• Corpus ID: 219708368

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

@article{Freulon2020CytOpTOT,
  title={CytOpT: Optimal Transport with Domain Adaptation for Interpreting Flow Cytometry data},
  author={Paul Freulon and J{\'e}r{\'e}mie Bigot and Boris P. Hejblum},
  journal={arXiv: Applications},
  year={2020}
}
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… 
1 Citations
Bayesian mixture models for cytometry data analysis
TLDR
This work acknowledges current computational challenges associated with the use of Bayesian mixture models for analyzing cytometry data, and draws attention to recent developments in advanced numerical algorithms for estimating large Bayes mixture models, which it believes have the potential to make Bayesianixture model more applicable to new types of single‐cell data with higher dimensions.

References

SHOWING 1-10 OF 29 REFERENCES
optimalFlow: optimal transport approach to flow cytometry gating and population matching
TLDR
The proposed optimalFlowTemplates + optimalFlowClassification addresses the problem of using supervised learning while accounting for biological and technical variability and provides a robust automated gating workflow that handles the intrinsic variability of flow cytometry data well.
Gating mass cytometry data by deep learning
TLDR
It is concluded that deep learning in general, and DeepCyTOF specifically, offers a powerful computational approach for semi-automated gating of CyTOF and flow cytometry data.
flowLearn: fast and precise identification and quality checking of cell populations in flow cytometry
TLDR
Results flowLearn is a semi‐supervised approach for the quality‐checked identification of cell populations, using a very small number of manually gated samples, and through density alignments it is able to predict gates on other samples with high accuracy and speed.
Sequential Dirichlet process mixtures of multivariate skew $t$-distributions for model-based clustering of flow cytometry data
TLDR
A Bayesian nonparametric approach with Dirichlet process mixture of multivariate skew $t$-distributions to perform model based clustering of flow-cytometry data and outperforms all other methods evaluated on the DALIA-1 data.
Critical assessment of automated flow cytometry data analysis techniques
TLDR
Several methods performed well as compared to manual gating or external variables using statistical performance measures, which suggests that automated methods have reached a sufficient level of maturity and accuracy for reliable use in FCM data analysis.
Stochastic Optimization for Regularized Wasserstein Estimators
TLDR
This work introduces an algorithm to solve a regularized version of this problem of Wasserstein estimators, with a time per step which is sublinear in the natural dimensions of the problem, and optimize it with stochastic gradient steps that can be computed directly from samples, without solving additional optimization problems at each step.
Computational flow cytometry: helping to make sense of high-dimensional immunology data
TLDR
This Review provides non-experts with a broad and practical overview of the many recent developments in computational flow cytometry.
Stochastic Optimization for Large-scale Optimal Transport
TLDR
A new class of stochastic optimization algorithms to cope with large-scale problems routinely encountered in machine learning applications, based on entropic regularization of the primal OT problem, which results in a smooth dual optimization optimization which can be addressed with algorithms that have a provably faster convergence.
Interpolating between Optimal Transport and MMD using Sinkhorn Divergences
TLDR
This paper studies the Sinkhorn Divergences, a family of geometric divergences that interpolates between MMD and OT, and provides theoretical guarantees for positivity, convexity and metrization of the convergence in law.
An Algorithm for Variable Density Sampling with Block-Constrained Acquisition
TLDR
A new way to draw the blocks in order to mimic CS strategies based on isolated measurements and an efficient minimization algorithm based on Nesterov's accelerated gradient descent in metric spaces are proposed.
...
...