@@ -21,7 +21,7 @@ License: Artistic-2.0

 Encoding: UTF-8

 LazyData: true

 RoxygenNote: 6.0.1

-Imports: rscala(>= 2.4.0), httr, GenomicRanges, rtracklayer, data.table, utils, plyr, xml2, methods, S4Vectors, dplyr

+Imports: rscala(>= 2.4.0), httr, GenomicRanges, rtracklayer, data.table, utils, plyr, xml2, methods, S4Vectors, dplyr, stats

 Depends: R(>= 3.3.2)

 VignetteBuilder: knitr

 Suggests: BiocStyle, knitr, rmarkdown

@@ -83,5 +83,6 @@ importFrom(methods,is)

 importFrom(plyr,revalue)

 importFrom(rtracklayer,export)

 importFrom(rtracklayer,import)

+importFrom(stats,setNames)

 importFrom(utils,read.delim)

 importFrom(utils,write.table)

@@ -59,26 +59,26 @@

 #'

 #' @examples

 #' 

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

-#' The COVER operation considers all areas defined by a minimum of two overlapping regions 

-#' in the input samples, up to any amount of overlapping regions.

+#' ## This GMQL 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.

 #' 

 #' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

-#' exp = read(test_path)

+#' exp = readDataset(test_path)

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

 #'

 #' \dontrun{

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

-#' their cell metadata attribute, 

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

-#' output regions are produced where at least 2 and at most 3 regions of grouped exp samples 

-#' overlap, setting as attributes of the resulting regions the minimum pValue of the overlapping regions 

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

+#' ## This GMQL statement computes the result grouping the input exp samples by the values of 

+#' ## their cell metadata attribute, 

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

+#' ## output regions are produced where at least 2 and at most 3 regions of grouped exp samples 

+#' ## overlap, setting as attributes of the resulting regions the minimum pvalue of the overlapping regions 

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

 #' 

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

 #' exp = read(test_path)

-#' res = cover(input_data = exp,2,3, c("cell"), list(min_pValue = MIN(pValue)))

+#' res = cover(input_data = exp,2,3, c("cell"), list(min_pValue = MIN("pvalue")))

 #' }

 #' @export

 #'

@@ -136,17 +136,17 @@ cover <- function(input_data, minAcc, maxAcc, groupBy = NULL, aggregates = NULL)

 #'

 #' @examples

 #'

-#' ### This GMQL statement computes the result grouping the input \emph{exp} samples 

-#' by the values of their \emph{cell} metadata attribute, 

-#' thus one output \emph{res} sample is generated for each cell type. 

-#' Output regions are produced by dividing results from COVER in contiguous subregions 

-#' according to the varying accumulation values (from 2 to 4 in this case): 

-#' one region for each accumulation value;

+#' ## This GMQL statement computes the result grouping the input \emph{exp} samples 

+#' ## by the values of their \emph{cell} metadata attribute, 

+#' ## thus one output \emph{res} sample is generated for each cell type. 

+#' ## Output regions are produced by dividing results from COVER in contiguous subregions 

+#' ## according to the varying accumulation values (from 2 to 4 in this case): 

+#' ## one region for each accumulation value;

 #'

 #' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

-#' exp = read(test_path)

-#' res = histogram(exp, 2,4,groupBy = c("cell")) exp 

+#' exp = readDataset(test_path)

+#' res = histogram(exp, 2,4,groupBy = c("cell"))

 #' 

 #' @export

 #'

@@ -206,16 +206,16 @@ histogram <- function(input_data, minAcc, maxAcc, groupBy = NULL, aggregates = N

 #'

 #' @examples

 #'

-#' ### This GMQL statement computes the result grouping the input \emph{exp} samples by the values 

-#' of their \emph{cell} metadata attribute, thus one output \emph{res} sample is generated 

-#' for each cell type.

-#' Output regions are produced by extracting the highest accumulation overlapping 

-#' (sub)regions according to the methodologies described above;

+#' ## This GMQL statement computes the result grouping the input \emph{exp} samples by the values 

+#' ## of their \emph{cell} metadata attribute, thus one output \emph{res} sample is generated 

+#' ## for each cell type.

