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

 Package: RGMQL

 Type: Package

 Title: GenoMetric Query Language for R/Bioconductor

-Version: 0.99.36

+Version: 0.99.37

 Author: Simone Pallotta, Marco Masseroli

 Maintainer: Simone Pallotta <simonepallotta@hotmail.com>

 Description: This package brings the GenoMetric Query Language (GMQL)

@@ -82,7 +82,6 @@ biocViews:

 Collate: 

     'AllClasses.R'

     'AllGenerics.R'

-    'GMQL4TFarm.R'

     'GMQLtoGRanges.R'

     'GRangesToGMQL.R'

     'S3Aggregates.R'

@@ -91,6 +90,7 @@ Collate:

     'S3Operator.R'

     'Utils.R'

     'evaluation-functions.R'

+    'filter-extract-function.R'

     'gmql_cover.R'

     'gmql_difference.R'

     'gmql_extend.R'

@@ -29,7 +29,6 @@ export(SQRT)

 export(STD)

 export(SUM)

 export(UP)

-export(collect)

 export(compile_query)

 export(compile_query_fromfile)

 export(delete_dataset)

@@ -86,8 +85,12 @@ importFrom(S4Vectors,aggregate)

 importFrom(S4Vectors,merge)

 importFrom(S4Vectors,metadata)

 importFrom(data.table,fread)

+importFrom(dplyr,arrange)

 importFrom(dplyr,bind_cols)

+importFrom(dplyr,collect)

 importFrom(dplyr,filter)

+importFrom(dplyr,group_by)

+importFrom(dplyr,select)

 importFrom(glue,glue)

 importFrom(methods,is)

 importFrom(methods,isClass)

@@ -1,20 +1,9 @@

-#' Method filter

-#' 

-#' Wrapper to GMQL select function

-#' 

-#' @name filter

-#' @rdname filter-GMQLDataset-method

-#' @aliases filter

-#' 

-setGeneric("filter", function(.data, m_predicate = NULL, r_predicate = NULL, 

-                            semijoin = NULL, ...) standardGeneric("filter"))

-

 #' Method cover

 #' 

-#' Wrapper to GMQL cover function

+#' Wrapper to GMQL COVER operator

 #' 

 #' @name cover

-#' @rdname cover-GMQLDataset-method

+#' @rdname cover

 #' @aliases cover

 #' 

 setGeneric("cover", function(data, ...) standardGeneric("cover"))

@@ -24,29 +13,20 @@ setGeneric("cover", function(data, ...) standardGeneric("cover"))

 #' Wrapper to GMQL map function

 #' 

 #' @name map

-#' @rdname map-GMQLDataset-method

-#' @aliases map

+#' @rdname map

+#' @aliases map,GMQLDataset-method

 #' 

 setGeneric("map", function(x, y, ...) standardGeneric("map"))

-#' Method collect

-#' 

-#' Wrapper to GMQL materialize function

-#' 

-#' @name collect

-#' @rdname collect-GMQLDataset-method

-#' @export

-setGeneric("collect", function(x, dir_out = getwd(), name = "ds1", ...) 

-                standardGeneric("collect"))

-

-

 #' Method take

 #' 

 #' Wrapper to take function

 #' 

 #' @name take

-#' @rdname take-GMQLDataset-method

+#' @rdname take

+#' @aliases take,GMQLDataset-method

+#' 

 setGeneric("take", function(data, ...) standardGeneric("take"))

@@ -55,39 +35,8 @@ setGeneric("take", function(data, ...) standardGeneric("take"))

 #' Wrapper to GMQL extend function

 #' 

 #' @name extend

-#' @rdname extend-GMQLDataset-method

-#' @aliases extend GMQLDataset-method

-setGeneric("extend", function(.data, ...) standardGeneric("extend"))

-

-#' Method select

+#' @rdname extend

+#' @aliases extend,GMQLDataset-method

 #' 

-#' Wrapper to GMQL project function

-#' 

-#' @name select

-#' @rdname select-GMQLDataset-method

-#' @aliases select 

-setGeneric("select", function(.data, ...) standardGeneric("select"))

-

-

-#' Method arrange

-#' 

-#' Wrapper to GMQL order function

-#' 

-#' @name arrange

-#' @rdname arrange-GMQLDataset-method

-#' @aliases arrange 

-#' 

-setGeneric("arrange", function(.data, metadata_ordering = NULL, 

-                    regions_ordering = NULL, fetch_opt = NULL, num_fetch = 0, 

-                    reg_fetch_opt = NULL, reg_num_fetch = 0, ...) 

