mockgene: Mock Gene Data

In FusionLearn: Fusion Learning

Mock Gene Data

Description

This dataset is a mock version of two different microarray experiments on breast cancer cells.

Usage

data("mockgene1")
data("mockgene2")

Format

The first data "mockgene1" contains 98 subjects, and the second data "mockgene2" contains 286 subjects.

The first column for each data is ID number.

The second column is subjects' status. If the status is the estrogen-receptor-positive, y=1; if the status is estrogen-receptor-negative, y=0. Other columns record the gene expression values.

Details

This is an example to implement the FusionLearn algorithm for binary responses. In this case, the two experiments followed different protocols, and the two sets of gene expression profiles are different. The objective is to select a suitable subset gene predictors for the disease analysis based on both experiments.

Source

This data is a mock version of the original data. The original gene data contain over 20,000 profile expressions, and more details can be found on https://www.ncbi.nlm.nih.gov/ with series numbers GSE2034 and GSE22093.

FusionLearn documentation built on April 25, 2022, 1:05 a.m.