [Formula: see text] subsets which resolve into distinct functional populations. Our approach yields new insights into the dynamics of tissue-localized immune memory, and is a novel basis for interpreting time series of high-dimensional data, broadly applicable to diverse biological systems.
format Article
id doaj-art-4901575af94a4118b5be8a08bfa3b32d
institution Kabale University
issn 1553-734X
1553-7358
language English
publishDate 2025-07-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS Computational Biology
spelling doaj-art-4901575af94a4118b5be8a08bfa3b32d2025-08-23T05:31:15ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582025-07-01217e101324210.1371/journal.pcbi.1013242A variational deep-learning approach to modeling memory T cell dynamics.Christiaan H van DorpJoshua I GrayDaniel H PaikDonna L FarberAndrew J YatesMechanistic models of dynamic, interacting cell populations have yielded many insights into the growth and resolution of immune responses. Historically these models have described the behavior of pre-defined cell types based on small numbers of phenotypic markers. The ubiquity of deep phenotyping therefore presents a new challenge; how do we confront tractable and interpretable mathematical models with high-dimensional data? To tackle this problem, we studied the development and persistence of lung tissue-resident memory CD4 and CD8 T cells ([Formula: see text]) in mice infected with influenza virus. We developed an approach in which dynamical model parameters and the population structure are inferred simultaneously. This method uses deep learning and stochastic variational inference and is trained on the single-cell flow-cytometry data directly, rather than on the kinetics of pre-identified clusters. We show that during the resolution phase of the immune response, memory CD4 and CD8 T cells within the lung are phenotypically diverse, with subsets exhibiting highly distinct and time-dependent dynamics. [Formula: see text] heterogeneity is maintained long-term by ongoing differentiation of relatively persistent Bcl-2hi CD4 and CD8 [Formula: see text] subsets which resolve into distinct functional populations. Our approach yields new insights into the dynamics of tissue-localized immune memory, and is a novel basis for interpreting time series of high-dimensional data, broadly applicable to diverse biological systems.https://doi.org/10.1371/journal.pcbi.1013242
spellingShingle Christiaan H van Dorp
Joshua I Gray
Daniel H Paik
Donna L Farber
Andrew J Yates
A variational deep-learning approach to modeling memory T cell dynamics.
PLoS Computational Biology
title A variational deep-learning approach to modeling memory T cell dynamics.
title_full A variational deep-learning approach to modeling memory T cell dynamics.
title_fullStr A variational deep-learning approach to modeling memory T cell dynamics.
title_full_unstemmed A variational deep-learning approach to modeling memory T cell dynamics.
title_short A variational deep-learning approach to modeling memory T cell dynamics.
title_sort variational deep learning approach to modeling memory t cell dynamics
url https://doi.org/10.1371/journal.pcbi.1013242
work_keys_str_mv AT christiaanhvandorp avariationaldeeplearningapproachtomodelingmemorytcelldynamics
AT joshuaigray avariationaldeeplearningapproachtomodelingmemorytcelldynamics
AT danielhpaik avariationaldeeplearningapproachtomodelingmemorytcelldynamics
AT donnalfarber avariationaldeeplearningapproachtomodelingmemorytcelldynamics
AT andrewjyates avariationaldeeplearningapproachtomodelingmemorytcelldynamics
AT christiaanhvandorp variationaldeeplearningapproachtomodelingmemorytcelldynamics
AT joshuaigray variationaldeeplearningapproachtomodelingmemorytcelldynamics
AT danielhpaik variationaldeeplearningapproachtomodelingmemorytcelldynamics
AT donnalfarber variationaldeeplearningapproachtomodelingmemorytcelldynamics
AT andrewjyates variationaldeeplearningapproachtomodelingmemorytcelldynamics