Knowledge Discovery in Microarray Data

We present a method of prioritizing potential drug targets based on their gene expression “signature”. Primary human pre-cursor neuronal cells were treated with three classes (antidepressant, antipsychotic, opiod receptor agonist) of psychoactive drugs for 24 hours. Microarray technology was used to capture expression of ~11, 000 genes induced by these three categories of drugs. It was demonstrated that a Neural Network model and a Decision Tree (C5.0) model could classify these drugs based on their gene expression with 80% and 92 % accuracy, respectively. TwoStep clustering algorithm was used to separate gene expression profiles into natural groups. When cluster information was used as input for the Neural Network model, classification accuracy increased to 88%. It was also demonstrated that the confidence index generated by each classification model could successfully be used to prioritize a portfolio of novel drug targets. Refreshments will be served at 3:00 pm. For further information: [email protected] (860) 832-2839 [email protected] (860) 832-2851