@@ -1,11 +1,11 @@

 Package: RGMQL

 Type: Package

 Title: GenoMetric Query Language for R/Bioconductor

-Version: 0.99.23

+Version: 0.99.24

 Author: Simone Pallotta, Marco Masseroli

 Maintainer: Simone Pallotta <simonepallotta@hotmail.com>

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

-  into the R environment.

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

+  functionalities into the R environment.

   GMQL is a high-level, declarative language to query and compare multiple and heterogeneous genomic 

   datasets for biomedical knowledge discovery. It allows expressing easily queries 

   and processing over genomic regions and their metadata, in a way similar to 

@@ -55,7 +55,7 @@ LazyData: true

 RoxygenNote: 6.0.1

 Imports: httr, rJava,GenomicRanges, rtracklayer, data.table, utils, plyr, xml2, 

     methods, S4Vectors, dplyr, stats

-Depends: R(>= 3.4.2)

+Depends: R(<= 3.4.2)

 VignetteBuilder: knitr

 Suggests: BiocStyle, knitr, rmarkdown

 biocViews: Software,Infrastructure,DataImport,Network

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

 #' another dataset (with a single sample, if no \emph{groupby} option is 

 #' 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).

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

+#' coordinates, and Jaccard indexes (JaccardIntersect and 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 

@@ -70,9 +70,10 @@

 #' @param aggregates list 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}}, 

-#' \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}}.

+#' \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 

@@ -181,9 +182,10 @@ cover <- function(input_data, minAcc, maxAcc, groupBy = NULL,

 #' @param aggregates list 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}}, 

-#' \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}}.

+#' \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 

@@ -282,9 +284,10 @@ histogram <- function(input_data, minAcc, maxAcc, groupBy = NULL,

 #' @param aggregates list 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}}, 

-#' \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}}.

+#' \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 

@@ -380,9 +383,10 @@ summit <- function(input_data, minAcc, maxAcc, groupBy = NULL,

 #' @param aggregates list 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}}, 

-#' \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}}.

+#' \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 

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

 #' GMQL Operation: DIFFERENCE

 #'

 #' It produces one sample in the result for each sample of the left operand,

-#' by keeping the same metadata of the left input sample and only those regions

-#' (with their schema and values) of the left input sample which do not 

-#' intersect with any region in the right operand sample.

+#' by keeping the same metadata of the left input sample and only those 

+#' regions (with their schema and values) of the left input sample which 

+#' do not intersect with any region in the right operand sample.

 #' The optional \emph{joinby} clause is used to extract a subset of couples

 #' from the cartesian product of two dataset 

 #' \emph{left_input_data} x \emph{right_input_data} on which to apply 

@@ -13,9 +13,10 @@

 #' @param metadata list 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}}, 

-#' \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}}.

+#' \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 

@@ -108,7 +108,7 @@ filter_and_extract <- function(data, metadata = NULL,

 }

 .extract_from_GRangesList <- function(rangesList, metadata = NULL,

-                                        metadata_prefix = NULL, regions = NULL)

+                                metadata_prefix = NULL, regions = NULL)

 {

     if(!is(rangesList,"GRangesList"))

         stop("only GrangesList admitted")

@@ -146,7 +146,7 @@ export_gmql <- function(samples, dir_out, is_gtf)

         names(columns) <- plyr::revalue(names(columns),c(type = "feature",

                                             phase = "frame"))

         fixed_element = c(seqname = "character", source = "character", 

-                            feature = "character",start = "long", end = "long", 

+                        feature = "character",start = "long", end = "long", 

                             score = "numeric", strand = "character",

                             frame = "character")

         node_list <- c(fixed_element, columns)

@@ -54,8 +54,8 @@

 #' \item{contig: outputs the concatenation between the left_input_data and 

 #' right_input_data regions that satisfy the genometric predicate, 

 #' (i.e. the output regionis defined as having left (right) coordinates

-#' equal to the minimum (maximum) of the corresponding coordinate values in the 

-#' left_input_data and right_input_data regions satisfying 

+#' equal to the minimum (maximum) of the corresponding coordinate values 

+#' in the left_input_data and right_input_data regions satisfying 

 #' the genometric predicate)}

 #' }

 #'

@@ -65,12 +65,12 @@

 #'

 #' @examples

 #' 

-#' ## Given a dataset 'hm' and one called 'tss' with a sample including 

-#' ## Transcription Start Site annotations, it searches for those regions of hm 

-#' ## that are at a minimal distance from a transcription start site (TSS) 

-#' ## and takes the first/closest one for each TSS, provided that such distance 

-#' ## is lesser than 120K bases and joined 'tss' and 'hm' samples are obtained 

-#' ## from the same provider (joinby clause).

