# Lab 4 for the University of Tulsa's CS-6643 Bioinformatics Course
# Differential Expression
# Professor: Dr. McKinney, Fall 2022
# Noah L. Schrick - 1492657

## Set Working Directory to file directory - RStudio approach
setwd(dirname(rstudioapi::getActiveDocumentContext()$path))

#### Part A: Preparing Data
load("sense.filtered.cpm.Rdata")
# load phenotype (mdd/hc) data
subject.attrs <- read.csv("Demographic_symptom.csv", 
                          stringsAsFactors = FALSE)

if (!require("dplyr")) install.packages("dplyr")
library(dplyr)
# grab intersecting X (subject ids) and Diag (Diagnosis) from columns
phenos.df <- subject.attrs %>% 
  filter(X %in% colnames(sense.filtered.cpm)) %>%
  dplyr::select(X, Diag)  
mddPheno <- as.factor(phenos.df$Diag)  

# Normalized and transform
library(preprocessCore)
mddExprData_quantile <- normalize.quantiles(sense.filtered.cpm)
mddExprData_quantileLog2 <- log2(mddExprData_quantile)
# attach phenotype names and gene names to data 
colnames(mddExprData_quantileLog2) <- mddPheno  
rownames(mddExprData_quantileLog2) <- rownames(sense.filtered.cpm)

length(rownames(sense.filtered.cpm))
#### Part B: Filter noise genes