[BioC] AnnBuilder links to unigene

[Margaret Gardiner-Garden]

Hi,

I am using AnnBuilder for the first time and am having trouble getting
GenBank identifiers to find LocusLink and Unigene IDs from the NCBI server.
The error I get is

Failed to create a data connection
Error in readURL(infoUrl) : Can't read from url:
ftp://ftp.ncbi.nih.gov/repository/UniGene/Hs.info

I have checked that I can access this site using my browser (outside the
AnnBuilder program).

I tried using the data sets in the "How to use AnnBuilder tutorial" and got
the same error.

When I tried to leave out unigene and just go for locuslink on the NCBI
server I got a different error
Error in toupper(x) : non-character argument to toupper()

I have put a text version of my session using the tutorial data below.

I was wondering if anyone might have any idea where I am going wrong. Any
help would be greatly appreciated!

Thanks
Marg Gardiner-Garden (Garvan Institue of Medical Research)



read.table(file.path(.path.package("AnnBuilder"),"data", "thgu95a"),
sep="\t", header= FALSE, as.is=TRUE)

          V1       V2
1 32468_f_at   D90278
2   32469_at   L00693
3   32481_at AL031663
4   33825_at   X68733
5   35730_at   X03350
6   36512_at   L32179
7   38912_at   D90042
8   38936_at   M16652
9   39368_at AL031668

myBase <- file.path(.path.package("AnnBuilder"), "data", "thgu95a")

myBase #[1] "C:/PROGRA~1/R/RW1090~1/library/AnnBuilder/data/thgu95a"

myBaseType <- "gb" #this was the second column in the file



mySrcUrls <-
c(LL="http://www.bioconductor.org/datafiles/wwwsources/T11_tmp1.gz",
UG="http://www.bioconductor.org/datafiles/wwwsources/Ths.data.gz",
GO="http://www.bioconductor.org/datafiles/wwwsources/Tgo.xml")


read.table(file.path(.path.package("AnnBuilder"), "data", "srca"), sep="\t",
header=FALSE,  as.is=TRUE)
	#          V1   V2
	#1 32468_f_at   NA
	#2   32469_at    2
	#3   32481_at   NA
	#4   33825_at    9
	#5   35730_at 1576r
	#6   36512_at   NA
	#7   38912_at   10
	#8   38936_at   NA
	#9   39368_at   NA


read.table(file.path(.path.package("AnnBuilder"), "data", "srcb"), sep="\t",
header=FALSE,  as.is=TRUE)

          V1   V2
	#1 32468_f_at   NA
	#2   32469_at   NA
	#3   32481_at 7051
	#4   33825_at   NA
	#5   35730_at   NA
	#6   36512_at 1084
	#7   38912_at   NA
	#8   38936_at   NA
	#   39368_at   89

myOtherSrc <- c(srcone=file.path(.path.package("AnnBuilder"), "data",
"srca"), srctwo= file.path(.path.package("AnnBuilder"), "data", "srcb"))

myOtherSrc

 	#                                              srcone
#                  srctwo
	#"C:/PROGRA~1/R/RW1090~1/library/AnnBuilder/data/srca"
"C:/PROGRA~1/R/RW1090~1/	 #library/AnnBuilder/data/srcb"

myDir <- tempdir()

myDir #[1] "C:\\DOCUME~1\\margar\\LOCALS~1\\Temp\\Rtmp23936"



if (.Platform$OS.type !="windows"){
ABPkgBuilder(baseName=myBase, srcUrls= mySrcUrls, baseMapType= myBaseType,
otherSrc= myOtherSrc, pkgName ="myPkg", pkgPath=myDir, organism="human",
version ="1.9.0", makeXML= TRUE, author=list(author="MGG",
maintainer="m.gardiner-garden at garvan.org.au"),fromWeb= TRUE)
}

	#didn't seem to process so tried without the if statement


	#The folder "C:\\DOCUME~1\\margar\\LOCALS~1\\Temp\\Rtmp23936" existed but
there 	 	#was no myPkg in it



ABPkgBuilder(baseName=myBase, srcUrls= mySrcUrls, baseMapType= myBaseType,
otherSrc= myOtherSrc, pkgName ="myPkg", pkgPath=myDir, organism="human",
version ="1.9.0", makeXML= TRUE, author=list(author="MGG",
maintainer="m.gardiner-garden at garvan.org.au"),fromWeb= TRUE)

	#[1] "It may take me a while to process the data. Be patient!"
	#Warning message:
	#Failed to create a data connection
	#Error in readURL(infoUrl) : Can't read from url: ftp://ftp.ncbi.nih.gov/
#repository/UniGene/Hs.info



	#Try it without the unigene (ie just getting LocusLink from NCBI)

mySrcUrls <- getSrcUrl(src = "LL", organism = "human", xml = TRUE, dateOnly
= FALSE)

mySrcUrls
	#[1] "ftp://ftp.ncbi.nih.gov/refseq/LocusLink/LL_tmpl.gz"



ABPkgBuilder(baseName=myBase, srcUrls= mySrcUrls, baseMapType= myBaseType,
otherSrc= myOtherSrc, pkgName ="myPkg", pkgPath=myDir, organism="human",
version ="1.9.0", makeXML= TRUE, author=list(author="MGG",
maintainer="m.gardiner-garden at garvan.org.au"),fromWeb= TRUE)


	#[1] "It may take me a while to process the data. Be patient!"
	#Error in toupper(x) : non-character argument to toupper()