+#' ## Output regions are produced by extracting the highest accumulation overlapping 

+#' ## (sub)regions according to the methodologies described above;

 #'

 #'

 #' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

-#' exp = read(test_path)

+#' exp = readDataset(test_path)

 #' res = summit(input_data = exp,2,4, c("cell"))

 #' 

 #' @export

@@ -274,15 +274,15 @@ summit <- function(input_data, minAcc, maxAcc, groupBy = NULL, aggregates = NULL

 #'

 #' @examples

 #' 

-#' ### This GMQL statement computes the result grouping the input \emph{exp} samples by 

-#' the values of their \emph{cell} metadata attribute, thus one output \emph{res} sample 

-#' is generated for each cell type. 

-#' Output regions are produced by concatenating all regions which would have been used 

-#' to construct a COVER(2,4) statement on the same dataset; 

+#' ## This GMQL statement computes the result grouping the input \emph{exp} samples by 

+#' ## the values of their \emph{cell} metadata attribute, thus one output \emph{res} sample 

+#' ## is generated for each cell type. 

+#' ## Output regions are produced by concatenating all regions which would have been used 

+#' ## to construct a COVER(2,4) statement on the same dataset; 

 #' 

 #' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

-#' exp = read(test_path)

+#' exp = readDataset(test_path)

 #' res = flat(input_data = exp,2,4, c("cell"))

 #'

 #' @export

@@ -34,8 +34,8 @@

 #'

 #' @examples

 #'

-#' #### This GMQL statement returns all the regions in the first dataset that do not 

-#' overlap any region in the second dataset.

+#' ## This GMQL statement returns all the regions in the first dataset that do not 

+#' ## overlap any region in the second dataset.

 #' 

 #' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

@@ -45,10 +45,10 @@

 #' out = difference(r_left,r_right)

 #' 

 #' \dontrun{

-#' ### 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 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.

 #' 

 #' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

@@ -30,22 +30,22 @@

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

 #' r = readDataset(test_path)

 #'

-#' ### it counts the regions in each sample and stores their number as value of the new metadata 

-#' RegionCount attribute of the sample.

-#' e = extend(input_data = r, list(RegionCount = COUNT())

+#' ## it counts the regions in each sample and stores their number as value of the new metadata 

+#' ## RegionCount attribute of the sample.

+#' e = extend(input_data = r, list(RegionCount = COUNT()))

 #' \dontrun{

 #' 

 #' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

 #' exp = readDataset(test_path)

 #'

-#' ### it copies all samples of exp dataset into res dataset, and then calculates 

-#' for each of them two new metadata attributes:

-#' 1. RegionCount is the number of sample regions;

-#' 2. MinP is the minimum Pvalue of the sample regions.

-#' res sample regions are the same as the ones in exp.

+#' ## it copies all samples of exp dataset into res dataset, and then calculates 

+#' ## for each of them two new metadata attributes:

+#' ##  1. RegionCount is the number of sample regions;

+#' ##  2. MinP is the minimum pvalue of the sample regions.

+#' ## res sample regions are the same as the ones in exp.

 #' 

-#' res = extend(input_data = exp, list(RegionCount = COUNT(),MinP = MIN(pValue))

+#' res = extend(input_data = exp, list(RegionCount = COUNT(),MinP = MIN(pvalue)))

 #' 

 #' }

 #' 

@@ -45,18 +45,18 @@

 #'

 #' @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).

 #' 

-#' #' initGMQL("gtf")

+#' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

 #' test_path2 <- system.file("example","DATA_SET_VAR_GDM",package = "GMQL")

 #' TSS = readDataset(test_path)

 #' HM = readDataset(test_path2)

-#' join_data = join(tss,hm,genometric_predicate=list(list(MD("1"),DLE("120000"))),c("provider"),region_output="RIGHT")

+#' join_data = join(TSS,HM,genometric_predicate=list(list(MD(1),DLE(120000))),c("provider"),region_output="RIGHT")

 #'

 #' @export

 #'

@@ -47,19 +47,19 @@

 #'

 #' @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.

