@@ -1,7 +1,7 @@

 Package: methylGSA

 Type: Package

 Title: methylGSA: Gene Set Analysis Using the Outcome of Differential Methylation

-Version: 0.99.11

+Version: 0.99.12

 Authors@R: c(

     person("Xu", "Ren", 

         email = "[email protected]", role = c("aut", "cre")),

@@ -17,7 +17,6 @@ Imports:

     RobustRankAggreg,

     stringr,

     stats,

-    minfi,

     clusterProfiler,

     missMethyl,

     org.Hs.eg.db,

@@ -1,8 +1,10 @@

 # Generated by roxygen2: do not edit by hand

+export(getGS)

 export(methylRRA)

 export(methylglm)

 export(methylgometh)

+export(prepareAnnot)

 import(IlluminaHumanMethylation450kanno.ilmn12.hg19)

 import(IlluminaHumanMethylationEPICanno.ilm10b2.hg19)

 import(RobustRankAggreg)

@@ -11,7 +13,6 @@ import(reactome.db)

 import(stats)

 importFrom(AnnotationDbi,select)

 importFrom(clusterProfiler,GSEA)

-importFrom(minfi,getAnnotation)

 importFrom(missMethyl,gometh)

 importFrom(missMethyl,gsameth)

 importFrom(stringr,str_length)

@@ -1,3 +1,6 @@

+# methylGSA 0.99.10 

+* Support user-supplied mapping between CpGs and Genes

+

 # methylGSA 0.99.7  

 * Development version   

 * Changed package name to methylGSA

@@ -5,7 +5,6 @@

 #' @import IlluminaHumanMethylation450kanno.ilmn12.hg19

 #' @import IlluminaHumanMethylationEPICanno.ilm10b2.hg19

 #' @importFrom stringr str_length

-#' @importFrom minfi getAnnotation

 #' @details The implementation of the function is modified

 #' from .flattenAnn function in missMethyl package.

 #' @return A data frame contains CpG IDs and gene symbols.

@@ -20,13 +19,9 @@

 getAnnot = function(array.type){

     if(array.type=="450K")

-        FullAnnot = getAnnotation(

-            IlluminaHumanMethylation450kanno.ilmn12.hg19

-            ::IlluminaHumanMethylation450kanno.ilmn12.hg19)

+        FullAnnot = getAnnotation(IlluminaHumanMethylation450kanno.ilmn12.hg19)

     else

-        FullAnnot = getAnnotation(

-            IlluminaHumanMethylationEPICanno.ilm10b2.hg19

-            ::IlluminaHumanMethylationEPICanno.ilm10b2.hg19)

+        FullAnnot = getAnnotation(IlluminaHumanMethylationEPICanno.ilm10b2.hg19)

     FullAnnot = FullAnnot[,c("Name","UCSC_RefGene_Name")]

     FullAnnot = FullAnnot[str_length(rownames(FullAnnot))==10,]

@@ -1,8 +1,10 @@

 #' @title Get Gene Sets

 #'

 #' @description This function gets gene sets information.

-#' @param geneids A vector contains all gene ids of interest.

+#' @param geneids A vector contains all gene ids of interest. Gene ids should

+#' be gene symbol.

 #' @param GS.type A string. "GO", "KEGG", or "Reactome".

+#' @export

 #' @import org.Hs.eg.db

 #' @import reactome.db

 #' @importFrom AnnotationDbi select

@@ -12,22 +14,26 @@

 #' Genome wide annotation for Human. R package version 3.5.0.

 #' @references Ligtenberg W (2017). reactome.db:

 #' A set of annotation maps for reactome. R package version 1.62.0.

+#' @examples

+#' geneids = c("FKBP5", "NDUFA1", "STAT5B")

+#' GO.list = getGS(geneids, "KEGG")

+#' head(GO.list)

 getGS = function(geneids, GS.type){

-    message("retrieving", GS.type, "sets...")