-                            standardGeneric("arrange"))

-

-#' Method group_by

-#' 

-#' Wrapper to GMQL group function

-#' 

-#' @name group_by

-#' @rdname group_by-GMQLDataset-method

-#' @aliases group_by 

-setGeneric("group_by", function(.data, ...) standardGeneric("group_by"))

+setGeneric("extend", function(.data, ...) standardGeneric("extend"))

@@ -158,7 +158,7 @@ take_value.META_AGGREGATES <- function(obj){

 #' res = extend(exp, m_score = MEDIAN("score"))

 #' 

 #' 

-#' @name SUM

+#' @name AGGREGATES-Object

 #' @aliases SUM

 #' @rdname aggr-class

 #' @export

@@ -173,7 +173,7 @@ SUM <- function(value)

     return(list)

 }

-#' @name MIN

+#' @name AGGREGATES-Object

 #' @aliases MIN

 #' @rdname aggr-class

 #' @export

@@ -189,7 +189,7 @@ MIN <- function(value)

 }

-#' @name MAX

+#' @name AGGREGATES-Object

 #' @aliases MAX

 #' @rdname aggr-class 

 #' @export

@@ -204,7 +204,7 @@ MAX <- function(value)

     return(list)

 }

-#' @name AVG

+#' @name AGGREGATES-Object

 #' @aliases AVG

 #' @rdname aggr-class

 #' @export

@@ -219,7 +219,7 @@ AVG <- function(value)

     return(list)

 }

-#' @name BAG

+#' @name AGGREGATES-Object

 #' @aliases BAG

 #' @rdname aggr-class

 #' @export

@@ -234,7 +234,7 @@ BAG <- function(value)

     return(list)

 }

-#' @name COUNT

+#' @name AGGREGATES-Object

 #' @aliases COUNT

 #' @rdname aggr-class

 #' @export

@@ -252,7 +252,7 @@ as.character.COUNT <- function(obj) {

 }

 check.COUNT <- function(obj){}

-#' @name STD

+#' @name AGGREGATES-Object

 #' @aliases STD

 #' @rdname aggr-class

 #' @export

@@ -268,7 +268,7 @@ STD <- function(value)

 }

-#' @name MEDIAN

+#' @name AGGREGATES-Object

 #' @aliases MEDIAN

 #' @rdname aggr-class

 #' @export

@@ -283,7 +283,7 @@ MEDIAN <- function(value)

     return(list)

 }

-#' @name Q1

+#' @name AGGREGATES-Object

 #' @aliases Q1

 #' @rdname aggr-class

 #' @export

@@ -298,7 +298,7 @@ Q1 <- function(value)

     return(list)

 }

-#' @name Q2

+#' @name AGGREGATES-Object

 #' @aliases Q2

 #' @rdname aggr-class

 #' @export

@@ -312,7 +312,7 @@ Q2 <- function(value)

     return(list)

 }

-#' @name Q3

+#' @name AGGREGATES-Object

 #' @aliases Q3

 #' @rdname aggr-class

 #' @export

@@ -327,7 +327,7 @@ Q3 <- function(value)

     return(list)

 }

-#' @name BAGD

+#' @name AGGREGATES-Object

 #' @aliases BAGD

 #' @rdname aggr-class

 #' @export

@@ -25,34 +25,48 @@ print.PARAMETER <- function(obj){

 #' to be used in GMQL cover method

 #' 