 #' 

 #' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

 #' test_path2 <- system.file("example","DATA_SET_VAR_GDM",package = "GMQL")

-#' exp = read(test_path)

-#' ref = read(test_path2)

+#' exp = readDataset(test_path)

+#' ref = readDataset(test_path2)

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

 #' 

 #' 

@@ -68,7 +68,7 @@

 map <- function(left_input_data, right_input_data, aggregates = NULL, joinBy = NULL)

 {

   if(!is.null(aggregates))

-    metadata_matrix <- .aggregates(metadata,"OPERATOR")

+    metadata_matrix <- .aggregates(aggregates,"OPERATOR")

   else

     metadata_matrix = scalaNull("Array[Array[String]]")

@@ -77,7 +77,7 @@ map <- function(left_input_data, right_input_data, aggregates = NULL, joinBy = N

   else

     join_condition_matrix <- scalaNull("Array[Array[String]]")

-  out<-WrappeR$map(join_condition_matrix,aggregates,left_input_data$value,right_input_data$value)

+  out<-WrappeR$map(join_condition_matrix,metadata_matrix,left_input_data$value,right_input_data$value)

   if(grepl("No",out,ignore.case = TRUE))

     stop(out)

@@ -18,8 +18,10 @@

 #' s = select(input_data = r)

 #' m = merge(groupBy = c("antibody_targer","cell_karyotype"),input_data = s)

 #' materialize(input_data = m, dir_out = test_path)

-#' execute()

 #' 

+#' \dontrun{

+#' execute()

+#' }

 #' @export

 #'

 execute <- function()

@@ -51,7 +53,7 @@ execute <- function()

 #'

 #' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

-#' r = read(test_path)

+#' r = readDataset(test_path)

 #' s = select(input_data = r)

 #' m = merge(groupBy = c("antibody_targer","cell_karyotype"),input_data = s)

 #' materialize(input_data = m, dir_out = test_path)

@@ -76,7 +78,8 @@ materialize <- function(input_data, dir_out = getwd())

 #' as folder (like if execution was invoked)

 #'

 #' @import GenomicRanges

-#'

+#' @importFrom stats setNames

+#' 

 #' @param input_data returned object from any GMQL function

 #' @param rows number of rows for each sample regions that you want to retrieve and stored in memory

 #' by default is 0 that means take all rows for each sample

@@ -87,10 +90,10 @@ materialize <- function(input_data, dir_out = getwd())

 #'

 #' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

-#' r = read(test_path)

+#' r = readDataset(test_path)

 #' s = select(input_data = r)

 #' m = merge(groupBy = c("antibody_targer","cell_karyotype"),input_data = s)

-#' take(input_data = m, rows = 45)

+#' g <- take(input_data = m, rows = 45)

 #' 

 #' @export

 #'

@@ -134,7 +137,7 @@ take <- function(input_data, rows=0L)

     x <- x[-1]

   })

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

-    setNames(as.list(as.character(x[[2]])), x[[1]])

+    stats::setNames(as.list(as.character(x[[2]])), x[[1]])

   })

 }

@@ -26,15 +26,15 @@

 #'

 #' @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.

 #' 

 #' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

 #' exp = readDataset(test_path)

-#' merged = merge(input_data = exp, groupBy = c("antibody_targer"))

+#' merged = merge(input_data = exp, groupBy = c("antibody_target"))

 #' 

 #' @export

 #'

@@ -36,7 +36,7 @@

 #'

 #' @return DAGgraph class object. It contains the value associated to the graph used 

 #' as input for the subsequent GMQL function

-#' #'

+#' 

 #' @details

 #' mtop, mtopg,mtopp, rtop, rtopg and rtopp are normally numbers: if you specify a vector,

 #' only the first element will be used

@@ -47,26 +47,13 @@

 #'

 #' @examples

 #' 

-#' ### it orders the samples according to the Region_count metadata attribute and takes the two samples 

-#' that have the highest count. 