+    message("retrieving ", GS.type, " sets...")

     if(GS.type == "KEGG")

         GS.type = "PATH"

     if(GS.type == "Reactome"){

         ## first convert id to entrezid to use reactome.db

         gene.entrez = suppressMessages(

             select(org.Hs.eg.db, geneids,

-                   columns = "ENTREZID",keytype = "SYMBOL")$ENTREZID)

+                        columns = "ENTREZID",keytype = "SYMBOL")$ENTREZID)

         GOdf = suppressMessages(

             select(reactome.db, gene.entrez,

-                   columns = "REACTOMEID", keytype = "ENTREZID"))

+                        columns = "REACTOMEID", keytype = "ENTREZID"))

         genesymbol = suppressMessages(

             select(org.Hs.eg.db, GOdf$ENTREZID,

-                   columns = "SYMBOL", keytype = "ENTREZID")$SYMBOL)

+                        columns = "SYMBOL", keytype = "ENTREZID")$SYMBOL)

         GS.type = "REACTOMEID"

     }

@@ -35,7 +41,7 @@ getGS = function(geneids, GS.type){

         GOs = suppressMessages(

             na.omit(unique(

                 select(org.Hs.eg.db, geneids,

-                       GS.type,keytype = "SYMBOL")[,GS.type])))

+                            GS.type,keytype = "SYMBOL")[,GS.type])))

         GOdf = suppressMessages(

             select(org.Hs.eg.db, GOs, "SYMBOL", keytype = GS.type))

         genesymbol = GOdf$SYMBOL

@@ -6,9 +6,9 @@

 #' @param cpg.pval A named vector containing p-values of differential

 #' methylation test. Names should be CpG IDs.

 #' @param array.type A string. Either "450K" or "EPIC". Default is "450K".

-#' This argument will be ignore if CpG2Gene is provided.

-#' @param CpG2Gene A matrix or data frame with 1st column CpG ID and 2nd

-#' column gene name. Default is NULL.

+#' This argument will be ignored if FullAnnot is provided.

+#' @param FullAnnot A data frame provided by prepareAnnot function.

+#' Default is NULL.

 #' @param method A string. "ORA" or "GSEA". Default is "ORA"

 #' @param GS.list A list. Default is NULL. If there is no input list,

 #' Gene Ontology is used. Entry names are gene sets names, and elements

@@ -42,11 +42,12 @@

 #' data(cpgtoy)

 #' data(GSlisttoy)

 #' GS.list = GS.list[1:10]

-#' res1 = methylRRA(cpg.pval = cpg.pval, CpG2Gene = CpG2Gene,

+#' FullAnnot = prepareAnnot(CpG2Gene)

+#' res1 = methylRRA(cpg.pval = cpg.pval, FullAnnot = FullAnnot,

 #' method = "ORA", GS.list = GS.list)

 #' head(res1)

-methylRRA <- function(cpg.pval, array.type = "450K", CpG2Gene = NULL,

+methylRRA <- function(cpg.pval, array.type = "450K", FullAnnot = NULL,

                             method = "ORA", GS.list=NULL, GS.idtype = "SYMBOL",

                             GS.type = "GO", minsize = 100, maxsize = 500){

     if(!is.vector(cpg.pval) | !is.numeric(cpg.pval) | is.null(names(cpg.pval)))

@@ -64,18 +65,7 @@ methylRRA <- function(cpg.pval, array.type = "450K", CpG2Gene = NULL,

                         keytype = GS.idtype)$SYMBOL))

     GS.type = match.arg(GS.type, c("GO", "KEGG", "Reactome"))

-    if(!is.null(CpG2Gene)){

-        if(!is.character(CpG2Gene[,1])|!is.character(CpG2Gene[,2]))

-            stop("CpG2Gene should be a matrix or data frame with

-                    1st column CpG ID and 2nd column gene name")

-        if(ncol(CpG2Gene)!=2)

-            stop("CpG2Gene should contain two columns")

-        FullAnnot = data.frame(CpG2Gene)

-        colnames(FullAnnot) = c("Name", "UCSC_RefGene_Name")

-        rownames(FullAnnot) = FullAnnot$Name

-    }

-

-    else{

+    if(is.null(FullAnnot)){

         if(array.type!="450K" & array.type!="EPIC")

             stop("Input array type should be either 450K or EPIC")

         if(array.type=="450K")

@@ -6,9 +6,9 @@

 #' @param cpg.pval A named vector containing p-values of differential

 #' methylation test. Names should be CpG IDs.

