Turtle shell clustering: A mixture approach to discriminative clustering with applications to flow cytometry and other data

TL;DR

The paper introduces the turtle shell clustering method, an unsupervised probabilistic approach that combines generative and discriminative ideas to automatically determine the number of clusters and handle complex data shapes.

Contribution

It presents a novel fully unsupervised clustering algorithm that estimates non-linear boundaries and automatically selects the number of components using a regularized mutual information objective.

Findings

Successfully applied to simulated and real datasets.

Effective in handling noise and irregular cluster shapes.

Extended analysis to flow cytometry data.

Abstract

Generative approaches to clustering provide information on geometric properties of clusters, whereas discriminative approaches provide boundaries between clusters. Ideas from both approaches are incorporated to present a fully unsupervised, probabilistic, and discriminative clustering method via a regularized mutual information objective function, wherein a mixture of mixtures of Gaussian and uniform distributions is used for formulation of the conditional model. Automatic selection of the number of components is established with the introduction of the regularizing term and a merge step, similar to those applied in reversible jump Markov chain Monte Carlo methods used in Bayesian clustering. Consequently, the turtle shell method -- a fully unsupervised clustering method capable of estimating non-linear boundary lines, automatically selecting the number of components, and capturing intuitive clusters in the presence of data abnormalities such as noise and/or irregular cluster shapes -- is introduced. We test this method on various simulated and real datasets commonly explored in clustering research, and extend the analysis to datasets arising from flow cytometry experiments.