@@ -7,6 +7,7 @@ export(AVG)

 export(BAG)

 export(BAGD)

 export(COUNT)

+export(COUNTSAMP)

 export(DESC)

 export(DG)

 export(DGE)

@@ -39,8 +40,8 @@ export(import_gmql)

 export(init_gmql)

 export(login_gmql)

 export(logout_gmql)

-export(read)

-export(read_dataset)

+export(read_GMQL)

+export(read_GRangesList)

 export(remote_processing)

 export(run_query)

 export(run_query_fromfile)

@@ -73,6 +74,7 @@ exportMethods(setdiff)

 exportMethods(take)

 exportMethods(union)

 import(GenomicRanges)

+import(RGMQLScalaLib)

 import(httr)

 import(xml2)

 importClassesFrom(GenomicRanges,GRangesList)

@@ -96,6 +98,7 @@ importFrom(methods,is)

 importFrom(methods,isClass)

 importFrom(methods,new)

 importFrom(plyr,revalue)

+importFrom(rJava,.jaddClassPath)

 importFrom(rJava,.jarray)

 importFrom(rJava,.jevalArray)

 importFrom(rJava,.jinit)

@@ -112,7 +112,7 @@ take_value.META_AGGREGATES <- function(obj){

 #' 

 #' init_gmql()

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

-#' exp = read_dataset(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: 

@@ -137,8 +137,7 @@ take_value.META_AGGREGATES <- function(obj){

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

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

 #' 

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

-#' avg_signal = AVG("signal") )

+#' 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, 

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

 #' 

 #' init_gmql()

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

-#' exp = read_dataset(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 

@@ -85,8 +85,8 @@ check.DISTAL <- function(value)

 #' init_gmql()

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

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

-#' TSS = read_dataset(test_path)

-#' HM = read_dataset(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 

@@ -96,7 +96,7 @@ check.DISTAL <- function(value)

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

 #' 

 #' join_data = merge(TSS, HM, 

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

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

 #' region_output = "RIGHT")

 #'

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

@@ -107,8 +107,8 @@ check.DISTAL <- function(value)

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

 #' 

 #' join_data = merge(TSS, HM, 

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

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

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

+#' region_output = "RIGHT")

 #'

 #' @name DISTAL-Object

 #' @aliases DL

@@ -63,7 +63,7 @@ as.character.OPERATOR <- function(obj) {

 #' 

 #' init_gmql()

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

-#' exp = read_dataset(test_path)

+#' exp = read_GMQL(test_path)

 #' 

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

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

@@ -26,9 +26,6 @@

 #' @return list of 2-D array containing method of evaluation and metadata 

 #' attribute name

 #' 

-#' @examples

-#' 

-#' "Where is my example?"

 #' 

 #' @name Evaluation-Function

 #' @aliases condition_evaluation

@@ -98,7 +98,7 @@

 #' 

 #' init_gmql()

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

-#' exp = read_dataset(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 a minimum 

@@ -123,7 +123,7 @@

 #' @aliases cover-method

 #' @export

 setMethod("cover", "GMQLDataset",

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

+            function(.data, min_acc, max_acc, groupBy = conds(), 

                     variation = "cover", ...)

             {

                 val <- value(.data)

@@ -40,8 +40,8 @@

 #' init_gmql()

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

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

-#' data1 = read_dataset(test_path)

-#' data2 = read_dataset(test_path2)

+#' data1 = read_GMQL(test_path)

+#' data2 = read_GMQL(test_path2)

 #' 

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

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

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

 #' @aliases setdiff-method

 #' @export

 setMethod("setdiff", c("GMQLDataset","GMQLDataset"),

-            function(x, y, joinBy = NULL, is_exact = FALSE)

+            function(x, y, joinBy = conds(), is_exact = FALSE)

             {

                 ptr_data_x = value(x)

                 ptr_data_y = value(y)

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

 #' 

 #' init_gmql()

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

-#' data <- read_dataset(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.

