In leekgroup/phenopredict: Predicting phenotypes from RNA-seq expression data

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "README-"
)

phenopredict

The goal of phenopredict is to build predictors from expression data (RNA-Seq) that will predict necessary phenotype information across samples.The phenotypes sex, tissue, sequencing strategy, and sample source have been predicted across the ~70,000 samples currently available in recount.

Installation

You can install phenopredict from GitHub with:

# install.packages("devtools")
devtools::install_github("leekgroup/phenopredict")

Examples using phenopredict

Details of how the predicted phenotypes previously generated for the recount data) are available on GitHub.

Adding predicted phenotypes in recount

If you're looking to find the phenotype information previously generated across the recount samples, an example of how to use add_predictions() within recount is provided below.

library('recount')

download_study('ERP001942', type='rse-gene')
load(file.path('ERP001942', 'rse_gene.Rdata'))
rse <- scale_counts(rse_gene)

rse_with_pred <- add_predictions(rse)