 #' \itemize{

-#' \item{ANY: It defines any amount of overlapping regions to be considered.}

-#' \item{ALL: It defines the minimum (and/or maximum) to the number of samples 

-#' in the input dataset.}

+#' \item{ALL: It represents the number of samples in the input dataset.}

+#' \item{ANY: It represents any amount of overlapping regions to be 

+#' considered.}

 #' }

 #' 

-#' @return param object

+#' @return Param object

 #'

 #' @examples

 #' 

+#' ## This statement initializes and runs the GMQL server for local execution 

+#' ## and creation of results on disk. Then, with system.file() it defines 

+#' ## the path to the file "DATASET" in the subdirectory "example"

+#' ## of the package "RGMQL" and opens such file as a GMQL dataset named "exp" 

+#' ## using customParser

+#' 

 #' init_gmql()

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

 #' exp = read_dataset(test_path)

 #' 

-#' ## This statement produces an output dataset with a single output sample. 

-#' ## The COVER operation considers all areas defined by a minimum 

-#' ## of two overlapping regions in the input samples, 

-#' ## up to maximum amount of overlapping regions.

+#' ## The following statement produces an output dataset with a single 

+#' ## output sample. The COVER operation considers all areas defined by 

+#' ## a minimum of two overlapping regions in the input samples, 

+#' ## up to maximum amount of overlapping regions equal to the number 

+#' ## of input samples.

 #' 

 #' res = cover(exp, 2, ALL())

 #' 

-#' ## This statement produces an output dataset with a single output sample. 

-#' ## The COVER operation considers all areas defined by a minimum 

-#' ## of two overlapping regions in the input samples, 

+#' ## The following statement produces an output dataset with a single 

+#' ## output sample. The COVER operation considers all areas defined by 

+#' ## a minimum of two overlapping regions in the input samples, 

+#' ## up to any amount of overlapping regions.

+#' 

+#' res = cover(exp, 2, ANY())

+#' 

+#' ## The following statement produces an output dataset with a single 

+#' ## output sample. The COVER operation considers all areas defined by 

+#' ## a half of maximum amount of overlapping regions in the input samples, 

 #' ## up to any amount of overlapping regions.

 #' 

-#' res = cover(exp, 2, ANY()+2/3)

+#' res = cover(exp, ALL()/2, ANY())

 #' 

-#' @name ALL

+#' @name Cover-Param

 #' @aliases ALL

 #' @rdname cover-param-class

 #' @export

@@ -65,7 +79,7 @@ ALL <- function()

     return(list)

 }

-#' @name ANY

+#' @name Cover-Param

 #' @aliases ANY

 #' @rdname cover-param-class

 #' @export

@@ -101,7 +101,7 @@ check.DISTAL <- function(value)

 #' genometric_predicate = list(MD(1), DGE(12000), DOWN()), 

 #' DF("provider"), region_output = "RIGHT")

 #'

-#' @name DL

+#' @name DISTAL-Object

 #' @aliases DL

 #' @rdname distal-class

 #' @export

@@ -129,7 +129,7 @@ DG <- function(value)

     return(list)

 }

-#' @name DLE

+#' @name DISTAL-Object

 #' @aliases DLE

 #' @rdname distal-class

 #' @export

@@ -143,7 +143,7 @@ DLE <- function(value)

     return(list)

 }

-#' @name DGE

+#' @name DISTAL-Object

 #' @aliases DGE

 #' @rdname distal-class

 #' @export

@@ -157,7 +157,7 @@ DGE <- function(value)

     return(list)

 }

-#' @name MD

+#' @name DISTAL-Object

 #' @aliases MD

 #' @rdname distal-class

 #' @export

@@ -172,7 +172,7 @@ MD <- function(value)

 }

-#' @name UP

+#' @name DISTAL-Object

 #' @aliases UP

 #' @rdname distal-class

 #' @export

@@ -190,7 +190,7 @@ as.character.UP <- function(obj) {

 }

-#' @name DOWN

+#' @name DISTAL-Object

 #' @aliases DOWN

 #' @rdname distal-class

 #' @export

@@ -87,7 +87,7 @@ as.character.OPERATOR <- function(obj) {

 #' exp = read_dataset(test_path)