-#'

-#' initGMQL("gtf")

-#' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

-#' r = readDataset(test_path)

-#' o = order(r,list(DESC(Region_Count)), mtop = 2)

-#' 

-#' \dontrun{

-#' 

-#' ### it extracts the first 5 samples on the basis of their region counter 

-#' (those with the smaller RegionCount) and then, for each of them, 

-#' 7 regions on the basis of their mutation counter (those with the higher MutationCount).

+#' ## it orders the samples according to the Region_count metadata attribute and takes the two samples 

+#' ## that have the highest count. 

 #'

 #' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

 #' r = readDataset(test_path)

-#' o = order(r,list(ASC(Region_Count)), mtop = 5,regions_ordering = list(DESC(MutationCount)),rtop=7)

-#'  

-#' }

+#' o = order(r,list(DESC("Region_Count")), mtop = 2)

 #'

 #' @export

 #'

@@ -79,13 +66,13 @@ order <- function(input_data, metadata_ordering = NULL, mtop = 0, mtopg = 0,mtop

   if(length(mtop)>0 || length(mtopg)>0 || length(rtop)>0 || length(rtopg)>0

      || length(mtopp)>0 || length(rtopp)>0)

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

+    warning("only the first element is taken by 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

   mtop = as.integer(mtop[1])

-  mtog = as.integer(mtopg[1])

+  mtopg = as.integer(mtopg[1])

   mtopp = as.integer(mtopp[1])

   rtop = as.integer(rtop[1])

@@ -95,37 +82,37 @@ order <- function(input_data, metadata_ordering = NULL, mtop = 0, mtopg = 0,mtop

   if(mtop > 0 && mtopg >0)

   {

     warning("cannot be used together.\nWe set mtopg = 0")

-    mtopg = 0

+    mtopg = 0L

   }

   if(mtop >0 && mtopp>0)

   {

     warning("cannot be used together.\nWe set mtopp = 0")

-    mtopp = 0

+    mtopp = 0L

   }

   if(mtopg >0 && mtopp>0)

   {

     warning("cannot be used together.\nWe set mtopp = 0")

-    mtopp = 0

+    mtopp = 0L

   }

   if(rtop > 0 && rtopg >0)

   {

     warning("cannot be used together.\nWe set rtopg = 0")

-    rtopg = 0

+    rtopg = 0L

   }

   if(rtop >0 && rtopp>0)

   {

     warning("cannot be used together.\nWe set rtopp = 0")

-    rtopp = 0

+    rtopp = 0L

   }

   if(rtopg >0 && rtopp>0)

   {

     warning("cannot be used together.\nWe set rtopp = 0")

-    rtopp = 0

+    rtopp = 0L

   }

   if(!is.null(metadata_ordering))

@@ -12,7 +12,7 @@

 #'

 #' @param input_data string pointer taken from GMQL function

 #' @param metadata vector of string made up by metadata attribute

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

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

 #' @param all_but_reg logical value indicating which schema filed attribute you want to exclude.

 #' If FALSE only the regions you choose is kept in the output of the project operation,

 #' if TRUE the schema region are all except ones include in region parameter.

@@ -33,24 +33,24 @@

 #' @examples

 #' 

 #' ## it creates a new dataset called CTCF_NORM_SCORE by preserving all region attributes apart from score,

-#' and creating a new region attribute called new_score by dividing the existing score value 

-#' of each region by 1000.0 and incrementing it by 100.

-#' It also generates, for each sample of the new dataset, 

-#' a new metadata attribute called normalized with value 1, which can be used in future selections.

+#' ## and creating a new region attribute called new_score by dividing the existing score value 

+#' ## of each region by 1000.0 and incrementing it by 100.

+#' ## It also generates, for each sample of the new dataset, 

+#' ## a new metadata attribute called normalized with value 1, which can be used in future selections.