+#' # Given a dataset 'hm' and one called 'tss' with a sample including 

+#' # Transcription Start Site annotations, it searches for those regions of hm 

+#' # that are at a minimal distance from a transcription start site (TSS) 

+#' # and takes the first/closest one for each TSS, provided that such distance 

+#' # is lesser than 120K bases and joined 'tss' and 'hm' samples are obtained 

+#' # from the same provider (joinby clause).

 #' 

 #' init_gmql()

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

@@ -83,8 +83,9 @@

 #'

 #' @export

 #'

-join <- function(right_input_data, left_input_data, genometric_predicate = NULL,

-                    joinBy = NULL, region_output="contig")

+join <- function(right_input_data, left_input_data, 

+                    genometric_predicate = NULL, joinBy = NULL, 

+                    region_output="contig")

 {

     if(!is.null(genometric_predicate))

     {

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

 #' The number of generated output samples is the Cartesian product 

 #' of the samples in the two input datasets;

 #' each output sample has the same regions as the related input left sample, 

-#' with their attributes and values, plus the attributes computed as aggregates 

-#' over right region values.

+#' with their attributes and values, plus the attributes computed as 

+#' aggregates over right region values.

 #' Output sample metadata are the union of the related input sample metadata,

 #' whose attribute names are prefixed with "left" or "right" respectively.

 #'

@@ -24,9 +24,10 @@

 #' @param aggregates list 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}}, 

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

-#' \code{\link{STD}}, \code{\link{MEDIAN}},\code{\link{BAG}}, 

-#' \code{\link{BAGD}}, \code{\link{Q1}}, \code{\link{Q2}}, \code{\link{Q3}}.

+#' \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

 #' Argument of 'aggregate' must exist in schema

 #' Two style are allowed:

@@ -59,21 +60,22 @@

 #'

 #' @examples

 #'

-#' ## It counts the number of regions in each sample from exp that overlap with 

-#' ## a ref region, and for each ref region it computes the minimum score 

-#' ## of all the regions in each exp sample that overlap with it. 

-#' ## The MAP joinby option ensures that only the exp samples referring to 

-#' ## the same 'cell_tissue' of a ref sample are mapped on such ref sample; 

-#' ## exp samples with no cell_tissue metadata attribute, or with such metadata 

-#' ## but with a different value from the one(s) of ref sample(s), 

-#' ## are disregarded.

+#' # It counts the number of regions in each sample from exp that overlap with 

+#' # a ref region, and for each ref region it computes the minimum score 

+#' # of all the regions in each exp sample that overlap with it. 

+#' # The MAP joinby option ensures that only the exp samples referring to 

+#' # the same 'cell_tissue' of a ref sample are mapped on such ref sample; 

+#' # exp samples with no cell_tissue metadata attribute, or with such metadata 

+#' # but with a different value from the one(s) of ref sample(s), 

+#' # are disregarded.

 #' 

 #' init_gmql()

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

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

 #' exp = read_dataset(test_path)

 #' ref = read_dataset(test_path2)

-#' out = map(ref,exp, list(minScore = MIN("score")), joinBy = c("cell_tissue"))

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

+#' joinBy = c("cell_tissue"))

 #' 

 #' 

 #' @export

@@ -38,10 +38,10 @@

 #' 

 #' @examples

 #' 

-#' ## It creates a dataset called merged which contains one sample for each 

-#' ## antibody_target value found within the metadata of the exp dataset sample; 

-#' ## each created sample contains all regions from all 'exp' samples 

-#' ## with a specific value for their antibody_target metadata attribute.

