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

 Package: RGMQL

 Type: Package

 Title: GenoMetric Query Language for R/Bioconductor

-Version: 0.99.41

+Version: 0.99.42

 Author: Simone Pallotta, Marco Masseroli

 Maintainer: Simone Pallotta <simonepallotta@hotmail.com>

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

@@ -11,7 +11,7 @@ Description: This package brings the GenoMetric Query Language (GMQL)

 	GMQL adopts algorithms efficiently designed for big data using cloud-computing 

     technologies (like Apache Hadoop and Spark) allowing GMQL to run on modern

 	infrastructures, in order to achieve scalability and high performance.

-	It allows to to create, manipulate and extract genomic data from different 

+	It allows to create, manipulate and extract genomic data from different 

 	data sources both locally and remotely. Our RGMQL functions allow complex 

 	queries and processing leveraging on the R idiomatic paradigm. 

 	The RGMQL package also provides a rich set of ancillary classes that allow

@@ -40,8 +40,8 @@ export(import_gmql)

 export(init_gmql)

 export(login_gmql)

 export(logout_gmql)

-export(read_GMQL)

 export(read_GRangesList)

+export(read_gmql)

 export(remote_processing)

 export(run_query)

 export(run_query_fromfile)

@@ -20,7 +20,7 @@

 #' @examples

 #' 

 #' ## This statement defines the path to the subdirectory "example" of the 

-#' ## package "RGMQL" and import as GRangesList the GMQL dataset

+#' ## package "RGMQL" and imports as GRangesList the contained GMQL dataset

 #' 

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

 #' grl = import_gmql(test_path, TRUE)

@@ -25,24 +25,24 @@

 #' The GMQL dataset is made up by two different file types:

 #'

 #' \itemize{

-#' \item{metadata files: they contain metadata associated to corrisponding 

+#' \item{metadata files: they contain metadata associated with corrisponding 

 #' sample.}

-#' \item{region files: they contain many genomic regions data.}

-#' \item{region schema file: XML file that contains region attribute name 

+#' \item{region files: they contain genomic regions data.}

+#' \item{region schema file: XML file that contains region attribute names 

 #' (e.g. chr, start, end, pvalue)}

 #' }

-#' Region sample files and metadata files are associated through file name:

+#' Sample region files and metadata files are associated through file name:

 #' for example S_0001.gdm for region file and S_0001.gdm.meta for 

 #' its metadata file

 #'

 #'

 #' @examples

 #' 

-#' ## load and attach add-on GenomicRanges package

+#' ## Load and attach add-on GenomicRanges package

 #' library(GenomicRanges)

 #' 

-#' ## These statemens create two GRanges with the region attribute: seqnames, 

-#' ## ranges (region coordinates) and strand, plus two column element:  

+#' ## These statemens create two GRanges with the region attributes: seqnames, 

+#' ## ranges (region coordinates) and strand, plus two column elements:  

 #' ## score and GC

 #' 

 #' gr1 <- GRanges(seqnames = "chr2", ranges = IRanges(3, 6), strand = "+", 

@@ -56,11 +56,11 @@

 #' grl = GRangesList(gr1, gr2)

 #' 

 #' ## This statement defines the path to the subdirectory "example" of the 

-#' ## package "RGMQL" and export the GRangesList as GMQL dataset using the 

+#' ## package "RGMQL" and exports the GRangesList as GMQL datasets using the 

 #' ## last name of 'dir_out' path as dataset name

 #' 

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

-#' export_gmql(grl, test_out_path,TRUE)

+#' export_gmql(grl, test_out_path, TRUE)

 #' 

 #' 

 #' @export

@@ -73,7 +73,8 @@ take_value.META_AGGREGATES <- function(obj){

 #' \item{COUNT: It prepares input parameter to be passed to the library 

 #' function count, performing all the type conversions needed }

 #' \item{COUNTSAMP: It prepares input parameter to be passed to the library 

-#' function third quartile, performing all the type conversions needed }

+#' function countsamp, performing all the type conversions needed.

