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_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))) %>% arrange(-log_MCF7)
## make a matrix of just the data
Breast_Cancer_matrix <-breast_cancer_data %>% select(MCF10A_1:SKBR3_2) %>% as.matrix() %>% round(.,2)

head(Breast_Cancer_matrix)
##      MCF10A_1 MCF10A_2 MCF7_1 MCF7_2 MDA231_1 MDA231_2 MDA468_1 MDA468_2
## [1,]        0        0  23.16  18.89     3.85     4.11     9.97    17.04
## [2,]        0        0  13.77  12.28     2.62     4.54    13.78    10.42
## [3,]        0        0  12.06  13.46     2.79     3.14    11.24    11.59
## [4,]        0        0  13.41  11.71     5.87     4.61     9.34    10.50
## [5,]        0        0  10.91  13.05     8.61     5.15    17.83    15.20
## [6,]        0        0  10.64  11.44     0.80     0.00    30.50    29.84
##      SKBR3_1 SKBR3_2
## [1,]    9.25   13.73
## [2,]   19.67   22.91
## [3,]   21.97   23.75
## [4,]   18.95   25.61
## [5,]   12.39   16.85
## [6,]    9.57    7.21
## make a heatmap from the data
pheatmap(Breast_Cancer_matrix, color=pats_cols,cellwidth=30,cellheight=.06,cluster_cols=FALSE,cluster_rows=FALSE,legend=TRUE,fontsize = 7,scale="row")

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_MCF=-log10(pvalue_MCF7_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_MCF7,y=neglog_MCF,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_MCF7>2 & neglog_MCF>2.99),"UP", ifelse((log_MCF7<c(-2) & neglog_MCF>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_MCF7,y=neglog_MCF,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 MCF7 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))

head(Breast_Cancer_long)
## # A tibble: 6 × 5
##   Gene_Symbol Description                                 Pepti…¹ varia…²  value
##   <chr>       <chr>                                         <dbl> <chr>    <dbl>
## 1 CDC37L1     Hsp90 co-chaperone Cdc37-like 1 OS=Homo sa…       1 MCF10A…  0.001
## 2 CDC37L1     Hsp90 co-chaperone Cdc37-like 1 OS=Homo sa…       1 MCF10A…  0.001
## 3 CDC37L1     Hsp90 co-chaperone Cdc37-like 1 OS=Homo sa…       1 MCF7_1  23.2  
## 4 CDC37L1     Hsp90 co-chaperone Cdc37-like 1 OS=Homo sa…       1 MCF7_2  18.9  
## 5 CDC37L1     Hsp90 co-chaperone Cdc37-like 1 OS=Homo sa…       1 MDA231…  3.85 
## 6 CDC37L1     Hsp90 co-chaperone Cdc37-like 1 OS=Homo sa…       1 MDA231…  4.11 
## # … with abbreviated variable names ¹​Peptides, ²​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<-Breast_Cancer_long %>% filter(Gene_Symbol=="METTL7A" | Gene_Symbol=="FMNL1" | Gene_Symbol=="EXOG") 
  
## 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=="AGR3" | Gene_Symbol=="SYT7"|Gene_Symbol=="FBP2")

head(Examples_Up)
## # A tibble: 6 × 5
##   Gene_Symbol Description                                  Pepti…¹ varia…² value
##   <chr>       <chr>                                          <dbl> <chr>   <dbl>
## 1 FBP2        Fructose-1,6-bisphosphatase isozyme 2 OS=Ho…       2 MCF10A…  1.13
## 2 FBP2        Fructose-1,6-bisphosphatase isozyme 2 OS=Ho…       2 MCF10A…  0.76
## 3 FBP2        Fructose-1,6-bisphosphatase isozyme 2 OS=Ho…       2 MCF7_1  43.9 
## 4 FBP2        Fructose-1,6-bisphosphatase isozyme 2 OS=Ho…       2 MCF7_2  41.4 
## 5 FBP2        Fructose-1,6-bisphosphatase isozyme 2 OS=Ho…       2 MDA231…  2.24
## 6 FBP2        Fructose-1,6-bisphosphatase isozyme 2 OS=Ho…       2 MDA231…  1.7 
## # … 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
Breast_Cancer_table_DR <- breast_cancer_data %>% filter(Gene_Symbol=="METTL7A" | Gene_Symbol=="FMNL1" | Gene_Symbol=="EXOG") %>% select(Gene_Symbol,Description,Peptides)
head(Breast_Cancer_table_DR)
## # A tibble: 3 × 3
##   Gene_Symbol Description                                                Pepti…¹
##   <chr>       <chr>                                                        <dbl>
## 1 EXOG        Nuclease EXOG, mitochondrial OS=Homo sapiens GN=EXOG PE=1…       3
## 2 METTL7A     Methyltransferase-like protein 7A OS=Homo sapiens GN=METT…       3
## 3 FMNL1       Isoform 2 of Formin-like protein 1 OS=Homo sapiens GN=FMN…       1
## # … with abbreviated variable name ¹​Peptides
#Upregulated
Breast_Cancer_table_UR <- breast_cancer_data %>% filter(Gene_Symbol=="AGR3" | Gene_Symbol=="SYT7"|Gene_Symbol=="FBP2") %>% select(Gene_Symbol,Description,Peptides) 
head(Breast_Cancer_table_UR)
## # A tibble: 3 × 3
##   Gene_Symbol Description                                                Pepti…¹
##   <chr>       <chr>                                                        <dbl>
## 1 FBP2        Fructose-1,6-bisphosphatase isozyme 2 OS=Homo sapiens GN=…       2
## 2 AGR3        Anterior gradient protein 3 homolog OS=Homo sapiens GN=AG…       5
## 3 SYT7        Synaptotagmin-7 OS=Homo sapiens GN=SYT7 PE=1 SV=3                1
## # … with abbreviated variable name ¹​Peptides