@@ -10,7 +10,6 @@ setGeneric("aggregate", function(x, ...)

                                     standardGeneric("aggregate"))

-

 #' Method filter

 #' 

 #' Wrapper to GMQL select function

@@ -56,7 +55,7 @@ setGeneric("collect", function(x, dir_out = getwd(), name = "ds1", ...)

 #' Method take

 #' 

-#' GMQL Operation: TAKE

+#' Wrapper to take function

 #' 

 #' @name take

 #' @rdname take-GMQLDataset-method

@@ -4,8 +4,9 @@

 #' Condition evaluation functions

 #'

-#' These functions is used to create a series of metadata as string

-#' that require evaluation on value.

+#' These functions is used to support joinBy and/or groupBy function parameter.

+#' It create a list of one element: matrix containing the two coloumn:

+#' type of condition evaluation and the metadata attribute

 #'

 #' \itemize{

 #' \item{FN: It defines a FULL (FULLNAME) evaluation of the input values.

@@ -149,8 +149,7 @@ setMethod("cover", "GMQLDataset",

-gmql_cover <- function(data, min_acc, max_acc, groupBy = NULL, 

-                            aggregates = NULL, flag)

+gmql_cover <- function(data, min_acc, max_acc, groupBy, aggregates, flag)

 {

     if(!is.null(groupBy))

@@ -68,8 +68,6 @@ execute <- function()

 #' Method collect

-#' 

-#' Wrapper to GMQL materialize function

 #'

 #' It saves the contents of a dataset that contains samples metadata and 

 #' samples regions.

@@ -62,7 +62,7 @@

 #' data <- read_dataset(test_path)

 #' join_data <- read_dataset(test_path2)

 #' jun_tf <- filter(data, antibody_target == "JUN", pValue < 0.01, 

-#' semijoin(join_data, TRUE, DF("cell")))

+#' semijoin(join_data, TRUE, list(DF("cell"))))

 #' 

 #' }

 #' 

@@ -130,8 +130,7 @@ gmql_select <- function(input_data, predicate, region_predicate, s_join)

 #' considering semi_join NOT IN semi_join_dataset, F => semijoin is performed 

 #' considering semi_join IN semi_join_dataset

 #' 

-#' @param ... Additional arguments for use in specific methods and functions 

-#' to define condition evaluation on metadata.

+#' @param groupBy it define condition evaluation on metadata.

 #' \itemize{

 #' \item{\code{\link{FN}}: Fullname evaluation, two attributes match 

 #' if they both end with value and, if they have a further prefixes,

@@ -162,13 +161,18 @@ gmql_select <- function(input_data, predicate, region_predicate, s_join)

 #' test_path2 <- system.file("example", "DATASET_GDM", package = "RGMQL")

 #' data <- read_dataset(test_path)

 #' join_data <-  read_dataset(test_path2)

-#' jun_tf <- filter(data,NULL,NULL, semijoin(join_data, TRUE, DF("cell")))

+#' jun_tf <- filter(data,NULL,NULL, semijoin(join_data, TRUE, 

+#' list(DF("cell"))))

 #' 

 #' @return semijoin condition as list

 #' @export

-semijoin <- function(data, not_in = FALSE, ...)

+semijoin <- function(data, not_in = FALSE, groupBy = NULL)

 {

-    semij_cond = list(...)

+    if(!is.list(groupBy))

+        stop("groupBy: must be a list")

+    

+    semij_cond = groupBy

+    

     if(is.null(data))

         stop("data cannot be NULL")

@@ -907,7 +907,7 @@ delete_dataset <- function(url,datasetName)

 #' @rdname download_dataset

 #' @export

 #'

-download_dataset <- function(url,datasetName,path = getwd())

+download_dataset <- function(url, datasetName, path = getwd())

 {

     url <- sub("/*[/]$","",url)

     URL <- paste0(url,"/datasets/",datasetName,"/zip")

@@ -920,9 +920,9 @@ download_dataset <- function(url,datasetName,path = getwd())

     else

     {

         zip_path <- paste0(path,"/",datasetName,".zip")

-        dir_out <-paste0(path,"/")

-        writeBin(content,zip_path)

-        unzip(zip_path,exdir=dir_out)

+        dir_out <- paste0(path,"/")

+        writeBin(content, zip_path)

+        unzip(zip_path,exdir = dir_out)

         print("Download Complete")

     }

 }

@@ -27,9 +27,6 @@ None

 \description{

 Wrapper to GMQL materialize function

-Wrapper to GMQL materialize function

-}

-\details{

 It saves the contents of a dataset that contains samples metadata and 

 samples regions.

 It is normally used to persist the contents of any dataset generated 

@@ -20,8 +20,9 @@ to be evaluated}

 list of 2-D array containing method of evaluation and metadata

 }

 \description{

-These functions is used to create a series of metadata as string

-that require evaluation on value.