 #' 

 #' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

 #' input = readDataset(test_path)

-#' CTCF_NORM_SCORE = project(input,metadata_update="normalized AS 1",

-#' regions_update="new_score AS (score / 1000.0) + 100" , regions=c("score"),all_but_reg=T,)

+#' CTCF_NORM_SCORE = project(input,metadata_update="normalized AS 1", regions_update="new_score AS (score / 1000.0) + 100" , regions=c("score"), all_but_reg=TRUE)

 #' 

 #' 

 #' \dontrun{

-#' ### it produces an output dataset that contains the same samples as the input dataset. 

-#' Each output sample only contains, as region attributes, 

-#' the four basic coordinates (chr, left, right, strand) and the specified region attributes 

-#' 'variant_classification' and 'variant_type', and as metadata attributes only the specified ones, 

-#' i.e. manually_curated__tissue_status and manually_curated__tumor_tag.

+#' 

+#' ## it produces an output dataset that contains the same samples as the input dataset. 

+#' ## Each output sample only contains, as region attributes, 

+#' ## the four basic coordinates (chr, left, right, strand) and the specified region attributes 

+#' ## 'variant_classification' and 'variant_type', and as metadata attributes only the specified ones, 

+#' ## i.e. manually_curated__tissue_status and manually_curated__tumor_tag.

 #' 

 #' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

@@ -76,6 +76,8 @@ project <-function(input_data, metadata = NULL,metadata_update=NULL,all_but_meta

     if(length(metadata)==0)

       metadata <- scalaNull("Array[String]")

+    

+    metadata <- (I(as.character(metadata)))

   }

   else

     metadata <- scalaNull("Array[String]")

@@ -90,6 +92,9 @@ project <-function(input_data, metadata = NULL,metadata_update=NULL,all_but_meta

     if(length(regions)==0)

       regions <- scalaNull("Array[String]")

+    

+    regions <- (I(as.character(regions)))

+    

   }

   else

     regions <- scalaNull("Array[String]")

@@ -68,6 +68,8 @@ initGMQL <- function(output_format="gtf", remote_processing = FALSE)

 #' and override value is FALSE an error occures.

 #' useful only in remote processing

 #' 

+#' @importFrom methods is

+#' 

 #' @return DAGgraph class object. It contains the value associated to the graph used 

 #' as input for the subsequent GMQL function

 #'

@@ -158,17 +160,16 @@ readDataset <- function(dataset, parser = "CustomParser",is_local=TRUE,url=NULL,

 #'

 #' Read a GrangesList saving in scala memory that can be referenced in R

 #'

+#'

+#' @importFrom S4Vectors metadata

 #' @param samples GrangesList

+#' 

 #'

 #' @return DAGgraph class object. It contains the value associated to the graph used 

 #' as input for the subsequent GMQL function

 #' 

 #' @examples

-#'

-#' \dontrun{

-#' 

-#' }

-#' ""

+#' "prova prova"

 #'

 #' @export

 #'

@@ -177,7 +178,7 @@ read <- function(samples)

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

     stop("only GrangesList")

-  meta <- metadata(samples)

+  meta <- S4Vectors::metadata(samples)

   if(is.null(meta)) {

     warning("GrangesList has no metadata. we provide two metadata for you")

     meta_matrix <- matrix(c("Provider","Polimi", "Application", "R-GMQL"),ncol = 2,byrow = TRUE)

@@ -36,7 +36,7 @@

 #' @examples

 #' 

 #' ## it selects from input data samples of patients younger than 70 years old, 

-#' based on filtering on sample metadata attribute Patient_age

+#' ## based on filtering on sample metadata attribute Patient_age

 #' 

 #' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

@@ -108,6 +108,7 @@ select <- function(input_data, predicate = NULL, region_predicate = NULL, semi_j

     join_condition_matrix <- .join_condition(semi_join)

   }

+  

   out <- WrappeR$select(predicate,region_predicate,join_condition_matrix,semi_join_dataset,

                         semi_join_negation,input_data$value)

   if(grepl("No",out,ignore.case = TRUE) || grepl("expected",out,ignore.case = TRUE))

@@ -23,16 +23,16 @@

 #' @references \url{http://www.bioinformatics.deib.polimi.it/genomic_computing/GMQL/doc/GMQLUserTutorial.pdf}

 #'

 #' @examples

-#' ### it creates a dataset called full which contains all samples from the datasets 

-#' data1 and data2 whose schema is defined by merging data1 and data2 dataset schemas 

-#' (union of all the attributes present in the two input datasets).