+#' # It creates a dataset called merged which contains one sample for each 

+#' # antibody_target value found within the metadata of the exp dataset sample; 

+#' # each created sample contains all regions from all 'exp' samples 

+#' # with a specific value for their antibody_target metadata attribute.

 #' 

 #' init_gmql()

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

@@ -73,7 +73,7 @@ order <- function(input_data, metadata_ordering = NULL, mtop = 0, mtopg = 0,

     if(length(mtop)>1 || length(mtopg)>1 || length(rtop)>1 || length(rtopg)>1

         || length(mtopp)>1 || length(rtopp)>1)

-        warning("only first element is taken by rtop, mtop, mtopg, rtopg, rtopp, mtopp")

+        warning("only first element: rtop, mtop, mtopg, rtopg, rtopp, mtopp")

     # we consider only the first element even if input is a vector of Int

     # we cut the other arguments

@@ -234,7 +234,7 @@ We provide two metadata for you")

     if("phase" %in% col_names) # if GTF, change

     {

         col_names <- plyr::revalue(col_names,c(type = "feature", 

-                                        phase = "frame", seqnames = "seqname"))

+                                    phase = "frame", seqnames = "seqname"))

         schema_matrix <- cbind(toupper(col_types),col_names)

         schema_matrix<- schema_matrix[setdiff(rownames(schema_matrix),

                                         c("group","width")),]

@@ -264,9 +264,11 @@ We provide two metadata for you")

 {

     parser <- toupper(parser)

     if(!identical(parser,"BEDPARSER") && !identical(parser,"ANNPARSER") &&

-        !identical(parser,"BROADPROJPARSER") && !identical(parser,"BASICPARSER") 

-        && !identical(parser,"NARROWPEAKPARSER") && 

-        !identical(parser,"RNASEQPARSER") && !identical(parser,"CUSTOMPARSER"))

+        !identical(parser,"BROADPROJPARSER") && 

+        !identical(parser,"BASICPARSER") && 

+        !identical(parser,"NARROWPEAKPARSER") && 

+        !identical(parser,"RNASEQPARSER") && 

+        !identical(parser,"CUSTOMPARSER"))

         stop("parser not defined")

     parser

@@ -132,8 +132,9 @@ Function will be invoked with these parameters as NULL")

                                             dispatch = TRUE)

     }

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

-    response <- WrappeR$select(predicate,region_predicate,join_condition_matrix,

-                    semi_join_dataset, semi_join_negation, input_data$value)

+    response <- WrappeR$select(predicate,region_predicate, 

+                                join_condition_matrix, semi_join_dataset, 

+                                semi_join_negation, input_data$value)

     error <- strtoi(response[1])

     data <- response[2]

     if(error!=0)

@@ -40,7 +40,7 @@

     names <- names(meta_data)

     if(is.null(names))

     {

-        warning("You did not assign a names to a list.\nWe build names for you")

+        warning("You did not assign a names to a list.\nWe build it for you")

         names <- sapply(meta_data, take_value.META_AGGREGATES)

     }

     else

@@ -14,7 +14,7 @@ check.META_AGGREGATES <- function(value)

 {

     if(is.character(value) && length(value)>1)

         stop("value: no multiple string")

-

+    

     if(!is.character(value))

         stop("value: is not a string")

 }

@@ -42,10 +42,10 @@ if(getRversion() >= "3.1.0")

 login_gmql <- function(url, username = NULL, password = NULL)

 {

     as_guest <- TRUE

-

+    

     if(!is.null(username) || !is.null(password))

         as_guest <- FALSE

-

+    

     if(as_guest)

     {

         h <- c('Accept' = "Application/json")

@@ -55,8 +55,8 @@ check.CONDITION <- function(value)

 #' 

 #' ## select with condition

 #' ## the first and the third attribute are DEF the second one is EXACT

-#' s = select(r, semi_join = list("cell_type", EXACT("cell"), "attribute_tag"), 

-#' semi_join_dataset = r)

+#' s = select(r, semi_join = list("cell_type", EXACT("cell"), 

+#' "attribute_tag"), semi_join_dataset = r)

 #'

 #' \dontrun{

 #'

@@ -413,8 +413,8 @@ download_as_GRangesList <- function(url,datasetName)

 #' Shows metadata list from dataset sample

 #'

