R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

summary(cars)
##      speed           dist       
##  Min.   : 4.0   Min.   :  2.00  
##  1st Qu.:12.0   1st Qu.: 26.00  
##  Median :15.0   Median : 36.00  
##  Mean   :15.4   Mean   : 42.98  
##  3rd Qu.:19.0   3rd Qu.: 56.00  
##  Max.   :25.0   Max.   :120.00

Including Plots

You can also embed plots, for example:

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.

library(rmarkdown)
knitr::opts_chunk$set(echo = TRUE, message=FALSE,warning=FALSE,collapse = TRUE)
library(reshape2)
library(ggplot2)
library(dplyr)
library(plotly)
library(viridis)
library(data.table)
library(pheatmap)
library(tidyverse)
library(ggthemes)
library(clipr)
library(tidyr)
library(Rcpp)
mycolors<-c(viridis(15))
felix_cols<-mycolors[c(5,2)]
felix_4cols<-mycolors[c(15,10,8,2)]
plain_cols1<-c("blue","gray")
plain_cols2<-c("red","gray")

pats_cols<-colorRampPalette(c("#FDE725FF", "white","#440154FF"))(21)
leos_cols<-colorRampPalette(c("white","blue"))(10)
## load the dataset 
cancer_data<-read_csv(file="breast_cancer_cells.csv")

## make some new columns that store the log ratios  

cancer_data<-cancer_data %>% mutate(
  log_MCF7=log2((MCF7_1+MCF7_2)/(MCF10A_1+MCF10A_2)), 
  log_MDA231=log2((MDA231_1+MDA231_2)/(MCF10A_1+MCF10A_2)), 
  log_MDA468=log2((MDA468_1+MDA468_2)/(MCF10A_1+MCF10A_2)),
  log_SKBR3=log2((SKBR3_1+SKBR3_2)/(MCF10A_1+MCF10A_2)))

view(cancer_data)
## make a matrix of just log values the data

cancer_mat1<-cancer_data %>% select(log_MCF7:log_SKBR3) %>% as.matrix() %>% round(.,2)

head(cancer_mat1)
##      log_MCF7 log_MDA231 log_MDA468 log_SKBR3
## [1,]    -0.43       1.90      -0.74         0
## [2,]    -0.96      -0.35      -0.71         0
## [3,]     0.27       0.29      -0.04         0
## [4,]     0.88       0.78      -0.05         0
## [5,]     0.79       1.19       0.92         0
## [6,]    -0.79      -0.90      -1.28         0
## making a heatmap from the data

pheatmap(cancer_mat1, color=pats_cols,cellwidth=30,cellheight=.03,cluster_cols=FALSE,cluster_rows=FALSE,legend=TRUE,fontsize = 7,scale="column")

##BASIC VOLCANO PLOT

## Add a column that stores the negative log of the pvalue of interest
cancer_data<-cancer_data %>% mutate(neglog_MDA468=-log10(pvalue_MDA468_vs_MCF10A))

## Use ggplot to plot the log ratio against the -log p-value
volcano_plot<-cancer_data %>% ggplot(aes(x=log_MDA468,y=neglog_MDA468,description=Gene_Symbol))+
  geom_point(alpha=0.7,color="royalblue")

volcano_plot


  
## BETTER VOLCANO PLOT

## Define the significant ones (by using ifelse and setting # parameters) so they can be colored
cancer_data<-cancer_data %>% mutate(significance=ifelse((log_MDA468>2 & neglog_MDA468>2.99),"UP", ifelse((log_MDA468<c(-2) & neglog_MDA468>2.99),"DOWN","NOT SIG")))

## Some standard colors
plain_cols3<-c("red","gray","blue")

## volcano plot as before with some added things
better_volcano_plot<-cancer_data %>% ggplot(aes(x=log_MDA468,y=neglog_MDA468,description=Gene_Symbol,color=significance))+
  geom_point(alpha=0.7)+
  scale_color_manual(values=plain_cols3)+
  xlim(-6,6)+
  theme_bw()+
  theme(axis.text = element_text(colour = "black",size=14))+
  theme(text = element_text(size=14))+
  labs(x="Log Ratio of Breast Cancer Cells MDA468 Compared to MCF10A",y="-log(p-value)")
  

better_volcano_plot

## use ggplotly to see hover over the points to see the gene names. Record these for the next step 
ggplotly(better_volcano_plot)
## Significant up regulated are: ___, ___ and _____ ## Significant down regulated are: _____. _____ and ____
# Make a pivot longer table of the data for Control_2h_1:Virus_24h_2
cancer_long<-pivot_longer(cancer_data, cols = c(MCF10A_1:SKBR3_2), names_to = 'variable')%>% select(-c(pvalue_MDA468_vs_MCF10A:significance))%>%select(-Description, Peptides)

head(cancer_long)
## # A tibble: 6 × 6
##   Gene_Symbol Peptides pvalue_MCF7_vs_MCF10A pvalue_MDA231_vs_MC…¹ varia…² value
##   <chr>          <dbl>                 <dbl>                 <dbl> <chr>   <dbl>
## 1 NES                7                 0.542                0.0185 MCF10A…  9.54
## 2 NES                7                 0.542                0.0185 MCF10A…  4.58
## 3 NES                7                 0.542                0.0185 MCF7_1   5.07
## 4 NES                7                 0.542                0.0185 MCF7_2   5.42
## 5 NES                7                 0.542                0.0185 MDA231… 25.4 
## 6 NES                7                 0.542                0.0185 MDA231… 27.4 
## # … with abbreviated variable names ¹​pvalue_MDA231_vs_MCF10A, ²​variable