 #' out = select(exp, metadata_update = list(concSq = SQRT("concentration")))

 #' 

-#' @name META

+#' @name OPERATOR-Object

 #' @aliases META

 #' @rdname operator-class

 #' @export

@@ -123,7 +123,7 @@ check.META <- function(type)

 }

-#' @name NIL

+#' @name OPERATOR-Object

 #' @aliases NIL

 #' @rdname operator-class

 #' @export

@@ -147,7 +147,7 @@ check.NIL <- function(value)

 }

-#' @name SQRT

+#' @name OPERATOR-Object

 #' @aliases SQRT

 #' @rdname operator-class

 #' @export

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

 #' Condition evaluation functions

 #'

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

+#' These functions are 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

+#' type of condition evaluation and the metadata attribute name

 #'

 #' \itemize{

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

@@ -26,11 +26,9 @@

 #' 

 #' @examples

 #' 

-#' init_gmql()

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

-#' r = read_dataset(test_path)

+#' "where is my example?"

 #' 

-#' @name FN

+#' @name Evaluation-Function

 #' @aliases FN

 #' @rdname condition_eval_func

 #' @export

@@ -51,7 +49,7 @@ FN <- function(...)

     join_condition_matrix

 }

-#' @name EX

+#' @name Evaluation-Function

 #' @aliases EX

 #' @rdname condition_eval_func

 #' @export

@@ -72,7 +70,7 @@ EX <- function(...)

     join_condition_matrix

 }

-#' @name DF

+#' @name Evaluation-Function

 #' @aliases DF

 #' @rdname condition_eval_func

 #' @export

similarity index 86%

rename from R/GMQL4TFarm.R

rename to R/filter-extract-function.R

@@ -1,44 +1,44 @@

-#' FILTER AND EXTRACT

+#' Filter and extract function

 #'

-#' This function let user to create a new GRangeslist with fixed information:

-#' seqnames,ranges ans strand and a variable part made up by the regions

-#' defined as input.

-#' The metadata and metadata_prefix are used to filter the data and choose

-#' only the samples that match at least one metdatata with its prefix.

-#' The input regions are shown for each sample obtained from filtering.

+#' This function lets user to create a new GRangesList with fixed information:

+#' seqnames, ranges and strand, and a variable part made up by the regions

+#' defined as input. The metadata and metadata_prefix are used to filter 

+#' the data and choose only the samples that match at least one metdatata 

+#' with its prefix. The input regions are shown for each sample obtained 

+#' from filtering.

 #'

 #' @import xml2

 #' @importFrom dplyr bind_cols

 #' @importFrom data.table fread

 #' @importFrom rtracklayer import

 #'

-#' @param data string GMQL dataset folder path or GrangesList

+#' @param data string GMQL dataset folder path or GRangesList

 #' object

-#' @param metadata vector of character containing names of metadata

+#' @param metadata vector of strings containing names of metadata attributes

 #' to be searched for in metadata files.

-#' data will be extracted if at least one condition is satisfied:

-#' this condition will be logically "ANDed" with prefix filtering (see below)

-#' if NULL no filtering action occured

-#' (i.e every sample will be taken for regions filtering)

-#' @param metadata_prefix vector of character that will filter metadata

+#' Data will be extracted if at least one condition is satisfied:

+#' this condition is logically "ANDed" with prefix filtering (see below)

+#' if NULL no filtering action occures

+#' (i.e every sample is taken for region filtering)

+#' @param metadata_prefix vector of strings that will filter metadata

 #' containing rispectively every element of this vector.

