###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<-read_csv(file="breast_cancer_cells.csv")
## make some new columns that store the log ratios
data1<-breast_cancer %>%
mutate(log2_mcf7=log2((MCF7_1+MCF7_2)/(MCF10A_1+MCF10A_2)),
log2_mda231=log2((MDA231_1+MDA231_2)/(MCF10A_1+MCF10A_2)),
log2_mda468=log2((MDA468_1+MDA468_2)/(MCF10A_1+MCF10A_2)),
log2_skbr3=log2((SKBR3_1+SKBR3_2)/(MCF10A_1+MCF10A_2)))
data1
## # A tibble: 5,144 × 21
## Gene_…¹ Descr…² Pepti…³ MCF10…⁴ MCF10…⁵ MCF7_1 MCF7_2 MDA23…⁶ MDA23…⁷ MDA46…⁸
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 NES Nestin… 7 9.54 4.58 5.07 5.42 25.4 27.4 4.56
## 2 ZC3HC1 Isofor… 2 14 11.6 6.49 6.64 9.8 10.3 6.84
## 3 CAMSAP… Isofor… 5 10.2 8.29 11.6 10.8 12.5 10.1 9.54
## 4 COBRA1 Negati… 3 9 6.35 13.4 14.8 14.9 11.3 6.87
## 5 HAUS6 Isofor… 5 8.21 4.44 12.1 9.82 16.5 12.3 15.4
## 6 CHCHD4 Isofor… 5 12.5 15.8 8.05 8.38 6.78 8.46 4.48
## 7 DHX30 Isofor… 17 12.6 8.18 9.51 9.76 12.7 11.4 7.3
## 8 SLC12A2 Isofor… 15 6.33 4.21 11.3 11.5 3.03 2.28 27.2
## 9 PTPRJ Recept… 5 9.7 6.2 4.58 4.94 25.7 21.2 5.89
## 10 ATP6AP2 Renin … 8 9.02 5.69 14.5 15.2 7.25 6.2 14.3
## # … with 5,134 more rows, 11 more variables: MDA468_2 <dbl>, SKBR3_1 <dbl>,
## # SKBR3_2 <dbl>, pvalue_MCF7_vs_MCF10A <dbl>, pvalue_MDA231_vs_MCF10A <dbl>,
## # pvalue_MDA468_vs_MCF10A <dbl>, pvalue_SKBR3_vs_MCF10A <dbl>,
## # log2_mcf7 <dbl>, log2_mda231 <dbl>, log2_mda468 <dbl>, log2_skbr3 <dbl>,
## # and abbreviated variable names ¹Gene_Symbol, ²Description, ³Peptides,
## # ⁴MCF10A_1, ⁵MCF10A_2, ⁶MDA231_1, ⁷MDA231_2, ⁸MDA468_1
## make a matrix of just the data
breast_cancer_mat1<-data1 %>%
select(log2_mcf7:log2_skbr3) %>%
as.matrix() %>%
round(.,2)
head(breast_cancer_mat1)
## log2_mcf7 log2_mda231 log2_mda468 log2_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")
##BASIC VOLCANO PLOT
## Add a column that stores the negative log of the pvalue of interest
volcano<-data1 %>%
mutate(neglog_MDA468=-log10(pvalue_MCF7_vs_MCF10A))
volcano
## # A tibble: 5,144 × 22
## Gene_…¹ Descr…² Pepti…³ MCF10…⁴ MCF10…⁵ MCF7_1 MCF7_2 MDA23…⁶ MDA23…⁷ MDA46…⁸
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 NES Nestin… 7 9.54 4.58 5.07 5.42 25.4 27.4 4.56