## make sure that our timepoints will be in the proper order by adding a new column using the factor() function
#this should be excluded in other datasets where order is not needed

cancer_long$order <- as.character(cancer_long$variable)
cancer_long$order <- factor(cancer_long$order,levels=c('MCF10A_1','MCF10A_2','MCF7_1','MCF7_2','MDA231_1','MDA231_2','MDA468_1','MDA468_2','SKBR3_1','SKBR3_2'))


## based on the gene symbols from plotly, select a few proteins from the table. Select just the data and gene symbols and pivot longer
Examples_Down<-cancer_long %>% filter(Gene_Symbol=="PLAU" | Gene_Symbol=="PTPRE" | Gene_Symbol=="ADCK3") 

head(Examples_Down)
## # A tibble: 6 × 7
##   Gene_Symbol Peptides pvalue_MCF7_vs_MCF10A pvalue_MDA231…¹ varia…² value order
##   <chr>          <dbl>                 <dbl>           <dbl> <chr>   <dbl> <fct>
## 1 PTPRE              1                 0.525          0.0470 MCF10A…  11.4 MCF1…
## 2 PTPRE              1                 0.525          0.0470 MCF10A…  11.1 MCF1…
## 3 PTPRE              1                 0.525          0.0470 MCF7_1   10.3 MCF7…
## 4 PTPRE              1                 0.525          0.0470 MCF7_2   11.3 MCF7…
## 5 PTPRE              1                 0.525          0.0470 MDA231…  23.9 MDA2…
## 6 PTPRE              1                 0.525          0.0470 MDA231…  19.3 MDA2…
## # … with abbreviated variable names ¹​pvalue_MDA231_vs_MCF10A, ²​variable
  
## make barplots facetted by Gene Symbol (when working with other data sets - change x=order to x = variable)
Example_plot_down<-Examples_Down %>% 
  ggplot(aes(x=variable,y=value))+ 
  geom_bar(stat="identity",fill="red")+
  facet_wrap(~Gene_Symbol)+
  theme_bw()+
  theme(axis.text = element_text(colour = "black",size=10))+
  theme(text = element_text(size=14))+
  theme(axis.text.x = element_text(angle=45, hjust=1))+
  labs(x="sample",y="relative intensity")
  
Example_plot_down

## Same process for the upregulated ones
Examples_Up<-cancer_long %>% filter(Gene_Symbol=="PADI2" | Gene_Symbol=="CES1" | Gene_Symbol=="S100P")

head(Examples_Up)
## # A tibble: 6 × 7
##   Gene_Symbol Peptides pvalue_MCF7_vs_MCF10A pvalue_MDA231…¹ varia…² value order
##   <chr>          <dbl>                 <dbl>           <dbl> <chr>   <dbl> <fct>
## 1 CES1               6                 0.724           0.256 MCF10A…  1.97 MCF1…
## 2 CES1               6                 0.724           0.256 MCF10A…  1.13 MCF1…
## 3 CES1               6                 0.724           0.256 MCF7_1   1.32 MCF7…
## 4 CES1               6                 0.724           0.256 MCF7_2   2.29 MCF7…
## 5 CES1               6                 0.724           0.256 MDA231…  1    MDA2…
## 6 CES1               6                 0.724           0.256 MDA231…  0.66 MDA2…
## # … with abbreviated variable names ¹​pvalue_MDA231_vs_MCF10A, ²​variable

Example_plot_up<-Examples_Up %>% ggplot(aes(x=variable,y=value))+ 
  geom_bar(stat="identity",fill="royalblue")+
  facet_wrap(~Gene_Symbol)+
  theme_bw()+
  theme(axis.text = element_text(colour = "black",size=10))+
  theme(text = element_text(size=14))+
  theme(axis.text.x = element_text(angle=45, hjust=1))+
  labs(x="sample",y="relative intensity")
  
Example_plot_up

Downregulated <- cancer_data %>% filter(Gene_Symbol=='PLAU'| Gene_Symbol=="PTPRE" | Gene_Symbol=="ADCK3") %>% select(Gene_Symbol, Description, Peptides)

Upregulated <- cancer_data %>% filter(Gene_Symbol=="PADI2" | Gene_Symbol=="CES1" | Gene_Symbol=="S100P") %>% select(Gene_Symbol, Description, Peptides)