Provide functionality for cancer subtyping using existing published methods or machine learning based on TCGA data.
Currently support mRNA subtyping for LUSC, LUAD, HNSC, STAD, and BLCA using nearest centroids method or machine-learning-based method by training TCGA data.
This is a basic example for predicting the subtypes for LUSC.
library(OncoSubtype)
library(tidyverse)
set.seed(2121)
data <- get_median_centered(example_fpkm)
data <- assays(data)$centered
rownames(data) <- rowData(example_fpkm)$external_gene_name
# use default wilkerson's nearest centroids method
output1 <- centroids_subtype(data, disease = 'LUSC')
table(output1$subtypes)