-#' number of elelment in both vector must match

-#' @param regions vector of character that will extract only region

-#' attribute specified; if NULL no regions will be taken and the output

-#' will be only GRanges made up by the first attribute

-#' (seqnames,start,end,strand)

+#' number of element in both vector must match

+#' @param regions vector of strings that extracts only region attribute 

+#' specified; if NULL no regions attribute is taken and the output is only 

+#' GRanges made up by the region coordinate attributes 

+#' (seqnames, start, end, strand)

 #' @param suffix name for each metadata column of GRanges. by default is the 

 #' "antibody_target". This string is taken from sample metadata file or from

 #' metadata() associated. If not present, the column name is the name of 

 #' selected regions

 #'

 #' @details

-#' This function works only with datatset or Grangeslist that have the same

+#' This function works only with datatset or GRangesList that has the same

 #' information about regions attribute (but of course different value)

 #' In case of Grangeslist data input the function will search for metadata

 #' into metadata() function associated to Grangeslist.

 #'

-#' @return granges with selected regions (if any) in elementMetadata

+#' @return Granges with selected regions (if any) in elementMetadata

 #'

 #' @examples

 #'

@@ -5,14 +5,15 @@

 #' specified) by “collapsing” the input dataset samples and their regions 

 #' according to certain rules specified by the input parameters.

 #' The attributes of the output genomic regions are only the region 

-#' coordinates, and Jaccard indexes (JaccardIntersect and JaccardResult).

+#' coordinates, and Jaccard indexes (\emph{JaccardIntersect} and 

+#' \emph{JaccardResult}).

 #' Jaccard Indexes are standard measures of similarity of the contributing 

 #' regions, added as default region attributes.

 #' The JaccardIntersect index is calculated as the ratio between the lengths 

 #' of the intersection and of the union of the contributing regions; 

 #' the JaccardResult index is calculated as the ratio between the lengths 

 #' of the result and the union of the contributing regions.

-#' If aggregate functions are specified, a new attributes is added for 

+#' If aggregate functions are specified, a new attribute is added for 

 #' each aggregate function specified.

 #' Output metadata are the union of the input ones.

 #' If \emph{groupby} clause is specified, the input samples are partitioned 

@@ -24,54 +25,47 @@

 #' 

 #' @include AllClasses.R

 #' @importFrom methods is

-#' @importFrom rJava J

-#' @importFrom rJava .jnull

-#' @importFrom rJava .jarray

+#' @importFrom rJava J .jnull .jarray

 #' 

 #' @param data GMQLDataset class object

 #' @param min_acc minimum number of overlapping regions to be considered 

-#' during execution

-#' Is a integer number, declared also as string.

-#' minAcc accept also:

+#' during execution. It is an integer number, declared also as string.

+#' minAcc accepts also:

 #' \itemize{

-#' \item{PARAMETER class object: \code{\link{ALL}} that represents the number 

+#' \item{PARAMETER class object: \code{\link{ALL}}, that represents the number 

 #' of samples in the input dataset}

-#' \item{and expression built using PARAMETER object: (ALL() + N) / K or

-#' ALL() / K }

+#' \item{an expression built using PARAMETER object: (ALL() + N) / K or

+#' ALL() / K, with N and K integer values }

 #' }

 #' @param max_acc maximum number of overlapping regions to be considered 

-#' during execution

-#' Is a integer number, declared also as string.

+#' during execution. It is an integer number, declared also as string.

 #' maxAcc accept also:

 #' \itemize{

-#' \item{PARAMETER class object: \code{\link{ALL}} that represents the number 

+#' \item{PARAMETER class object: \code{\link{ALL}}, that represents the number 

 #' of samples in the input dataset}

-#' \item{PARAMETER calss object: \code{\link{ANY}}} that acts as a wildcard, 

-#' considering any amount of overlapping.

-#' \item{and expression built using PARAMETER object: (ALL() + N) / K or

-#' ALL() / K }

+#' \item{PARAMETER class object: \code{\link{ANY}}}, that acts as a wildcard, 

+#' considering any amount of overlapping regions.

