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 (breast cancer cells)
breast_cancer_cells<-read_csv(file="breast_cancer_cells.csv")

## make some new columns that store the log ratios using the data given. MCF10A is the "control" while everything else is a cancer cell.
breast_cancer_cells<-breast_cancer_cells %>% 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(breast_cancer_cells)
## make a matrix of just the data labelled breast_cancer_cells_mat1
breast_cancer_cells_mat1<-breast_cancer_cells %>% select(log_MCF7:log_SKBR3) %>% as.matrix() %>% round(.,2)

head(breast_cancer_cells_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(breast_cancer_cells_mat1, color=pats_cols,cellwidth=30,cellheight=.03,cluster_cols=FALSE,cluster_rows=FALSE,legend=TRUE,fontsize = 7,scale="column")


##log_SKBR3 is different from the other cell lines, therefore plot a volcano to take a closer look

PLOTTING A VOLCANO

##BASIC VOLCANO PLOT

## Add a column that stores the negative log of the pvalue of interest, in this case, SKBR3 vs MCF10A (control)
breast_cancer_cells<-breast_cancer_cells %>% 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<-breast_cancer_cells %>% 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 (using ifelse and setting # parameters) so they can be colored
breast_cancer_cells<-breast_cancer_cells %>% 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. Plot was very vast (-6, 16) and contained a lot of vast space, therefore, we took a snapshot of (-6,6) to ensure important data was captured and focused upon, and outliers were ignored. Compared SKBR3 cell lines to the control (no direction to do otherwise - Elijah said so). 
better_volcano_plot<-breast_cancer_cells %>% 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 cancer cells compared to control",y="-log(p-value)")
  

better_volcano_plot


## Comparing SKBR3 to control led to only 4 down points and 5 up points.
## use ggplotly to see hover over the points to see the gene names
ggplotly(better_volcano_plot)
## Significant up regulated are: TDP2, FNBP1L, GCLC, KRT23 and DENND4C ## Significant down regulated are: HMGN5, MYO1B, HLA-A and APOA1

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. Don't have accession like the COVID example

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

head(breast_cancer_cells_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<-breast_cancer_cells_long %>% filter(Gene_Symbol=="MYO1B" | Gene_Symbol=="APOA1" | Gene_Symbol=="HLA-A"|Gene_Symbol=="HMGN5") 

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


## Significant down regulated: HMGN5, MYO1B, HLA-A and APOA1
## Same process for the upregulated ones
Examples_Up<-breast_cancer_cells_long %>% filter(Gene_Symbol=="TDP2" | Gene_Symbol=="FNBP1L" | Gene_Symbol=="GCLC" | Gene_Symbol=="KRT23" | Gene_Symbol=="DENND4C")

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="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


## Significant up regulated: TDP2, FNBP1L, GCLC, KRT23 and DENND4C

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
breast_cancer_cells_down<-breast_cancer_cells %>% filter(Gene_Symbol=="MYO1B" | Gene_Symbol=="APOA1" | Gene_Symbol=="HLA-A"|Gene_Symbol=="HMGN5") %>% 
  select(Gene_Symbol,Description,Peptides)

head(breast_cancer_cells_down)
## # 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-A       HLA class I histocompatibility antigen, A-2 alpha chain O…      21
## 4 HMGN5       High mobility group nucleosome-binding domain-containing …       4
## 5 MYO1B       Isoform 2 of Myosin-Ib OS=Homo sapiens GN=MYO1B                 22
## 6 HLA-A       HLA class I histocompatibility antigen, A-1 alpha chain O…       1
## # … with abbreviated variable name ¹​Peptides

#Upregulated
breast_cancer_cells_up<-breast_cancer_cells %>%
filter(Gene_Symbol=="TDP2" | Gene_Symbol=="FNBP1L" | Gene_Symbol=="GCLC" | Gene_Symbol=="KRT23" | Gene_Symbol=="DENND4C") %>% 
  select(Gene_Symbol,Description,Peptides)

head(breast_cancer_cells_up)
## # A tibble: 5 × 3
##   Gene_Symbol Description                                                Pepti…¹
##   <chr>       <chr>                                                        <dbl>
## 1 TDP2        Isoform 2 of Tyrosyl-DNA phosphodiesterase 2 OS=Homo sapi…       3
## 2 DENND4C     Isoform 2 of DENN domain-containing protein 4C OS=Homo sa…       1
## 3 KRT23       Keratin, type I cytoskeletal 23 OS=Homo sapiens GN=KRT23 …       3
## 4 FNBP1L      Isoform 2 of Formin-binding protein 1-like OS=Homo sapien…       6
## 5 GCLC        Glutamate--cysteine ligase catalytic subunit OS=Homo sapi…       6
## # … with abbreviated variable name ¹​Peptides