 #' @param array.type A string. Either "450K" or "EPIC". Default is "450K".

-#' This argument will be ignore if CpG2Gene is provided.

-#' @param CpG2Gene A matrix or data frame with 1st column CpG ID and 2nd

-#' column gene name. Default is NULL.

+#' This argument will be ignored if FullAnnot is provided.

+#' @param FullAnnot A data frame provided by prepareAnnot function.

+#' Default is NULL.

 #' @param GS.list A list. Default is NULL. If there is no input list,

 #' Gene Ontology is used. Entry names are gene sets names, and elements

 #' correpond to genes that gene sets contain.

@@ -39,11 +39,12 @@

 #' data(cpgtoy)

 #' data(GSlisttoy)

 #' GS.list = GS.list[1:10]

-#' res = methylglm(cpg.pval = cpg.pval, CpG2Gene = CpG2Gene, GS.list = GS.list,

-#' GS.idtype = "SYMBOL")

+#' FullAnnot = prepareAnnot(CpG2Gene)

+#' res = methylglm(cpg.pval = cpg.pval, FullAnnot = FullAnnot,

+#' GS.list = GS.list, GS.idtype = "SYMBOL")

 #' head(res)

-methylglm <- function(cpg.pval, array.type = "450K", CpG2Gene = NULL,

+methylglm <- function(cpg.pval, array.type = "450K", FullAnnot = NULL,

                             GS.list=NULL, GS.idtype = "SYMBOL", GS.type = "GO",

                             minsize = 100, maxsize = 500){

     if(!is.vector(cpg.pval) | !is.numeric(cpg.pval) | is.null(names(cpg.pval)))

@@ -62,18 +63,7 @@ methylglm <- function(cpg.pval, array.type = "450K", CpG2Gene = NULL,

                             keytype = GS.idtype)$SYMBOL))

     GS.type = match.arg(GS.type, c("GO", "KEGG", "Reactome"))

-    if(!is.null(CpG2Gene)){

-        if(!is.character(CpG2Gene[,1])|!is.character(CpG2Gene[,2]))

-            stop("CpG2Gene should be a matrix or data frame with

-                    1st column CpG ID and 2nd column gene name")

-        if(ncol(CpG2Gene)!=2)

-            stop("CpG2Gene should contain two columns")

-        FullAnnot = data.frame(CpG2Gene)

-        colnames(FullAnnot) = c("Name", "UCSC_RefGene_Name")

-        rownames(FullAnnot) = FullAnnot$Name

-    }

-

-    else{

+    if(is.null(FullAnnot)){

         if(array.type!="450K" & array.type!="EPIC")

             stop("Input array type should be either 450K or EPIC")

         if(array.type=="450K")

@@ -11,7 +11,7 @@

 #' Gene Ontology is used. Entry names are gene sets names, and elements

 #' correpond to genes that gene sets contain.

 #' @param GS.idtype A string. "SYMBOL", "ENSEMBL", "ENTREZID" or "REFSEQ".

-#' Default is "SYMBOL"

+#' Default is "SYMBOL".

 #' @param GS.type A string. "GO", "KEGG", or "Reactome"

 #' @param minsize An integer. If the number of genes in a gene set

 #' is less than this integer, this gene set is not tested. Default is 100.

@@ -34,11 +34,13 @@

 #' @references Carlson M (2017). org.Hs.eg.db: Genome wide annotation

 #' for Human. R package version 3.5.0.

