Table 1 Summary of datasets.

From: MOGONET integrates multi-omics data using graph convolutional networks allowing patient classification and biomarker identification

Dataset

Categories

Number of features mRNA, meth, miRNA

Number of features for training mRNA, meth, miRNA

ROSMAP

NC: 169, AD: 182

55,889, 23,788, 309

200, 200, 200

LGG

Grade 2: 246, Grade 3: 264

20,531, 20,114, 548

2000, 2000, 548

KIPAN

KICH: 66, KIRC: 318, KIRP: 274

20,531, 20,111, 445

2000, 2000, 445

BRCA

Normal-like: 115, Basal-like: 131, HER2-enriched: 46, Luminal A: 436, Luminal B: 147

20,531, 20,106, 503

1000, 1000, 503

  1. mRNA refers to mRNA expression data. meth refers to DNA methylation data. miRNA refers to miRNA expression data. The ROSMAP dataset is for the classification of Alzheimer’s disease (AD) patients vs. normal control (NC). The LGG dataset is for grade classification in low-grade glioma (LGG). The KIPAN dataset is for kidney cancer type classification with chromophobe renal cell carcinoma (KICH), clear renal cell carcinoma (KIRC), and papillary renal cell carcinoma (KIRP). The BRCA dataset is for breast invasive carcinoma (BRCA) PAM50 subtype classification with normal-like, basal-like, human epidermal growth factor receptor 2 (HER2)-enriched, Luminal A, and Luminal B subtypes.
Back to article page