+#' ## it creates a dataset called full which contains all samples from the datasets 

+#' ## data1 and data2 whose schema is defined by merging data1 and data2 dataset schemas 

+#' ## (union of all the attributes present in the two input datasets).

 #' 

 #' initGMQL("gtf")

 #' test_path <- system.file("example","DATA_SET_VAR_GTF",package = "GMQL")

 #' test_path2 <- system.file("example","DATA_SET_VAR_GDM",package = "GMQL")

 #' data1 = readDataset(test_path)

 #' data2 = readDataset(test_path2)

-#' full = union(r2,r)

+#' full = union(data1,data2)

 #' 

 #'

 #' @export

@@ -31,26 +31,26 @@

 }

 # aggregates factory

-.aggregates <- function(metadata,class)

+.aggregates <- function(meta_data,class)

 {

-  if(!is.list(metadata))

-    stop("metadata: invalid input")

+  if(!is.list(meta_data))

+    stop("meta_data: invalid input")

-  if(!all(sapply(metadata, function(x) is(x,class))))

+  if(!all(sapply(meta_data, function(x) is(x,class))))

     stop("All elements must be META_OPERATOR object")

-  names <- names(metadata)

+  names <- names(meta_data)

   if(is.null(names))

   {

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

-    names <- sapply(metadata, take_value.META_OPERATOR)

+    names <- sapply(meta_data, take_value.META_OPERATOR)

   }

   else

   {

     if("" %in% names)

       stop("No partial names assignment is allowed")

   }

-  aggregate_matrix <- t(sapply(metadata, function(x) {

+  aggregate_matrix <- t(sapply(meta_data, function(x) {

     new_value = as.character(x)

     matrix <- matrix(new_value)

@@ -34,13 +34,6 @@ if(getRversion() >= "3.1.0")

 #' PolimiUrl = "http://130.186.13.219/gmql-rest"

 #' login.GMQL(PolimiUrl)

 #'

-#' \dontrun{

-#' 

-#' ### login with username and password

-#' PolimiUrl = "http://130.186.13.219/gmql-rest"

-#' login.GMQL(PolimiUrl,"test101","test")

-#' 

-#' }

 #' @export

 #'

 login.GMQL <- function(url,username = NULL, password = NULL)

@@ -100,13 +93,6 @@ login.GMQL <- function(url,username = NULL, password = NULL)

 #' login.GMQL(PolimiUrl)

 #' logout.GMQL(PolimiUrl)

 #'

-#' \dontrun{

-#' ##### login with username and password, then logout

-#' PolimiUrl = "http://130.186.13.219/gmql-rest"

-#' login.GMQL(PolimiUrl,"test101","test")

-#' logout.GMQL(PolimiUrl)

-#' }

-#'

 #' @return None

 #'

 #' @export

@@ -156,8 +142,8 @@ logout.GMQL <- function(url)

 #'

 #' @examples

 #' 

-#' ##### this user already exist, it's a test account

-#' ##### don't use it

+#' ### this user already exist, it's a test account, don't use it!!!

