R

library(Biobase)

## Loading required package: BiocGenerics

## Loading required package: parallel

## 
## Attaching package: 'BiocGenerics'

## The following objects are masked from 'package:parallel':
## 
##     clusterApply, clusterApplyLB, clusterCall, clusterEvalQ,
##     clusterExport, clusterMap, parApply, parCapply, parLapply,
##     parLapplyLB, parRapply, parSapply, parSapplyLB

## The following objects are masked from 'package:stats':
## 
##     IQR, mad, xtabs

## The following objects are masked from 'package:base':
## 
##     anyDuplicated, append, as.data.frame, cbind, colnames,
##     do.call, duplicated, eval, evalq, Filter, Find, get, grep,
##     grepl, intersect, is.unsorted, lapply, lengths, Map, mapply,
##     match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,
##     Position, rank, rbind, Reduce, rownames, sapply, setdiff,
##     sort, table, tapply, union, unique, unsplit, which, which.max,
##     which.min

## Welcome to Bioconductor
## 
##     Vignettes contain introductory material; view with
##     'browseVignettes()'. To cite Bioconductor, see
##     'citation("Biobase")', and for packages 'citation("pkgname")'.

library(GEOquery)

## Setting options('download.file.method.GEOquery'='auto')

## Setting options('GEOquery.inmemory.gpl'=FALSE)

#gset <- getGEO("GSE89093", GSEMatrix =TRUE, getGPL=FALSE)
#if (length(gset) > 1) idx <- grep("GPL13534", attr(gset, "names")) else idx <- 1
#gset <- gset[[idx]]

# set parameters and draw the plot

# dev.new(width=4+dim(gset)[[2]]/5, height=6)
# par(mar=c(2+round(max(nchar(sampleNames(gset)))/2),4,2,1))
# title <- paste ("GSE89093", '/', annotation(gset), " selected samples", sep ='')
# boxplot(exprs(gset), boxwex=0.7, notch=T, main=title, outline=FALSE, las=2)
# 
library(readxl)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following object is masked from 'package:Biobase':
## 
##     combine

## The following objects are masked from 'package:BiocGenerics':
## 
##     combine, intersect, setdiff, union

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

metadata <- read_excel("Metadata.xlsx")

# dat <- tbl_df(table(metadata$`Cancer location`))
dat <- tbl_df(na.omit(metadata$`Cancer location`))
#names(dat) <- c("Types", "Counts")
names(dat)

## [1] "value"

dat$value <- gsub("\\b(.)", "\\U\\1", dat$value, perl=TRUE)
dat$value <- gsub("Gland_thyroid", "Thyroid", dat$value)
dat$value <- gsub("Endometrium", "Uterine", dat$value)
dat$value <- gsub("Melanoma", "Skin", dat$value)

library(ggplot2)
science_theme = theme(axis.line = element_line(size = 0.7, color = "black"), legend.position = "none", text = element_text(size = 14, color = "black"), axis.text=element_text(size=15), axis.title=element_text(size=17), panel.background = element_rect(fill = "white"))
p <- ggplot(dat, aes(value)) + science_theme+ geom_bar() + xlab("Cancer Location") + ylab("Counts") + scale_y_continuous(expand = c(0,0))
print(p)