Experimental results on eight skewed multiclass cancer microarray datasets indicate that unlike many traditional classification approaches, our methods are insensitive to class imbalance.
Taken together, these additional analyses of various public microarray datasets indicate that the prognostic value of ICS extends beyond node-negative and chemotherapy naïve HRneg/Tneg cases, to those of more advanced clinical stage and despite intervention with aggressive adjuvant chemotherapy.
While these methods differ in important details, they all use variations of two basic steps: (i) compute a score at each genomic locus (typically a probe in microarray datasets) indicating the recurrence; (ii) examine correlations between recurrences scores of nearby loci to separate the true target region from other close, high-scoring regions.
The best performance of each cancer classification approach for each microarray dataset is indicated in bold.
A number of gene expression changes were further validated using qRT-PCR and we report a good correlation between the datasets, indicating the robustness of the microarray protocol employed.
Two subset of NAC genes exhibited specifically high transcript accumulation in active and dormant cambiums respectively, from two independent microarray datasets [ 85, 86], strongly indicating their specific roles in wood-formation.
Analyses of multiple microarray datasets derived from human colorectal cancer indicated that correlation levels of FoxM1 and pituitary tumor transforming gene (PTTG1) are highly concordant (R = 0.68 ~ 0.89, p = 2.1E-226 ~ 9.6E-86 9.6E-86
Table 3 shows the correlation of gene expression behaviour with that of Nnat, in four microarray datasets; entries with a null value indicate that this gene is missing in the specific dataset; their fold change information in BAIR fat-fed mice and human with obesity are shown in Table 4.
AQP: aquaporin; AC: adenocarcinoma; SCC: squamous cell carcinoma; fold change was calculated across microarray datasets (median); fold change in bold and marked indicates statistical significance (p-value < 0.05).