+#' 

 #' PolimiUrl = "http://130.186.13.219/gmql-rest"

 #' register.GMQL(url = PolimiUrl,"jonh","Doe","jonh@doe.com","JD","JD46")

 #'

@@ -22,6 +22,7 @@

 #' @examples

 #'

 #' PolimiUrl = "http://130.186.13.219/gmql-rest"

+#' 

 #' login.GMQL(PolimiUrl)

 #' list <- showQueries(PolimiUrl)

 #'

@@ -104,7 +104,7 @@ DEF <- function(value)

 #' 

 #' #### select with condition

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

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

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

 #'

 #' \dontrun{

 #'

@@ -152,7 +152,7 @@ EXACT <- function(value)

 #' 

 #' #### select with condition

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

-#' s = select(input_data = r, semi_join = list("cell_type",FULL("cell"),attribute_tag), semi_join_dataset = c)

+#' s = select(input_data = r, semi_join = list("cell_type",FULL("cell"),"attribute_tag"), semi_join_dataset = c)

 #'

 #' \dontrun{

 #'

@@ -23,7 +23,8 @@

 #' @examples

 #'

 #' #### show dataset when logged as guest

-#' PolimiUrl = "http://genomic.elet.polimi.it/gmql-rest"

+#' 

+#' PolimiUrl = "http://130.186.13.219/gmql-rest"

 #' login.GMQL(url = PolimiUrl)

 #' list <- showDatasets(PolimiUrl)

 #'

@@ -72,7 +73,7 @@ showDatasets <- function(url)

 #'

 #' @examples

 #'

-#' PolimiUrl = "http://genomic.elet.polimi.it/gmql-rest"

+#' PolimiUrl = "http://130.186.13.219/gmql-rest"

 #' login.GMQL(url = PolimiUrl)

 #' list <- showSamplesFromDataset(PolimiUrl,"public.GRCh38_ENCODE_BROAD_MAY_2017")

 #'

@@ -120,7 +121,7 @@ showSamplesFromDataset <- function(url,datasetName)

 #' @examples

 #'

 #' ### show schema of public dataset

-#' PolimiUrl = "http://genomic.elet.polimi.it/gmql-rest"

+#' PolimiUrl = "http://130.186.13.219/gmql-rest"

 #' login.GMQL(url = PolimiUrl)

 #' list <- showSchemaFromDataset(PolimiUrl,"public.GRCh38_ENCODE_BROAD_MAY_2017")

 #'

@@ -174,7 +175,7 @@ showSchemaFromDataset <- function(url,datasetName)

 #' 

 #' ### upload of GMQL dataset with no schema selection

 #' test_path <- system.file("example","DATA_SET_VAR_GDM",package = "GMQL")

-#' PolimiUrl = "http://genomic.elet.polimi.it/gmql-rest"

+#' PolimiUrl = "http://130.186.13.219/gmql-rest"

 #' login.GMQL(url = PolimiUrl)

 #' uploadSamples(PolimiUrl,"dataset1",folderPath = test_path)

 #' }

@@ -253,10 +254,13 @@ uploadSamples <- function(url,datasetName,folderPath,schemaName=NULL,isGMQL=TRUE

 #' @examples

 #'

 #' \dontrun{

-#'

-#' PolimiUrl = "http://genomic.elet.polimi.it/gmql-rest"

-#' login.GMQL(url = PolimiUrl,"test101","test")

+#' 

+#' ### this dataset does not exist

+#' 

+#' PolimiUrl = "http://130.186.13.219/gmql-rest"

+#' login.GMQL(url = PolimiUrl)

 #' deleteDataset(PolimiUrl,"job_test1_test101_20170604_180908_RESULT_DS")

+#' 

 #' }

 #' 

 #' @export

@@ -297,9 +301,11 @@ deleteDataset <- function(url,datasetName)

 #' @examples

 #'

 #' #### download dataset in r working directory

-#' PolimiUrl = "http://genomic.elet.polimi.it/gmql-rest"

-#' login.GMQL(url = PolimiUrl,"test101","test")

-#' downloadDataset(PolimiUrl,"dataset_test",path = getwd())

+#' #### in this case we try to download public dataset

+#' 

+#' PolimiUrl = "http://130.186.13.219/gmql-rest"

+#' login.GMQL(url = PolimiUrl)

+#' downloadDataset(PolimiUrl,"public.HG19_BED_ANNOTATION",path = getwd())

