Table 2 Pipeline for data processing.

From: Interpretable graph Kolmogorov–Arnold networks for multi-cancer classification and biomarker identification using multi-omics data

Datatype

mRNA

miRNA

DNA Methylation

Original Features

60,660

1881

485,577

Differentially Expressed Analysis

26,768

-

-

LIMMA Model (Selected Features)

-

-

139,321

LASSO Regression Model (Selected Features)

520

-

393

All Tumor Samples and Normal

10,668

10,465

9,171

Unique Tumor Samples and Normal

10,667

10,465

8,674

Common Samples and Features

8,464 Samples and 2,794 Features