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

## make some new columns that store the log ratios  
breastcancer_data<-breastcancer_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(breastcancer_data)
## make a matrix of just the data
breastcancer_mat1<-breastcancer_data %>% select(log_MCF7:log_SKBR3) %>% as.matrix() %>% round(.,2)

head(breastcancer_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(breastcancer_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
breastcancer_data<-breastcancer_data %>% 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<-breastcancer_data %>% 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
breastcancer_data<-breastcancer_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 graph features 
better_volcano_plot<-breastcancer_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 at SKBR3 breast cancer gene compared to control",y="-log(p-value)")

better_volcano_plot

## use ggplotly to see hover over the points to see the gene names. Record these for next step.
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
breastcancer_long<-pivot_longer(breastcancer_data, cols = c(MCF10A_1:SKBR3_2), names_to = 'variable')%>% select(-c(pvalue_SKBR3_vs_MCF10A:significance))

head(breastcancer_long)
## # A tibble: 6 × 8
##   Gene_Symbol Description          Pepti…¹ pvalu…² pvalu…³ pvalu…⁴ varia…⁵ value
##   <chr>       <chr>                  <dbl>   <dbl>   <dbl>   <dbl> <chr>   <dbl>
## 1 NES         Nestin OS=Homo sapi…       7   0.542  0.0185   0.374 MCF10A…  9.54
## 2 NES         Nestin OS=Homo sapi…       7   0.542  0.0185   0.374 MCF10A…  4.58
## 3 NES         Nestin OS=Homo sapi…       7   0.542  0.0185   0.374 MCF7_1   5.07
## 4 NES         Nestin OS=Homo sapi…       7   0.542  0.0185   0.374 MCF7_2   5.42
## 5 NES         Nestin OS=Homo sapi…       7   0.542  0.0185   0.374 MDA231… 25.4 
## 6 NES         Nestin OS=Homo sapi…       7   0.542  0.0185   0.374 MDA231… 27.4 
## # … with abbreviated variable names ¹​Peptides, ²​pvalue_MCF7_vs_MCF10A,
## #   ³​pvalue_MDA231_vs_MCF10A, ⁴​pvalue_MDA468_vs_MCF10A, ⁵​variable


## 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_long %>% filter(Gene_Symbol=="APOA1" | Gene_Symbol=="MYO1B" | Gene_Symbol=="HMGN5" | Gene_Symbol=="HLA-A") 

Examples_Down_2<-breastcancer_long %>% filter(Gene_Symbol=="APOA1" | Gene_Symbol=="MYO1B" | Gene_Symbol=="HMGN5" | Gene_Symbol=="HLA-A") #object was not running above


head(Examples_Down_2)
## # A tibble: 6 × 8
##   Gene_Symbol Description          Pepti…¹ pvalu…² pvalu…³ pvalu…⁴ varia…⁵ value
##   <chr>       <chr>                  <dbl>   <dbl>   <dbl>   <dbl> <chr>   <dbl>
## 1 HLA-A       HLA class I histoco…       3  0.0312   0.122  0.0131 MCF10A…  5.42
## 2 HLA-A       HLA class I histoco…       3  0.0312   0.122  0.0131 MCF10A…  6.62
## 3 HLA-A       HLA class I histoco…       3  0.0312   0.122  0.0131 MCF7_1   2.22
## 4 HLA-A       HLA class I histoco…       3  0.0312   0.122  0.0131 MCF7_2   2.69
## 5 HLA-A       HLA class I histoco…       3  0.0312   0.122  0.0131 MDA231…  4.56
## 6 HLA-A       HLA class I histoco…       3  0.0312   0.122  0.0131 MDA231…  4.23
## # … with abbreviated variable names ¹​Peptides, ²​pvalue_MCF7_vs_MCF10A,
## #   ³​pvalue_MDA231_vs_MCF10A, ⁴​pvalue_MDA468_vs_MCF10A, ⁵​variable
## make barplots facetted by Gene Symbol (if copying COVID example - change x=order to x = variable)
Example_plot_down<-Examples_Down_2 %>% 
  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<-breastcancer_long %>% filter(Gene_Symbol=="GCLC" | Gene_Symbol=="KRT23" | Gene_Symbol=="FNBP1L" | Gene_Symbol=="DENND4C" | Gene_Symbol=="TDP2")

head(Examples_Up)
## # A tibble: 6 × 8
##   Gene_Symbol Description          Pepti…¹ pvalu…² pvalu…³ pvalu…⁴ varia…⁵ value
##   <chr>       <chr>                  <dbl>   <dbl>   <dbl>   <dbl> <chr>   <dbl>
## 1 TDP2        Isoform 2 of Tyrosy…       3  0.0400  0.0281   0.100 MCF10A…  2.36
## 2 TDP2        Isoform 2 of Tyrosy…       3  0.0400  0.0281   0.100 MCF10A…  1.72
## 3 TDP2        Isoform 2 of Tyrosy…       3  0.0400  0.0281   0.100 MCF7_1   5.89
## 4 TDP2        Isoform 2 of Tyrosy…       3  0.0400  0.0281   0.100 MCF7_2   4.71
## 5 TDP2        Isoform 2 of Tyrosy…       3  0.0400  0.0281   0.100 MDA231…  5.94
## 6 TDP2        Isoform 2 of Tyrosy…       3  0.0400  0.0281   0.100 MDA231…  7.38
## # … with abbreviated variable names ¹​Peptides, ²​pvalue_MCF7_vs_MCF10A,
## #   ³​pvalue_MDA231_vs_MCF10A, ⁴​pvalue_MDA468_vs_MCF10A, ⁵​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
Downregulated<-breastcancer_data%>%filter(Gene_Symbol=="CSTZ"|Gene_Symbol=="APOA1"|Gene_Symbol=="HLA-A"|Gene_Symbol=="HMGN5"|Gene_Symbol=="MYO1B")%>%select(Gene_Symbol,Description,Peptides)
#Upregulated
Upregulated<-breastcancer_data%>%filter(Gene_Symbol=="GCLC"|Gene_Symbol=="KRT23"|Gene_Symbol=="FNBP1L"|Gene_Symbol=="DENND4C"|Gene_Symbol=="TDP2")%>%select(Gene_Symbol,Description,Peptides)