@@ -1,6 +1,6 @@

 Package: CNEr 

-Version: 1.11.2

-Date: 2016-10-19

+Version: 1.11.3

+Date: 2016-10-25

 Title: CNE Detection and Visualization

 Description: Large-scale identification and advanced visualization 

              of sets of conserved noncoding elements.

@@ -25,7 +25,8 @@ Imports: Biostrings (>= 2.33.4),

          poweRlaw (>= 0.60.3),

          annotate (>= 1.50.0),

          GO.db (>= 3.3.0),

-         R.utils (>= 2.3.0)

+         R.utils (>= 2.3.0),

+         KEGGREST (>= 1.14.0)

 Depends: R (>= 3.2.2)

 Suggests: Gviz (>= 1.7.4),

           BiocStyle,

@@ -66,4 +67,5 @@ Collate:

         WholeGenomeAlignment.R

         Ancora.R

         CNE-methods.R

-        GO.R

\ No newline at end of file

+        GO.R

+        KEGG.R

\ No newline at end of file

@@ -62,6 +62,7 @@ importFrom(GO.db, GOCCANCESTOR, GOCCOFFSPRING, GOCCCHILDREN,

                   GOMFANCESTOR, GOMFOFFSPRING, GOMFCHILDREN)

 importFrom("grDevices", "jpeg", "pdf", "png", "postscript")

 importFrom(R.utils, gunzip, gzip)

+importFrom(KEGGREST, keggGet)

 ### -----------------------------------------------------------------

 ### Export S4 classes defined in CNEr

@@ -1,3 +1,9 @@

+CHANGES IN Bioc 3.5

+------------------------

+NEW FEATURES

+    o Add function orgKEGGIds2EntrezIDs to fetch the mapping between KEGG IDs

+      and Entrez IDs

+    

 CHANGES IN Bioc 3.4

 ------------------------

 NEW FEATURES

new file mode 100644

@@ -0,0 +1,53 @@

+### -----------------------------------------------------------------

+### orgKEGGIds2EntrezIDs: This script is supposed to parse the html page of 

+###              certain species's pathway from KEGG and 

+###              download the associated information for each KEGG pathway ID.

+### Exported!

+orgKEGGIds2EntrezIDs <- function(organism="Homo sapiens"){

+  ## Species mapping

+  organismMapping <- read.table("http://rest.kegg.jp/list/organism",

+                                header=FALSE, sep="\t", quote="",

+                                comment.char="")

+  organismID <- organismMapping[grepl(organism, organismMapping$V3,

+                                      ignore.case=TRUE),

+                                2, drop=TRUE]

+  if(length(organismID) == 0L){

+    stop("The provided organism is not available.",

+         "Please refer to http://rest.kegg.jp/list/organism for available",

+         "organisms")

+  }

+  html <- readLines(paste0("http://www.genome.jp/kegg-bin/show_organism?menu_type=pathway_maps&org=", organismID))

+  html <- grep("^\\d{5}&", html, value=TRUE)

+  ### Hopefully the ID is always 5-digit

+  pathwayIDs <- paste0(organismID, substr(html, 1L, 5L))

+  groups <- sample(rep_len(1L:ceiling(length(pathwayIDs) / 10),

+                           length.out=length(pathwayIDs)))

+  pathwayIDs <- split(pathwayIDs, groups)

+  

+  ## query with KEGG Rest server with 10 entries (maximal) a time, 

+  ## and 200s to 400s gap between each query.

+  query <- lapply(pathwayIDs,

+                  function(x){Sys.sleep(sample(200L:400L, size=1L));keggGet(x)})

+  

+  ## re-organise the query object

+  pathways <- list()

+  for(i in 1:length(query)){

+    for(j in 1:length(query[[i]])){

+      pathways[[query[[i]][[j]]$ENTRY]] <-

+        query[[i]][[j]]

+    }

+  }

+  ## Get the Pathway IDs to Entrez Gene IDs mapping

+  pathwayIDs2GeneIDs <- list()

+  for(i in 1:length(pathways)){

+    genesInfo <- pathways[[i]]$GENE

+    if(is.null(genesInfo)){

+      pathwayIDs2GeneIDs[[pathways[[i]]$ENTRY]] <- NA

+      next

+    }

+    pathwayIDs2GeneIDs[[pathways[[i]]$ENTRY]] <-

+      genesInfo[seq(1, length(genesInfo), by=2)]

+  }

+  pathwayIDs2GeneIDs <- pathwayIDs2GeneIDs[!is.na(pathwayIDs2GeneIDs)]

+  return(pathwayIDs2GeneIDs)

+}

\ No newline at end of file

new file mode 100644

@@ -0,0 +1,31 @@

+\name{orgKEGGIds2EntrezIDs}

+\alias{orgKEGGIds2EntrezIDs}

+\title{

+  Fetch mapping from KEGG IDs to Entrez IDs

+}

+\description{

+  Given the desired organism name, fetch the mapping between KEGG IDs and Entrez

+  gene IDs.

+}

+\usage{

+  orgKEGGIds2EntrezIDs(organism="Homo sapiens")

+}

+

+\arguments{

+  \item{organism}{

+    \code{character}(1): the name of prganism to query. It has to be available

+    at http://rest.kegg.jp/list/organism.

+  }

+}

+\value{

+  A \code{list} of Entrez gene IDs with KEGG IDs as names.

+}

+\author{

+  Ge Tan

+}

+

+\examples{

+  \donttest{

+    orgKEGGIds2EntrezIDs(organism="Homo sapiens")

+  }

+}

\ No newline at end of file