(410b) Gene-Pair Relative Expression Binary Barcode for the Diagnosis of Various Diseases of the Human Brain Conference: AIChE Annual MeetingYear: 2009Proceeding: 2009 AIChE Annual MeetingGroup: Systems BiologySession: Genomic Approaches to Systems Biology Time: Wednesday, November 11, 2009 - 12:48pm-1:06pm Authors: Sung, J., University of Illinois at Urbana Champaign Kim, P., University of Illinois Urbana Champaign Price, N. D., University of Illinois at Urbana-Champaign One of the main challenges in cancer therapy is the accurate diagnosis of tumor class and progression grade, which can be difficult because of morphologically indistinguishable tissue representation and inter-observer variability. In order to address this issue, cancer diagnosis is moving from classification based on microscopic observations of histological specimens alone, to a method based on molecular criteria by using gene expression profiling. In this study, we have developed a disease classification scheme based on the concept of finding gene-pairs that exhibit relative expression reversals between different classes. For an extensive collection of publicly available gene expression microarray data, we have identified gene-pair relative expression decision rules that can distinguish eleven different classes and progression grades of cancerous, as well as non cancerous human brain diseases. These gene-pair decision rules were accumulated into a binary barcode panel that can serve as classifier markers for the diagnosis of brain disease. Our classifier marker panel distinguishes each disease at high accuracy according to ten-fold cross validation, proving to be a potential strategy for stratifying patients based on gene expression signatures. Furthermore, the investigation of the biological function and chromosome location of genes in the panel, led to the discovery of novel molecular properties of each brain disease, which may help elucidate some of the causes of disease manifestation. This binary barcode panel of gene-pair relative expression classifiers is the first to be built for the diagnosis of such a large number of different brain disease classes, and can serve as a highly accurate diagnostic tool in combination with traditional histopathological techniques.