+#' \item{an expression built using PARAMETER object: (ALL() + N) / K or

+#' ALL() / K, with N and K integer values  }

 #' }

-#' @param groupBy list of evalation function to define condition 

-#' evaluation on metadata:

+#' @param groupBy list of evalation functions to define 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,

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

+#' if they both end with \emph{value} and, if they have further prefixes,

 #' the two prefix sequence are identical}

-#' \item{\code{\link{EX}}: Exact evaluation, only attributes exactly 

-#' as value will match; no further prefixes are allowed. }

-#' \item{\code{\link{DF}}: Default evaluation, the two attributes match 

-#' if both end with value.}

+#' \item{\code{\link{EX}}(value): Exact evaluation, only attributes exactly 

+#' as \emph{value} match; no further prefixes are allowed. }

+#' \item{\code{\link{DF}}(value): Default evaluation, the two attributes match 

+#' if both end with \emph{value}.}

 #' }

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

-#' 

-#' In this case a series of element in the form \emph{key} = \emph{aggregate}.

-#' The \emph{aggregate} is an object of class AGGREGATES

-#' The aggregate functions available are: \code{\link{SUM}}, 

+#' @param ... a series of expressions separated by comma in the form 

+#' \emph{key} = \emph{aggregate}. The \emph{aggregate} is an object of 

+#' class AGGREGATES. The aggregate functions available are: \code{\link{SUM}}, 

 #' \code{\link{COUNT}}, \code{\link{MIN}}, \code{\link{MAX}}, 

 #' \code{\link{AVG}}, \code{\link{MEDIAN}}, \code{\link{STD}}, 

 #' \code{\link{BAG}}, \code{\link{BAGD}}, \code{\link{Q1}}, 

 #' \code{\link{Q2}}, \code{\link{Q3}}.

-#' Every aggregate accepts a string value, execet for COUNT, which does not 

+#' Every aggregate accepts a string value, except for COUNT, which does not 

 #' have any value.

 #' Argument of 'aggregate function' must exist in schema, i.e. among region 

 #' attributes. Two style are allowed:

@@ -81,53 +75,60 @@

 #' }

 #' "mixed style" is not allowed

 #'

-#' @param variation string identifying the cover GMQL function variation.

-#' The admissible string are:

+#' @param variation string identifying the cover GMQL operator variation.

+#' The admissible strings are:

 #' \itemize{

-#' \item{FLAT: returns the contiguous region that starts from the first end 

-#' and stops at the last end of the regions which would contribute 

-#' to each region of the \emph{cover}.}

-#' \item{SUMMIT: returns regions that start from a position

+#' \item{FLAT: It returns the regions that start from the first end and stop 

+#' at the last end of the regions which would contribute to each region 

+#' of the \emph{cover}.}

+#' \item{SUMMIT: It returns regions that start from a position

 #' where the number of intersecting regions is not increasing afterwards and

-#' stops at a position where either the number of intersecting regions 

+#' stop at a position where either the number of intersecting regions 

 #' decreases, or it violates the max accumulation index.}

-#' \item{HISTOGRAM: returns the non-overlapping regions contributing to 

-#' the cover, each with its accumulation index value, which is assigned to 

-#' the AccIndex region attribute.}

+#' \item{HISTOGRAM: It returns the non-overlapping regions contributing to 

+#' the \emph{cover}, each with its accumulation index value, which is assigned 

+#' to the \emph{AccIndex} region attribute.}

 #' \item{COVER: default value.}

 #' }

+#' Can be all caps or lowercase

 #' 

 #' @return GMQLDataset object. It contains the value to use as input 

 #' for the subsequent GMQLDataset method

 #' 

 #' @examples

 #' 

-#' ## This statement produces an output dataset with a single output sample. 

-#' ## The COVER operation considers all areas defined by a minimum 

-#' ## of two overlapping regions in the input samples, 

-#' ## up to any amount of overlapping regions.

+#' ## This statement initializes and runs the GMQL server for local execution 

+#' ## and creation of results on disk. Then, with system.file() it defines 

+#' ## the path to the folder "DATASET" in the subdirectory "example"

+#' ## of the package "RGMQL" and opens such file as a GMQL dataset named "exp" 

+#' ## using customParser

 #' 

 #' init_gmql()

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

 #' exp = read_dataset(test_path)

+#'   

+#' ## the following statement produces an output dataset with a single output 

+#' ## sample. The COVER operation considers all areas defined by a minimum 

+#' ## of two overlapping regions in the input samples, up to any amount of 

+#' ## overlapping regions.

