CytOpT: Optimal Transport with Domain Adaptation for Interpreting Flow Cytometry data - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Annals of Applied Statistics Year : 2023

CytOpT: Optimal Transport with Domain Adaptation for Interpreting Flow Cytometry data

Abstract

The automated analysis of flow cytometry measurements is an active research field. We introduce a new algorithm, referred to as CytOpT, using regularized optimal transport to directly estimate the different cell population proportions from a biological sample characterized with flow cytometry measurements. We rely on the regularized Wasserstein metric to compare cytometry measurements from different samples, thus accounting for possible mis-alignment of a given cell population across sample (due to technical variability from the technology of measurements). In this work, we rely on a supervised learning technique based on the Wasserstein metric that is used to estimate an optimal re-weighting of class proportions in a mixture model from a source distribution (with known segmentation into cell sub-populations) to fit a target distribution with unknown segmentation. Due to the high-dimensionality of flow cytometry data, we use stochastic algorithms to approximate the regularized Wasserstein metric to solve the optimization problem involved in the estimation of optimal weights representing the cell population proportions in the target distribution. Several flow cytometry data sets are used to illustrate the performances of CytOpT that are also compared to those of existing algorithms for automatic gating based on supervised learning.
Fichier principal
Vignette du fichier
2006.09003.pdf (2.94 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03100405 , version 1 (07-01-2021)

Licence

Identifiers

Cite

Paul Freulon, Jérémie Bigot, Boris Hejblum. CytOpT: Optimal Transport with Domain Adaptation for Interpreting Flow Cytometry data. Annals of Applied Statistics, 2023, 17 (2), pp.1086-1104. ⟨10.1214/22-AOAS1660⟩. ⟨hal-03100405⟩
96 View
239 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More