Microarray gene expression: a study of between-platform association of Affymetrix and cDNA arrays

摘要

Microarrays technology has been expanding remarkably since its launch about 15 years ago. With itsadvancement along with the increase of popularity, the technology affords the luxury that gene expressionscan be measured in any of its multiple platforms. However, the generated results from the microarrayplatforms remain incomparable. In this direction, we earlier developed and tested an approach toaddress the incomparability of the expression measures of Affymetrix®- and cDNA-platforms. Themethod was an exploit involving transformation of Affymetrix data, which brought the gene expressionsof both cDNA and Affymetrix platforms to a common and comparable level. The encouraging outcomeof that investigation has subsequently acted as a motivator to focus attention on examining further inthe direction of defining the association between the two platforms. Accordingly, this paper takes on anovel exploration towards determining a precise association using a wide range of statistical and machinelearning approaches. Specifically, the various models are elaborately trailed using – regression(linear, cubic-polynomial, loess, bootstrap aggregating) and artificial neural networks (self-organizingmaps and feedforward networks). After careful comparison in the end, the existing relationship betweenthe data from the two platforms is found to be nonlinear where feedforward neural network captures thebest delineation of the association.