@@ -1,5 +1,5 @@

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

-    groupBy_regions = NULL, region_aggregates = NULL, meta_aggregates = NULL)

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

+    groupBy_regions = c(""), region_aggregates = NULL, meta_aggregates = NULL)

 {

     ptr_data = value(.data)

     gmql_group(ptr_data, groupBy_meta, groupBy_regions, region_aggregates, 

@@ -18,7 +18,7 @@ group_by.GMQLDateset <- function(.data, groupBy_meta = NULL,

 #' groupBy or JoinBy input parameter

 #' 

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

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

+#' @param region_aggregates It accept a list 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

@@ -36,7 +36,7 @@ group_by.GMQLDateset <- function(.data, groupBy_meta = NULL,

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

 #' }

 #' "mixed style" is not allowed

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

+#' @param meta_aggregates It accept a list 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

@@ -61,6 +61,57 @@ group_by.GMQLDateset <- function(.data, groupBy_meta = NULL,

 #'

 #' @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 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_GMQL(test_path)

+#' 

+#' ## This GMQL statement groups samples of the input 'exp' dataset according to 

+#' ## their value of the metadata attribute 'tumor_type' and computes the 

+#' ## maximum value that the metadata attribute size takes inside the samples 

+#' ## belonging to each group. The samples in the output GROUPS_T dataset 

+#' ## have a new _group metadata attribute which indicates which group they 

+#' ## belong to, based on the grouping on the metadata attribute tumor_type. 

+#' ## In addition, they present the new metadata aggregate attribute MaxSize. 

+#' ## Note that the samples without metadata attribute tumor_type are assigned 

+#' ## to a single group with _group value equal 0

+#' 

+#' GROUPS_T = group_by(exp, conds("tumor_type"), 

+#' meta_aggregates = list(max_size = MAX("size")))

+#' 

+#' ## This GMQL statement takes as input dataset the same input dataset as 

+#' ## the previous example. Yet, it calculates new _group values based on the 

+#' ## grouping attribute 'cell', and adds the metadata aggregate attribute 

+#' ## 'n_samp', which counts the number of samples belonging to the respective 

+#' ## group. It has the following output GROUPS_C dataset samples 

+#' ## (note that now no sample has metadata attribute _group with value equal 0 

+#' ## since all input samples include the metadata attribute cell, 

+#' ## with different values, on which the new grouping is based)

+#' 

+#' GROUPS_C = group_by(exp, conds("cell"),

+#' meta_aggregates = list(n_samp AS COUNTSAMP()))

+#' 

+#' ## This GMQL statement groups the regions of each 'exp' dataset sample by 

+#' ## region coordinates chr, left, right, strand  (these are implicitly 

+#' ## considered) and the additional region attribute score (which is explicitly 

+#' ## specified), and keeps only one region for each group. 

+#' ## In the output GROUPS dataset schema, the new region attributes 

+#' ## avg_pvalue and max_qvalue are added, respectively computed as the 

+#' ## average of the values taken by the pvalue and the maximum of the values 

+#' ## taken by the qvalue region attributes in the regions grouped together, 

+#' ## and the computed value is assigned to each region of each output sample. 

+#' ## Note that the region attributes which are not coordinates or score are 

+#' ## discarded.

+#' 

+#' GROUPS = group_by(exp, group_reg = "score", 

+#' region_aggregates = list(avg_pvalue = AVG("pvalue"), 

+#' max_qvalue = MAX("qvalue")))

+#' 

 #' @name group_by

 #' @rdname group_by

 #' @aliases group_by,GMQLDataset-method

@@ -73,8 +73,8 @@

 #' init_gmql()

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

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

-#' TSS = read_dataset(test_path)

-#' HM = read_dataset(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 

@@ -83,10 +83,8 @@

 #' ## is lesser than 120K 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), DLE(120000)), DF("provider"), 

-#' region_output = "RIGHT")

+#' join_data = merge(TSS, HM, genometric_predicate = list(MD(1), DLE(120000)), 

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

 #' 

