ABSTRACT
Microarray data has numerous scientific applications and, in many instances, investigators may not need to go beyond the statistical analysis of an expressional profile obtained on array. An example would be a situation in which a certain microarray signature is proven to have a diagnostic validity. For example, RNA samples from 74 patients with Dukes’ B colon cancer were analyzed using an Affymetrix U133a GeneChip [1]. Class prediction approaches were used to identify gene markers that can best discriminate between patients who would experience relapse and patients who would remain disease-free. Gene expression profiling identified a 23-gene signature that predicts recurrence in Dukes’ B patients [1]. In a number of other instances, however, validation of microarray data may become an integral part of research projects. Validation means answering one or several of the following questions:
1. Are the observed statistically significant changes for certain genes real (relates to false positive)?
