####Run through this example and try to understand what is going on with the data
####So, lets 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 cell type comparisons)
breast_cancer_cells<-read_csv(file="breast_cancer_cells.csv")
## make some new columns that store the log ratios
bcc_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))) %>%
arrange(-log_mcf7)
view(bcc_data)
## shows the log of each cell type/divided by the "normal" control cell MCF10A (fold change)
## make a matrix of just log values the data
bcc_mat_1<-bcc_data %>% select(log_mcf7:log_skbr3) %>% as.matrix() %>% round(.,2)
head(bcc_mat_1)
## log_mcf7 log_mda231 log_mda468 log_skbr3
## [1,] 14.36 11.96 13.72 13.49
## [2,] 13.67 11.81 13.56 14.38
## [3,] 13.64 11.53 13.48 14.48
## [4,] 13.62 12.36 13.28 14.44
## [5,] 13.55 12.75 14.01 13.84
## [6,] 13.43 8.65 14.88 13.03
## make a heatmap from the data
pheatmap(bcc_mat_1, color=pats_cols,cellwidth=30,cellheight=.03,cluster_cols=FALSE,cluster_rows=FALSE,legend=TRUE,fontsize = 7,scale="column")
# shows the heat map of the bcc_mat_1. Demonstrates that their are two proteins with a darker color in all cancer cell types (they are highly expressed in cancer cells compared to normal cells)
##BASIC VOLCANO PLOT
## Add a column that stores the negative log of the pvalue of interest
bcc_volcano_data<-bcc_data %>% mutate(neglog_skbr3=-log10(pvalue_SKBR3_vs_MCF10A))
## Use ggplot to plot the log ratio at 24 hours against the -log p-value at 24 hours
volcano_plot<-bcc_volcano_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 (by using ifelse and setting # parameters) so they can be colored
bcc_better_volcano<-bcc_volcano_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 things
better_volcano_plot<-bcc_better_volcano %>% 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 SKBR3 proteins compared to control MCF10A",y="-log(p-value)")
better_volcano_plot
## use ggplotly to see hover over the points to see the gene names. Record these for the next step
ggplotly(better_volcano_plot)
## Significant up regulated are: GCLC,FNBP1L,DENND4C, KRT23, TDP2
## Significant down regulated are: APOA1, HLA-A, MYO1B, HMGN5
# Make a pivot longer table of the data
bcc_long<-pivot_longer(bcc_better_volcano, cols = c(MCF10A_1:SKBR3_2), names_to = 'variable')%>% select(-c(pvalue_MCF7_vs_MCF10A:significance))
head(bcc_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 ¹Peptides, ²variable
## Because ggplot will automatically plot alphabetically on the x-axis, we need to make sure that our timepoints will be in the proper order by adding a new column using the factor() function
#this should be excluded in other datasets where order is not needed
bcc_long$order <- as.character(bcc_long$variable)
bcc_long$order <- factor(bcc_long$order,levels=c('MCF10A_1','MCF10A_2','MCF7_1','MCF7_2','MDA231_1','MDA231_2','MDA468_1','MDA468_2','SKBR3_1','SKBR3_2'))
## based on the gene symbols from plotly, select a few proteins from the table. Select just the data and gene symbols and pivot longer
bcc_down<-bcc_long %>% filter(Gene_Symbol=="GCLC" | Gene_Symbol=="TDP2" | Gene_Symbol=="KRT23")
head(bcc_down)
## # A tibble: 6 × 6
## Gene_Symbol Description Pepti…¹ varia…² value order
## <chr> <chr> <dbl> <chr> <dbl> <fct>
## 1 GCLC Glutamate--cysteine ligase catalytic … 6 MCF10A… 3.01 MCF1…
## 2 GCLC Glutamate--cysteine ligase catalytic … 6 MCF10A… 2.82 MCF1…
## 3 GCLC Glutamate--cysteine ligase catalytic … 6 MCF7_1 9.28 MCF7…
## 4 GCLC Glutamate--cysteine ligase catalytic … 6 MCF7_2 9.85 MCF7…
## 5 GCLC Glutamate--cysteine ligase catalytic … 6 MDA231… 5.66 MDA2…
## 6 GCLC Glutamate--cysteine ligase catalytic … 6 MDA231… 4.96 MDA2…
## # … with abbreviated variable names ¹Peptides, ²variable
## make barplots facetted by Gene Symbol (when working with other data sets - change x=order to x = variable)
bcc_plot_down<-bcc_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")
bcc_plot_down
## Same process for the up-regulated ones
bcc_up<-bcc_long %>% filter(Gene_Symbol=="APOA1" | Gene_Symbol=="HLA-A" | Gene_Symbol=="MYO1B")
head(bcc_up)
## # A tibble: 6 × 6
## Gene_Symbol Description Pepti…¹ varia…² value order
## <chr> <chr> <dbl> <chr> <dbl> <fct>
## 1 HLA-A HLA class I histocompatibility antige… 1 MCF10A… 0.001 MCF1…
## 2 HLA-A HLA class I histocompatibility antige… 1 MCF10A… 1.69 MCF1…
## 3 HLA-A HLA class I histocompatibility antige… 1 MCF7_1 1.22 MCF7…
## 4 HLA-A HLA class I histocompatibility antige… 1 MCF7_2 3.07 MCF7…
## 5 HLA-A HLA class I histocompatibility antige… 1 MDA231… 1.43 MDA2…
## 6 HLA-A HLA class I histocompatibility antige… 1 MDA231… 1.16 MDA2…
## # … with abbreviated variable names ¹Peptides, ²variable
bcc_plot_up<-bcc_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")
bcc_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
down_regulated<-bcc_data %>%
filter(Gene_Symbol=="GCLC" | Gene_Symbol=="TDP2" | Gene_Symbol=="KRT23") %>%
select(Gene_Symbol,Description,Peptides)
down_regulated
## # A tibble: 3 × 3
## Gene_Symbol Description Pepti…¹
## <chr> <chr> <dbl>
## 1 GCLC Glutamate--cysteine ligase catalytic subunit OS=Homo sapi… 6
## 2 TDP2 Isoform 2 of Tyrosyl-DNA phosphodiesterase 2 OS=Homo sapi… 3
## 3 KRT23 Keratin, type I cytoskeletal 23 OS=Homo sapiens GN=KRT23 … 3
## # … with abbreviated variable name ¹Peptides
#Upregulated
up_regulated<-bcc_data %>%
filter(Gene_Symbol=="APOA1" | Gene_Symbol=="HLA-A" | Gene_Symbol=="MYO1B") %>%
select(Gene_Symbol,Description,Peptides)
up_regulated
## # A tibble: 6 × 3
## Gene_Symbol Description Pepti…¹
## <chr> <chr> <dbl>
## 1 HLA-A HLA class I histocompatibility antigen, A-30 alpha chain … 1
## 2 HLA-A HLA class I histocompatibility antigen, A-23 alpha chain … 3
## 3 HLA-A HLA class I histocompatibility antigen, A-2 alpha chain O… 21
## 4 MYO1B Isoform 2 of Myosin-Ib OS=Homo sapiens GN=MYO1B 22
## 5 APOA1 Apolipoprotein A-I OS=Homo sapiens GN=APOA1 PE=1 SV=1 2
## 6 HLA-A HLA class I histocompatibility antigen, A-1 alpha chain O… 1
## # … with abbreviated variable name ¹Peptides
##now you can knit this and publish to save and share your code in your ELN. Make sure each person in your group has completed this.
##Annotate when you have trouble and reference which line of code you need help on ## good luck and have fun!