 #' 

 #' @name merge

@@ -95,7 +93,7 @@

 #' @export

 setMethod("merge", c("GMQLDataset","GMQLDataset"),

                 function(x, y, genometric_predicate = NULL, 

-                    region_output = "CAT", joinBy = NULL, reg_attr = NULL)

+                    region_output = "CAT", joinBy = conds(), reg_attr = c(""))

                 {

                     ptr_data_x <- value(x)

                     ptr_data_y <- value(y)

@@ -150,8 +148,8 @@ gmql_join <- function(left_data, right_data, genometric_predicate, joinBy,

         if(!length(reg_attributes))

             reg_attributes <- .jnull("java/lang/String")

-        

-        reg_attributes <- .jarray(reg_attributes)

+        else

+            reg_attributes <- .jarray(reg_attributes, dispatch = TRUE)

     }

     else

         reg_attributes <- .jnull("java/lang/String")

@@ -58,8 +58,8 @@

 #' 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)

+#' exp = read_GMQL(test_path)

+#' ref = read_GMQL(test_path2)

 #' 

 #' # 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 

@@ -77,7 +77,7 @@

 #' @aliases map-method

 #' @export

 setMethod("map", "GMQLDataset",

-            function(x, y, ..., joinBy = NULL, count_name = "")

+            function(x, y, ..., joinBy = conds(), count_name = "")

             {

                 left_data <- value(x)

                 right_data <- value(y)

@@ -16,7 +16,7 @@

 #' 

 #' init_gmql()

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

-#' data = read_dataset(test_path)

+#' data = read_GMQL(test_path)

 #' 

 #' ## The following statement materialize the dataset, previoulsy read, at 

 #' ## th specific destination path into local folder "ds1" opportunely created

@@ -116,7 +116,7 @@ collect.GMQLDataset <- function(x, dir_out = getwd(), name = "ds1")

 #'

 #' init_gmql()

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

-#' data = read_dataset(test_path)

+#' data = read_GMQL(test_path)

 #' 

 #' ## The following statement materialize the dataset, previoulsy read, at 

 #' ## th specific destination path into local folder "ds1" opportunely created

@@ -188,9 +188,9 @@ gmql_materialize <- function(input_data, dir_out, name)

 #' 

 #' init_gmql()

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

-#' rd = read_dataset(test_path)

+#' rd = read_GMQL(test_path)

 #' 

-#' aggr = aggregate(rd, list(DF("antibody_target", "cell_karyotype")))

+#' aggr = aggregate(rd, conds(c("antibody_target", "cell_karyotype")))

 #' taken <- take(aggr, rows = 45)

 #' 

 #' @name take

@@ -31,7 +31,7 @@

 #'

 #' init_gmql()

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

-#' exp = read_dataset(test_path)

+#' exp = read_GMQL(test_path)

 #'

 #' ## This statement creates a dataset called merged which contains one 

 #' ## sample for each antibody_target and cell value found within the metadata 

@@ -49,7 +49,7 @@

 #' @export

 #' 

 setMethod("aggregate", "GMQLDataset",

-            function(x, groupBy = NULL)

+            function(x, groupBy = conds())

             {

                 ptr_data = value(x)

                 gmql_merge(ptr_data, groupBy)

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

 arrange.GMQLDataset <- function(.data, metadata_ordering = NULL, 

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

-        reg_fetch_opt = NULL, reg_num_fetch = 0L)

+        regions_ordering = NULL, fetch_opt = "", num_fetch = 0L, 

+        reg_fetch_opt = "", reg_num_fetch = 0L)

 {

     ptr_data <- value(.data)

     gmql_order(ptr_data, metadata_ordering, regions_ordering, 

@@ -70,7 +70,7 @@ arrange.GMQLDataset <- function(.data, metadata_ordering = NULL,

 #' 

 #' init_gmql()

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

-#' data = read_dataset(test_path)

+#' data = read_GMQL(test_path)

 #' 

 #' ## The following statement orders the samples according to the Region_Count 

 #' ## metadata attribute and takes the two samples that have the highest count. 