 #' @examples

+#' \dontrun{

 #' library(IlluminaHumanMethylation450kanno.ilmn12.hg19)

 #' data(cpgtoy)

 #' res = methylgometh(cpg.pval = cpg.pval, sig.cut = 0.001, GS.type = "KEGG",

 #' minsize = 200, maxsize = 205)

 #' head(res)

+#' }

 methylgometh <- function(cpg.pval, sig.cut, array.type = "450K",

new file mode 100644

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

+#' @title Prepare user-supplied mapping between CpGs and genes.

+#'

+#' @description This function prepares CpG to gene mapping which will be

+#' used by methylRRA and methylglm.

+#' @param CpG2Gene A matrix, or a data frame or a list contains CpG to gene

+#' mapping. For a matrix or data frame, 1st column should be CpG ID and 2nd

+#' column should be gene name. For a list, entry names should be gene names,

+#' and elements correpond to CpG IDs.

+#' @param geneidtype A string. "SYMBOL", "ENSEMBL", "ENTREZID" or "REFSEQ".

+#' Default is "SYMBOL".

+#' @export

+#' @import org.Hs.eg.db

+#' @importFrom AnnotationDbi select

+#' @return A data frame contains ready to use CpG to gene mapping.

+#' @references Carlson M (2017). org.Hs.eg.db:

+#' Genome wide annotation for Human. R package version 3.5.0.

+#' @examples

+#' data(CpG2Genetoy)

+#' FullAnnot = prepareAnnot(CpG2Gene)

+#' head(FullAnnot)

+

+prepareAnnot <- function(CpG2Gene, geneidtype = "SYMBOL"){

+    geneidtype = match.arg(

+        geneidtype,c("SYMBOL", "ENSEMBL", "ENTREZID", "REFSEQ"))

+

+    if(is.matrix(CpG2Gene)|is.data.frame(CpG2Gene)){

+        if(!is.character(CpG2Gene[,1]))

+            stop("CpG ID should be characters")

+        if(ncol(CpG2Gene)!=2)

+            stop("CpG2Gene should contain two columns")

+        FullAnnot = data.frame(CpG2Gene)

+    }

+    else if(is.list(CpG2Gene)){

+        FullAnnot = data.frame(

+            CpG = unlist(CpG2Gene),

+            gene = rep(names(CpG2Gene),vapply(CpG2Gene, length, FUN.VALUE = 0)))

+    }

+    else

+        stop("CpG2Gene should be a matrix or a data frame or a list.")

+

+    colnames(FullAnnot) = c("Name", "UCSC_RefGene_Name")

+

+    if(geneidtype!="SYMBOL"){

+        temp = suppressMessages(

+            select(org.Hs.eg.db, FullAnnot$UCSC_RefGene_Name,

+                        columns = "SYMBOL",keytype = geneidtype))

+        FullAnnot$UCSC_RefGene_Name = temp$SYMBOL

+    }

+    rownames(FullAnnot) = FullAnnot$Name

+    return(FullAnnot)

+}

+

+

@@ -19,6 +19,7 @@ NULL

 #' @keywords datasets

 NULL

+

 #' @title An example of user user-supplied mapping between CpGs and genes

 #'

 #' @description An example of user user-supplied mapping between CpGs and genes

Binary files a/data/CpG2Genetoy.RData and b/data/CpG2Genetoy.RData differ

@@ -13,6 +13,7 @@ FullAnnot$UCSC_RefGene_Name = temp

 colnames(FullAnnot) = c("CpG", "Gene")

 rownames(FullAnnot) = NULL

 CpG2Gene = FullAnnot

+CpG2Gene = data.frame(CpG2Gene)

 save(CpG2Gene, file = 'data/CpG2Genetoy.RData', compress = 'xz')

@@ -7,7 +7,8 @@

 getGS(geneids, GS.type)

 }

 \arguments{

-\item{geneids}{A vector contains all gene ids of interest.}

+\item{geneids}{A vector contains all gene ids of interest. Gene ids should

+be gene symbol.}

 \item{GS.type}{A string. "GO", "KEGG", or "Reactome".}

 }

@@ -18,6 +19,11 @@ interest and their corresponding genes.