## 2 ZC3HC1 Isofor… 2 14 11.6 6.49 6.64 9.8 10.3 6.84
## 3 CAMSAP… Isofor… 5 10.2 8.29 11.6 10.8 12.5 10.1 9.54
## 4 COBRA1 Negati… 3 9 6.35 13.4 14.8 14.9 11.3 6.87
## 5 HAUS6 Isofor… 5 8.21 4.44 12.1 9.82 16.5 12.3 15.4
## 6 CHCHD4 Isofor… 5 12.5 15.8 8.05 8.38 6.78 8.46 4.48
## 7 DHX30 Isofor… 17 12.6 8.18 9.51 9.76 12.7 11.4 7.3
## 8 SLC12A2 Isofor… 15 6.33 4.21 11.3 11.5 3.03 2.28 27.2
## 9 PTPRJ Recept… 5 9.7 6.2 4.58 4.94 25.7 21.2 5.89
## 10 ATP6AP2 Renin … 8 9.02 5.69 14.5 15.2 7.25 6.2 14.3
## # … with 5,134 more rows, 12 more variables: MDA468_2 <dbl>, SKBR3_1 <dbl>,
## # SKBR3_2 <dbl>, pvalue_MCF7_vs_MCF10A <dbl>, pvalue_MDA231_vs_MCF10A <dbl>,
## # pvalue_MDA468_vs_MCF10A <dbl>, pvalue_SKBR3_vs_MCF10A <dbl>,
## # log2_mcf7 <dbl>, log2_mda231 <dbl>, log2_mda468 <dbl>, log2_skbr3 <dbl>,
## # neglog_MDA468 <dbl>, and abbreviated variable names ¹Gene_Symbol,
## # ²Description, ³Peptides, ⁴MCF10A_1, ⁵MCF10A_2, ⁶MDA231_1, ⁷MDA231_2,
## # ⁸MDA468_1
## 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<-volcano %>%
ggplot(aes(x=log2_mcf7,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
better_volcano<-volcano %>%
mutate(significance=ifelse((log2_mcf7>2 & neglog_MDA468>2.99),"UP", ifelse((log2_mcf7<c(-2) & neglog_MDA468>2.99),"DOWN","NOT SIG")))
better_volcano
## # A tibble: 5,144 × 23
## Gene_…¹ Descr…² Pepti…³ MCF10…⁴ MCF10…⁵ MCF7_1 MCF7_2 MDA23…⁶ MDA23…⁷ MDA46…⁸
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 NES Nestin… 7 9.54 4.58 5.07 5.42 25.4 27.4 4.56
## 2 ZC3HC1 Isofor… 2 14 11.6 6.49 6.64 9.8 10.3 6.84
## 3 CAMSAP… Isofor… 5 10.2 8.29 11.6 10.8 12.5 10.1 9.54
## 4 COBRA1 Negati… 3 9 6.35 13.4 14.8 14.9 11.3 6.87
## 5 HAUS6 Isofor… 5 8.21 4.44 12.1 9.82 16.5 12.3 15.4
## 6 CHCHD4 Isofor… 5 12.5 15.8 8.05 8.38 6.78 8.46 4.48
## 7 DHX30 Isofor… 17 12.6 8.18 9.51 9.76 12.7 11.4 7.3
## 8 SLC12A2 Isofor… 15 6.33 4.21 11.3 11.5 3.03 2.28 27.2
## 9 PTPRJ Recept… 5 9.7 6.2 4.58 4.94 25.7 21.2 5.89
## 10 ATP6AP2 Renin … 8 9.02 5.69 14.5 15.2 7.25 6.2 14.3
## # … with 5,134 more rows, 13 more variables: MDA468_2 <dbl>, SKBR3_1 <dbl>,
## # SKBR3_2 <dbl>, pvalue_MCF7_vs_MCF10A <dbl>, pvalue_MDA231_vs_MCF10A <dbl>,
## # pvalue_MDA468_vs_MCF10A <dbl>, pvalue_SKBR3_vs_MCF10A <dbl>,
## # log2_mcf7 <dbl>, log2_mda231 <dbl>, log2_mda468 <dbl>, log2_skbr3 <dbl>,
## # neglog_MDA468 <dbl>, significance <chr>, and abbreviated variable names
## # ¹Gene_Symbol, ²Description, ³Peptides, ⁴MCF10A_1, ⁵MCF10A_2, ⁶MDA231_1,
## # ⁷MDA231_2, ⁸MDA468_1
## Some standard colors
plain_cols3<-c("red","gray","blue")
## volcano plot as before with some added graph features
better_volcano_plot<-better_volcano %>% ggplot(aes(x=log2_mcf7,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 at 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)
## 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
long_data<-pivot_longer(better_volcano, cols = c(MCF10A_1:SKBR3_2), names_to = 'variable')%>%
