###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_cells<-read_csv(file="breast_cancer_cells.csv")
## make some new columns that store the log ratios
breast_cancer_cells_data<-breast_cancer_cells %>% 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_cells_data)
## make a matrix of just the data
breast_cancer_cells_mat1<-breast_cancer_cells_data %>% select(MCF7_1:SKBR3_2) %>% as.matrix() %>% round(.,2)
head(breast_cancer_cells_mat1)
## MCF7_1 MCF7_2 MDA231_1 MDA231_2 MDA468_1 MDA468_2 SKBR3_1 SKBR3_2
## [1,] 5.07 5.42 25.43 27.42 4.56 3.88 8.46 5.64
## [2,] 6.49 6.64 9.80 10.31 6.84 8.75 11.91 13.67
## [3,] 11.55 10.82 12.48 10.11 9.54 8.46 9.10 9.43
## [4,] 13.40 14.82 14.94 11.33 6.87 7.92 8.54 6.82
## [5,] 12.08 9.82 16.51 12.34 15.43 8.50 7.93 4.75
## [6,] 8.05 8.38 6.78 8.46 4.48 7.18 13.27 15.05
## make a heatmap from the data
pheatmap(breast_cancer_cells_mat1, color=pats_cols,cellwidth=30,cellheight=.03,cluster_cols=FALSE,cluster_rows=TRUE,legend=TRUE,fontsize = 7,scale="column")
##BASIC VOLCANO PLOT
## Add a column that stores the negative log of the pvalue of interest
breast_cancer_cells_data<-breast_cancer_cells_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_cells_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_cells_data<-breast_cancer_cells_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_cells_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 cells in cancer patient(log_SKBR3)compared to control(neg_log_SKBR3)",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
## UP GCLC, FNBP1L
breast_cancer_cells_long <- breast_cancer_cells %>%
pivot_longer(cols = c(MCF10A_1:SKBR3_2), names_to = 'variable') %>%
select(-c(pvalue_MCF7_vs_MCF10A:pvalue_SKBR3_vs_MCF10A)) %>%
mutate(order = factor(variable, levels = c("MCF10A_1", "MCF10A", "MCF7_1", "MCF7_2", "MDA231_1", "MDA231_2", "MDA468_1", "MDA468_2", "SKBR3_1", "SKBR3_2")))
breast_cancer_cells_long
## # A tibble: 51,440 × 6
## Gene_Symbol Description Pepti…¹ varia…² value order
## <chr> <chr> <dbl> <chr> <dbl> <fct>
## 1 NES Nestin OS=Homo sapiens GN=NES PE=1 S… 7 MCF10A… 9.54 MCF1…
## 2 NES Nestin OS=Homo sapiens GN=NES PE=1 S… 7 MCF10A… 4.58 <NA>
## 3 NES Nestin OS=Homo sapiens GN=NES PE=1 S… 7 MCF7_1 5.07 MCF7…
## 4 NES Nestin OS=Homo sapiens GN=NES PE=1 S… 7 MCF7_2 5.42 MCF7…
## 5 NES Nestin OS=Homo sapiens GN=NES PE=1 S… 7 MDA231… 25.4 MDA2…
## 6 NES Nestin OS=Homo sapiens GN=NES PE=1 S… 7 MDA231… 27.4 MDA2…
## 7 NES Nestin OS=Homo sapiens GN=NES PE=1 S… 7 MDA468… 4.56 MDA4…
## 8 NES Nestin OS=Homo sapiens GN=NES PE=1 S… 7 MDA468… 3.88 MDA4…
## 9 NES Nestin OS=Homo sapiens GN=NES PE=1 S… 7 SKBR3_1 8.46 SKBR…
## 10 NES Nestin OS=Homo sapiens GN=NES PE=1 S… 7 SKBR3_2 5.64 SKBR…
## # … with 51,430 more rows, and abbreviated variable names ¹Peptides, ²variable
examples_up<-breast_cancer_cells_long%>% filter(Gene_Symbol=="GCLC" | Gene_Symbol=="FNBP1L" | Gene_Symbol=="KRT23" | Gene_Symbol=="DENND4C" | Gene_Symbol=="TDP2")
examples_plot_up<-examples_up%>%
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")
examples_plot_up
# Make a pivot longer table of the data for initial columns. Exclude the p-values and log columns
breast_cancer_cells_long<-pivot_longer(breast_cancer_cells_data, cols = c(MCF10A_1:SKBR3_2), names_to = 'variable')%>% select(-c(pvalue_SKBR3_vs_MCF10A:significance))
head(breast_cancer_cells_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 ¹Peptides, ²pvalue_MCF7_vs_MCF10A,
## # ³pvalue_MDA231_vs_MCF10A, ⁴pvalue_MDA468_vs_MCF10A, ⁵variable
## 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
## make barplots facetted by Gene Symbol (if copying COVID example - change x=order to x = variable)
## Same process for the upregulated ones
examples_down<-breast_cancer_cells_long%>% filter(Gene_Symbol=="APOA1" | Gene_Symbol=="HLA-A" | Gene_Symbol=="MYO1B" | Gene_Symbol=="HMGN5")
examples_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")
examples_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
#Upregulated