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 
C19_data<-read_csv(file="breast_cancer_cells.csv")

## make some new columns that store the log ratios  
C19_data<-C19_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(C19_data)
## make a matrix of just the data

C19_mat1<-C19_data %>% select(log_MCF7:log_SKBR3) %>% as.matrix() %>% round(.,3)


head(C19_mat1)
##      log_MCF7 log_MDA231 log_MDA468 log_SKBR3
## [1,]   -0.429      1.904     -0.742    -0.002
## [2,]   -0.962     -0.347     -0.714     0.000
## [3,]    0.273      0.287     -0.040     0.002
## [4,]    0.878      0.775     -0.054     0.001
## [5,]    0.792      1.189      0.920     0.003
## [6,]   -0.787     -0.895     -1.282    -0.002
## make a heatmap from the data
pheatmap(C19_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

C19_data<-C19_data %>% mutate(neglog_MDA468=-log10(pvalue_MDA468_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<-C19_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 so they can be colored
C19_data<-C19_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 graph features 
better_volcano_plot<-C19_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 MDA468 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 up regulated are: ___, ___ and _____ ## Significant down regulated are: _____. _____ and ____

Barplots of significant points of interest

## EXAMPLES OF A COUPLE PROTEINS or GENES

# Make a pivot longer table of the data for initial columns. Exclude the p-values and log columns
C19_long<-pivot_longer(C19_data, cols = c(MCF10A_1:SKBR3_2), names_to = 'variable')%>% select(-c(pvalue_MCF7_vs_MCF10A:significance))

head(C19_long)
## # A tibble: 6 × 5
##   Gene_Symbol Description                             Peptides variable value
##   <chr>       <chr>                                      <dbl> <chr>    <dbl>
## 1 NES         Nestin OS=Homo sapiens GN=NES PE=1 SV=2        7 MCF10A_1  9.54
## 2 NES         Nestin OS=Homo sapiens GN=NES PE=1 SV=2        7 MCF10A_2  4.58
## 3 NES         Nestin OS=Homo sapiens GN=NES PE=1 SV=2        7 MCF7_1    5.07
## 4 NES         Nestin OS=Homo sapiens GN=NES PE=1 SV=2        7 MCF7_2    5.42
## 5 NES         Nestin OS=Homo sapiens GN=NES PE=1 SV=2        7 MDA231_1 25.4 
## 6 NES         Nestin OS=Homo sapiens GN=NES PE=1 SV=2        7 MDA231_2 27.4


## 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 

Examples_Down<-C19_long %>% filter(Gene_Symbol=="PLAU" | Gene_Symbol=="HLA-A" | Gene_Symbol=="HLA-B" | Gene_Symbol=="CTNNA1") 

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



  
## make barplots facetted by Gene Symbol (if copying COVID example - 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<-C19_long %>% filter(Gene_Symbol=="SYT7" | Gene_Symbol=="AKR1C2" | Gene_Symbol=="ALDH1A3" | Gene_Symbol=="NLRP2") 

head(Examples_Up)
## # A tibble: 6 × 5
##   Gene_Symbol Description                                  Pepti…¹ varia…² value
##   <chr>       <chr>                                          <dbl> <chr>   <dbl>
## 1 AKR1C2      Aldo-keto reductase family 1 member C2 OS=H…      27 MCF10A…  1.89
## 2 AKR1C2      Aldo-keto reductase family 1 member C2 OS=H…      27 MCF10A…  1.59
## 3 AKR1C2      Aldo-keto reductase family 1 member C2 OS=H…      27 MCF7_1   6.6 
## 4 AKR1C2      Aldo-keto reductase family 1 member C2 OS=H…      27 MCF7_2   8.1 
## 5 AKR1C2      Aldo-keto reductase family 1 member C2 OS=H…      27 MDA231…  1.6 
## 6 AKR1C2      Aldo-keto reductase family 1 member C2 OS=H…      27 MDA231…  1.35
## # … with abbreviated variable names ¹​Peptides, ²​variable



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

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
Down_bonus_table<-C19_data %>% select(Gene_Symbol,Description,Peptides) %>% filter(Gene_Symbol=="PLAU" | Gene_Symbol=="HLA-A" | Gene_Symbol=="HLA-B" | Gene_Symbol=="CTNNA1") 

head(Down_bonus_table)
## # A tibble: 6 × 3
##   Gene_Symbol Description                                                Pepti…¹
##   <chr>       <chr>                                                        <dbl>
## 1 HLA-A       HLA class I histocompatibility antigen, A-23 alpha chain …       3
## 2 HLA-A       HLA class I histocompatibility antigen, A-30 alpha chain …       1
## 3 HLA-B       HLA class I histocompatibility antigen, B-15 alpha chain …       4
## 4 HLA-A       HLA class I histocompatibility antigen, A-2 alpha chain O…      21
## 5 HLA-B       HLA class I histocompatibility antigen, B-41 alpha chain …       1
## 6 HLA-B       HLA class I histocompatibility antigen, B-52 alpha chain …       1
## # … with abbreviated variable name ¹​Peptides

#Upregulated
Up_bonus_table<-C19_data %>% select(Gene_Symbol,Description,Peptides) %>% filter(Gene_Symbol=="SYT7" | Gene_Symbol=="AKR1C2" | Gene_Symbol=="ALDH1A3" | Gene_Symbol=="NLRP2") 

head(Up_bonus_table)
## # A tibble: 4 × 3
##   Gene_Symbol Description                                                Pepti…¹
##   <chr>       <chr>                                                        <dbl>
## 1 AKR1C2      Aldo-keto reductase family 1 member C2 OS=Homo sapiens GN…      27
## 2 NLRP2       Isoform 2 of NACHT, LRR and PYD domains-containing protei…       2
## 3 SYT7        Synaptotagmin-7 OS=Homo sapiens GN=SYT7 PE=1 SV=3                1
## 4 ALDH1A3     Aldehyde dehydrogenase family 1 member A3 OS=Homo sapiens…      16
## # … with abbreviated variable name ¹​Peptides