Working from the COVID.rmd model, fill in the blank chunks with code to analize the dataset of your choice. You will need to think about what you are copying and pasting and what needs to be updated to make the code relevant to your chosen dataset. Double check all syntax and be precise!

###First, let’s load RMarkdown

library(rmarkdown)

set messages to FALSE on everything (prevents certain boring things from being shown in the results)

knitr::opts_chunk$set(echo = TRUE, message=FALSE,warning=FALSE,collapse = TRUE)

PACKAGES

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)

COLORS

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 DATA AND MAKE AN OVERALL HEATMAP

## load the dataset 

BCC<-read_csv(file="breast_cancer_cells.csv")

## make some new columns that store the log ratios  

BCC<-BCC %>% 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))) 
 
## make a matrix of just the data

BCC_mat1<-BCC %>% select(log_MCF7:log_SKBR3) %>% as.matrix() %>% round(.,2)

head(BCC_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
## make a heatmap from the data

pheatmap(BCC_mat1, color=pats_cols, cellwidth = 30, cellheight = .03, cluster_cols = FALSE, cluster_rows = FALSE, legend=TRUE, fontsize = 7, scale = "column")

PLOTTING A VOLCANO

##BASIC VOLCANO PLOT

## Add a column that stores the negative log of the pvalue of interest

BCC<-BCC %>% mutate(neglog_SKBR3=-log10(pvalue_SKBR3_vs_MCF10A))

## Use ggplot to plot the log ratio a column (cell line or treatment) of interest against the -log p-value of that same column of interest

volcano_plot<-BCC %>% 
  ggplot(aes(x=log_SKBR3, y=neglog_SKBR3, Description=Gene_Symbol))+ geom_point(alpha=0.7, color="royalblue")

volcano_plot


  
## BETTER VOLCANO PLOT

## Define the significant ones so they can be colored

BCC<-BCC %>% mutate(significance=ifelse((log_SKBR3>2 & 
neglog_SKBR3>2.99), "UP", ifelse((log_SKBR3<c(-2) & neglog_SKBR3>2.99), "DOWN", "NOT SIG")))

## Some standard colors

plain_cols3<-c("red", "gray", "blue")

## volcano plot as before with some added graph features 

better_volcano_plot<-BCC %>% ggplot(aes(x=log_SKBR3,y=neglog_SKBR3,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 SKBR3 compared to MCF10A",y="-log(p-value)")

better_volcano_plot

## use ggplotly to see hover over the points to see the gene names

ggplotly(better_volcano_plot)
## Significant down regulated are: APOA1, HLA-A and MYO1B ## Significant up regulated are: FNBP1L. KRT23 and TDP2

Barplots of significant points of interest

## EXAMPLES OF A COUPLE PROTEINS or GENES

BCC_long<-pivot_longer(BCC, cols = c(MCF10A_1:SKBR3_2), names_to = 'variable')%>% select(-c(pvalue_MCF7_vs_MCF10A:significance))

# Make a pivot longer table of the data for initial columns. Exclude the p-values and log columns


## based on the gene symbols from plotly, select a few proteins from the table. Select just the data and gene symbols from the pivot longer table you just made 

  
## make barplots facetted by Gene Symbol (if copying COVID example - change x=order to x = variable)

Examples_Down<-BCC_long %>% filter(Gene_Symbol=="APOA1" | Gene_Symbol=="MYO1B" | Gene_Symbol=="HLA-A") 

head(Examples_Down)
## # A tibble: 6 × 5
##   Gene_Symbol Description                                  Pepti…¹ varia…² value
##   <chr>       <chr>                                          <dbl> <chr>   <dbl>
## 1 HLA-A       HLA class I histocompatibility antigen, A-2…       3 MCF10A…  5.42
## 2 HLA-A       HLA class I histocompatibility antigen, A-2…       3 MCF10A…  6.62
## 3 HLA-A       HLA class I histocompatibility antigen, A-2…       3 MCF7_1   2.22
## 4 HLA-A       HLA class I histocompatibility antigen, A-2…       3 MCF7_2   2.69
## 5 HLA-A       HLA class I histocompatibility antigen, A-2…       3 MDA231…  4.56
## 6 HLA-A       HLA class I histocompatibility antigen, A-2…       3 MDA231…  4.23
## # … with abbreviated variable names ¹​Peptides, ²​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<-BCC_long %>% filter(Gene_Symbol=="FNBP1L" | Gene_Symbol=="KRT23" | Gene_Symbol=="TDP2") 

head(Examples_up)
## # A tibble: 6 × 5
##   Gene_Symbol Description                                  Pepti…¹ varia…² value
##   <chr>       <chr>                                          <dbl> <chr>   <dbl>
## 1 TDP2        Isoform 2 of Tyrosyl-DNA phosphodiesterase …       3 MCF10A…  2.36
## 2 TDP2        Isoform 2 of Tyrosyl-DNA phosphodiesterase …       3 MCF10A…  1.72
## 3 TDP2        Isoform 2 of Tyrosyl-DNA phosphodiesterase …       3 MCF7_1   5.89
## 4 TDP2        Isoform 2 of Tyrosyl-DNA phosphodiesterase …       3 MCF7_2   4.71
## 5 TDP2        Isoform 2 of Tyrosyl-DNA phosphodiesterase …       3 MDA231…  5.94
## 6 TDP2        Isoform 2 of Tyrosyl-DNA phosphodiesterase …       3 MDA231…  7.38
## # … with abbreviated variable names ¹​Peptides, ²​variable

Example_plot_up<-Examples_up %>% 
  ggplot(aes(x=variable,y=value))+ 
  geom_bar(stat="identity",fill="blue")+
  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

BONUS CODE- for figuring out what the gene symbols are

#your original table contains descriptions of each gene. Write some code to create yourself a table to filter for your gene symbols of interest and select for the gene symbol, description, and peptides. Do this for both the significantly upregulated and downregulated points of interest.

#Downregulated

#Upregulated