Mondrian Processes for Flow Cytometry Analysis

TL;DR

This paper introduces a Bayesian nonparametric approach using Mondrian processes for automated, interpretable gating of flow cytometry data, aiming to improve reproducibility and incorporate prior expert knowledge.

Contribution

It presents a novel application of Mondrian processes for automated cell classification, enabling uncertainty quantification and interpretability in flow cytometry analysis.

Findings

Effective automated gating comparable to manual methods

Provides interpretable visualizations of cell classifications

Quantifies uncertainty in cell type assignments

Abstract

Analysis of flow cytometry data is an essential tool for clinical diagnosis of hematological and immunological conditions. Current clinical workflows rely on a manual process called gating to classify cells into their canonical types. This dependence on human annotation limits the rate, reproducibility, and complexity of flow cytometry analysis. In this paper, we propose using Mondrian processes to perform automated gating by incorporating prior information of the kind used by gating technicians. The method segments cells into types via Bayesian nonparametric trees. Examining the posterior over trees allows for interpretable visualizations and uncertainty quantification - two vital qualities for implementation in clinical practice.