+#' It is used only with group_by functions}

 #' \item{MIN: It prepares input parameter to be passed to the library 

 #' function minimum, performing all the type conversions needed  }

 #' \item{MAX: It prepares input parameter to be passed to the library 

@@ -88,7 +89,7 @@ take_value.META_AGGREGATES <- function(obj){

 #' function bag; this function creates comma-separated strings of 

 #' attribute values, performing all the type conversions needed}

 #' \item{BAGD: It prepares input parameter to be passed to the library 

-#' function bag; this function creates comma-separated strings of distinct 

+#' function bagd; this function creates comma-separated strings of distinct 

 #' attribute values, performing all the type conversions needed}

 #' \item{Q1: It prepares input parameter to be passed to the library 

 #' function fist quartile, performing all the type conversions needed}

@@ -112,22 +113,22 @@ take_value.META_AGGREGATES <- function(obj){

 #' 

 #' init_gmql()

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

-#' exp = read_GMQL(test_path)

+#' exp = read_gmql(test_path)

 #' 

 #' ## This statement copies all samples of exp dataset into res dataset, and 

-#' ## then calculates new metadata attribute for each of them: 

-#' ## sum_score is the sum of score of the sample regions.

+#' ## then calculates new metadata attribute 'sum_score' for each of them: 

+#' ## sum_score is the sum of score values of the sample regions.

 #' 

 #' res = extend(exp, sum_score = SUM("score"))

 #' 

 #' ## This statement copies all samples of exp dataset into res dataset, 

-#' ## and then calculates new metadata attribute for each of them: 

+#' ## and then calculates new metadata attribute 'min_pvalue' for each of them: 

 #' ## min_pvalue is the minimum pvalue of the sample regions.

 #' 

 #' res = extend(exp, min_pvalue = MIN("pvalue"))

 #' 

 #' ## This statement copies all samples of exp dataset into res dataset, 

-#' ## and then calculates new metadata attribute for each of them: 

+#' ## and then calculates new metadata attribute 'max_score' for each of them: 

 #' ## max_score is the maximum score of the sample regions.

 #' 

 #' res = extend(exp, max_score = MAX("score"))

@@ -135,30 +136,31 @@ take_value.META_AGGREGATES <- function(obj){

 #' ## The following cover operation produces output regions where at least 2 

 #' ## and at most 3 regions of exp dataset overlap, having as resulting region 

 #' ## attribute the average signal of the overlapping regions; 

-#' ## the result has one sample for each input cell.

+#' ## the result has one sample for each input cell value.

 #' 

 #' res = cover(exp, 2, 3, groupBy = conds("cell"), avg_signal = AVG("signal"))

 #' 

-#' ## This statement copies all samples of DATA dataset into OUT dataset, 

-#' ## and then for each of them it adds another metadata attribute, allScores, 

+#' ## This statement copies all samples of 'exp' dataset into 'out' dataset, 

+#' ## and then for each of them it adds another metadata attribute, allScore, 

 #' ## which is the aggregation comma-separated list of all the values 

 #' ## that the region attribute score takes in the sample.

 #' 

 #' out = extend(exp, allScore = BAG("score"))

 #' 

 #' ## This statement counts the regions in each sample and stores their number 

-#' ## as value of the new metadata RegionCount attribute of the sample.

+#' ## as value of the new metadata 'RegionCount' attribute of the sample.

 #' 

 #' out = extend(exp, RegionCount = COUNT())

 #' 

 #' ## This statement copies all samples of exp dataset into res dataset, 

-#' ## and then calculates new metadata attribute for each of them: 

-#' ## std_score is the standard deviation score of the sample regions.

+#' ## and then calculates new metadata attribute 'std_score' for each of them: 

+#' ## std_score is the standard deviation of the score values of the sample 

+#' ## regions.

 #' 

 #' res = extend(exp, std_score = STD("score"))

 #' 

 #' ## This statement copies all samples of exp dataset into res dataset, 

-#' ## and then calculates new metadata attribute for each of them: 

+#' ## and then calculates new metadata attribute 'm_score' for each of them: 

 #' ## m_score is the median score of the sample regions.

 #' 

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

@@ -42,7 +42,7 @@ print.PARAMETER <- function(obj){

 #' 

 #' init_gmql()

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

-#' exp = read_GMQL(test_path)

+#' exp = read_gmql(test_path)

 #' 

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

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

@@ -61,8 +61,8 @@ print.PARAMETER <- function(obj){

 #' 

 #' ## 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.