 \description{

 This function gets gene sets information.

 }

+\examples{

+geneids = c("FKBP5", "NDUFA1", "STAT5B")

+GO.list = getGS(geneids, "KEGG")

+head(GO.list)

+}

 \references{

 Carlson M (2017). org.Hs.eg.db:

 Genome wide annotation for Human. R package version 3.5.0.

@@ -5,7 +5,7 @@

 \title{Enrichment analysis after adjusting multiple p-values of

 each gene by Robust Rank Aggregation}

 \usage{

-methylRRA(cpg.pval, array.type = "450K", CpG2Gene = NULL, method = "ORA",

+methylRRA(cpg.pval, array.type = "450K", FullAnnot = NULL, method = "ORA",

   GS.list = NULL, GS.idtype = "SYMBOL", GS.type = "GO", minsize = 100,

   maxsize = 500)

 }

@@ -14,10 +14,10 @@ methylRRA(cpg.pval, array.type = "450K", CpG2Gene = NULL, method = "ORA",

 methylation test. Names should be CpG IDs.}

 \item{array.type}{A string. Either "450K" or "EPIC". Default is "450K".

-This argument will be ignore if CpG2Gene is provided.}

+This argument will be ignored if FullAnnot is provided.}

-\item{CpG2Gene}{A matrix or data frame with 1st column CpG ID and 2nd

-column gene name. Default is NULL.}

+\item{FullAnnot}{A data frame provided by prepareAnnot function.

+Default is NULL.}

 \item{method}{A string. "ORA" or "GSEA". Default is "ORA"}

@@ -48,7 +48,8 @@ data(CpG2Genetoy)

 data(cpgtoy)

 data(GSlisttoy)

 GS.list = GS.list[1:10]

-res1 = methylRRA(cpg.pval = cpg.pval, CpG2Gene = CpG2Gene,

+FullAnnot = prepareAnnot(CpG2Gene)

+res1 = methylRRA(cpg.pval = cpg.pval, FullAnnot = FullAnnot,

 method = "ORA", GS.list = GS.list)

 head(res1)

 }

@@ -5,7 +5,7 @@

 \title{Implement logistic regression adjusting

 for number of probes in enrichment analysis}

 \usage{

-methylglm(cpg.pval, array.type = "450K", CpG2Gene = NULL, GS.list = NULL,

+methylglm(cpg.pval, array.type = "450K", FullAnnot = NULL, GS.list = NULL,

   GS.idtype = "SYMBOL", GS.type = "GO", minsize = 100, maxsize = 500)

 }

 \arguments{

@@ -13,10 +13,10 @@ methylglm(cpg.pval, array.type = "450K", CpG2Gene = NULL, GS.list = NULL,

 methylation test. Names should be CpG IDs.}

 \item{array.type}{A string. Either "450K" or "EPIC". Default is "450K".

-This argument will be ignore if CpG2Gene is provided.}

+This argument will be ignored if FullAnnot is provided.}

-\item{CpG2Gene}{A matrix or data frame with 1st column CpG ID and 2nd

-column gene name. Default is NULL.}

+\item{FullAnnot}{A data frame provided by prepareAnnot function.

+Default is NULL.}

 \item{GS.list}{A list. Default is NULL. If there is no input list,

 Gene Ontology is used. Entry names are gene sets names, and elements

@@ -49,8 +49,9 @@ data(CpG2Genetoy)

 data(cpgtoy)

 data(GSlisttoy)

 GS.list = GS.list[1:10]

-res = methylglm(cpg.pval = cpg.pval, CpG2Gene = CpG2Gene, GS.list = GS.list,

-GS.idtype = "SYMBOL")

+FullAnnot = prepareAnnot(CpG2Gene)

+res = methylglm(cpg.pval = cpg.pval, FullAnnot = FullAnnot,

+GS.list = GS.list, GS.idtype = "SYMBOL")

 head(res)

 }

 \references{

@@ -21,7 +21,7 @@ Gene Ontology is used. Entry names are gene sets names, and elements

 correpond to genes that gene sets contain.}

 \item{GS.idtype}{A string. "SYMBOL", "ENSEMBL", "ENTREZID" or "REFSEQ".

