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 
C24_data<-read_csv(file="breast_cancer_cells.csv")

## make some new columns that store the log ratios  
C24_data<-C24_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(C24_data)
## make a matrix of just the data
C24_mat1<-C24_data %>% select(log_MCF7:log_SKBR3) %>% as.matrix() %>% round(.,2)

head(C24_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(C24_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
C24_data<-C24_data %>% mutate(neglog_MDA231=-log10(pvalue_MDA231_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<-C24_data %>% ggplot(aes(x=log_MDA231,y=neglog_MDA231,description=Gene_Symbol))+
  geom_point(alpha=0.7,color="royalblue")

volcano_plot


  
## BETTER VOLCANO PLOT

## Define the significant ones so they can be colored
C24_data<-C24_data %>% mutate(significance=ifelse((log_MDA231>2 & neglog_MDA231>2.99),"UP", ifelse((log_MDA231<c(-2) & neglog_MDA231>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<-C24_data %>% ggplot(aes(x=log_MDA231,y=neglog_MDA231,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 at of MDA231 compared to control MCF10A ",y="-log(MDA231)")
  

better_volcano_plot

## use ggplotly to see hover over the points to see the gene names
ggplotly(better_volcano_plot)

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
C24_long<-pivot_longer(C24_data, cols = c(MCF10A_1:SKBR3_2), names_to = 'variable')%>% select(-c(pvalue_MCF7_vs_MCF10A:significance))%>%select(-Description & -Peptides)

head(C24_long)
## # A tibble: 6 × 3
##   Gene_Symbol variable value
##   <chr>       <chr>    <dbl>
## 1 NES         MCF10A_1  9.54
## 2 NES         MCF10A_2  4.58
## 3 NES         MCF7_1    5.07
## 4 NES         MCF7_2    5.42
## 5 NES         MDA231_1 25.4 
## 6 NES         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<-C24_long %>% filter(Gene_Symbol=="ABCB6" | Gene_Symbol=="METTL7A" | Gene_Symbol=="F11R" | Gene_Symbol=="SPNS1" | Gene_Symbol=="ADCK3" | Gene_Symbol=="PTGFRN" | Gene_Symbol=="HIST1H1A" | Gene_Symbol=="HLA-A" | Gene_Symbol=="APOA1") 

head(Examples_Down)
## # A tibble: 6 × 3
##   Gene_Symbol variable value
##   <chr>       <chr>    <dbl>
## 1 SPNS1       MCF10A_1 14.2 
## 2 SPNS1       MCF10A_2 14.0 
## 3 SPNS1       MCF7_1   10.8 
## 4 SPNS1       MCF7_2   13.6 
## 5 SPNS1       MDA231_1  3.03
## 6 SPNS1       MDA231_2  3.13

  
## 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<-C24_long %>% filter(Gene_Symbol=="ACSS3")

head(Examples_Up)
## # A tibble: 6 × 3
##   Gene_Symbol variable value
##   <chr>       <chr>    <dbl>
## 1 ACSS3       MCF10A_1  2.61
## 2 ACSS3       MCF10A_2  2.66
## 3 ACSS3       MCF7_1   13.3 
## 4 ACSS3       MCF7_2   12.1 
## 5 ACSS3       MDA231_1 12.4 
## 6 ACSS3       MDA231_2 12.1

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
Downregulated <- C24_data %>% filter(Gene_Symbol=="ABCB6" | 
Gene_Symbol=="METTL7A" |
Gene_Symbol=="F11R" | 
Gene_Symbol=="SPNS1" | 
Gene_Symbol=="ADCK3" | 
Gene_Symbol=="PTGFRN" |
Gene_Symbol=="HIST1H1A" | 
Gene_Symbol=="HLA-A" | 
Gene_Symbol=="APOA1") %>% select(Gene_Symbol,Description,Peptides)
                                           
                                                                                                                                      #Upregulated
Upregulated <- C24_data %>% filter(Gene_Symbol=="ACSS3")%>% select(Gene_Symbol,Description,Peptides)