Ensemble Methods with Voting Protocols Exhibit Superior Performance for Predicting Cancer Clinical Endpoints and Providing More Complete Coverage of Disease-Related Genes

Figure 1

Work flow of the whole process. First, the datasets were downloaded from the GDC (Genomic Data Commons) database. Next, the downloaded mRNA and microRNA sequencing data are united by the usable information. The t-test was used afterwards to determine the significantly expressed genes. Five selection methods were used to select the cancer-associated genes and the subdatasets generated according to the ranks. Finally, the prediction results were integrated by a voting protocol. Note that every subdataset was divided into two pieces for cross-validation and independent test in the ratio 4 : 1 before variable selection. Only the datasets for cross-validation will be used for variable selection and modeling.