如何为affymetrix exon array chip创建一个R下的annotation package

probeset<-read.csv("MoEx-1_0-st-v1/MoEx-1_0-st-v1.na31.mm9.probeset.csv",comment.char="#")
#所有的genbank号都可以在gene_assignment中找到。在gene_assignment中，有两种分隔符，“///”以及"//"
#///用于分隔不同的注释行 //用于分隔一行内不同的注释内容。其中genbank号在注释行的第一格。
probeset<-probeset[,c("probeset_id","gene_assignment")]
gc()
genbank<-as.character(probeset$gene_assignment)
genbank<-strsplit(genbank,"///")
names(genbank)<-probeset$probeset_id
genbank<-sapply(genbank,function(x){x<-gsub(" ","",x); x<-do.call(rbind,sapply(x,strsplit,"//")); x[,1]})
#下面将genbank变成一对一的列表，需要使用yapply
yapply<-function(X,FUN, ...) { 
  index <- seq(length.out=length(X)) 
  namesX <- names(X) 
  if(is.null(namesX)) namesX <- rep(NA,length(X))
 
  FUN <- match.fun(FUN) 
  fnames <- names(formals(FUN)) 
  if( ! "INDEX" %in% fnames ){ 
    formals(FUN) <- append( formals(FUN), alist(INDEX=) )   } 
  if( ! "NAMES" %in% fnames ){ 
    formals(FUN) <- append( formals(FUN), alist(NAMES=) )   } 
  mapply(FUN,X,INDEX=index, NAMES=namesX,MoreArgs=list(...)) }
 
genbank<-yapply(genbank,function(.ele){cbind(rep(NAMES,length(.ele)),.ele)})
genbank<-do.call(rbind,genbank)
colnames(genbank)<-c("probeset_id","genbank")
rownames(genbank)<-1:nrow(genbank)
#因为其中夹杂着有ensembl id，所以需要把这些号转换成genbank id，这里使用biomaRt来完成转换
ensembl_t_ids<-genbank[grepl("^ENS",genbank[,2]),2]
library(biomaRt)
ensembl = useMart("ensembl")
ensembl = useDataset("mmusculus_gene_ensembl",mart=ensembl)
access<-getBM(attributes = c("ensembl_transcript_id","ox_refseq_mrna__dm_dbprimary_acc_1074"), filters = "ensembl_transcript_id",values=ensembl_t_ids,mart=ensembl)
access<-merge(genbank,access,by.x="genbank",by.y="ensembl_transcript_id")
access<-access[,c(2,3)]
colnames(access)<-colnames(genbank)
genbank<-rbind(genbank[!grepl("^ENS",genbank[,2]),],access)

genbank<-genbank[genbank[,2]!="---",]
genbank<-genbank[genbank[,2]!="",]
genbank<-unique(genbank)
write.table(genbank, file = "MoEx-1_0-st-v1_probeset.txt", sep = "\t", col.names = F, row.names=F, qmethod = "double")

library(AnnotationDbi)
source("http://bioconductor.org/biocLite.R")
biocLite("mouse.db0")
Infile <- "MoEx-1_0-st-v1_probeset.txt"
OutDir <- "where-you-want-to-save-your-package"
library(org.Mm.eg.db)
makeDBPackage("MOUSECHIP_DB",
              affy = FALSE,
              prefix = "moex10stv1probeset",
              fileName = Infile,
              outputDir=OutDir,
              baseMapType = "gbNRef",
              version = "1.0.0",
              manufacturer = "Affymetrix",
              chipName = "moex10stv1",
              manufacturerUrl = "http://www.affymetrix.com",
              author = "Jianhong Ou",
              maintainer = "qiuworld.com")