+#' ## minimum of overlapping regions in the input samples equal to half of 

+#' ## the number of input samples, up to any amount of overlapping regions.

 #' 

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

 #' 

@@ -37,74 +37,74 @@ check.DISTAL <- function(value)

 #' \itemize{

 #' \item{DL: It denotes the less distance clause, 

 #' which selects all the regions of a joined experiment dataset sample such 

-#' that their distance from the anchor region of a joined reference dataset 

+#' that their distance from the anchor region of the joined reference dataset 

 #' sample is less than 'value' bases.}

-#' \item{DLE: It denotes the less distance clause, 

+#' \item{DLE: It denotes the less equal distance clause, 

 #' which selects all the regions of a joined experiment dataset sample such 

-#' that their distance from the anchor region of a joined reference dataset 

+#' that their distance from the anchor region of the joined reference dataset 

 #' sample is less than, or equal to, 'value' bases.}

-#' \item{DG: It denotes the less distance clause, 

+#' \item{DG: It denotes the great distance clause, 

 #' which selects all the regions of a joined experiment dataset sample such 

-#' that their distance from the anchor region of a joined reference dataset 

+#' that their distance from the anchor region of the joined reference dataset 

 #' sample is greater than 'value' bases. }

-#' \item{DGE: It denotes the less distance clause, 

+#' \item{DGE: It denotes the great equal distance clause, 

 #' which selects all the regions of a joined experiment dataset sample such 

-#' that their distance from the anchor region of a joined reference dataset 

+#' that their distance from the anchor region of the joined reference dataset 

 #' sample is greater than, or equal to, 'value' bases.}

 #' \item{MD: It denotes the minimum distance clause, which selects 

-#' the first 'value' regions of a joined experiment at minimial distance 

-#' from the anchor region of a joined reference dataset sample.}

+#' the first 'value' regions of the joined experiment at minimial distance 

+#' from the anchor region of the joined reference dataset sample.}

 #' \item{UP: It denotes the upstream direction of the genome.

-#' It makes predicates to be hold on the upstream of the regions of a joined 

-#' experiment dataset sample.

-#' UP is true when region of a joined experiment dataset sample is in the

-#' upstream genome of the anchor region of a joined reference dataset sample.

+#' It makes predicates to be hold on the upstream of the regions of the joined 

+#' reference dataset sample.

+#' UP is true when region of the joined experiment dataset sample is in the

+#' upstream genome of the anchor region of the joined reference dataset sample.

 #' When this clause is not present, distal conditions apply to both 

 #' directions of the genome.}

 #' \item{DOWN:  It denotes the downstream direction of the genome.

-#' It makes predicates to be hold on the downstream of the regions of a joined 

-#' experiment dataset sample.

-#' UP is true when region of a joined experiment dataset sample is in the

-#' downstream genome of the anchor region of a joined reference dataset sample.

-#' When this clause is not present, distal conditions apply to both 

+#' It makes predicates to be hold on the downstream of the regions of the 

+#' joined reference dataset sample.

+#' DOWN is true when region of the joined experiment dataset sample is in the

+#' downstream genome of the anchor region of the joined reference dataset 

+#' sample. When this clause is not present, distal conditions apply to both 

 #' directions of the genome.}

 #' }

 #' 

 #' @param value string identifying distance between genomic regions 

-#' in base pair, 

+#' in base pair

 #'

 #' @return Distal object

 #' 

 #' @examples

-#' ## Thi statement initializes and runs the GMQL server for local execution 

+#' ## 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 folders "DATASET" and "DATASET_GDM" in the subdirectory 

-#' ## "example" of the package "RGMQL" and opens such folder as a GMQL 

-#' ## dataset named "TSS" and "HM" respectively using customParser

+#' ## "example" of the package "RGMQL", and opens such folders as a GMQL 

+#' ## datasets named "TSS" and "HM", respectively, using customParser

 #' 

 #' init_gmql()

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

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

-#' TSS = read_GMQL(test_path)

-#' HM = read_GMQL(test_path2)

+#' TSS = read_gmql(test_path)

+#' HM = read_gmql(test_path2)

 #' 

 #' ## 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).

+#' ## Transcription Start Site annotations, this statement  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).

