Additional data file 1:

The ROC curves of the optimal LS-SVM models for all considered combinations of data sets shown in Tables 2 and 4 are shown. Additional Figures 1-3 show the ROC curves for the prediction of WHEELER, pN-STAGE, and CRM in rectal cancer, respectively. For prostate cancer, the ROC curves for the prediction of GRADE, STAGE, METASTASIS, and RECURRENCE are shown in additional Figures 4-7, respectively.

Format: PDF Size: 33KB Download file

This file can be viewed with: Adobe Acrobat Reader

Additional data file 2:

The results for the prediction of WHEELER, pN-STAGE, and CRM in rectal cancer, using step C models for which a sample is required at both time points and for which both technologies need to be performed. The AUC value and the number of included features are shown for each model. Significance tests were performed to compare these models with the best model based on two data sets shown in bold in Table 2.

Format: PDF Size: 32KB Download file

This file can be viewed with: Adobe Acrobat Reader

Additional data file 3:

Additional Tables 1-3 show all genes and proteins selected by the best performing models MPT₁ for the prediction of WHEELER (25 genes, 12 proteins), pN-STAGE (21 genes, 14 proteins), and CRM (7 genes, 33 proteins) in rectal cancer. Additional Tables 4-7 show, for prostate cancer, the genes and CNVs selected by the best performing models MG for the prediction of GRADE (6 genes, 8 CNVs), STAGE (42 genes, 22 CNVs), METASTASIS (18 genes, 3 CNVs), and RECURRENCE (32 genes, 2 CNVs). All tables additionally show the number of LOO iterations in which each gene, protein, or CNV was selected, their chromosomal region, and whether it is up- or down-regulated.

Format: PDF Size: 59KB Download file

This file can be viewed with: Adobe Acrobat Reader