+#' 

 #' res = cover(exp, 2, ANY())

 #'

-#' \dontrun{

-#' ## This GMQL statement computes the result grouping the input exp samples 

-#' ## by the values of their cell metadata attribute, 

+#' ## The following GMQL statement computes the result grouping the input 

+#' ## exp samples by the values of their cell metadata attribute, 

 #' ## thus one output res sample is generated for each cell type; 

 #' ## output regions are produced where at least 2 and at most 3 regions 

 #' ## of grouped exp samples overlap, setting as attributes of the resulting 

 #' ## regions the minimum pvalue of the overlapping regions (min_pvalue) 

 #' ## and their Jaccard indexes (JaccardIntersect and JaccardResult).

 #' 

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

-#' exp = read_dataset(test_path)

 #' res = cover(exp, 2, 3, groupBy = list(DF("cell")), 

 #' min_pValue = MIN("pvalue"))

-#' }

 #' 

-#' @aliases cover cover-method

+#' @name cover

+#' @rdname cover

+#' @aliases cover,GMQLDataset-method

+#' @aliases cover-method

 #' @export

 setMethod("cover", "GMQLDataset",

             function(data, min_acc, max_acc, groupBy = NULL, 

@@ -56,6 +56,8 @@

 #' 

 #' }

 #' 

+#' @name extend

+#' @rdname extend

 #' @aliases extend-method

 #' @export

 setMethod("extend", "GMQLDataset", function(.data, ...)

@@ -1,32 +1,83 @@

+group_by.GMQLDateset <- function(.data, groupBy_meta = NULL, 

+    groupBy_regions = NULL, region_aggregates = NULL, meta_aggregates = NULL)

+{

+    ptr_data = .data@value

+    gmql_group(ptr_data, groupBy_meta, groupBy_regions, region_aggregates, 

+                meta_aggregates)

+}

+

 #' Method group_by

 #' 

+#' @description Wrapper to GMQL GROUP operator

 #' 

 #' @importFrom rJava J .jarray .jnull

-#' 

+#' @importFrom dplyr group_by

 #' 

 #' @param .data GMQLDataset object

-#'

+#' @param groupBy_meta 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,

+#' the two prefix sequence are identical}

+#' \item{\code{\link{EX}}: Exact evaluation, only attributes exactly 

+#' as value will match; no further prefixes are allowed. }

+#' \item{\code{\link{DF}}: Default evaluation, the two attributes match 

+#' if both end with value.}

+#' }

+#' @param groupBy_regions vector of string made up by schema field attribute

+#' @param region_aggregates It accept a series of aggregate function on 

+#' region attribute. 

+#' All the element in the form \emph{key} = \emph{aggregate}.

+#' The \emph{aggregate} is an object of class AGGREGATES

+#' The aggregate functions available are: \code{\link{SUM}}, 

+#' \code{\link{COUNT}}, \code{\link{MIN}}, \code{\link{MAX}}, 

+#' \code{\link{AVG}}, \code{\link{MEDIAN}}, \code{\link{STD}}, 

+#' \code{\link{BAG}}, \code{\link{BAGD}}, \code{\link{Q1}}, 

+#' \code{\link{Q2}}, \code{\link{Q3}}.

+#' Every aggregate accepts a string value, execet for COUNT, which does not 

+#' have any value.

+#' Argument of 'aggregate function' must exist in schema, i.e. among region 

+#' attributes. Two style are allowed:

+#' \itemize{

+#' \item list of key-value pairs: e.g. sum = SUM("pvalue")

+#' \item list of values: e.g. SUM("pvalue")

+#' }

+#' "mixed style" is not allowed

+#' @param meta_aggregates It accept a series of aggregate function on 

+#' metadata attribute.

+#' All the element in the form \emph{key} = \emph{aggregate}.

