Gene expression module-based chemical function similarity search

Abstract

Investigation of biological processes using selective chemical interventions is generally applied in biomedical research and drug discovery. Many studies of this kind make use of gene expression experiments to explore cellular responses to chemical interventions. Recently, some research groups constructed libraries of chemical related expression profiles, and introduced similarity comparison into chemical induced transcriptome analysis. Resembling sequence similarity alignment, expression pattern comparison among chemical intervention related expression profiles provides a new way for chemical function prediction and chemical-gene relation investigation. However, existing methods place more emphasis on comparing profile patterns globally, which ignore noises and marginal effects. At the same time, though the whole information of expression profiles has been used, it is difficult to uncover the underlying mechanisms that lead to the functional similarity between two molecules. Here a new approach is presented to perform biological effects similarity comparison within small biologically meaningful gene categories. Regarding gene categories as units, a reduced similarity matrix is generated for measuring the biological distances between query and profiles in library and pointing out in which modules do chemical pairs resemble. Through the modularization of expression patterns, this method reduces experimental noises and marginal effects and directly correlates chemical molecules with gene function modules.

Figure 1.

Workflow of gene expression module-based similarity search. Workflow of expression function pattern similarity search: (A) A query profile is uploaded and GOMs significantly affected are found using hypergeometric test; (B) for each GOM found in the first step, expression pattern comparison is performed between the query and every reference instance to calculate for each GOM a S score and a P-value. Instances whose P-value is above the threshold (default is 0.05) are filtered out. Instances are arranged in descending order according to the number of matched (or reverse-matched) GOMs; (C) results are returned in both graphic and textual forms.