Hierarchical Bayesian mixture modelling for antigen-specific T-cell subtyping in combinatorially encoded flow cytometry studies

Abstract

Novel uses of automated flow cytometry technology for measuring levels of protein markers on thousands to millions of cells are promoting increasing need for relevant, customized Bayesian mixture modelling approaches in many areas of biomedical research and application. In studies of immune profiling in many biological areas, traditional flow cytometry measures relative levels of abundance of marker proteins using fluorescently labeled tags that identify specific markers by a single-color. One specific and important recent development in this area is the use of combinatorial marker assays in which each marker is targeted with a probe that is labeled with two or more fluorescent tags. The use of several colors enables the identification of, in principle, combinatorially increasingly numbers of subtypes of cells, each identified by a subset of colors. This represents a major advance in the ability to characterize variation in immune responses involving larger numbers of functionally differentiated cell subtypes. We describe novel classes of Markov chain Monte Carlo methods for model fitting that exploit distributed GPU (graphics processing unit) implementation. We discuss issues of cellular subtype identification in this novel, general model framework, and provide a detailed example using simulated data. We then describe application to a data set from an experimental study of antigen-specific T-cell subtyping using combinatorially encoded assays in human blood samples. Summary comments discuss broader questions in applications in immunology, and aspects of statistical computation.

High-speed automatic characterization of rare events in flow cytometric data

“…The stochastic expression of cells in high-dimensional marker-space of cytometric data naturally leads to the idea of modeling each cell population with a multivariate statistical distribution whose parameters can describe its characteristics [14]. Over the past decade, computational cytometric studies have therefore led to a number of new applications of finite mixture models [4,6,[15][16][17]. Some of these have also involved hierarchical and multi-level models [8,10,17].…”

“…Over the past decade, computational cytometric studies have therefore led to a number of new applications of finite mixture models [4,6,[15][16][17]. Some of these have also involved hierarchical and multi-level models [8,10,17]. Often, such methods were designed with the aim of detecting both known as well as rare cell clusters [4,[18][19][20] in an automated manner.…”

Bayesian immunological model development from the literature: Example investigation of recent thymic emigrants

“…187–217). See Costa et al (2011) and Lin et al (2013) for recent applications. Another approach, applicable to models in fewer parameters, is grid approximation (Section 6.6) in which the prior (Kruschke 2011, p. 105) and, even more importantly for the method of the present paper, the likelihood do not need to be discrete versions of any particular parametric distribution (i.e., distribution-free ).…”

From Physical to Cyber

“…Applications of mixture models have appeared in various fields including biomedical studies [37,38,21], economics [34,61] and marketing research [58,48]. Within the family of mixture models, the mixture of Gaussian regression models has the tight structure of a parametric model and retains the flexibility of a nonparametric method.…”