-#' It retrieves metadata for a specific sample in dataset using the proper GMQL 

-#' web service available on a remote server

+#' It retrieves metadata for a specific sample in dataset using the proper 

+#' GMQL web service available on a remote server

 #'

 #' @import httr

 #'

@@ -463,7 +463,8 @@ sample_metadata <- function(url, datasetName,sampleName)

 #'

 #' It retrieves regions for a specific sample 

 #' (whose name is specified in the paramter "sampleName")

-#' in a specific dataset (whose name is specified in the paramter "datasetName") 

+#' in a specific dataset 

+#' (whose name is specified in the parameter "datasetName") 

 #' using the proper GMQL web service available on a remote server

 #'

 #' @import httr

@@ -25,7 +25,7 @@ check.DISTAL <- function(value)

 {

     if(!is.numeric(value))

         stop("value: is not a numeric")

-  

+    

     if(is.numeric(value) && length(value)>1)

         stop("value: no multiple string")

 }

@@ -49,12 +49,12 @@ check.DISTAL <- function(value)

 #' 

 #' @examples

 #' 

-#' ### Given a dataset HM and one called TSS with a sample including 

-#' ## Transcription Start Site annotations, it searches for those regions of hm 

-#' ## that are at a minimal distance from a transcription start site (TSS) 

-#' ## and takes the first/closest one for each TSS, 

-#' ## provided that such distance is lesser than 1200 bases and joined TSS 

-#' ## and HM samples are obtained from the same provider (joinby clause).

+#' ## Given a dataset HM and one called TSS with a sample including 

+#' # Transcription Start Site annotations, it searches for those regions of hm 

+#' # that are at a minimal distance from a transcription start site (TSS) 

+#' # and takes the first/closest one for each TSS, 

+#' # provided that such distance is lesser than 1200 bases and joined TSS 

+#' # and HM samples are obtained from the same provider (joinby clause).

 #' 

 #' init_gmql()

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

@@ -65,13 +65,11 @@ check.DISTAL <- function(value)

 #' genometric_predicate = list(list(MD(1), DL(1200))), c("provider"), 

 #' region_output = "RIGHT")

 #'

-#' 

 #' @export

 #'

 DL <- function(value)

 {

     check.DISTAL(value)

-  

     list <- list(value = as.integer(value))

     ## Set the name for the class

     class(list) <- c("DL","DISTAL")

@@ -96,12 +94,12 @@ DL <- function(value)

 #' 

 #' @examples

 #' 

-#' ### Given a dataset HM and one called TSS with a sample including 

-#' ## Transcription Start Site annotations, it searches for those regions of hm 

-#' ## that are at a minimal distance from a transcription start site 'TSS' 

-#' ## and takes the first/closest one for each TSS, provided that such distance 

-#' ## is greater than 12 bases and joined TSS and HM samples are obtained 

-#' ## from the same provider 'joinby clause'.

+#' ## Given a dataset HM and one called TSS with a sample including 

+#' # Transcription Start Site annotations, it searches for those regions of hm 

+#' # that are at a minimal distance from a transcription start site 'TSS' 

+#' # and takes the first/closest one for each TSS, provided that such distance 

+#' # is greater than 12 bases and joined TSS and HM samples are obtained 

+#' # from the same provider 'joinby clause'.

 #' 

 #' init_gmql()

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

@@ -118,7 +116,6 @@ DL <- function(value)

 DG <- function(value)

 {

     check.DISTAL(value)

-  

     list <- list(value = as.integer(value))

     ## Set the name for the class

     class(list) <- c("DG","DISTAL")

@@ -149,12 +146,12 @@ DG <- function(value)

 #' 

 #' @examples

 #' 

-#' ### Given a dataset HM and one called TSS with a sample including 

-#' ## Transcription Start Site annotations, it searches for those regions of hm 

-#' ## that are at a minimal distance from a transcription start site (TSS) 

-#' ## and takes the first/closest one for each TSS, provided that such distance 

-#' ## is lesser than 120K bases and joined TSS and HM samples are obtained 

-#' ## from the same provider (joinby clause).