-Default is "SYMBOL"}

+Default is "SYMBOL".}

 \item{GS.type}{A string. "GO", "KEGG", or "Reactome"}

@@ -39,12 +39,14 @@ This function calls gometh or gsameth function

 in missMethyl package to adjust number of probes in gene set testing

 }

 \examples{

+\dontrun{

 library(IlluminaHumanMethylation450kanno.ilmn12.hg19)

 data(cpgtoy)

 res = methylgometh(cpg.pval = cpg.pval, sig.cut = 0.001, GS.type = "KEGG",

 minsize = 200, maxsize = 205)

 head(res)

 }

+}

 \references{

 Phipson, B., Maksimovic, J., and Oshlack, A. (2015).

 missMethyl: an R package for analysing methylation data from Illuminas

new file mode 100644

@@ -0,0 +1,33 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/prepareAnnot.R

+\name{prepareAnnot}

+\alias{prepareAnnot}

+\title{Prepare user-supplied mapping between CpGs and genes.}

+\usage{

+prepareAnnot(CpG2Gene, geneidtype = "SYMBOL")

+}

+\arguments{

+\item{CpG2Gene}{A matrix, or a data frame or a list contains CpG to gene

+mapping. For a matrix or data frame, 1st column should be CpG ID and 2nd

+column should be gene name. For a list, entry names should be gene names,

+and elements correpond to CpG IDs.}

+

+\item{geneidtype}{A string. "SYMBOL", "ENSEMBL", "ENTREZID" or "REFSEQ".

+Default is "SYMBOL".}

+}

+\value{

+A data frame contains ready to use CpG to gene mapping.

+}

+\description{

+This function prepares CpG to gene mapping which will be

+used by methylRRA and methylglm.

+}

+\examples{

+data(CpG2Genetoy)

+FullAnnot = prepareAnnot(CpG2Gene)

+head(FullAnnot)

+}

+\references{

+Carlson M (2017). org.Hs.eg.db:

+Genome wide annotation for Human. R package version 3.5.0.

+}

@@ -3,6 +3,13 @@ context("Test internal functions")

 library(org.Hs.eg.db)

 library(reactome.db)

 data(GSlisttoy)

+data(CpG2Genetoy)

+

+test_that("check prepareAnnot", {

+    colnames(CpG2Gene) = c("Name", "UCSC_RefGene_Name")

+    rownames(CpG2Gene) = CpG2Gene$Name

+    expect_identical(prepareAnnot(CpG2Gene), CpG2Gene)

+})

 test_that("check getGS", {

     geneids = GS.list[[1]]

@@ -28,7 +35,6 @@ test_that("check getGS", {

     expect_identical(getGS(geneids, "KEGG"), KEGG.list)

-

     gene.entrez = suppressMessages(

         select(org.Hs.eg.db, geneids,

                columns = "ENTREZID",keytype = "SYMBOL")$ENTREZID)

@@ -4,9 +4,10 @@ data(CpG2Genetoy)

 data(cpgtoy)

 data(GSlisttoy)

 GS.list = GS.list[1:10]

+FullAnnot = prepareAnnot(CpG2Gene)

 test_that("check for valid output", {

-    res1 = methylglm(cpg.pval = cpg.pval, CpG2Gene = CpG2Gene,

+    res1 = methylglm(cpg.pval = cpg.pval, FullAnnot = FullAnnot,

                      GS.list = GS.list, GS.idtype = "SYMBOL",

                      minsize = 100, maxsize = 300)

     expect_is(res1, 'data.frame')

@@ -15,7 +16,7 @@ test_that("check for valid output", {

     expect_true(all(res1$padj>=0 & res1$padj<=1))

     expect_true(all(colnames(res1) %in% c("ID", "size", "pvalue", "padj")))