@@ -88,7 +88,7 @@ setMethod("arrange", "GMQLDataset", arrange.GMQLDataset)

 gmql_order <- function(input_data, metadata_ordering, regions_ordering,

                     fetch_opt, num_fetch, reg_fetch_opt, reg_num_fetch)

 {

-    if(!is.null(fetch_opt))

+    if(!is.null(fetch_opt) && !identical(fetch_opt,""))

         fetch_opt <- .check_option(fetch_opt)

     else

         fetch_opt <- .jnull("java/lang/String")

@@ -103,7 +103,7 @@ gmql_order <- function(input_data, metadata_ordering, regions_ordering,

     else

         reg_num_fetch <- 0L

-    if(!is.null(reg_fetch_opt))

+    if(!is.null(reg_fetch_opt) && !identical(reg_fetch_opt,""))

         reg_fetch_opt <- .check_option(reg_fetch_opt)

     else

         reg_fetch_opt <- .jnull("java/lang/String")

@@ -85,7 +85,7 @@ select.GMQLDataset <- function(.data, metadata = NULL, metadata_update = NULL,

 #' 

 #' init_gmql()

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

-#' data = read_dataset(test_path)

+#' data = read_GMQL(test_path)

 #' 

 #' ## It creates a new dataset called CTCF_NORM_SCORE by preserving all 

 #' ## region attributes apart from score, and creating a new region attribute 

@@ -49,24 +49,26 @@

 #' 

 #' init_gmql()

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

-#' data = read_dataset(test_path)

+#' data = read_GMQL(test_path)

 #' 

 #' ## This statement opens such folder as a GMQL dataset named "data" using 

 #' ## "NarrowPeakParser" 

-#' dataPeak = read_dataset(test_path,"NarrowPeakParser")

+#' dataPeak = read_GMQL(test_path,"NarrowPeakParser")

 #' 

 #' ## This statement reads a remote public dataset stored into GMQL system 

 #' ## repository. For a public dataset in a (remote) GMQL repository the 

 #' ## prefix "public." is needed before dataset name

 #' 

-#' data1 = read_dataset("public.Example_Dataset1",is_local = FALSE)

+#' remote_url = "http://genomic.deib.polimi.it/gmql-rest-r/"

+#' login_gmql(remote_url)

+#' data1 = read_GMQL("public.Example_Dataset1",is_local = FALSE)

 #' 

-#' @name read_dataset

+#' @name read_GMQL

 #' @rdname read-function

 #' @export

 #'

-read_dataset <- function(dataset, parser = "CustomParser", is_local=TRUE, 

-                            is_GMQL=TRUE)

+read_GMQL <- function(dataset, parser = "CustomParser", is_local = TRUE, 

+                            is_GMQL = TRUE)

 {

     .check_input(dataset)

     .check_logical(is_local)

@@ -128,11 +130,11 @@ read_dataset <- function(dataset, parser = "CustomParser", is_local=TRUE,

 #' 

 #' @param samples GRangesList

 #' 

-#' @name read_dataset

+#' @name read_GMQL

 #' @rdname read-function

 #' @export

 #'

-read <- function(samples)

+read_GRangesList <- function(samples)

 {

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

         stop("only GrangesList")

@@ -70,7 +70,7 @@ filter.GMQLDateset <- function(.data, m_predicate = NULL, r_predicate = NULL,

 #' 

 #' init_gmql()

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

-#' data <- read_dataset(test_path) 

+#' data <- read_GMQL(test_path) 

 #' 

 #' ## This statement selects from input data samples of patients younger 

 #' ## than 70 years old, based on filtering on sample metadata attribute 

@@ -83,7 +83,7 @@ filter.GMQLDateset <- function(.data, m_predicate = NULL, r_predicate = NULL,

 #' ## as a GMQL dataset named "join_data"

 #' 

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

-#' join_data <- read_dataset(test_path2) 

+#' join_data <- read_GMQL(test_path2) 

 #' 

 #' ## This statement creates a new dataset called 'jun_tf' by selecting those 

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

@@ -94,10 +94,10 @@ filter.GMQLDateset <- function(.data, m_predicate = NULL, r_predicate = NULL,

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

 #' ## of the 'join_data' dataset.