+#' ## Given a dataset HM and one called TSS with a sample including 

+#' # Transcription Start Site annotations, it searches for those regions of hm 

+#' # that are at a minimal distance from a transcription start site (TSS) 

+#' # and takes the first/closest one for each TSS, provided that such distance 

+#' # is lesser than 120K bases and joined TSS and HM samples are obtained 

+#' # from the same provider (joinby clause).

 #' 

 #' init_gmql()

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

@@ -171,7 +168,6 @@ DG <- function(value)

 DLE <- function(value)

 {

     check.DISTAL(value)

-  

     list <- list(value = as.integer(value))

     ## Set the name for the class

     class(list) <- c("DLE","DISTAL")

@@ -198,12 +194,12 @@ DLE <- function(value)

 #' 

 #' @examples

 #' 

-#' ## Given a dataset 'hm' and one called 'tss' with a sample including 

-#' ## Transcription Start Site annotations, it searches for those regions of hm 

-#' ## that are at a minimal distance from a transcription start site (TSS) 

-#' ## and takes the first/closest one for each TSS, provided that such distance 

-#' ## is greater than 120K bases and joined 'tss' and 'hm' samples are obtained 

-#' ## from the same provider (joinby clause).

+#' # Given a dataset 'hm' and one called 'tss' with a sample including 

+#' # Transcription Start Site annotations, it searches for those regions of hm 

+#' # that are at a minimal distance from a transcription start site (TSS) 

+#' # and takes the first/closest one for each TSS, provided that such distance 

+#' # is greater than 120K bases and joined 'tss' and 'hm' samples are obtained 

+#' # from the same provider (joinby clause).

 #' 

 #' init_gmql()

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

@@ -219,7 +215,6 @@ DLE <- function(value)

 DGE <- function(value)

 {

     check.DISTAL(value)

-  

     list <- list(value = as.integer(value))

     ## Set the name for the class

     class(list) <- c("DGE","DISTAL")

@@ -249,12 +244,12 @@ DGE <- function(value)

 #' @examples

 #' 

 #' 

-#' ### Given a dataset 'hm' and one called 'tss' with a sample including 

-#' ## Transcription Start Site annotations, it searches for those regions of hm 

-#' ## that are at a minimal distance from a transcription start site (TSS) 

-#' ## and takes the first/closest one for each TSS, 

-#' ## provided that such distance is greater than 120K bases and joined 'tss' 

-#' ## and 'hm' samples are obtained from the same provider (joinby clause).

+#' # Given a dataset 'hm' and one called 'tss' with a sample including 

+#' # Transcription Start Site annotations, it searches for those regions of hm 

+#' # that are at a minimal distance from a transcription start site (TSS) 

+#' # and takes the first/closest one for each TSS, 

+#' # provided that such distance is greater than 120K bases and joined 'tss' 

+#' # and 'hm' samples are obtained from the same provider (joinby clause).

 #' 

 #' init_gmql()

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

@@ -270,7 +265,6 @@ DGE <- function(value)

 MD <- function(value)

 {

     check.DISTAL(value)

-  

     list <- list(value = as.integer(value))

     ## Set the name for the class

     class(list) <- c("MD","DISTAL")

@@ -300,12 +294,12 @@ MD <- function(value)

 #' @examples

 #' 

 #'

-#' ### Given a dataset 'hm' and one called 'tss' with a sample including 

-#' ## Transcription Start Site annotations, it searches for those regions of hm 

-#' ## that are at a minimal distance from a transcription start site (TSS) 

-#' ## and takes the first/closest one for each TSS, provided that such distance 

-#' ## is greater than 120K bases and joined 'tss' and 'hm' samples are obtained 

-#' ## from the same provider (joinby clause).

+#' # Given a dataset 'hm' and one called 'tss' with a sample including 

+#' # Transcription Start Site annotations, it searches for those regions of hm 

+#' # that are at a minimal distance from a transcription start site (TSS) 

+#' # and takes the first/closest one for each TSS, provided that such distance 

+#' # is greater than 120K bases and joined 'tss' and 'hm' samples are obtained 

+#' # from the same provider (joinby clause).

