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

## make some new columns that store the log ratios  
breast_cancer<-breast_cancer %>% 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)
## make a matrix of just the data

breast_cancer1<-breast_cancer %>% select(log_MCF7:log_SKBR3) %>% as.matrix() %>% round(.,2)

head(breast_cancer1)
##      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_cancer1, 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
breast_cancer<-breast_cancer %>% 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 %>% 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
breast_cancer<-breast_cancer %>% 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<-breast_cancer %>% ggplot(aes(x=log_SKBR3,y=neglog_SKBR3,description=Gene_Symbol,color=significance))+
  geom_point(alpha=0.7)+
  xlim(-6,6)+
  scale_color_manual(values=plain_cols3)+
  theme_bw()+
  theme(axis.text = element_text(colour = "black",size=14))+
  theme(text = element_text(size=14))+
  labs(x="log ratio for SKBR3 cancer cell line compared to control cells",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: GCLC, FNBP1L, and TDP2 ## Significant down regulated are: APOA1, HLA-A, EFNB2, etc

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

head(breastcancer_longer)
## # 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<-breastcancer_longer %>% filter(Gene_Symbol=="APOA1" | Gene_Symbol=="HLA-A" | Gene_Symbol=="ENFB2") 

head(Examples_Down)
## # A tibble: 6 × 3
##   Gene_Symbol variable value
##   <chr>       <chr>    <dbl>
## 1 HLA-A       MCF10A_1  5.42
## 2 HLA-A       MCF10A_2  6.62
## 3 HLA-A       MCF7_1    2.22
## 4 HLA-A       MCF7_2    2.69
## 5 HLA-A       MDA231_1  4.56
## 6 HLA-A       MDA231_2  4.23
  
## 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="order",y="relative intensity")

Example_plot_down

## Same process for the upregulated ones
Examples_Up<-breastcancer_longer %>% filter(Gene_Symbol=="GCLC" | Gene_Symbol=="FNB1L" | Gene_Symbol=="TDP2") 

(Examples_Up)
## # A tibble: 20 × 3
##    Gene_Symbol variable value
##    <chr>       <chr>    <dbl>
##  1 TDP2        MCF10A_1  2.36
##  2 TDP2        MCF10A_2  1.72
##  3 TDP2        MCF7_1    5.89
##  4 TDP2        MCF7_2    4.71
##  5 TDP2        MDA231_1  5.94
##  6 TDP2        MDA231_2  7.38
##  7 TDP2        MDA468_1 30.6 
##  8 TDP2        MDA468_2 16.0 
##  9 TDP2        SKBR3_1  12.7 
## 10 TDP2        SKBR3_2  12.7 
## 11 GCLC        MCF10A_1  3.01
## 12 GCLC        MCF10A_2  2.82
## 13 GCLC        MCF7_1    9.28
## 14 GCLC        MCF7_2    9.85
## 15 GCLC        MDA231_1  5.66
## 16 GCLC        MDA231_2  4.96
## 17 GCLC        MDA468_1 19.3 
## 18 GCLC        MDA468_2 20.8 
## 19 GCLC        SKBR3_1  12.0 
## 20 GCLC        SKBR3_2  12.4

Example_plot_up<-Examples_Up %>% 
  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="order",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<-breast_cancer %>% 
  filter(Gene_Symbol=="APOA1"|Gene_Symbol=="HLA-A" |Gene_Symbol=="EFNB2") %>% 
  select(Gene_Symbol, Description, Peptides)
downregulated
## # 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 HLA-A       HLA class I histocompatibility antigen, A-1 alpha chain O…       1
## 5 EFNB2       Ephrin-B2 OS=Homo sapiens GN=EFNB2 PE=1 SV=1                     1
## 6 APOA1       Apolipoprotein A-I OS=Homo sapiens GN=APOA1 PE=1 SV=1            2
## # … with abbreviated variable name ¹​Peptides

#Upregulated
upregulated<-breast_cancer %>% 
  filter(Gene_Symbol=="A"|Gene_Symbol=="FNBP1L" |Gene_Symbol=="TDP2") %>% 
  select(Gene_Symbol, Description, Peptides)
upregulated
## # A tibble: 2 × 3
##   Gene_Symbol Description                                                Pepti…¹
##   <chr>       <chr>                                                        <dbl>
## 1 TDP2        Isoform 2 of Tyrosyl-DNA phosphodiesterase 2 OS=Homo sapi…       3
## 2 FNBP1L      Isoform 2 of Formin-binding protein 1-like OS=Homo sapien…       6
## # … with abbreviated variable name ¹​Peptides