Plotting Answer 2

These exercises cover the sections on Plotting in R PlottingInR.

Section 1

• Please load the dateset SubsetRlog_7D.csv from "data/SubsetRlog_7D.csv"

• hint: use read.csv() function to load SubsetRlog_7D.csv. If you failed to import SubsetRlog_7D.csv to R, please check whether you set up your work directory properly by using getwd() and setwd()

# This is the work directory I am using and yours will be different
# setwd("/Volumes/bioinfomatics$/yfwang/BioinformaticsCore/GitHub/LMS_PlottingInR/course/")
exp_Data <- read.csv("data/SubsetRlog_7D.csv")

head(exp_Data)

##                    X  DOX24H_1  DOX24H_2  DOX24H_3   DOX7D_1   DOX7D_2
## 1 ENSMUSG00000050711 12.109594 12.155740 12.089761 13.891323 13.856755
## 2 ENSMUSG00000026463 12.288243 12.069297 11.934777 11.971843 11.908514
## 3 ENSMUSG00000051079  7.177476  7.282678  7.415341  8.097972  8.558204
## 4 ENSMUSG00000037995  9.178713  9.370469  9.047744  7.834046  7.667787
## 5 ENSMUSG00000039910  9.024315  8.790573  8.878026  9.497840  9.751352
## 6 ENSMUSG00000019880  8.308681  8.701553  8.403844  9.026944  9.351475
##     DOX7D_3  VEH24H_1  VEH24H_2  VEH24H_3   VEH7D_1   VEH7D_2   VEH7D_3
## 1 14.095029 12.361107 12.560950 12.404746 13.640879 13.552177 13.578203
## 2 11.748345 12.543844 12.334998 12.195093 12.357483 12.181816 12.315383
## 3  8.653715  6.761927  6.861818  6.899967  7.445987  7.440482  7.938914
## 4  7.540055  9.222387  9.152175  9.299462  8.064490  7.994608  8.025586
## 5  9.731984  9.257527  9.246675  9.442477  9.346837  9.238912  9.323775
## 6  9.373127  8.305506  8.296453  8.429132  8.762056  8.791535  8.877247

colnames(exp_Data)[1] <- "EnsemblID"

1. transform the wide data.frame to the long data.frame using melt() function from reshape2 package

library(reshape2)
exp_Data_long <- melt(exp_Data,id="EnsemblID") 
head(exp_Data_long)

##            EnsemblID variable     value
## 1 ENSMUSG00000050711 DOX24H_1 12.109594
## 2 ENSMUSG00000026463 DOX24H_1 12.288243
## 3 ENSMUSG00000051079 DOX24H_1  7.177476
## 4 ENSMUSG00000037995 DOX24H_1  9.178713
## 5 ENSMUSG00000039910 DOX24H_1  9.024315
## 6 ENSMUSG00000019880 DOX24H_1  8.308681

2. add columns 'Treatment', 'TimePoint' and 'Rep' based on 'variable' column information

• hint: check how to use sub() function by using ?sub

unique(exp_Data_long$variable)

##  [1] DOX24H_1 DOX24H_2 DOX24H_3 DOX7D_1  DOX7D_2  DOX7D_3  VEH24H_1 VEH24H_2
##  [9] VEH24H_3 VEH7D_1  VEH7D_2  VEH7D_3 
## 12 Levels: DOX24H_1 DOX24H_2 DOX24H_3 DOX7D_1 DOX7D_2 DOX7D_3 ... VEH7D_3

exp_Data_long$Treatment <- sub("(.+)([2|7].+)(_\\d)","\\1",exp_Data_long$variable)
exp_Data_long$TimePoint <- sub("(.+)([2|7].+)(_\\d)","\\2",exp_Data_long$variable)
exp_Data_long$Rep <- sub("(.+)([2|7].+)(_\\d)","Rep\\3",exp_Data_long$variable)
head(exp_Data_long)

##            EnsemblID variable     value Treatment TimePoint   Rep
## 1 ENSMUSG00000050711 DOX24H_1 12.109594       DOX       24H Rep_1
## 2 ENSMUSG00000026463 DOX24H_1 12.288243       DOX       24H Rep_1
## 3 ENSMUSG00000051079 DOX24H_1  7.177476       DOX       24H Rep_1
## 4 ENSMUSG00000037995 DOX24H_1  9.178713       DOX       24H Rep_1
## 5 ENSMUSG00000039910 DOX24H_1  9.024315       DOX       24H Rep_1
## 6 ENSMUSG00000019880 DOX24H_1  8.308681       DOX       24H Rep_1

3. add columns 'Group' based on 'Treatment' and 'TimePoint' columns

• hint: check how to use paste() function by using ?paste

exp_Data_long$Group <- paste(exp_Data_long$Treatment,exp_Data_long$TimePoint,
                             sep=".")
head(exp_Data_long)

##            EnsemblID variable     value Treatment TimePoint   Rep   Group
## 1 ENSMUSG00000050711 DOX24H_1 12.109594       DOX       24H Rep_1 DOX.24H
## 2 ENSMUSG00000026463 DOX24H_1 12.288243       DOX       24H Rep_1 DOX.24H
## 3 ENSMUSG00000051079 DOX24H_1  7.177476       DOX       24H Rep_1 DOX.24H
## 4 ENSMUSG00000037995 DOX24H_1  9.178713       DOX       24H Rep_1 DOX.24H
## 5 ENSMUSG00000039910 DOX24H_1  9.024315       DOX       24H Rep_1 DOX.24H
## 6 ENSMUSG00000019880 DOX24H_1  8.308681       DOX       24H Rep_1 DOX.24H

4. Please create the figure below using geom_boxplot() + geom_point()

• hint: The x-axis labels can be rotated 45 degrees by using theme(axis.text.x = element_text(angle=45, hjust=1))

library(ggplot2)

## Warning in register(): Can't find generic `scale_type` in package ggplot2 to
## register S3 method.

ggplot(exp_Data_long, aes(x=variable,y=value)) +
  geom_boxplot(outlier.shape = NA) +
  geom_point(alpha=0.5,
             position=position_dodge2(width = 0.5)) +
  theme(axis.text.x = element_text(angle=45, hjust=1))+
  ylab("rlog")

5. Please create the figure below using geom_violin() + geom_boxplot()

• hint: please see the difference between geom_boxplot() and geom_boxplot(position = position_dodge(0.9),width=0.4)

library(ggplot2)

# use geom_boxplot()
plotv1 <- ggplot(exp_Data_long, aes(x=Rep,y=value, fill=Group)) +
  geom_violin() +
  geom_boxplot() +
  ylab("rlog")
plotv1

# use geom_boxplot(position = position_dodge(0.9),width=0.4)
plotv2 <- ggplot(exp_Data_long, aes(x=Rep,y=value, fill=Group)) +
  geom_violin() +
  geom_boxplot(position = position_dodge(0.9),width=0.4) +
  ylab("rlog")
plotv2