Analysis of imputed microarray data using data mining techniques

Abstract

Rapid development of huge amount of data like microarray gene expression data that is stored in databases need powerful tools so as to analyze and extract interesting patterns Microarray technique provides a platform which can be used to measure the expression levels of thousands of genes simultaneously in a single experiment whereas in traditional techniques the expression level of single gene could be measured at a time As a result powerful tools need to be developed to handle these massive data Clustering is one of the powerful data mining techniques that can be used to deal with microarray gene expression data as it groups similar objects together and allows the biologist to understand cellular activities and identify potentially meaningful relationships between the objects Another issue while analyzing the input data is occurrence of missing values due to flaws such as scratches insufficient resolution or hybridization errors on the chips In recent years there has been an explosion of data in the field of biotechnology gene expression profiles generated by the high throughput microarray experiments often contain missing values which significantly affect the performance of subsequent statistical analysis and machine learning algorithms newline