Partition Decoupling for Multi-gene Analysis of Gene Expression Profiling Data

TL;DR

The paper introduces the Partition Decoupling Method, a novel unsupervised technique for gene expression analysis that uncovers complex data geometries and phenotypic differences beyond individual gene expression levels.

Contribution

It extends the Partition Decoupling Method to gene expression data, enabling multi-gene analysis and improved phenotypic discrimination over existing methods.

Findings

Successfully identified cell types and treatments with higher accuracy.

Revealed phenotypic differences without differential gene expression.

Facilitated pathway-level analysis to find mechanistically-related gene sets.

Abstract

We present the extention and application of a new unsupervised statistical learning technique--the Partition Decoupling Method--to gene expression data. Because it has the ability to reveal non-linear and non-convex geometries present in the data, the PDM is an improvement over typical gene expression analysis algorithms, permitting a multi-gene analysis that can reveal phenotypic differences even when the individual genes do not exhibit differential expression. Here, we apply the PDM to publicly-available gene expression data sets, and demonstrate that we are able to identify cell types and treatments with higher accuracy than is obtained through other approaches. By applying it in a pathway-by-pathway fashion, we demonstrate how the PDM may be used to find sets of mechanistically-related genes that discriminate phenotypes.