Fig. 2
From: PrognosiT: Pathway/gene set-based tumour volume prediction using multiple kernel learning
The predictive performance of RF algorithm (RF), SVR algorithm (SVR), PrognosiT algorithm with the Hallmark gene set collection (MKL[H]) and PrognosiT algorithm with the Pathway Interaction Database pathway collection (MKL[P]) on thyroid carcinoma (THCA) data set. Comparison of the NRMSE values resulted from 100 replications for each of the four algorithms is made using the box-and-whisker plots. RF is compared against SVR, MKL[H] and MKL[P] algorithms using the two-tailed paired t-test to check whether there is a significant difference between their performances. In addition, SVR is compared against MKL[H] and MKL[P]. The resulting p-values are reported. The color of p-values matches with the color of the winning algorithm, for each pairwise comparison