select(-c(pvalue_MCF7_vs_MCF10A:significance))
head(long_data)
## # A tibble: 6 × 5
## Gene_Symbol Description Peptides variable value
## <chr> <chr> <dbl> <chr> <dbl>
## 1 NES Nestin OS=Homo sapiens GN=NES PE=1 SV=2 7 MCF10A_1 9.54
## 2 NES Nestin OS=Homo sapiens GN=NES PE=1 SV=2 7 MCF10A_2 4.58
## 3 NES Nestin OS=Homo sapiens GN=NES PE=1 SV=2 7 MCF7_1 5.07
## 4 NES Nestin OS=Homo sapiens GN=NES PE=1 SV=2 7 MCF7_2 5.42
## 5 NES Nestin OS=Homo sapiens GN=NES PE=1 SV=2 7 MDA231_1 25.4
## 6 NES Nestin OS=Homo sapiens GN=NES PE=1 SV=2 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<-long_data %>%
filter(Gene_Symbol=="HLA-A" | Gene_Symbol=="APOA1" | Gene_Symbol=="CTSZ")
head(examples_down)
## # A tibble: 6 × 5
## Gene_Symbol Description Pepti…¹ varia…² value
## <chr> <chr> <dbl> <chr> <dbl>
## 1 HLA-A HLA class I histocompatibility antigen, A-2… 3 MCF10A… 5.42
## 2 HLA-A HLA class I histocompatibility antigen, A-2… 3 MCF10A… 6.62
## 3 HLA-A HLA class I histocompatibility antigen, A-2… 3 MCF7_1 2.22
## 4 HLA-A HLA class I histocompatibility antigen, A-2… 3 MCF7_2 2.69
## 5 HLA-A HLA class I histocompatibility antigen, A-2… 3 MDA231… 4.56
## 6 HLA-A HLA class I histocompatibility antigen, A-2… 3 MDA231… 4.23
## # … with abbreviated variable names ¹Peptides, ²variable
## 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<-long_data %>%
filter(Gene_Symbol=="C17orf28" | Gene_Symbol=="FBP2" | Gene_Symbol=="DICER1")
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 ¹Peptides, ²variable
example_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")
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<-data1 %>%
filter(Gene_Symbol=="HLA-A" | Gene_Symbol=="APOA1" | Gene_Symbol=="CTSZ") %>%
select(Gene_Symbol,Description,Peptides)
downregulated
## # 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 CTSZ Cathepsin Z OS=Homo sapiens GN=CTSZ PE=1 SV=1 8
## 5 HLA-A HLA class I histocompatibility antigen, A-1 alpha chain O… 1
## 6 APOA1 Apolipoprotein A-I OS=Homo sapiens GN=APOA1 PE=1 SV=1 2
## # … with abbreviated variable name ¹Peptides
#Upregulated
upregulated<-data1 %>%
filter(Gene_Symbol=="C17orf28" | Gene_Symbol=="FBP2" | Gene_Symbol=="DICER1") %>%
select(Gene_Symbol,Description,Peptides)
upregulated
## # 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 DICER1 Endoribonuclease Dicer OS=Homo sapiens GN=DICER1 PE=1 SV=3 1
## 3 C17orf28 Isoform 2 of UPF0663 transmembrane protein C17orf28 OS=Ho… 3
## # … with abbreviated variable name ¹Peptides