 #' 

 #' init_gmql()

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

@@ -352,12 +346,12 @@ as.character.UP <- function(obj) {

 #' @examples

 #' 

 #' 

-#' ### Given a dataset 'hm' and one called 'tss' with a sample including 

-#' ## Transcription Start Site annotations, it searches for those regions of hm 

-#' ## that are at a minimal distance from a transcription start site (TSS) 

-#' ## and takes the first/closest one for each TSS, provided that such distance 

-#' ## is greater than 12K bases and joined 'tss' and 'hm' samples are obtained 

-#' ## from the same provider (joinby clause).

+#' # Given a dataset 'hm' and one called 'tss' with a sample including 

+#' # Transcription Start Site annotations, it searches for those regions of hm 

+#' # that are at a minimal distance from a transcription start site (TSS) 

+#' # and takes the first/closest one for each TSS, provided that such distance 

+#' # is greater than 12K bases and joined 'tss' and 'hm' samples are obtained 

+#' # from the same provider (joinby clause).

 #' 

 #' init_gmql()

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

@@ -365,8 +359,8 @@ as.character.UP <- function(obj) {

 #' TSS = read_dataset(test_path)

 #' HM = read_dataset(test_path2)

 #' join_data = join(TSS, HM, 

-#' genometric_predicate = list(list(MD(1), DGE(12000), DOWN())), c("provider"), 

-#' region_output = "RIGHT")

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

+#' c("provider"), region_output = "RIGHT")

 #' 

 #' 

 #' @export

@@ -23,12 +23,12 @@ region is less than, or equal to, 'value' bases.

 }

 \examples{

-### Given a dataset HM and one called TSS with a sample including 

-## Transcription Start Site annotations, it searches for those regions of hm 

-## that are at a minimal distance from a transcription start site 'TSS' 

-## and takes the first/closest one for each TSS, provided that such distance 

-## is greater than 12 bases and joined TSS and HM samples are obtained 

-## from the same provider 'joinby clause'.

+## Given a dataset HM and one called TSS with a sample including 

+# Transcription Start Site annotations, it searches for those regions of hm 

+# that are at a minimal distance from a transcription start site 'TSS' 

+# and takes the first/closest one for each TSS, provided that such distance 

+# is greater than 12 bases and joined TSS and HM samples are obtained 

+# from the same provider 'joinby clause'.

 init_gmql()

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

@@ -24,12 +24,12 @@ or equal to, 'value' bases.

 }

 \examples{

-## Given a dataset 'hm' and one called 'tss' with a sample including 

-## Transcription Start Site annotations, it searches for those regions of hm 

-## that are at a minimal distance from a transcription start site (TSS) 

-## and takes the first/closest one for each TSS, provided that such distance 

-## is greater than 120K bases and joined 'tss' and 'hm' samples are obtained 

-## from the same provider (joinby clause).

+# Given a dataset 'hm' and one called 'tss' with a sample including 

+# Transcription Start Site annotations, it searches for those regions of hm 

+# that are at a minimal distance from a transcription start site (TSS) 

+# and takes the first/closest one for each TSS, provided that such distance 

+# is greater than 120K bases and joined 'tss' and 'hm' samples are obtained 

+# from the same provider (joinby clause).

 init_gmql()

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

@@ -24,12 +24,12 @@ that their distance from the anchor region is less than, or equal to,

 }

 \examples{

-### Given a dataset HM and one called TSS with a sample including 

-## Transcription Start Site annotations, it searches for those regions of hm 

-## that are at a minimal distance from a transcription start site (TSS) 

-## and takes the first/closest one for each TSS, 

-## provided that such distance is lesser than 1200 bases and joined TSS 

-## and HM samples are obtained from the same provider (joinby clause).

+## Given a dataset HM and one called TSS with a sample including 

+# Transcription Start Site annotations, it searches for those regions of hm 

+# that are at a minimal distance from a transcription start site (TSS) 

+# and takes the first/closest one for each TSS, 

+# provided that such distance is lesser than 1200 bases and joined TSS 

+# and HM samples are obtained from the same provider (joinby clause).

 init_gmql()

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

@@ -40,7 +40,6 @@ join_data = join(TSS, HM,

 genometric_predicate = list(list(MD(1), DL(1200))), c("provider"), 

 region_output = "RIGHT")

-

 }

 \seealso{

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

@@ -28,12 +28,12 @@ the anchor region

 }

 \examples{

-### Given a dataset HM and one called TSS with a sample including 

-## Transcription Start Site annotations, it searches for those regions of hm 

-## that are at a minimal distance from a transcription start site (TSS) 

-## and takes the first/closest one for each TSS, provided that such distance 

-## is lesser than 120K bases and joined TSS and HM samples are obtained 

-## from the same provider (joinby clause).

