Last data update: 2014.03.03

R: fetch sequence by id
fetchSequenceR Documentation

fetch sequence by id

Description

fetch amino acid sequence by given identifiers via biomaRt or proteome prepared by prepareProteome

Usage

fetchSequence(IDs, type="entrezgene", anchorAA=NULL, anchorPos,
                            mart, proteome, upstreamOffset, downstreamOffset)

Arguments

IDs

A vector of Identifiers to retrieve peptides

type

type of identifiers

anchorAA

a vector of character, anchor Amino Acid

anchorPos

a vector of character or numeric, anchor position, for example, K121. Or a vector of character with amino acid sequences. If AA sequences is used, the anchorAA must be the a vector of character with single AA for each.

mart

an object of Mart

proteome

an object of Proteome, output of prepareProteome

upstreamOffset

an integer, upstream offset position

downstreamOffset

an integer, downstream offset position

Value

return an object of dagPeptides

Author(s)

Jianhong Ou, Alexey Stukalov, Julie Zhu

See Also

formatSequence

Examples

if(interactive()){
    mart <- useMart("ensembl", "dmelanogaster_gene_ensembl")
    dat <- read.csv(system.file("extdata", "dagLogoTestData.csv", package="dagLogo"))
    seq <- fetchSequence(as.character(dat$entrez_geneid[1:5]), 
                anchorPos=as.character(dat$NCBI_site[1:5]), 
                mart=mart, 
                upstreamOffset=7, 
                downstreamOffset=7)
    ## sample: use sequence as anchorPos
    sequences <- seq@peptides
    sequences[, 8] <- "k"
    sequences <- apply(sequences, 1, paste, collapse="")
    seq <- fetchSequence(as.character(seq@data$IDs),
                        anchorAA="k",
                        anchorPos=sequences,
                        mart=mart,
                        upstreamOffset=7,
                        downstreamOffset=7)
    ## sample: use sequence as anchorPos 2
    sequences <- cbind(seq@peptides[, 1:8], "*", seq@peptides[, 9:15])
    sequences <- apply(sequences, 1, paste, collapse="")
    seq <- fetchSequence(as.character(seq@data$IDs),
                        anchorAA="*",
                        anchorPos=sequences,
                        mart=mart,
                        upstreamOffset=7,
                        downstreamOffset=7)
}

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(dagLogo)
Loading required package: biomaRt
Loading required package: grImport
Loading required package: grid
Loading required package: XML
Loading required package: motifStack
Loading required package: MotIV
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


Attaching package: 'MotIV'

The following object is masked from 'package:stats':

    filter

Loading required package: ade4

Attaching package: 'ade4'

The following object is masked from 'package:BiocGenerics':

    score

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
> png(filename="/home/ddbj/snapshot/RGM3/R_BC/result/dagLogo/fetchSequence.Rd_%03d_medium.png", width=480, height=480)
> ### Name: fetchSequence
> ### Title: fetch sequence by id
> ### Aliases: fetchSequence
> ### Keywords: misc
> 
> ### ** Examples
> 
> #if(interactive()){
>     mart <- useMart("ensembl", "dmelanogaster_gene_ensembl")
>     dat <- read.csv(system.file("extdata", "dagLogoTestData.csv", package="dagLogo"))
>     seq <- fetchSequence(as.character(dat$entrez_geneid[1:5]), 
+                 anchorPos=as.character(dat$NCBI_site[1:5]), 
+                 mart=mart, 
+                 upstreamOffset=7, 
+                 downstreamOffset=7)
>     ## sample: use sequence as anchorPos
>     sequences <- seq@peptides
>     sequences[, 8] <- "k"
>     sequences <- apply(sequences, 1, paste, collapse="")
>     seq <- fetchSequence(as.character(seq@data$IDs),
+                         anchorAA="k",
+                         anchorPos=sequences,
+                         mart=mart,
+                         upstreamOffset=7,
+                         downstreamOffset=7)
>     ## sample: use sequence as anchorPos 2
>     sequences <- cbind(seq@peptides[, 1:8], "*", seq@peptides[, 9:15])
>     sequences <- apply(sequences, 1, paste, collapse="")
>     seq <- fetchSequence(as.character(seq@data$IDs),
+                         anchorAA="*",
+                         anchorPos=sequences,
+                         mart=mart,
+                         upstreamOffset=7,
+                         downstreamOffset=7)
> #}
> 
> 
> 
> 
> 
> dev.off()
null device 
          1 
>