Each bag contains a sample representative of the original dataset and the sampling is done with replacement.
It should be noted, however, that three samples interpreted as ccRCC in the Rhodes et al [ 2] and Xu et al [ 3] studies were actually normal samples in the original dataset and thus the sample headings were misleading.
In LOOCV, one sample from the original dataset is considered testing dataset, and the remaining samples are considered training dataset.
Briefly, each sample (either mutated or not) was individually removed from the dataset, and the remaining samples were used to select again significant genes and redefine the four signatures.
Then, for each trial, 939 samples are randomly generated from the whole dataset as the training dataset and the rest samples are assigned to the testing dataset.
To test the generalization ability of the proposed method, we divided the dataset into the training set (sample size n = 70; 38 LC, 32 non-LC) which covered 2/3 samples of the dataset and the test set (sample size n = 37; 20 LC, 17 non-LC) which covered the other 1/3 specimens of the dataset.
The reference, sample size, number of genes in each dataset, and the number of samples in each class are summarized in Tables 3 and 4. The number of classes ranges from 2 to 14.
Reads were again generated, and treated as the dataset for the sample 2. To test the effects of sequencing depth, we varied the number of generated reads for each dataset from 1 to 50 million (M).
The mean intensity of SALL4 was calculated for the dataset, and each sample was then stratified as SALL4 high or SALL4 low according to their SALL4 expression value.
In addition, Dawes (1999) emphasizes that choosing subjective measures may be helpful when the dataset is not homogenous, and the sample of companies comes from different industries, making it easier to compare performance across industries.
