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

## make some new columns that store the log ratios  

breast_cancer_data<-breast_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(breast_cancer_data)
## make a matrix of just the data

breast_cancer_mat1<-breast_cancer_data %>% select(log_MCF7:log_SKBR3) %>% as.matrix() %>% round(.,2)

head(breast_cancer_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_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
breast_cancer_data<-breast_cancer_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<-breast_cancer_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
breast_cancer_data<-breast_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 graph features 
better_volcano_plot<-breast_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 SKBR 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
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

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

head(breast_cancer_long)
## # A tibble: 6 × 4
##   Gene_Symbol Peptides variable value
##   <chr>          <dbl> <chr>    <dbl>
## 1 NES                7 MCF10A_1  9.54
## 2 NES                7 MCF10A_2  4.58
## 3 NES                7 MCF7_1    5.07
## 4 NES                7 MCF7_2    5.42
## 5 NES                7 MDA231_1 25.4 
## 6 NES                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_long %>% filter(Gene_Symbol=="APOA1" | Gene_Symbol=="HLA-A" | Gene_Symbol=="MYO1B" | Gene_Symbol=="HMGN5") 

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

## Same process for the upregulated ones

Examples_Up<-breast_cancer_long %>% filter(Gene_Symbol=="GCLC" | Gene_Symbol=="FNBP1L" | Gene_Symbol=="DENND4C" | Gene_Symbol=="KRT23" | Gene_Symbol=="TDP2")

head(Examples_Up)
## # A tibble: 6 × 4
##   Gene_Symbol Peptides variable value
##   <chr>          <dbl> <chr>    <dbl>
## 1 TDP2               3 MCF10A_1  2.36
## 2 TDP2               3 MCF10A_2  1.72
## 3 TDP2               3 MCF7_1    5.89
## 4 TDP2               3 MCF7_2    4.71
## 5 TDP2               3 MDA231_1  5.94
## 6 TDP2               3 MDA231_2  7.38

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_genes <- c("APOA1", "HLA-A","HMGN5", "MYO1B")
downregulated_table <- breast_cancer_data %>%
  filter(Gene_Symbol %in% downregulated_genes) %>%
  select(Gene_Symbol,Description,Peptides)
#Upregulated
upregulated_genes <- c("GCLC", "FNBP1L", "DENND4C", "KRT23", "TDP2")
upregulated_table <- breast_cancer_data %>%
  filter(Gene_Symbol %in% upregulated_genes) %>%
  select(Gene_Symbol,Description,Peptides)

head(downregulated_table)
## # 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
head(upregulated_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