Time-dependent changes in ARE-driven gene expression by use of a noise-filtering process for microarray data

The current study was designed to identify the time-dependent gene expression profiles of antioxidant responsive element (ARE)- driven genes induced by tert-butylhydroquinone (tBHQ). A set of simple noise-filtering methods was introduced to evaluate and minimize the variance of microarray datasets. Gene expression induced by tBHQ (10 muM) in IMR-32 human neuroblastoma cells was analyzed by means of large-scale oligonucleotide microarray. Rank analysis was used to determine the acceptable number of independent samples necessary to eliminate false positives from the dataset. A dramatic reduction in the number of genes passing the rank analysis was achieved by using a 3 x 3 matrix comparison. Reproducibility was evaluated based on the coefficient of variation for average difference change. Completion of these analyses revealed that 101 of the 9,670 genes examined showed dynamic changes with treatment ranging from 4 h to 48 h. Since certain ARE-driven genes have been already identified, gene clustering would presumably group them together based on similar regulation. Self-organizing map grouped the genes induced by tBHQ into 12 (4x3) distinct clusters. Those previously identified ARE-driven genes were shown to group into different clusters. Since all potential ARE-driven genes did not cluster together, we speculate that multiple transcription factors and/or multiple signal transduction pathways contribute to transcriptional activation of the ARE. In conclusion, many novel potential ARE-driven genes were identified in this study. They function in detoxification and antioxidant defense, neuronal proliferation and differentiation, and signal transduction. The noise-filtering process applied to these microarray data, therefore, has proven to be very useful in identification of the time-dependent changes in ARE-drive gene expression.