 #' 

 #' join_data = merge(TSS, HM, 

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

 #' region_output = "RIGHT")

 #'

-#' ## 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, this statement searches for those 

+#' ## regions of HM that are downstream and 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).

 #' 

 #' join_data = merge(TSS, HM, 

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

@@ -50,41 +50,42 @@ as.character.OPERATOR <- function(obj) {

 #' @param value string identifying name of metadata attribute

 #' @param type string identifying the type of the attribute value;

 #' it must be: INTEGER, DOUBLE or STRING

+#' For NIL() function, only INTEGER and DOUBLE are allowed

 #'

 #' @return Operator object

 #' 

 #' 

 #' @examples

-#' ## Thi statement initializes and runs the GMQL server for local execution 

+#' ## 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 folders "DATASET" in the subdirectory "example" 

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

 #' ## of the package "RGMQL" and opens such folder as a GMQL dataset 

 #' ## named "exp"

 #' 

 #' init_gmql()

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

-#' exp = read_GMQL(test_path)

+#' exp = read_gmql(test_path)

 #' 

-#' ## This statement allows to select, in all input sample, all those regions 

+#' ## This statement allows to select, in all input samples, all those regions 

 #' ## for which the region attribute score has a value which is greater 

 #' ## than the metadata attribute value "avg_score" in their sample.

 #' 

 #' data = filter(exp, r_predicate = score > META("avg_score"))

 #' 

-#' ## This statement defines a new numeric region attribute with "null" value. 

+#' ## This statement defines new numeric region attributes with "null" value. 

 #' ## The syntax for creating a new attribute with null value is 

-#' ## attribute_name = NULL(TYPE), where type may be INTEGER, DOUBLE or STRING.

+#' ## attribute_name = NULL(TYPE), where type may be INTEGER or DOUBLE.

 #' 

 #' out = select(exp, regions_update = list(signal = NIL("INTEGER"), 

 #' pvalue = NIL("DOUBLE")))

 #' 

-#' ## This statement allows to build an output dataset out such that all 

-#' ## the samples from the input dataset exp are conserved, 

+#' ## This statement allows to build an output dataset named 'out' such that 

+#' ## all the samples from the input dataset 'exp' are conserved, 

 #' ## as well as their region attributes (and their values) 

 #' ## and their metadata attributes (and their values). 

-#' ## The new metadata attribute concSq is added to all output samples 

+#' ## The new metadata attribute 'concSq' is added to all output samples 

 #' ## with value correspondent to the mathematical squared root 

-#' ## of the pre-existing metadata attribute concentration.

+#' ## of the pre-existing metadata attribute 'concentration'.

 #' 

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

 #' 

@@ -96,3 +96,25 @@

     if(length(value)>1)

         stop("no multiple string")

 }

+

+.is_login_expired <- function(url)

+{

+    if(exists("GMQL_credentials", envir = .GlobalEnv))

+    {

+        if(exists("authToken", where = GMQL_credentials))

+        {

+            authToken <- GMQL_credentials$authToken

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

+            h <- c('Accept' = 'Application/json', 'X-Auth-Token' = authToken)

+            URL <- paste0(url,"/user")

+            req <- httr::GET(URL,httr::add_headers(h))

+            if(req$status_code !=200)

+                return(TRUE)

+            else

+                return(FALSE)

+        }

+    }

+    return(TRUE)

+}

+

+

@@ -21,54 +21,55 @@

 #' if NULL no filtering action occures

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

 #' @param metadata_prefix vector of strings that will support the metadata

-#' filtering. If defined, each 'metadata' are concatenated with the 

+#' filtering. If defined, each 'metadata' is concatenated with the 

 #' corresponding prefix.

-#' @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 

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

+#' attributes  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

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

+#' value of the metadata attribute named "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 specified

+#' by 'regions' input parameter

 #'

 #' @details

-#' This function works only with datatset or GRangesList which samples or 

-#' Granges have the same regions coordinates (chr, ranges, strand)

+#' This function works only with datatset or GRangesList all whose samples or 

+#' Granges have the same region coordinates (chr, ranges, strand)

 #' 

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

-#' into metadata() function associated to Grangeslist.

+#' In case of GRangesList data input, the function searches for metadata

+#' into metadata() function associated to GRangesList.

