Latent Dirichlet Allocation for Double Clustering (LDA-DC): Discovering patients phenotypes and cell populations within a single Bayesian framework

Abstract

Background: Current clinical routines rely more and more on ``omics'' data such as flow cytometry data from host and sometimes microbiota. Cohorts variability in addition to patients' heterogeneity make any underlying structure of these high-dimensional difficult to understand. In order to patients stratification and diagnostics, there is an acute need to develop novel statistical machine learning methods that are robust with respect to the data heterogeneity, efficient from the computational viewpoint, and can be understood by human experts Results: We propose a novel approach to stratify cell-based observations within a single probabilistic framework, i.e., to extract meaningful phenotype from both patients and cells simultaneously. We define this problem as a double clustering problem that we tackle with the proposed approach. Our method is a practical extension of the Latent Dirichlet Allocation and is used for this Double Clustering task (LDA-DC). We first validate the method on artificial datasets, then we apply our method to two real problems of patients stratification from cytometry and microbiota data. We observe that the LDA-DC returns clusters of patients and simultaneously clusters of cells related to patients’ conditions.We also construct a graphical representation of the results which can be easily understood and a great help for human experts.