+These functions is used to support joinBy and/or groupBy function parameter.

+It create a list of one element: matrix containing the two coloumn:

+type of condition evaluation and the metadata attribute

 }

 \details{

 \itemize{

@@ -59,25 +59,25 @@ s <- filter(input, Patient_age < 70)

 \dontrun{

-# It creates a new dataset called 'jun_tf' by selecting those samples and 

-# their regions from the existing 'data' dataset such that:

-# Each output sample has a metadata attribute called antibody_target 

-# with value JUN.

-# Each output sample also has not a metadata attribute called "cell" 

-# that has the same value of at least one of the values that a metadata 

-# attribute equally called cell has in at least one sample 

-# of the 'join_data' dataset.

-# For each sample satisfying previous condition,only its regions that 

-# have a region attribute called pValue with the associated value 

-# less than 0.01 are conserved in output

+## It creates a new dataset called 'jun_tf' by selecting those samples and 

+## their regions from the existing 'data' dataset such that:

+## Each output sample has a metadata attribute called antibody_target 

+## with value JUN.

+## Each output sample also has not a metadata attribute called "cell" 

+## that has the same value of at least one of the values that a metadata 

+## attribute equally called cell has in at least one sample 

+## of the 'join_data' dataset.

+## For each sample satisfying previous condition,only its regions that 

+## have a region attribute called pValue with the associated value 

+## less than 0.01 are conserved in output

 init_gmql()

 test_path <- system.file("example", "DATASET", package = "RGMQL")

 test_path2 <- system.file("example", "DATASET_GDM", package = "RGMQL")

 data <- read_dataset(test_path)

-join_data <-  read_dataset(test_path2)

-jun_tf <- filter(data, antibody_target == 'JUN', pValue < 0.01, 

+join_data <- read_dataset(test_path2)

+jun_tf <- filter(data, antibody_target == "JUN", pValue < 0.01, 

 semijoin(join_data, TRUE, DF("cell")))

 }

@@ -14,7 +14,7 @@

 \item{y}{GMQLDataset class object}

-\item{genometric_predicate}{is a list of lists of DISTAL object

+\item{genometric_predicate}{is a list of DISTAL object

 For details of DISTAL objects see:

 \code{\link{DLE}}, \code{\link{DGE}}, \code{\link{DL}}, \code{\link{DG}},

 \code{\link{MD}}, \code{\link{UP}}, \code{\link{DOWN}}}

@@ -82,7 +82,7 @@ test_path2 <- system.file("example", "DATASET_GDM", package = "RGMQL")

 TSS = read_dataset(test_path)

 HM = read_dataset(test_path2)

 join_data = merge(TSS, HM, 

-genometric_predicate = list(list(MD(1), DLE(120000))), DF("provider"), 

+genometric_predicate = list(MD(1), DLE(120000)), DF("provider"), 

 region_output = "RIGHT")

@@ -4,7 +4,7 @@

 \alias{semijoin}

 \title{Semijoin Condtion}

 \usage{

-semijoin(data, not_in = FALSE, ...)

+semijoin(data, not_in = FALSE, groupBy = NULL)

 }

 \arguments{

 \item{data}{GMQLDataset class object}

@@ -13,8 +13,7 @@ semijoin(data, not_in = FALSE, ...)

 considering semi_join NOT IN semi_join_dataset, F => semijoin is performed 

 considering semi_join IN semi_join_dataset}

-\item{...}{Additional arguments for use in specific methods.

-It is also accpet a functions to define condition evaluation on metadata.

+\item{groupBy}{it define condition evaluation on metadata.

 \itemize{

 \item{\code{\link{FN}}: Fullname evaluation, two attributes match 

 if they both end with value and, if they have a further prefixes,

@@ -24,7 +24,7 @@ by default is 0 that means take all rows for each sample}

 GrangesList with associated metadata

 }

 \description{

-GMQL Operation: TAKE

+Wrapper to take function

 It saves the contents of a dataset that contains samples metadata 

 and samples regions as GrangesList.

@@ -270,8 +270,8 @@ In this example we show how versatile RGMQL package are.

 As specified above, we can directly read a list of GRanges previously created 

 starting from two GRanges.

 Both *read()* and *read_dataset()* functions returns a result object, 

-in this case *data_out* containing an internal R representation of the dataset 

-used as input for executing the subsequent GMQL operation.

+in this case *data_out*: an instance of GMQLDataset class used as input 

+for executing the subsequent GMQL operation.

 ### Queries

@@ -330,7 +330,8 @@ specific path defined as input parameter.

 ## Materialize the result dataset on disk

 collect(exon_res)

 ```

-by default *collect()* has R workig directoy as stored path.  

+by default *collect()* has R workig directoy as stored path and *ds1* as name 

+of resulted dataset folder 

 ### Execution