In fjcamlab/cohesiveness: Non-parametric feature selection for large omic datasets

library(knitr)
opts_chunk$set(warning=TRUE, message = FALSE, cache = FALSE, fig.path = "figures/", tidy = FALSE,
               tidy.opts = list(width.cutoff = 60))

---

Theoretical framework

Installation

The cohesiveness R source package can be downloaded from Bioconductor repository or GitHub repository.

## From Bioconductor repository
if (!requireNamespace("BiocManager", quietly = TRUE)) {
      install.packages("BiocManager")
  }
BiocManager::install("cohesiveness")

## Or from GitHub repository using devtools
BiocManager::install("devtools")
devtools::install_github("fjcamlab/cohesiveness")

library(cohesiveness)
library(leukemiasEset)
library(Biobase)

## Loading an example dataset
data(leukemiasEset)

## Formatting the dataset
mx <- exprs(leukemiasEset)

## Vector of sample categories
cl <- pData(leukemiasEset)[, "LeukemiaType"]
names(cl) <- rownames(pData(leukemiasEset))

Running cohesiveness

## Running cohesiveness on the dataset
coh <- cohesiveness(mx, cl)

Representation of results

plotCohesiveness(mx, cl, coh = coh, id = "ENSG00000182606")

fjcamlab/cohesiveness documentation built on May 6, 2019, 12:09 p.m.