 #'

 #' @return GRanges with selected regions

 #'

 #' @examples

 #' 

-#' ## This statement defines the path to the folders "DATASET" in the 

-#' ## subdirectory "example" of the package "RGMQL" and filter such folder 

-#' ## dataset including at output only "pvalue" and "peak" regions

+#' ## This statement defines the path to the folder "DATASET" in the 

+#' ## subdirectory "example" of the package "RGMQL" and filters such folder 

+#' ## dataset including at output only "pvalue" and "peak" region attributes

 #' 

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

-#' filter_and_extract(test_path, regions = c("pvalue", "peak"))

+#' filter_and_extract(test_path, region_attributes = c("pvalue", "peak"))

 #' 

-#' ## This statement import a GMQL dataset as GRangesList and filter it 

-#' ## including at output only "pvalue" and "peak" regions

+#' ## This statement imports a GMQL dataset as GRangesList and filters it 

+#' ## including at output only "pvalue" and "peak" region attributes

 #' 

 #' grl = import_gmql(test_path, TRUE)

-#' filter_and_extract(grl, regions = c("pvalue", "peak"))

+#' filter_and_extract(grl, region_attributes = c("pvalue", "peak"))

 #'

 #'

 #' @export

 #'

 filter_and_extract <- function(data, metadata = NULL,

-                                metadata_prefix = NULL, regions = NULL, 

-                                suffix = "antibody_target")

+                    metadata_prefix = NULL, region_attributes = NULL, 

+                    suffix = "antibody_target")

 {

     if(is(data,"GRangesList"))

-        .extract_from_GRangesList(data, metadata, metadata_prefix, regions, 

-                                    suffix)

+        .extract_from_GRangesList(data, metadata, metadata_prefix, 

+            region_attributes, suffix)

     else

-        .extract_from_dataset(data, metadata, metadata_prefix, regions, 

-                                    suffix)

+        .extract_from_dataset(data, metadata, metadata_prefix, 

+            region_attributes, suffix)

 }

 .extract_from_dataset <- function(datasetName, metadata, metadata_prefix, 

@@ -94,40 +95,43 @@ filter_and_extract <- function(data, metadata = NULL,

     vector_field <- .schema_header(datasetName)

+    

     if(length(gdm_meta_files))

     {

-        samples_with_suffix <- .check_metadata_files(metadata,metadata_prefix,

-                                                gdm_meta_files, suffix)

+        samples_file <- .check_metadata_files(metadata,metadata_prefix,

+                                                gdm_meta_files)

-        samples_file <- lapply(samples_with_suffix, function(x) x$sample)

-        suffix_vec <- lapply(samples_with_suffix, function(x) x$suffix)

-        suffixes <- unlist(suffix_vec)

-        samples_to_read <- unlist(samples_file)

+        samples_meta_to_read <- unlist(samples_file)

-        if(length(samples_to_read))

-            samples_to_read <- gsub(".meta$", "", samples_to_read)

+        if(length(samples_meta_to_read))

+            samples_to_read <- gsub(".meta$", "", samples_meta_to_read)

         else

+        {

             samples_to_read <- gsub(".meta$", "", gdm_meta_files)

+            samples_meta_to_read <- gtf_meta_files

+            

+        }

+        suffix_vec <- .get_suffix(suffix, FALSE, samples_meta_to_read)

         granges <- .parse_gdm_files(vector_field,samples_to_read,regions,

-                                                        suffixes)

+                                        suffix_vec)

     }

     else

     {

-        samples_with_suffix <- .check_metadata_files(metadata,metadata_prefix,

-                                                    gtf_meta_files, suffix)

-        

-        samples_file <- lapply(samples_with_suffix, function(x) x$sample)

-        suffix_vec <- lapply(samples_with_suffix, function(x) x$suffix)

-        suffixes <- unlist(suffix_vec)

-        samples_to_read <- unlist(samples_file)

+        samples_file <- .check_metadata_files(metadata,metadata_prefix,

+                                                    gtf_meta_files)

+        samples_meta_to_read <- unlist(samples_file)

-        if(length(samples_to_read))

-            samples_to_read <- gsub(".meta$", "", samples_to_read)

+        if(length(samples_meta_to_read))

