Loads a small example Roche 454 dataset (sff file) into a SffReadsQ object containing 1000 reads.
Author(s)
Matt Settles <msettles@uidaho.edu>
Examples
##Read in the included sample 454 data set.
sff <- load454SampleData()
##Generate summary statistics for read lengths.
summary(width(sff))
##Generate some QA plots:
##Read length histograms:
par(mfrow=c(2,2))
clipMode(sff) <- "raw"
hist(width(sff),breaks=500,col="grey",xlab="Read Length",main="Raw Read Length")
clipMode(sff) <- "full"
hist(width(sff),breaks=500,col="grey",xlab="Read Length",main="Clipped Read Length")
## Base by position plots:
clipMode(sff) <- "raw"
ac <- alphabetByCycle(sread(sff),alphabet=c("A","C","T","G","N"))
ac.reads <- apply(ac,2,sum)
acf <- sweep(ac,MARGIN=2,FUN="/",STATS=apply(ac,2,sum))
matplot(cbind(t(acf),ac.reads/ac.reads[1]),col=c("green","blue","black","red","darkgrey","purple"),
type="l",lty=1,xlab="Base Position",ylab="Base Frequency",
main="Base by position")
cols <- c("green","blue","black","red","darkgrey","purple")
leg <- c("A","C","T","G","N","%reads")
legend("topright", col=cols, legend=leg, pch=18, cex=.8)
clipMode(sff) <- "full"
ac <- alphabetByCycle(sread(sff),alphabet=c("A","C","T","G","N"))
ac.reads <- apply(ac,2,sum)
acf <- sweep(ac,MARGIN=2,FUN="/",STATS=apply(ac,2,sum))
matplot(cbind(t(acf),ac.reads/ac.reads[1]),col=c("green","blue","black","red","darkgrey","purple"),
type="l",lty=1,xlab="Base Position",ylab="Base Frequency",
main="Base by position")
legend("topright", col=cols, legend=leg, pch=18, cex=.8)
Results
R version 3.3.1 (2016-06-21) -- "Bug in Your Hair"
Copyright (C) 2016 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)
R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.
R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.
Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.
> library(rSFFreader)
Loading required package: ShortRead
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':
Filter, Find, Map, Position, Reduce, anyDuplicated, append,
as.data.frame, cbind, colnames, do.call, duplicated, eval, evalq,
get, grep, grepl, intersect, is.unsorted, lapply, lengths, mapply,
match, mget, order, paste, pmax, pmax.int, pmin, pmin.int, rank,
rbind, rownames, sapply, setdiff, sort, table, tapply, union,
unique, unsplit
Loading required package: BiocParallel
Loading required package: Biostrings
Loading required package: S4Vectors
Loading required package: stats4
Attaching package: 'S4Vectors'
The following objects are masked from 'package:base':
colMeans, colSums, expand.grid, rowMeans, rowSums
Loading required package: IRanges
Loading required package: XVector
Loading required package: Rsamtools
Loading required package: GenomeInfoDb
Loading required package: GenomicRanges
Loading required package: GenomicAlignments
Loading required package: SummarizedExperiment
Loading required package: Biobase
Welcome to Bioconductor
Vignettes contain introductory material; view with
'browseVignettes()'. To cite Bioconductor, see
'citation("Biobase")', and for packages 'citation("pkgname")'.
> png(filename="/home/ddbj/snapshot/RGM3/R_BC/result/rSFFreader/load454SampleData.Rd_%03d_medium.png", width=480, height=480)
> ### Name: load454SampleData
> ### Title: Load the example 454 dataset
> ### Aliases: load454SampleData
>
> ### ** Examples
>
> ##Read in the included sample 454 data set.
> sff <- load454SampleData()
Total number of reads to be read: 1000
reading header for sff file:/home/ddbj/local/lib64/R/library/rSFFreader/extdata/Small454Test.sff
reading file:/home/ddbj/local/lib64/R/library/rSFFreader/extdata/Small454Test.sff
> ##Generate summary statistics for read lengths.
> summary(width(sff))
Min. 1st Qu. Median Mean 3rd Qu. Max.
42.0 539.8 656.5 605.3 737.0 952.0
>
> ##Generate some QA plots:
> ##Read length histograms:
> par(mfrow=c(2,2))
> clipMode(sff) <- "raw"
> hist(width(sff),breaks=500,col="grey",xlab="Read Length",main="Raw Read Length")
>
> clipMode(sff) <- "full"
> hist(width(sff),breaks=500,col="grey",xlab="Read Length",main="Clipped Read Length")
>
> ## Base by position plots:
> clipMode(sff) <- "raw"
> ac <- alphabetByCycle(sread(sff),alphabet=c("A","C","T","G","N"))
> ac.reads <- apply(ac,2,sum)
> acf <- sweep(ac,MARGIN=2,FUN="/",STATS=apply(ac,2,sum))
>
> matplot(cbind(t(acf),ac.reads/ac.reads[1]),col=c("green","blue","black","red","darkgrey","purple"),
+ type="l",lty=1,xlab="Base Position",ylab="Base Frequency",
+ main="Base by position")
> cols <- c("green","blue","black","red","darkgrey","purple")
> leg <- c("A","C","T","G","N","%reads")
> legend("topright", col=cols, legend=leg, pch=18, cex=.8)
>
> clipMode(sff) <- "full"
> ac <- alphabetByCycle(sread(sff),alphabet=c("A","C","T","G","N"))
> ac.reads <- apply(ac,2,sum)
> acf <- sweep(ac,MARGIN=2,FUN="/",STATS=apply(ac,2,sum))
>
> matplot(cbind(t(acf),ac.reads/ac.reads[1]),col=c("green","blue","black","red","darkgrey","purple"),
+ type="l",lty=1,xlab="Base Position",ylab="Base Frequency",
+ main="Base by position")
> legend("topright", col=cols, legend=leg, pch=18, cex=.8)
>
>
>
>
>
>
> dev.off()
null device
1
>