Last data update: 2014.03.03

R: generate peptide FASTA file that contains novel junctions.
OutputNovelJunR Documentation

generate peptide FASTA file that contains novel junctions.

Description

Three-frame translation of novel junctions. And remove those could be found in normal protein sequences. This function requires a genome built by BSgenome package.

Usage

  OutputNovelJun(junction_type, genome, outfile,
    proteinseq, ...)

Arguments

junction_type

a data frame which is the output of function JunctionType()

genome

a BSgenome object. (e.g. Hsapiens)

outfile

output file name

proteinseq

a data frame cotaining amino acid sequence for each protein.

...

Additional arguments.

Value

FASTA file that contains novel junction peptides.

Author(s)

Xiaojing Wang

Examples

bedfile <- system.file("extdata/beds", "junctions1.bed", package="customProDB")
jun <-  Bed2Range(bedfile,skip=1,covfilter=5)
load(system.file("extdata/refseq", "splicemax.RData", package="customProDB"))
load(system.file("extdata/refseq", "ids.RData", package="customProDB"))
txdb <- loadDb(system.file("extdata/refseq", "txdb.sqlite",
            package="customProDB"))
junction_type <- JunctionType(jun, splicemax, txdb, ids)
table(junction_type[, 'jun_type'])
chrom <- paste('chr',c(1:22,'X','Y','M'),sep='')
junction_type <- subset(junction_type, seqnames %in% chrom)
outf_junc <- paste(tempdir(), '/test_junc.fasta', sep='')
load(system.file("extdata/refseq", "proseq.RData", package="customProDB"))
library('BSgenome.Hsapiens.UCSC.hg19')
OutputNovelJun <- OutputNovelJun(junction_type, Hsapiens, outf_junc,
            proteinseq)

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(customProDB)
Loading required package: IRanges
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: 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: AnnotationDbi
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")'.

Loading required package: biomaRt
> png(filename="/home/ddbj/snapshot/RGM3/R_BC/result/customProDB/OutputNovelJun.Rd_%03d_medium.png", width=480, height=480)
> ### Name: OutputNovelJun
> ### Title: generate peptide FASTA file that contains novel junctions.
> ### Aliases: OutputNovelJun
> 
> ### ** Examples
> 
> bedfile <- system.file("extdata/beds", "junctions1.bed", package="customProDB")
> jun <-  Bed2Range(bedfile,skip=1,covfilter=5)
> load(system.file("extdata/refseq", "splicemax.RData", package="customProDB"))
> load(system.file("extdata/refseq", "ids.RData", package="customProDB"))
> txdb <- loadDb(system.file("extdata/refseq", "txdb.sqlite",
+             package="customProDB"))
Loading required package: GenomicFeatures
Loading required package: GenomeInfoDb
Loading required package: GenomicRanges
> junction_type <- JunctionType(jun, splicemax, txdb, ids)
> table(junction_type[, 'jun_type'])

connect a known exon and a region overlap with known exon 
                                                        1 
                              connect two non-exon region 
                                                        9 
                                           known junction 
                                                       46 
> chrom <- paste('chr',c(1:22,'X','Y','M'),sep='')
> junction_type <- subset(junction_type, seqnames %in% chrom)
> outf_junc <- paste(tempdir(), '/test_junc.fasta', sep='')
> load(system.file("extdata/refseq", "proseq.RData", package="customProDB"))
> library('BSgenome.Hsapiens.UCSC.hg19')
Loading required package: BSgenome
Loading required package: Biostrings
Loading required package: XVector
Loading required package: rtracklayer
> OutputNovelJun <- OutputNovelJun(junction_type, Hsapiens, outf_junc,
+             proteinseq)
There were 20 warnings (use warnings() to see them)
> 
> 
> 
> 
> 
> dev.off()
null device 
          1 
>