###First, let’s load RMarkdown
library(rmarkdown)
knitr::opts_chunk$set(echo = TRUE, message=FALSE,warning=FALSE,collapse = TRUE)
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)
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 the dataset
breast_cancer_data<-read_csv(file="breast_cancer_cells.csv")
## make some new columns that store the log ratios
##MCF10A is a control and is non-tumorigenic, it can be used to compare against the different genes and their respective replicates
breast_cancer_data<-breast_cancer_data %>% mutate(
log_MCF7=log2((MCF7_2+MCF7_1)/(MCF10A_2+MCF10A_1)),
log_MDA231=log2((MDA231_2+MDA231_1)/(MCF10A_2+MCF10A_1)),
log_MDA468=log2((MDA468_2+MDA468_1)/(MCF10A_2+MCF10A_1)),
log_SKBR3=log2((SKBR3_2+SKBR3_1)/(MCF10A_2+MCF10A_1)))
## make a matrix of just the data
##selected for the columns that I made above
breast_cancer_mat1<-breast_cancer_data %>% select(log_MCF7:log_SKBR3) %>% as.matrix() %>% round(.,2)
## 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")
##BASIC VOLCANO PLOT
## Add a column that stores the negative log of the pvalue of interest
## The heat map above of cell line SKBR3 looked different near the top than the others so I am choosing this to pursue further.
##I am taking my data and adding a column so I mutate.
##I named my column neglog_SKBR3 (because that is the cell line of interest)
##I am taking the negative log of pvalue which is called pvalue_SKBR3_vs_MCF10A in the data column
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
##To make the volcano plot I take the cell line of interest (SKBR3) on the x, against the -log p-value column which I called neglog_SKBR
##geom point is how bright dot is
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
##Contains complete argument for determining significance (didn't change anything besides adding the name of the cell line I am interested in--SKBR3)
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("pink","gray","green")
## volcano plot as before with some added graph features
##colour is based on what I coded above
##Changed title to be more representative
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=" Regulatory Genes in log of SKBR3 compared to control",y="-log(p-value)")
better_volcano_plot
##12 rows were removed because of parameters set
##Noticed: 4 significant down (pink) and 5 significant up (green)
## use ggplotly to see hover over the points to see the gene names
##plotly allows to hover over and see gene symbol
ggplotly(better_volcano_plot)
##(in a pdf plooty doesn't plot wedget correctly, so used a url)
## EXAMPLES OF A COUPLE PROTEINS or GENES
##Down regulated (pink): APOA1, HLA-A, MYO1B, HMGN5
##Up regulated (green): GCLC, FNDP1C, KRT23, DENND4C, TDP2
# Make a pivot longer table of the data for initial columns. Exclude the p-values and log columns
##I named this new table "breast_cancer_long", then condensed all of the columns of interest and stacked them (MCF10A_1 all the way to SKBR3_2) by using c(MCF10A_1:SKBR3_2). I named this column variable.
##I deleted all the columns after SKBR3_2 (pvalue_MCF7_vs_MCF10A to significance) by using "select"
##I also deleted the colum description and peptides by using select
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) %>% select(-Peptides)
head(breast_cancer_long)
## # 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
##Used column title Gene_Symbol to find the significantly down regulated genes detected from the plot above.
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 × 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)
##x=variable since that is the column that contains what cell line it belongs to and y=value which is the number cooresponding to the cell line.
##changed colour to pink since that is the colour I choose for my down regulated genes.
Example_plot_down<-Examples_Down %>%
ggplot(aes(x=variable,y=value))+
geom_bar(stat="identity",fill="pink")+
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
##Shows the intensity of these genes throughout the different cell line.
## Same process for the upregulated ones
Examples_Up<-breast_cancer_long %>% filter(Gene_Symbol=="GCLC" | Gene_Symbol=="FNBP1L" | Gene_Symbol=="KRT23" | Gene_Symbol=="DENND4C" | Gene_Symbol=="TDP2")
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
Example_plot_Up<-Examples_Up %>%
ggplot(aes(x=variable,y=value))+
geom_bar(stat="identity",fill="green")+
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
#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_table<-breast_cancer_data %>% filter(Gene_Symbol=="APOA1" | Gene_Symbol=="HLA-A" | Gene_Symbol=="MYO1B" | Gene_Symbol=="HMGN5") %>%
select(Gene_Symbol: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 ¹Peptides
#Upregulated
upregulated_table<-breast_cancer_data %>% filter(Gene_Symbol=="GCLC" | Gene_Symbol=="FNBP1L" | Gene_Symbol=="KRT23" | Gene_Symbol=="DENND4C" | Gene_Symbol=="TDP2") %>%
select(Gene_Symbol: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 ¹Peptides