 #' ## For each sample satisfying previous conditions, only its regions that 

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

+#' ## have a region attribute called 'pvalue' with the associated value 

 #' ## less than 0.01 are conserved in output

 #' 

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

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

 #' semijoin(join_data, TRUE, conds("cell")))

 #' 

 #' 

@@ -147,16 +147,8 @@ gmql_select <- function(input_data, predicate, region_predicate, s_join)

 #' common with the same attributes defined in one sample of '.data'

 #' FALSE => semijoin condition is evaluated accordingly.

 #' 

-#' @param groupBy list of evalation functions to define evaluation on metadata:

-#' \itemize{

-#' \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}}(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 groupBy \code{\link{condition_evaluation}} function to support 

+#' methods with groupBy or JoinBy input paramter

 #' 

 #' @examples

 #' 

@@ -169,8 +161,8 @@ gmql_select <- function(input_data, predicate, region_predicate, s_join)

 #' init_gmql()

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

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

-#' data <- read_dataset(test_path)

-#' join_data <-  read_dataset(test_path2)

+#' data <- read_GMQL(test_path)

+#' join_data <-  read_GMQL(test_path2)

 #' 

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

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

@@ -184,7 +176,7 @@ gmql_select <- function(input_data, predicate, region_predicate, s_join)

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

 #' # less than 0.01 are conserved in output

 #' 

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

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

 #' semijoin(join_data, TRUE, conds("cell")))

 #' 

 #' @return semijoin condition as list

@@ -37,8 +37,8 @@

 #' init_gmql()

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

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

-#' data1 <- read_dataset(test_path)

-#' data2 <- read_dataset(test_path2)

+#' data1 <- read_GMQL(test_path)

+#' data2 <- read_GMQL(test_path2)

 #' 

 #' ## This statement creates a dataset called 'full' which contains all samples 

 #' ## from the datasets 'data1' and 'data2'

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

-#' @importFrom rJava .jpackage

-#' @importFrom rJava .jinit

-

+#' @importFrom rJava .jpackage .jinit

+#' @import RGMQLScalaLib

+#' 

 .onLoad <- function(libname, pkgname) {

     .jpackage(pkgname, lib.loc = libname)

     # tools::vignetteEngine("knitr", pattern = "[.]Rmd$", package = "knitr")

@@ -16,7 +16,6 @@

 }

-#' @importFrom utils download.file

 #' @importFrom rJava .jinit .jaddClassPath

 #' 

 initGMQLscalaAPI <- function(libLoc, mem = "12G") {

@@ -28,7 +28,7 @@

 #' 

 #' init_gmql()

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

-#' data = read_dataset(test_path)

+#' data = read_GMQL(test_path)

 #' 

 #' ## It orders the samples according to the Region_Count metadata attribute 

 #' ## and takes the two samples that have the lowest count. 

@@ -25,7 +25,7 @@ if(getRversion() >= "3.1.0")

 #' @param password string password used during signup

 #'

 #' @details

-#' If both username and password are NULL you will be logged as guest.

+#' If both username and password are missing you will be logged as guest.

 #' After login you will receive an authentication token.