+            samples_to_read <- gsub(".meta$", "", samples_meta_to_read)

         else

+        {

             samples_to_read <- gsub(".meta$", "", gtf_meta_files)

+            samples_meta_to_read <- gtf_meta_files

+        }

-        granges <- .parse_gtf_files(samples_to_read, regions, suffixes)

+        suffix_vec <- .get_suffix(suffix, FALSE, samples_meta_to_read)

+        granges <- .parse_gtf_files(samples_to_read, regions,suffix_vec)

     }

 }

@@ -141,8 +145,7 @@ filter_and_extract <- function(data, metadata = NULL,

         stop("rangesList empty")

     meta_list <- metadata(rangesList)

-    samples <- .check_metadata_list(metadata, metadata_prefix, meta_list, 

-                                        suffix)

+    samples <- .check_metadata_list(metadata, metadata_prefix, meta_list)

     if(!length(unlist(samples)))

         samples <- rangesList

     else

@@ -150,26 +153,73 @@ filter_and_extract <- function(data, metadata = NULL,

         index <- unlist(samples)

         samples <- rangesList[c(index)]

     }

-    granges <- .parse_Granges(samples,regions)

+    new_meta_list <- metadata(samples)

+    suffix_vec <- .get_suffix(suffix, TRUE, new_meta_list)

+    granges <- .parse_Granges(samples,regions,suffix_vec)

 }

-.parse_Granges <- function(region_list,regions)

+.parse_Granges <- function(region_list,regions,suffixes)

 {

+    if(is.null(suffixes))

+        suffixes = ""

+    

     g1 <- region_list[[1]]

     elementMetadata(g1) <- NULL

     if(!is.null(regions))

     {

-        DF_list <- lapply(region_list, function(g_x){

+        DF_list <- mapply(function(g_x,h){

             meta <- elementMetadata(g_x)[regions]

+            if(h!="")

+                names(meta) <- paste(regions,h,sep = ".")

             data.frame(meta)

-        })

+        },region_list, suffixes, SIMPLIFY = FALSE)

         DF_only_regions <- dplyr::bind_cols(DF_list)

         elementMetadata(g1) <- DF_only_regions

     }

     g1

 }

-.check_metadata_list <- function(metadata,metadata_prefix,meta_list,col_name)

+.get_suffix <- function(col_name, from_list, meta_fl)

+{

+    suffix <- paste0(col_name,"$")

+    

+    if(from_list)

+    {

+        meta_list <- mapply(function(x,index){

+            vec_names <- names(x)

+            s_index <- grep(suffix,vec_names)

+            first_index <- s_index[1]

+            suffix <- unlist(x[first_index]) # ne prendo solo uno

+            names(suffix) <- NULL

+        

+            #if found retrieve samples that has at least one choosen metadata

+            if(first_index && !is.na(first_index))

+                suffix

+            else

+                ""

+        }, meta_fl, seq_along(meta_fl)) 

+    }

+    else

+    {

+        meta_list <- vapply(meta_fl, function(x){

+            list <- .add_metadata(x)

+            vec_names <- names(list)

+            index <- grep(suffix,vec_names)

+            first_index <- index[1]

+            suffix <- unlist(list[first_index]) # ne prendo solo uno

+            names(suffix) <- NULL

+            #if found retrieve samples that has at least one choosen metadata

+            if(first_index && !is.na(first_index))

+                suffix

+            else

+                ""

+        },character(1))

+    }

+    names(meta_list) <- NULL

+    meta_list

+}

+

+.check_metadata_list <- function(metadata,metadata_prefix,meta_list)

 {

     vec_meta <- paste0(metadata_prefix,metadata)

     list <- mapply(function(x,index){

@@ -184,9 +234,8 @@ filter_and_extract <- function(data, metadata = NULL,

     }, meta_list, seq_along(meta_list))

 }

-.check_metadata_files <- function(metadata,metadata_prefix,meta_files,col_name)

+.check_metadata_files <- function(metadata,metadata_prefix,meta_files)

 {

-    suffix <- paste0(col_name,"$")

     vec_meta <- paste0(metadata_prefix,metadata)

     meta_list <- lapply(meta_files, function(x){

         list <- .add_metadata(x)

@@ -194,19 +243,11 @@ filter_and_extract <- function(data, metadata = NULL,

         a <- lapply(vec_meta, function(y)grep(y,vec_names))

