Inferring Similarity between Time-Series Microarrays: A Content-based Approach

Abstract

Public repositories for gene expression studies have been growing rapidly in the last decade. Retrieval of gene expression experiments based on textual descriptions does not provide sufficient data for biologists and clinicians. Content-based search has recently become more desirable in retrieving similar experiments. Current methods for content-based retrieval cannot address the problem of profiling the gene behaviors in multiple measurement points, i.e. in time course. This study, to the best of our knowledge, is the first attempt to build a fingerprint for each gene by considering all time points to infer its time-course profile to represent the experiment content in an information retrieval framework. An empirical study is performed on a large dataset of Arabidopsis microarrays from Gene Expression Omnibus (GEO). Experimental results show that relevant experiments are retrieved based on content similarity.