 #' As token remains vaild on server (until the next login / registration) 

 #' a user can safely use a token for a previous session as a convenience;

@@ -202,7 +202,7 @@ show_queries_list <- function(url)

 #' @param url string url of server: It must contain the server address 

 #' and base url; service name is added automatically

 #' @param queryName string name of query

-#' @param query string text of GMQL query

+#' @param queryTxt string text of GMQL query

 #'

 #' @return None

 #'

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

 \alias{AGGREGATES-Object}

 \alias{COUNT}

 \alias{AGGREGATES-Object}

+\alias{COUNTSAMP}

+\alias{AGGREGATES-Object}

 \alias{MIN}

 \alias{AGGREGATES-Object}

 \alias{MAX}

@@ -31,6 +33,8 @@ SUM(value)

 COUNT()

+COUNTSAMP()

+

 MIN(value)

 MAX(value)

@@ -67,6 +71,8 @@ to be used in GMQL functions that require aggregate on value.

 function sum, performing all the type conversions needed  }

 \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 }

 \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 

@@ -101,7 +107,7 @@ function third quartile, performing all the type conversions needed }

 init_gmql()

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

-exp = read_dataset(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: 

@@ -126,8 +132,7 @@ res = extend(exp, max_score = MAX("score"))

 ## attribute the average signal of the overlapping regions; 

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

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

-avg_signal = AVG("signal") )

+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, 

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

 \alias{aggregate,GMQLDataset-method}

 \title{Method aggregate}

 \usage{

-\S4method{aggregate}{GMQLDataset}(x, groupBy = NULL)

+\S4method{aggregate}{GMQLDataset}(x, groupBy = conds())

 }

 \arguments{

 \item{x}{GMQLDataset class object}

@@ -40,7 +40,7 @@ not present in the grouping metadata parameter are disregarded.

 init_gmql()

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

-exp = read_dataset(test_path)

+exp = read_GMQL(test_path)

 ## This statement creates a dataset called merged which contains one 

 ## sample for each antibody_target and cell value found within the metadata 

@@ -49,6 +49,6 @@ exp = read_dataset(test_path)

 ## antibody_target and cell metadata

 ## attributes.

-merged = aggregate(exp, condition_evaluation(c("antibody_target","cell")))

+merged = aggregate(exp, conds(c("antibody_target","cell")))

 }

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

 \title{Method arrange}

 \usage{

 \S4method{arrange}{GMQLDataset}(.data, metadata_ordering = NULL,

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

-  reg_fetch_opt = NULL, reg_num_fetch = 0L)

+  regions_ordering = NULL, fetch_opt = "", num_fetch = 0L,

+  reg_fetch_opt = "", reg_num_fetch = 0L)

 }

 \arguments{

 \item{.data}{GMQLDataset class object}

@@ -25,8 +25,8 @@ The functions available are: \code{\link{ASC}}, \code{\link{DESC}}.}

 first k samples; it can assume the values:

 \itemize{

 \item{mtop: it fetches the first k samples}

-\item{mtopg: it fetches the percentage of samples.}

-\item{mtopp: it fetches the first k samples in each group.}

+\item{mtopp: it fetches the first k percentage of samples.}

+\item{mtopg: it fetches the first k samples in each group.}

 }

 if NULL, \emph{num_fetch} is not considered}

@@ -39,8 +39,8 @@ s}

 first k regions; it can assume the values:

 \itemize{

 \item{rtop: it fetches the first k regions.}

-\item{rtopg: it fetches the first k percentage of regions.}

-\item{rtopp: it fetches the first k regions in each group.}

+\item{rtopp: it fetches the first k percentage of regions.}

+\item{rtopg: it fetches the first k regions in each group.}

 }

 if NULL, \emph{reg_num_fetch} is not considered}

@@ -73,7 +73,7 @@ added to either metadata, or regions, or both of them as specified in inputs

 init_gmql()

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

-data = read_dataset(test_path)

+data = read_GMQL(test_path)

 ## The following statement orders the samples according to the Region_Count 

 ## metadata attribute and takes the two samples that have the highest count. 

@@ -42,7 +42,7 @@ folder path

 init_gmql()

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

-data = read_dataset(test_path)

+data = read_GMQL(test_path)

 ## The following statement materialize the dataset, previoulsy read, at 

 ## th specific destination path into local folder "ds1" opportunely created

@@ -33,8 +33,3 @@ attribute name

 \description{

 This function is used to support joinBy and/or groupBy function parameter.

