Change Point Detection for Cell Populations Measured via Flow Cytometry

TL;DR

This paper introduces a novel statistical model for detecting change points in flow cytometry data of phytoplankton, enabling identification of significant ecological transitions in marine environments.

Contribution

It proposes a latent space Gaussian mixture-of-experts model with a group-fused LASSO penalty for change point detection in clustered microbial data.

Findings

Identified a key ecological change point in oceanographic data.

Aligned detected change point with a marine province transition zone.

Demonstrated effectiveness on real flow cytometry datasets.

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.