Initial microarray classification studies such as those presented in [ 4, 5] were able to characterize similarities and differences among samples based on mRNA expression level for large gene sets.
However, as it was already mentioned, a single classifier such as decision tree is far from an accurate classifier when applied to the problem of gene microarray classification which usually confronts several challenges such as curse of dimensionality, small sample size datasets, and huge amount of noise and uncertainties.
These methods are common used in microarray classification problems [ 49- 51].
Usually, microarray classification process comprised of two successive steps, that is, feature selection and classification.
In this work, we addressed RotBoost ensemble classification method to cope with gene microarray classification problems.
In the present work, we proposed a novel ANMM4CBR method for microarray classification.
We excluded other classifications, such as "elective".
It has been demonstrated that classification gene sets are profoundly influenced by the microarray methodology, such as the microarray technique, microarray platform, and preprocessing methods [ 4- 8].
There are various reports in which QDs have been used in microarray fabrication such as sandwich-based immunoassay type, RP protein microarray type, etc. [132 135].
Of course our methods can be applicable also to other high dimensional data where we consider classification problems such as protein microarrays, DNA copy number variation, exome profiling and RNAseq.
