Figure 1.
Scatter-plots of the top most gene of each level in the SRBCT data set.
Panels (a), (b) and (c) are the scatter-plots of the top most gene of level-1, level-2, and level-3, respectively. The top most genes are WAS (236282), PTPN12 (774502) and GSTA4 (504791), respectively. There are four classes in the SRBCT data set: Ewing sarcomas (EWS), Burkitt lymphomas (BL), neuroblastomas (NB), and rhabdomyosarcomas (RMS).
Table 1.
Summary of top 10 genes of each level selected by GMI in the SRBCT data set.
Table 2.
The comparison of top 10 level-2 genes selected by GMI and TBM in the SRBCT data set.
Figure 2.
The level-2-like and level-1-like genes ranked within top 10 level-3 genes by template-based method in the Lung Cancer data set.
Panels (a), (b), (c) and (d) are the scatter-plots of the level-2-like genes. Panels (e) and (f) are the scatter-plots of the level-1-like genes.
Figure 3.
Effect of sample size on Pearson's correlation coefficient values.
Table 3.
Summarization of the identified pathways related to the level-2 discriminatory genes in the Leukemia data set.
Table 4.
Summarization of the identified pathways related to the level-2 discriminatory genes in the Lung Cancer data set (Part I).
Table 5.
Summarization of the identified pathways related to the level-2 discriminatory genes in the Lung Cancer data set (Part II).
Figure 4.
Steps involved to compute GMI and to find the list of group specific genes for each level of discrimination.
Figure 5.
A 5-class synthetic example to illustrate computation of GMI.
There are four levels of discrimination in the 5-class synthetic data set. Panels (a) to (d) depict the computation of GMI values at each level of discrimination. The dotted lines in each panel indicate the two mean values used for GMI computation in each level of discrimination. All filled samples in each panel indicate the upper group samples. The remaining open samples in each panel indicate the lower group samples.