Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Change Point Detection for Cell Populations Measured via Flow Cytometry

Yik Lun Kei, Qi Wang, Paul Parker, Francois Ribalet, Sangwon Hyun

TL;DR

A latent space Gaussian mixture-of-experts model is proposed, facilitating change point detection in replicated and clustered phytoplankton observations, and a scientifically important change point that aligns with a transition zone between two marine provinces is identified.

Abstract

The ocean is filled with phytoplankton that contribute as much photosynthesis as all land plants combined, making them vital to the carbon cycle and climate system. Recent advances in flow cytometry allow oceanographers to measure the optical traits of individual cells along research cruise tracks, generating single-cell resolution microbial data. In marine microbial ecology, detecting locations of abrupt changes in the environmental response of cytometric plankton distributions is an important task. This manuscript proposes a latent space Gaussian mixture-of-experts model, facilitating change point detection in replicated and clustered phytoplankton observations. Change points are identified through shifts in prior means of low-dimensional representations, with piecewise-constant structure enforced by a group-fused LASSO penalty. The optimization problem is then solved via Alternating Direction Method of Multipliers. Applied to flow cytometry data, the proposed method identifies a scientifically important change point that aligns with a transition zone between two marine provinces.

Change Point Detection for Cell Populations Measured via Flow Cytometry

TL;DR

A latent space Gaussian mixture-of-experts model is proposed, facilitating change point detection in replicated and clustered phytoplankton observations, and a scientifically important change point that aligns with a transition zone between two marine provinces is identified.

Abstract

The ocean is filled with phytoplankton that contribute as much photosynthesis as all land plants combined, making them vital to the carbon cycle and climate system. Recent advances in flow cytometry allow oceanographers to measure the optical traits of individual cells along research cruise tracks, generating single-cell resolution microbial data. In marine microbial ecology, detecting locations of abrupt changes in the environmental response of cytometric plankton distributions is an important task. This manuscript proposes a latent space Gaussian mixture-of-experts model, facilitating change point detection in replicated and clustered phytoplankton observations. Change points are identified through shifts in prior means of low-dimensional representations, with piecewise-constant structure enforced by a group-fused LASSO penalty. The optimization problem is then solved via Alternating Direction Method of Multipliers. Applied to flow cytometry data, the proposed method identifies a scientifically important change point that aligns with a transition zone between two marine provinces.
Paper Structure (12 sections, 39 equations, 3 figures, 1 table)

This paper contains 12 sections, 39 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Latent Space Model
  3. Model Specification
  4. Change Points
  5. Learning and Inference
  6. Learning Priors from Observed Sequence
  7. Change Point Localization and Model Selection
  8. Change Point Localization
  9. Model Selection
  10. Simulation Study with Real Covariates
  11. Application to Flow Cytometry Data
  12. Discussion

Figures (3)

  • Figure 1: An overview of prior distributions and latent space Gaussian mixture-of-experts decoder.
  • Figure 2: Map of the research cruise trajectory in the North Pacific Ocean shown in yellow (the upward trajectory and downward trajectory are slightly separated for visibility). The research cruise (Gradients 2) traversed two different bodies of ocean water ---"subtropical gyre" in the south and "subarctic gyre" up north. Our proposed method applied to this dataset detected a change point at about 33.2 degrees North, in latitude, which is roughly consistent with several other change points found in the literature.
  • Figure 3: An illustration of the estimated $\Delta\mu$ for the flow cytometry data. The detected change points are indicated by the red vertical line. The detection threshold is displayed by the horizontal line.