Human Blood-Brain Differential Gene-Expression Correlates with Dipeptide Frequency of Gene Products
Differential gene expression in different tissues is largely considered to be the specific property of individual genes. In this work a relationship between overall dipeptide composition of proteins encoded by genes on the one hand and the difference in their expression level in two of the most important human organs i. e. blood and brain have been studied. Study is designed by developing a neural network that tries to predict the difference between expression of a gene in blood and brain from a 400-dimensional relative dipeptide composition vector. These vectors are derived from the amino acid sequence obtained by translating the corresponding gene. In a holdout validation scheme, such a model can predict gene expression from dipeptide composition with a significant Pearson’s correlation of 0.49 with a classification capacity between (expression wise) blood favored and brain favored genes reaching 68 to 70% accuracy. Results indicate that despite diverse biological function of each expressed gene within a tissue, some similarities in gene products do exist.
KeywordsNeural Network Differential Gene Expression Dipeptide Composition Estimate Gene Expression Predict Gene Expression
Unable to display preview. Download preview PDF.