+#' The \emph{aggregate} is an object of class AGGREGATES

+#' The aggregate functions available are: \code{\link{SUM}}, 

+#' \code{\link{COUNT}}, \code{\link{MIN}}, \code{\link{MAX}}, 

+#' \code{\link{AVG}}, \code{\link{MEDIAN}}, \code{\link{STD}}, 

+#' \code{\link{BAG}}, \code{\link{BAGD}}, \code{\link{Q1}}, 

+#' \code{\link{Q2}}, \code{\link{Q3}}.

+#' Every aggregate accepts a string value, execet for COUNT, which does not 

+#' have any value.

+#' Argument of 'aggregate function' must exist in schema, i.e. among region 

+#' attributes. Two style are allowed:

+#' \itemize{

+#' \item list of key-value pairs: e.g. sum = SUM("cell")

+#' \item list of values: e.g. SUM("cell")

+#' }

+#' "mixed style" is not allowed

+#' 

+#' 

 #' @return GMQLDataset object. It contains the value to use as input 

 #' for the subsequent GMQLDataset method

 #'

 #' @examples

 #' 

-#' 

-#' 

-#' @aliases group_by group_by-method

+#' @name group_by

+#' @rdname group_by

+#' @aliases group_by,GMQLDataset-method

+#' @aliases group_by-method

 #' @export

-setMethod("group_by","GMQLDataset",

-          function(.data, groupBy_meta = NULL, groupBy_regions = NULL, 

-            region_aggregates = NULL, meta_aggregates = NULL)

-          {

-              ptr_data = .data@value

-              gmql_group(ptr_data, groupBy_meta, groupBy_regions, 

-                            region_aggregates, meta_aggregates)

-          })

+setMethod("group_by","GMQLDataset",group_by.GMQLDateset)

-gmql_group <- function(input_data, group_meta, group_reg)

+gmql_group <- function(input_data, group_meta, group_reg, region_aggregates, 

+                            meta_aggregates)

 {

-    

     if(!is.null(group_meta))

     {

         cond <- .join_condition(group_meta)

@@ -69,7 +120,7 @@ gmql_group <- function(input_data, group_meta, group_reg)

     WrappeR <- J("it/polimi/genomics/r/Wrapper")

     response <- WrappeR$group(join_condition_matrix, metadata_matrix, 

-                                groupBy_regions, region_matrix, input_data)

+                                group_reg, region_matrix, input_data)

     error <- strtoi(response[1])

     data <- response[2]

     if(error!=0)

@@ -74,6 +74,8 @@

 #' out = map(ref,exp, minScore = MIN("score"), 

 #' joinBy = list(DF("cell_tissue")))

 #' 

+#' @name map

+#' @rdname map

 #' @aliases map-method

 #' @export

 setMethod("map", "GMQLDataset",

@@ -13,7 +13,7 @@

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

 #' rd = read_dataset(test_path)

 #' filtered = filter(rd)

-#' aggr = aggregate(filtered, DF("antibody_targer","cell_karyotype"))

+#' aggr = aggregate(filtered, list(DF("antibody_targer","cell_karyotype")))

 #' collect(aggr, dir_out = test_path)

 #' 

 #' \dontrun{

@@ -65,45 +65,61 @@ execute <- function()

     }

 }

+collect.GMQLDataset <- function(x, dir_out = getwd(), name = "ds1")

+{

+    ptr_data <- x@value

+    gmql_materialize(ptr_data, dir_out, name)

+}

 #' Method collect

 #'

-#' 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 

-#' during a GMQL query.

+#' @description Wrapper to GMQL MATERIALIZE operator

+#' 

+#' @description It saves the content of a dataset that contains samples 

+#' metadata and regions. It is normally used to persist the content of any 

+#' dataset generated during a GMQL query.

 #' Any dataset can be materialized, but the operation can be time-consuming.

 #' For best performance, materialize the relevant data only.

 #'

 #' @importFrom rJava J

+#' @importFrom dplyr collect

 #' 

 #' @param x GMQLDataset class object

 #' @param dir_out destination folder path.

-#' by default is current working directory of the R process