makeROCs: Multi-ROC Plotting for TCGA Gene Expression Data

In jblam251/tcgaRNAML: a Package for Applying Machine Learning Classifiers to Gene Expression Data from The Cancer Genome Atlas

Description

This function generates a multi-Receiver Operating Characteristic (ROC) plot using RNA-seq data from The Cancer Genome Atlas (TCGA) database and a user-specified target variable. TCGA data is imported using the TCGA2STAT package. Feature selection is performed, and the remaining variables (in this case, genes) are processed by five different machine learning classifiers: LASSO-Logistic, K-Nearest Neighbor, Random Forest, a Radial-Kernal Support Vector Machine, and a Sigmoid-Kernal Support Vector Machine. An ROC curve is generated from each classifier, and plotted onto one graph.

Usage

makeROCs(type, target)

Arguments

type	TCGA-supported acronyms that designate the type of cancer. makeROCs currently supports ACC, BLCA, KIRC, KIRP, LIHC, and THCA. Instead of specifying a type, “Random” can be used to generate a randomly-chosen type of cancer, as well as a randomly chosen target variable
target	the variable to be predicted. makeROCs currently supports prediction of tumor “stage” (which attempts to distinguish stage I tumors from stage II, III, and IV tumors) and the participant’s “gender”.

Details

Cancer type acronyms: ACC Adrenocortical Carcinoma, BLCA Bladder Urothelial Carcinoma, KIRC Kidney Renal Clear Cell Carcinoma, KIRP Kidney Renal Papillary Cell Carcinoma, LIHC Liver Heptocellular Carcinoma, THCA Thyroid Carcinoma

Author(s)

Jacob Blamer, [e-mail]

Examples

makeROCs("THCA", "Stage")
makeROCs("BLCA", "Gender")
makeROCs("Random")

jblam251/tcgaRNAML documentation built on June 8, 2019, 2:32 p.m.