+## Given a dataset HM and one called TSS with a sample including 

+# Transcription Start Site annotations, it searches for those regions of hm 

+# that are at a minimal distance from a transcription start site (TSS) 

+# and takes the first/closest one for each TSS, provided that such distance 

+# is lesser than 120K bases and joined TSS and HM samples are obtained 

+# from the same provider (joinby clause).

 init_gmql()

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

@@ -24,12 +24,12 @@ directions of the genome.

 \examples{

-### Given a dataset 'hm' and one called 'tss' with a sample including 

-## Transcription Start Site annotations, it searches for those regions of hm 

-## that are at a minimal distance from a transcription start site (TSS) 

-## and takes the first/closest one for each TSS, provided that such distance 

-## is greater than 12K bases and joined 'tss' and 'hm' samples are obtained 

-## from the same provider (joinby clause).

+# Given a dataset 'hm' and one called 'tss' with a sample including 

+# Transcription Start Site annotations, it searches for those regions of hm 

+# that are at a minimal distance from a transcription start site (TSS) 

+# and takes the first/closest one for each TSS, provided that such distance 

+# is greater than 12K bases and joined 'tss' and 'hm' samples are obtained 

+# from the same provider (joinby clause).

 init_gmql()

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

@@ -37,8 +37,8 @@ test_path2 <- system.file("example", "DATASET_GDM", package = "RGMQL")

 TSS = read_dataset(test_path)

 HM = read_dataset(test_path2)

 join_data = join(TSS, HM, 

-genometric_predicate = list(list(MD(1), DGE(12000), DOWN())), c("provider"), 

-region_output = "RIGHT")

+genometric_predicate = list(list(MD(1), DGE(12000), DOWN())), 

+c("provider"), region_output = "RIGHT")

 }

@@ -28,8 +28,8 @@ r = read_dataset(test_path)

 ## select with condition

 ## the first and the third attribute are DEF the second one is EXACT

-s = select(r, semi_join = list("cell_type", EXACT("cell"), "attribute_tag"), 

-semi_join_dataset = r)

+s = select(r, semi_join = list("cell_type", EXACT("cell"), 

+"attribute_tag"), semi_join_dataset = r)

 \dontrun{

@@ -27,12 +27,12 @@ if they exceed the 'value' limit.

 \examples{

-### Given a dataset 'hm' and one called 'tss' with a sample including 

-## Transcription Start Site annotations, it searches for those regions of hm 

-## that are at a minimal distance from a transcription start site (TSS) 

-## and takes the first/closest one for each TSS, 

-## provided that such distance is greater than 120K bases and joined 'tss' 

-## and 'hm' samples are obtained from the same provider (joinby clause).

+# Given a dataset 'hm' and one called 'tss' with a sample including 

+# Transcription Start Site annotations, it searches for those regions of hm 

+# that are at a minimal distance from a transcription start site (TSS) 

+# and takes the first/closest one for each TSS, 

+# provided that such distance is greater than 120K bases and joined 'tss' 

+# and 'hm' samples are obtained from the same provider (joinby clause).

 init_gmql()

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

@@ -24,12 +24,12 @@ the directions of the genome.

 \examples{

-### Given a dataset 'hm' and one called 'tss' with a sample including 

-## Transcription Start Site annotations, it searches for those regions of hm 

-## that are at a minimal distance from a transcription start site (TSS) 

-## and takes the first/closest one for each TSS, provided that such distance 

-## is greater than 120K bases and joined 'tss' and 'hm' samples are obtained 

-## from the same provider (joinby clause).

