## ----style, echo = FALSE, results = 'asis'-------------------------------
knitr::opts_chunk$set(
    eval=as.logical(Sys.getenv("KNITR_EVAL", "TRUE")),
    cache=as.logical(Sys.getenv("KNITR_CACHE", "TRUE"))
)
options(width = 75)


## ---- message = FALSE----------------------------------------------------
library(readr)
library(dplyr)


## ---- eval = FALSE-------------------------------------------------------
## if (!requireNamespace("BiocManager", quietly = TRUE))
##     install.packages("BiocManager")


## ---- eval = FALSE-------------------------------------------------------
## BiocManager::install(c("readr", "dplyr"))


## ---- eval = FALSE-------------------------------------------------------
## pdata_file <- file.choose()

## ---- echo = FALSE-------------------------------------------------------
pdata_file <-
    system.file(package="BiocIntro", "extdata", "ALL-sample-sheet.csv")


## ------------------------------------------------------------------------
pdata <- read_csv(pdata_file)


## ------------------------------------------------------------------------
pdata


## ------------------------------------------------------------------------
pdata %>% arrange(age)


## ------------------------------------------------------------------------
pdata %>% arrange(desc(age))


## ------------------------------------------------------------------------
pdata %>% summarize(n = n())


## ---- eval = FALSE-------------------------------------------------------
## pdata %>% group_by(sex)


## ------------------------------------------------------------------------
pdata %>% group_by(sex) %>% summarize(n = n())


## ---- eval = FALSE-------------------------------------------------------
## pdata %>% t.test(age ~ sex, data = .)


## ------------------------------------------------------------------------
pdata %>%
    group_by(mol.biol) %>%
    count()


## ------------------------------------------------------------------------
c("a", "b", "c", "b", "a") %in% c("a", "c")


## ---- message = FALSE----------------------------------------------------
library(ggplot2)


## ------------------------------------------------------------------------
ggplot(pdata, aes(x = sex, y = age))


## ------------------------------------------------------------------------
ggplot(pdata, aes(x = sex, y = age)) + 
    geom_boxplot()


## ------------------------------------------------------------------------
ggplot(pdata, aes(x = sex, y = age)) + 
    geom_boxplot() + 
    geom_jitter(width = .1, height = 0)


## ------------------------------------------------------------------------
sequences <- c("AAATCGA", "ATACAACAT", "TTGCCA")


## ------------------------------------------------------------------------
sequences
length(sequences)
nchar(sequences)
sequences[c(1, 3)]
sample(sequences)


## ---- eval=FALSE---------------------------------------------------------
## reverseComplement(sequences)


## ------------------------------------------------------------------------
my_sequence <-
    "All the world's a stage, And all the men and women merely players"


## ---- message = FALSE----------------------------------------------------
library(Biostrings)


## ---- eval = FALSE-------------------------------------------------------
## if (!requireNamespace("BiocManager", quietly = TRUE))
##     install.packages("BiocManager")
## BiocManager::install("Biostrings")
## library(Biostrings)


## ------------------------------------------------------------------------
dna <- DNAStringSet(sequences)
dna


## ------------------------------------------------------------------------
class(dna)


## ------------------------------------------------------------------------
fa_file <-
    system.file(package="Biostrings", "extdata", "dm3_upstream2000.fa.gz")


## ------------------------------------------------------------------------
readLines(fa_file, 5)


## ------------------------------------------------------------------------
tail(readLines(fa_file, 44), 5)


## ------------------------------------------------------------------------
dna <- readDNAStringSet(fa_file)
dna


## ------------------------------------------------------------------------
gc <- letterFrequency(dna, "GC", as.prob = TRUE)


## ------------------------------------------------------------------------
gc <- 
    dna %>%
    letterFrequency("GC", as.prob = TRUE) %>%
    tibble::as_tibble()
gc


## ------------------------------------------------------------------------
sessionInfo()