Identifying Stage II Colorectal Cancer Recurrence Associated Genes by Microarray Meta-Analysis and Building Predictive Models with Machine Learning Algorithms

Figure 3

(a) The correlation plot of the randomly selected 50 genes among the 479 universal stage II colorectal cancer recurrence associated genes. The blue color indicates positive correlations, while the red color indicates negative correlations. (b) Proportions of variance explained by principal components. Blue points show the proportion of variance explained by a single principal component, while red points show the cumulative proportions of variance. (c) The scatter plot of the selected principal components (the x-axis: PC1; the y-axis: PC2). Blue points indicate stage II colorectal cancer patients who had recurrent events within 3 years, while red points indicate patients who did not have recurrent events within 3 years. (d) The scatter plot of the selected principal components (the x-axis: PC1; the y-axis: PC3). (e) The scatter plot of the selected principal components (the x-axis: PC2; the y-axis: PC3).

(a)

(b)

(c)

(d)

(e)