Asymmetric latent semantic indexing for gene expression experiments visualization

TL;DR

This paper introduces an asymmetric latent semantic indexing method for visualizing gene expression data, capturing hierarchical relationships and identifying gene classes in cancer datasets.

Contribution

It adapts latent semantic indexing with asymmetry and hierarchy modeling for gene expression visualization, integrating prior knowledge and mixture models.

Findings

Effective visualization of gene hierarchies in cancer data

Identification of gene classes using the proposed method

Demonstrated utility on Human Cancer dataset

Abstract

We propose a new method to visualize gene expression experiments inspired by the latent semantic indexing, technique originally proposed in the textual analysis context. By using the correspondence word-gene document-experiment, we define an asymmetric similarity measure of association for genes that accounts for potential hierarchies in the data, the key to obtain meaningful gene mappings. We use the polar decomposition to obtain the sources of asymmetry of the similarity matrix, which are later combined with previous knowledge. Genetic classes of genes are identified by means of a mixture model applied in the genes latent space. We describe the steps of the procedure and we show its utility in the Human Cancer dataset.