Mixtures of Neural Network Experts with Application to Phytoplankton Flow Cytometry Data

TL;DR

This paper introduces a nonlinear mixture of experts model using neural networks to analyze phytoplankton flow cytometry data, enabling flexible, segment-specific environmental response estimation with improved realism.

Contribution

The work develops a neural network-based mixture of experts model that estimates subpopulation responses to environmental factors without heavy computational costs.

Findings

The model outperforms linear experts in simulated data.

It achieves comparable prediction accuracy on real data.

Provides more realistic estimates of phytoplankton behavior.

Abstract

Flow cytometry is a valuable technique that measures the optical properties of particles at a single-cell resolution. When deployed in the ocean, flow cytometry allows oceanographers to study different types of photosynthetic microbes called phytoplankton. It is of great interest to study how phytoplankton properties change in response to environmental conditions. In our work, we develop a nonlinear mixture of experts model to estimate separate regression functions for each subpopulation utilizing random-weight neural networks. Our model allows one to flexibly estimate how cell properties and relative abundances depend on environmental covariates in each segment of a heterogeneous sample, without the computational burden of backpropagation. We show that the proposed model provides superior predictive performance in simulated examples compared to a mixture of linear experts. Also, applying our model to real data, we show that our model has (1) comparable out-of-sample prediction performance, and (2) more realistic estimates of phytoplankton behavior.