####Run through this example and try to understand what is going on with the data

####So, lets 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 
B_Cancer_data<-read_csv(file="breast_cancer_cells.csv")

## make some new columns that store the log ratios  


B_Cancer_data<-B_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(B_Cancer_data)
## make a matrix of just log values the data
B_Cancer_mat1<-B_Cancer_data %>% select(log_MCF7:log_SKBR3) %>% as.matrix() %>% round(.,3)


head(B_Cancer_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(B_Cancer_mat1, color=pats_cols,cellwidth=30,cellheight=.03,cluster_cols=FALSE,cluster_rows=FALSE,legend=TRUE,fontsize = 7,scale="column")


##Let's look at SKBR3 using a volcano plot.
##BASIC VOLCANO PLOT

## Add a column that stores the negative log of the pvalue of interest 
B_Cancer_data<-B_Cancer_data %>% mutate(neglog_SKBR3=-log10(pvalue_SKBR3_vs_MCF10A))

## Use ggplot to plot the log ratio at 24 hours against the -log p-value at 24 hours
volcano_plot<-B_Cancer_data %>% ggplot(aes(x=log_SKBR3,y=neglog_SKBR3,description=Gene_Symbol))+
  geom_point(alpha=0.7,color="hot pink")

volcano_plot


  
## BETTER VOLCANO PLOT

## Define the significant ones (by using ifelse and setting # parameters) so they can be colored
B_Cancer_data<-B_Cancer_data %>% 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 things
better_volcano_plot<-B_Cancer_data %>% 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. Record these for the next step 
ggplotly(better_volcano_plot)
## Significant up regulated are:KRT23,TDP2,FNBP1L,DENND4C and GCLC ## Significant down regulated are: APOA1,HLA-A, MYO1B and HMGN5

Barplots of significant points of interest

EXAMPLES OF A COUPLE PROTEINS or GENES

## 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

Breast_Cancer_Cells_long<-pivot_longer(B_Cancer_data, 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=="APOA1" | Gene_Symbol=="HLA-A" | Gene_Symbol=="MYO1B"| 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


## Same process for the upregulated ones

Examples_Up<-Breast_Cancer_Cells_long %>% filter(Gene_Symbol=="GCLC" | Gene_Symbol=="KRT23" | Gene_Symbol=="FNBP1L"| Gene_Symbol=="TDP2"| 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

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<-B_Cancer_data %>% select(Gene_Symbol, Description, Peptides) %>% filter(Gene_Symbol=="APOA1" | Gene_Symbol=="HLA-A" | Gene_Symbol=="MYO1B" | Gene_Symbol=="HMGN5")
Down_bonus_table
## # A tibble: 7 × 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
## 7 APOA1       Apolipoprotein A-I OS=Homo sapiens GN=APOA1 PE=1 SV=1            2
## # … with abbreviated variable name ¹​Peptides

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