         ## we would like that manage more index from grep

         found <- as.logical(length(unlist(a)))

-        index <- grep(suffix,vec_names)

-        suffix <- unlist(list[index])[1] # ne prendo solo uno

-        names(suffix) <- NULL

         #if found retrieve samples that has at least one choosen metadata

-        if(found)

-            list("sample" = x, "suffix" = suffix )

-        else

-            list("sample" = NULL, "suffix" = suffix )

-            

+        if(found){x}

     })

 }

-

 .parse_gtf_files <- function(gtf_region_files, regions, suffixes)

 {

     g1 <- rtracklayer::import(con = gtf_region_files[1], format = "gtf")

@@ -229,7 +270,8 @@ filter_and_extract <- function(data, metadata = NULL,

     g1

 }

-.parse_gdm_files <- function(vector_field,gdm_region_files,regions,suffixes)

+.parse_gdm_files <- function(vector_field,gdm_region_files,regions,

+                                suffixes)

 {

     #read first sample cause chromosome regions are the same for all samples

     df <- data.table::fread(gdm_region_files[1],col.names = vector_field,

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

 #' Method cover

 #'

 #' 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 

+#' 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 

@@ -13,14 +13,14 @@

 #' 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 attribute is added for 

+#' If aggregate functions are specified, a new region 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 

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

 #' in groups, each with distinct values of the grouping metadata attributes, 

 #' and the \emph{cover} operation is separately applied to each group, 

 #' yielding to one sample in the result for each group.

-#' Input samples that do not satisfy the \emph{groupby} condition 

+#' Input samples that do not satisfy the \emph{groupBy} condition 

 #' are disregarded.

 #' 

 #' @include AllClasses.R

@@ -61,7 +61,7 @@

 #' 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:

+#' attributes. Two styles are allowed:

 #' \itemize{

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

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

@@ -83,7 +83,7 @@

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

 #' \item{COVER: default value.}

 #' }

-#' Can be all caps or lowercase

+#' It can be all caps or lowercase

 #' 

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

 #' for the subsequent GMQLDataset method

@@ -97,10 +97,10 @@

 #' ## using customParser

 #' 

 #' init_gmql()

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

-#' exp = read_GMQL(test_path)

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

+#' exp = read_gmql(test_path)

 #'   

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

+#' ## 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.

@@ -109,7 +109,7 @@

 #'

 #' ## 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; 

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

 #' ## 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) 

@@ -4,13 +4,13 @@

 #' 

 #' @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.

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

-#' from the Cartesian product of two dataset \emph{x} and \emph{y} 

+#' and only those regions (with their attributes and values) of the left input 

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

+#' The optional \emph{joinBy} clause is used to extract a subset of pairs

+#' from the Cartesian product of the two input datasets \emph{x} and \emph{y} 

 #' on which to apply the DIFFERENCE operator:

-#' only those samples that have the same value for each attribute

-#' are considered when performing the difference.

+#' only those samples that have the same value for each specified metadata 

+#' attribute are considered when performing the difference.

 #'

 #' @importFrom rJava J .jnull .jarray

 #' @importFrom BiocGenerics setdiff

@@ -18,14 +18,15 @@

 #' @param x GMQLDataset class object

 #' @param y GMQLDataset class object

 #' @param joinBy \code{\link{conds}} function to support methods with 

-#' groupBy or JoinBy input paramter

+#' groupBy or JoinBy input parameter

 #' 

 #' @param is_exact single logical value: TRUE means that the region difference 

-#' is executed only on regions in left_input_data with exactly the same 

-#' coordinates of at least one region present in right_input_data; 

+#' is executed only on regions in 'x' dataset with exactly the same 

+#' coordinates of at least one region present in 'y' dataset; 

 #' if is_exact = FALSE, the difference is executed on all regions in 

-#' left_input_data that overlap with at least one region in right_input_data 

-#' (even just one base).