 }

-\examples{

-

-"where is my example?"

-

-}

@@ -35,7 +35,7 @@ considered.}

 init_gmql()

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

-exp = read_dataset(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 

@@ -9,7 +9,7 @@

 \usage{

 cover(.data, ...)

-\S4method{cover}{GMQLDataset}(.data, min_acc, max_acc, groupBy = NULL,

+\S4method{cover}{GMQLDataset}(.data, min_acc, max_acc, groupBy = conds(),

   variation = "cover", ...)

 }

 \arguments{

@@ -54,8 +54,8 @@ considering any amount of overlapping regions.

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

 }}

-\item{groupBy}{\code{\link{condition_evaluation}} function to support 

-methods with groupBy or JoinBy input paramter}

+\item{groupBy}{\code{\link{conds}} function to support methods with 

+groupBy or JoinBy input parameter}

 \item{variation}{string identifying the cover GMQL operator variation.

 The admissible strings are:

@@ -114,7 +114,7 @@ are disregarded.

 init_gmql()

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

-exp = read_dataset(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 a minimum 

@@ -131,7 +131,6 @@ res = cover(exp, 2, ANY())

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

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

-res = cover(exp, 2, 3, groupBy = condition_evaluation(c("cell")), 

-min_pValue = MIN("pvalue"))

+res = cover(exp, 2, 3, groupBy = conds("cell"), min_pValue = MIN("pvalue"))

 }

@@ -89,8 +89,8 @@ directions of the genome.}

 init_gmql()

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

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

-TSS = read_dataset(test_path)

-HM = read_dataset(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 

@@ -100,7 +100,7 @@ HM = read_dataset(test_path2)

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

 join_data = merge(TSS, HM, 

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

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

 region_output = "RIGHT")

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

@@ -111,7 +111,7 @@ region_output = "RIGHT")

 ## from the same provider (joinby clause).

 join_data = merge(TSS, HM, 

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

-DF("provider"), region_output = "RIGHT")

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

+region_output = "RIGHT")

 }

@@ -22,7 +22,7 @@ The function works only after invoking at least one collect

 init_gmql()

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

-data = read_dataset(test_path)

+data = read_GMQL(test_path)

 ## The following statement materialize the dataset, previoulsy read, at 

 ## th specific destination path into local folder "ds1" opportunely created

@@ -54,7 +54,7 @@ Aggregate functions are applied sample by sample.

 init_gmql()

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

-data <- read_dataset(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.

@@ -50,7 +50,7 @@ no sample is extracted.

 init_gmql()

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

-data <- read_dataset(test_path) 

+data <- read_GMQL(test_path) 

 ## This statement selects from input data samples of patients younger 

 ## than 70 years old, based on filtering on sample metadata attribute 

@@ -63,7 +63,7 @@ filter_data <- filter(data, patient_age < 70)

 ## as a GMQL dataset named "join_data"

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

-join_data <- read_dataset(test_path2) 

+join_data <- read_GMQL(test_path2) 

 ## This statement creates a new dataset called 'jun_tf' by selecting those 

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

@@ -74,11 +74,11 @@ join_data <- read_dataset(test_path2)

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

 ## of the 'join_data' dataset.

 ## For each sample satisfying previous conditions, only its regions that 

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

+## have a region attribute called 'pvalue' with the associated value 

 ## less than 0.01 are conserved in output

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

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

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

+semijoin(join_data, TRUE, conds("cell")))

 }

@@ -6,27 +6,19 @@

 \alias{group_by,GMQLDataset-method}

 \title{Method group_by}

 \usage{

-\S4method{group_by}{GMQLDataset}(.data, groupBy_meta = NULL,

-  groupBy_regions = NULL, region_aggregates = NULL,

+\S4method{group_by}{GMQLDataset}(.data, groupBy_meta = conds(),

+  groupBy_regions = c(""), region_aggregates = NULL,

   meta_aggregates = NULL)

 }

 \arguments{

 \item{.data}{GMQLDataset object}

-\item{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