jnpaulson

---
title: "Beginner R Workshop"
output: html_document
date: October 27, 2016
author: Keegan Korthauer and Joseph N. Paulson
---

Today's workshop will be a gentle introduction to the
[R programming language](https://cran.r-project.org/).  We have provided RStudio Server instances that you can access on the web, but we'll also briefly overview how you can install R and RStudio on your own computer.  We'll start with some basics about programming and then get some hands-on experience with analyzing a real-world messy dataset that we'll collect from everyone live.  We hope that you'll get a feel for what R can do as well as learn where you can learn more to use it on your own (great resources are listed at the end).

jnpaulson

###########################
# Load Required Libraries #
###########################

library(vegan) # TSS Normalization
library(data.table) # fread
# Install MetagenomeSeq (EM_ZIG Model)
library(devtools)
# install_github('HCBravoLab/metagenomeSeq', ref='per_feature_em')
library(metagenomeSeq) #FIT-ZIG

jnpaulson

library(mgcv)
#library(modules) #devtools::install_github(klmr/modules)
#mgcv<-import_package("mgcv")

mspline<-function(x,y,k=10,lower=NA,upper=NA){
  #fits a monotonic spline to data
  #small values of k= more smoothing (flatter curves)
  #large values of k= more flexible (wiggly curves)
  #k is related to effective degrees of freedom and number of knots
  #use unconstrained gam to get rough parameter estimates

jnpaulson

stratified <- function(df, group, size, select = NULL, 
                       replace = FALSE, bothSets = FALSE) {
  if (is.null(select)) {
    df <- df
  } else {
    if (is.null(names(select))) stop("'select' must be a named list")
    if (!all(names(select) %in% names(df)))
      stop("Please verify your 'select' argument")
    temp <- sapply(names(select),
                   function(x) df[[x]] %in% select[[x]])

jnpaulson

downloadNotInstalled<-function(x){
  for(i in x){
    if(!require(i,character.only=TRUE)){
      if (!requireNamespace("BiocManager")){install.packages("BiocManager")}
      BiocManager::install(i)
    }
  }
}
requiredPackages = c("Biobase", "S4Vectors","SummarizedExperiment","devtools","edgeR")
downloadNotInstalled(requiredPackages)

jnpaulson

# Actually perform the differential expression analysis
library(yarn)
library(dplyr)
library(readr)
library(biomaRt)
library(limma)
source("voomweights.R")
obj <- readRDS("~/Desktop/gtex_v6p_lung_blood_norm.rds")
gender = pData(obj)$GENDER
batch  = factor(as.character(pData(obj)$SMNABTCHT))