+# Given a dataset 'hm' and one called 'tss' with a sample including 

+# Transcription Start Site annotations, it searches for those regions of hm 

+# that are at a minimal distance from a transcription start site (TSS) 

+# and takes the first/closest one for each TSS, provided that such distance 

+# is greater than 120K bases and joined 'tss' and 'hm' samples are obtained 

+# from the same provider (joinby clause).

 init_gmql()

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

@@ -53,9 +53,10 @@ evaluation: the two attributes match if both end with value.}

 \item{aggregates}{list 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}}, 

-\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}}.

+\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 

@@ -75,8 +76,8 @@ It takes as input a dataset containing one or more samples and returns

 another dataset (with a single sample, if no \emph{groupby} option is 

 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).

+The attributes of the output genomic regions are only the region 

+coordinates, and Jaccard indexes (JaccardIntersect and 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 

@@ -42,9 +42,9 @@ for the subsequent GMQL function

 }

 \description{

 It produces one sample in the result for each sample of the left operand,

-by keeping the same metadata of the left input sample and only those regions

-(with their schema and values) of the left input sample which do not 

-intersect with any region in the right operand sample.

+by keeping the same metadata of the left input sample and only those 

+regions (with their schema and values) of the left input sample which 

+do not intersect with any region in the right operand sample.

 The optional \emph{joinby} clause is used to extract a subset of couples

 from the cartesian product of two dataset 

 \emph{left_input_data} x \emph{right_input_data} on which to apply 

@@ -12,9 +12,10 @@ extend(input_data, metadata = NULL)

 \item{metadata}{list 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}}, 

-\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}}.

+\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 

@@ -51,9 +51,10 @@ evaluation: the two attributes match if both end with value.}

 \item{aggregates}{list 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}}, 

-\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}}.

+\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 

@@ -53,9 +53,10 @@ evaluation: the two attributes match if both end with value.}

 \item{aggregates}{list 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}}, 

-\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}}.

+\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 

@@ -49,8 +49,8 @@ no output is produced}

 \item{contig: outputs the concatenation between the left_input_data and 

 right_input_data regions that satisfy the genometric predicate, 

 (i.e. the output regionis defined as having left (right) coordinates

-equal to the minimum (maximum) of the corresponding coordinate values in the 

-left_input_data and right_input_data regions satisfying 

+equal to the minimum (maximum) of the corresponding coordinate values 

+in the left_input_data and right_input_data regions satisfying 

 the genometric predicate)}

 }}

 }

@@ -71,12 +71,12 @@ with their attribute names prefixed with left or right respectively.

 }

 \examples{

-## Given a dataset 'hm' and one called 'tss' with a sample including 

-## Transcription Start Site annotations, it searches for those regions of hm 

-## that are at a minimal distance from a transcription start site (TSS) 

-## and takes the first/closest one for each TSS, provided that such distance 

-## is lesser than 120K bases and joined 'tss' and 'hm' samples are obtained 

-## from the same provider (joinby clause).

+# Given a dataset 'hm' and one called 'tss' with a sample including 

+# Transcription Start Site annotations, it searches for those regions of hm 

+# that are at a minimal distance from a transcription start site (TSS) 

+# and takes the first/closest one for each TSS, provided that such distance 

+# is lesser than 120K bases and joined 'tss' and 'hm' samples are obtained 

+# from the same provider (joinby clause).

 init_gmql()

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

@@ -14,9 +14,10 @@ map(left_input_data, right_input_data, aggregates = NULL, joinBy = NULL)

 \item{aggregates}{list 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}}, 

-\code{\link{COUNT}},\code{\link{MIN}}, \code{\link{MAX}}, \code{\link{AVG}}, 

-\code{\link{STD}}, \code{\link{MEDIAN}},\code{\link{BAG}}, 

-\code{\link{BAGD}}, \code{\link{Q1}}, \code{\link{Q2}}, \code{\link{Q3}}.

+\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

 Argument of 'aggregate' must exist in schema

 Two style are allowed:

@@ -54,8 +55,8 @@ for each region of each sample in the left dataset;

 The number of generated output samples is the Cartesian product 

 of the samples in the two input datasets;

 each output sample has the same regions as the related input left sample, 

-with their attributes and values, plus the attributes computed as aggregates 

-over right region values.

+with their attributes and values, plus the attributes computed as 

+aggregates over right region values.