Independent component analysis algorithms for microarray data analysis

Abstract

Oligonucleotide Microarrays have become powerful tools in Genetic Research, as they serve as parallel scanning mechanisms to detect the presence of genes using test probes composed of controlled segments of gene code built by masking techniques. The detection of each gene depends on the multichannel differential expression of perfectly matched segments against mismatched ones. This methodology, devised to robustify the detection process posses some interesting problems under the point of view of Genomic Signal Processing, as test probes express themselves in rather different patterns, not showing proportional expression levels for most of the segment pairs, as it would be expected. These cases may be influenced by unexpected hybridization dynamics, and are worth of being studied with a double objective: gain insight into hybridization dynamics in microarrays, and to improve microarray production and processing as well. Two methods are proposed in this paper: modelling the dynamics of expression dynamics and isolating gene expressions showing unexpected behaviour to proceed in their further classification and study.

Diverse accurate feature selection for microarray cancer diagnosis

“…Feature reduction is generally addressed by some statistical approaches e.g. Principal Component Analysis (PCA) and Independent Component Analysis (ICA) able to transfer the original features to a lower dimensional space [20,24]. Regarding feature selection, there are two main approaches to reduce the dimensionality of the feature space.…”