+#' left_input_data that overlap (even just one base) with at least one 

+#' region in 'y' 

+#' 

 #' 

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

 #' for the subsequent GMQLDataset method

@@ -40,19 +41,19 @@

 #' init_gmql()

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

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

-#' data1 = read_GMQL(test_path)

-#' data2 = read_GMQL(test_path2)

+#' data1 = read_gmql(test_path)

+#' data2 = read_gmql(test_path2)

 #' 

-#' ## This GMQL statement returns all the regions in the first dataset 

+#' ## This statement returns all the regions in the first dataset 

 #' ## that do not overlap any region in the second dataset.

 #' 

 #' out = setdiff(data1, data2)

 #' 

-#' ## This GMQL statement extracts for every pair of samples s1 in EXP1 

-#' ## and s2 in EXP2 having the same value of the metadata 

-#' ## attribute 'antibody_target' the regions that appear in s1 but 

-#' ## do not overlap any region in s2; 

-#' ## metadata of the result are the same as the metadata of s1.

+#' ## This statement extracts for every pair of samples s1 in data1 

+#' ## and s2 in data2 having the same value of the metadata 

+#' ## attribute 'cell' the regions that appear in s1 but 

+#' ## do not overlap any region in s2.

+#' ## Metadata of the result are the same as the metadata of s1.

 #' 

 #' out_t = setdiff(data1, data2, conds("cell"))

 #'

@@ -38,7 +38,7 @@

 #' 

 #' init_gmql()

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

-#' data <- read_GMQL(test_path)

+#' data <- read_gmql(test_path)

 #' 

 #' ## This statement counts the regions in each sample and stores their number 

 #' ## as value of the new metadata attribute RegionCount of the sample.

@@ -9,6 +9,45 @@ group_by.GMQLDateset <- function(.data, groupBy_meta = conds(),

 #' Method group_by

 #' 

 #' @description Wrapper to GMQL GROUP operator

+#' @description It performs the grouping of samples of the input dataset 

+#' based on one specified metadata and/or region attribute. If the metadata 

+#' attribute is multi-value, i.e., it assumes multiple values for sample 

+#' (e.g., both <disease, cancer> and <disease, diabetes>), the grouping 

+#' identifies different groups of samples for each attribute value combination 

+#' (e.g., group1 for samples that feature the combination <disease, cancer>, 

+#' group2 for samples that feature the combination <disease, diabetes>, 

+#' and group3 for samples that feature both combinations <disease, cancer> 

+#' and <disease, diabetes>). For each obtained group, it is possible to 

+#' request the evaluation of aggregate functions on metadata attributes; 

+#' these functions consider the metadata contained in all samples of the group. 

+#' The regions, their attributes and their values in output are the same 

+#' as the ones in input for each sample, and the total number of samples 

+#' does not change. All metadata in the input samples are conserved with 

+#' their values in the output samples, with the addition of the "_group" 

+#' attribute, whose value is the identifier of the group to which the specific 

+#' sample is assigned; other metadata attributes can be added as aggregate 

+#' functions computed on specified metadata. When used on region attributes, 

+#' group_by can group regions of each sample individually, based on their 

+#' coordinates (chr, start, stop, strand) and possibly also on other 

+#' specified grouping region attributes (when these are present in the schema 

+#' of the input dataset). In each sample, regions found in the same group 

+#' (i.e., regions with same coordinates and grouping attribute values), 

+#' are combined into a single region; this allows to merge regions that are 

+#' duplicated inside the same sample (based on the values of their coordinates 

+#' and of other possible specified region attributes). For each grouped 

+#' region, it is possible to request the evaluation of aggregate functions 

+#' on other region attributes (i.e., which are not coordinates, or grouping 

+#' region attributes). This use is independent on the possible grouping 

+#' realised based on metadata. The generated output schema only contains the 

+#' original region attributes on which the grouping has been based, and 

+#' additionally the attributes in case calculated as aggregated functions.

+#' If the group_by is applied only on regions, the output metadata and their 

+#' values are equal to the ones in input. Both when applied on metadata and 

+#' on regions, the group_by operation returns a number of output samples 

+#' equal to the number of input ones. Note that the two possible uses of 

+#' group_by, on metadata and on regions, are perfectly orthogonal, 

+#' therefore they can be used in combination or independently.

+#' 

 #' 

 #' @importFrom rJava J .jarray .jnull

 #' @importFrom dplyr group_by

@@ -17,45 +56,45 @@ group_by.GMQLDateset <- function(.data, groupBy_meta = conds(),