Table 1 Datasets used for training meth-SemiCancer
Cancer | Labeled datasets (with the subtype information) | Total | Unlabeled datasets (without the subtype information) | Total | ||
|---|---|---|---|---|---|---|
BRCA | TCGA-BRCA | 1056 | GSE72251 GSE20712 GSE72245 | GSE75067 GSE69914 GSE156968 | GSE66695 GSE58999 GSE141441 | 1225 |
COAD | TCGA-COAD | 475 | GSE118970 GSE27130 | GSE131013 GSE57342 | GSE68060 GSE77954 | 436 |
GBM | TCGA-GBM | 375 | GSE200647 GSE195684 | GSE195640 GSE188547 | GSE121722 | 643 |
PRAD | TCGA-PRAD | 333 | GSE115413 GSE83917 | GSE112047 GSE26126 | GSE76938 | 400 |
RCC | TCGA-KICH, KIRC, KIRP | 900 | GSE61441 GSE105260 | GSE126441 | GSE113501 | 258 |
THCA | TCGA-THCA | 496 | GSE97466 | GSE86961 | GSE72729 | 156 |