###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
BC_data<-read_csv(file="breast_cancer_cells.csv")
## make some new columns that store the log ratios
BC_data<-BC_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)))
BC_mat1<-BC_data %>% select(log_MCF7:log_SKBR3) %>% as.matrix() %>% round(.,2)
## make a heatmap from the data
pheatmap(BC_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
BC_data<-BC_data %>% mutate(neglog_MDA468=-log10(pvalue_MDA468_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<-BC_data %>% ggplot(aes(x=log_MDA468,y=neglog_MDA468,description=Gene_Symbol))+
geom_point(alpha=0.7,color="royalblue")
volcano_plot
## BETTER VOLCANO PLOT
## Define the significant ones so they can be colored
BC_data<-BC_data %>% mutate(significance=ifelse((log_MDA468>2 & neglog_MDA468>2.99),"UP", ifelse((log_MDA468<c(-2) & neglog_MDA468>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<-BC_data %>% ggplot(aes(x=log_MDA468,y=neglog_MDA468,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 MDA468",y="-log(p-value)")
better_volcano_plot
## use ggplotly to see hover over the points to see the gene names
ggplotly(better_volcano_plot)
## 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
BC_long<-pivot_longer(BC_data, cols = c(MDA468_1:MCF10A_2), names_to = 'variable')%>% select(-c(Description:Peptides))
head(BC_long)
## # A tibble: 6 × 17
## Gene_Symbol MCF10A_1 MDA468_2 SKBR3_1 SKBR3_2 pvalue…¹ pvalu…² pvalu…³ pvalu…⁴
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 NES 9.54 3.88 8.46 5.64 0.542 0.0185 0.374 0.998
## 2 NES 9.54 3.88 8.46 5.64 0.542 0.0185 0.374 0.998
## 3 NES 9.54 3.88 8.46 5.64 0.542 0.0185 0.374 0.998
## 4 NES 9.54 3.88 8.46 5.64 0.542 0.0185 0.374 0.998
## 5 NES 9.54 3.88 8.46 5.64 0.542 0.0185 0.374 0.998
## 6 NES 9.54 3.88 8.46 5.64 0.542 0.0185 0.374 0.998
## # … with 8 more variables: log_MCF7 <dbl>, log_MDA231 <dbl>, log_MDA468 <dbl>,
## # log_SKBR3 <dbl>, neglog_MDA468 <dbl>, significance <chr>, variable <chr>,
## # value <dbl>, and abbreviated variable names ¹pvalue_MCF7_vs_MCF10A,
## # ²pvalue_MDA231_vs_MCF10A, ³pvalue_MDA468_vs_MCF10A, ⁴pvalue_SKBR3_vs_MCF10A
## 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<-BC_long %>% filter(Gene_Symbol=="CTNNA1" | Gene_Symbol=="PLAU" | Gene_Symbol=="PYGL")
## 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_Down<-BC_long %>% filter(Gene_Symbol=="SYT7" | Gene_Symbol=="AKR1C2" | Gene_Symbol=="PADI2")
Example_plot_down<-Examples_Down %>%
ggplot(aes(x=variable,y=value))+
geom_bar(stat="identity",fill="blue")+
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
#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<-BC_data %>% filter(Gene_Symbol=="PLAU"|Gene_Symbol=="FMNL1"|Gene_Symbol=="HLA-A"|Gene_Symbol=="ADCK3") %>% select(Gene_Symbol, Description, Peptides)
#Upregulated
Upregulated<-BC_data %>% filter(Gene_Symbol=="SYT7"|Gene_Symbol=="S100P"|Gene_Symbol=="CES1") %>% select(Gene_Symbol, Description, Peptides)