-    res2 = methylRRA(cpg.pval = cpg.pval, CpG2Gene = CpG2Gene,

+    res2 = methylRRA(cpg.pval = cpg.pval, FullAnnot = FullAnnot,

                      method = "ORA", GS.list = GS.list)

     expect_is(res2, 'data.frame')

     expect_equal(dim(res2)[2], 4)

@@ -23,7 +24,7 @@ test_that("check for valid output", {

     expect_true(all(res2$padj>=0 & res2$padj<=1))

     expect_true(all(colnames(res2) %in% c("ID", "size", "pvalue", "padj")))

-    res3 = methylRRA(cpg.pval = cpg.pval, CpG2Gene = CpG2Gene,

+    res3 = methylRRA(cpg.pval = cpg.pval, FullAnnot = FullAnnot,

                      method = "GSEA", GS.list = GS.list)

     expect_is(res3, 'data.frame')

     expect_equal(dim(res3)[2], 7)

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

 ---

 title: "methylGSA: Gene Set Analysis for DNA Methylation Datasets"

-author: "Pei Fen Kuan and Xu Ren"

+author: "Xu Ren and Pei Fen Kuan"

 date: "`r Sys.Date()`"

 output: 

     rmarkdown::html_document:

@@ -42,7 +42,7 @@ weighted resampling and Wallenius non-central hypergeometric approximation.

 * Gene Ontology (via org.Hs.eg.db)

 * KEGG (via org.Hs.eg.db)

 * Reactome (via reactome.db)

-* User input gene sets. Supported input gene ID types:

+* User-supplied gene sets. Supported input gene ID types:

     + "SYMBOL"

     + "ENSEMBL"

     + "ENTREZID"

@@ -169,10 +169,10 @@ head(res4, 15)

 methylGSA provides many other options for users to customize the analysis. 

 * `array.type` is to specify which array type to use. It is either "450K" or 

-"EPIC". Default is "450K". This argument will be ignore if CpG2Gene is 

+"EPIC". Default is "450K". This argument will be ignored if `FullAnnot` is 

 provided.

-* `CpG2Gene` is user supplied mapping between CpG ID and gene. It should be 

-a matrix or data frame with 1st column CpG ID and 2nd column gene name.

+* `FullAnnot` is preprocessed mapping between CpG ID and gene name provided by

+prepareAnnot function. Default is NULL. Check example below for details. 

 * `GS.list` is user input gene sets to be tested. It should be a list with 

 entry names gene sets IDs and elements correpond to genes that gene sets 

 contain. If there is no input list, Gene Ontology is used.

@@ -197,17 +197,27 @@ data(GSlisttoy)

 head(lapply(GS.list, function(x) return(x[1:30])), 3)   

 ```

-This is an example of user-supplied CpG to gene mapping

+methylglm and methylRRA support user supplied CpG ID to gene mapping. The 

+mapping is expected to be a matrix, or a data frame or a list. For a 

+matrix or data frame, 1st column should be CpG ID and 2nd column should be gene 

+name. For a list, entry names should be gene names and elements correpond to 

+CpG IDs. This is an example of user-supplied CpG to gene mapping:

 ```{r}

 data(CpG2Genetoy)

 head(CpG2Gene)   

 ```

-Test the gene sets using "ORA" in methylRRA

+To use user supplied mapping in methylglm or methylRRA, first preprocess the

+mapping by prepareAnnot function

+```{r}

+FullAnnot = prepareAnnot(CpG2Gene) 

+```

+Test the gene sets using "ORA" in methylRRA, use `FullAnnot` argument to 

+provide the preprocessed CpG ID to gene mapping.

 ```{r}

 GS.list = GS.list[1:10]

-res5 = methylRRA(cpg.pval = cpg.pval, CpG2Gene = CpG2Gene, method = "ORA", 

+res5 = methylRRA(cpg.pval = cpg.pval, FullAnnot = FullAnnot, method = "ORA", 

                     GS.list = GS.list, GS.idtype = "SYMBOL", 

                     minsize = 100, maxsize = 300)

 head(res5, 10)