Finding disease-related genomic experiments within an international repository: first steps in translational bioinformatics

Abstract

The amount of gene expression data in international repositories has grown exponentially. An important first step in translating the results of genomic experiments into medicine is to relate these genomic experiments to the human diseases they have studied. Unfortunately, repositories for expression data store the crucial annotative details only as free-text, making it manually intractable to link these with human disease. In this study, we sought to find experiments in NCBI GEO that are related to human diseases by making use of annotations relating these experiments with PUBMED identifiers representing the publication in which each experiment was published. In this manner, we find that 35% of PUBMED-associated genomic experiments can be related to a human disease, and that publicly-available data from these genomic experiments can already be related to over 270 human diseases and conditions. This represents an important first step in bridging the world of nucleotides, transcripts and expression with the afflications of us all.