 #'

 #' @export

 #'

@@ -313,11 +319,13 @@ downloadDataset <- function(url,datasetName,path = getwd())

   #print(content$result)

   content <- httr::content(req)

   if(req$status_code !=200)

-    stop(content)

-

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

-  writeBin(content,zip_path)

-  print("Download Complete")

+    print(content)

+  else

+  {

+    zip_path = paste0(path,"/",datasetName,".zip")

+    writeBin(content,zip_path)

+    print("Download Complete")

+  }

 }

 #' Download Dataset in GrangesList

@@ -340,11 +348,13 @@ downloadDataset <- function(url,datasetName,path = getwd())

 #'

 #' @examples

 #'

-#' #### create grangeslist from dataset in repository

-#' PolimiUrl = "http://genomic.elet.polimi.it/gmql-rest"

-#' login.GMQL(url = PolimiUrl,"test101","test")

-#' downloadDatasetToGrangesList(PolimiUrl,"dataset_test")

-#'

+#' \dontrun{

+#' #### create grangeslist from public dataset HG19_BED_ANNOTATION got from repository

+#' PolimiUrl = "http://130.186.13.219/gmql-rest"

+#' login.GMQL(url = PolimiUrl)

+#' downloadDatasetToGrangesList(PolimiUrl,"public.HG19_BED_ANNOTATION")

+#' }

+#' 

 #' @export

 #'

 downloadDatasetToGrangesList <- function(url,datasetName)

@@ -396,9 +406,9 @@ downloadDatasetToGrangesList <- function(url,datasetName)

 #' @examples

 #'

 #' ## download metadata with real test login

-#' PolimiUrl = "http://genomic.elet.polimi.it/gmql-rest"

-#' login.GMQL(url = PolimiUrl,"test101","test")

-#' metadataFromSample(PolimiUrl,"job_test1_test101_20170604_180908_RESULT_DS","S_00000")

+#' PolimiUrl = "http://130.186.13.219/gmql-rest"

+#' login.GMQL(url = PolimiUrl)

+#' metadataFromSample(PolimiUrl,"public.HG19_BED_ANNOTATION","genes")

 #'

 #' @export

 #'

@@ -448,10 +458,12 @@ metadataFromSample <- function(url, datasetName,sampleName)

 #'

 #' @examples

 #'

-#' PolimiUrl = "http://genomic.elet.polimi.it/gmql-rest"

-#' login.GMQL(url = PolimiUrl,"test101","test")

-#' regionFromSample(PolimiUrl,"job_test1_test101_20170604_180908_RESULT_DS","S_00000")

-#'

+#' 

+#' PolimiUrl = "http://130.186.13.219/gmql-rest"

+#' login.GMQL(url = PolimiUrl)

+#' regionFromSample(PolimiUrl,"public.HG19_BED_ANNOTATION","genes")

+#' 

+#' 

 #' @export

 #'

 regionFromSample <- function(url, datasetName,sampleName)

@@ -466,7 +478,7 @@ regionFromSample <- function(url, datasetName,sampleName)

   else

   {

     list <- showSchemaFromDataset(url,datasetName)

-    schema_type <- list$schemaType

+    schema_type <- list$type

     temp <- tempfile("temp") #use temporary files

     write.table(content,temp,quote = FALSE,sep = '\t',col.names = FALSE,row.names = FALSE)

@@ -478,9 +490,15 @@ regionFromSample <- function(url, datasetName,sampleName)

         name <- x$name

       })

       df <- data.table::fread(temp,header = FALSE,sep = "\t")

+      a <- df[1,2]

+      if(is.na(as.numeric(a)))

+        df <- df[-1]

       data.table::setnames(df,vector_field)

-      samples <- GenomicRanges::makeGRangesFromDataFrame(df,keep.extra.columns = TRUE,start.field = "left",end.field = "right")

-    }

+      samples <- GenomicRanges::makeGRangesFromDataFrame(df,keep.extra.columns = TRUE,

+                                                         start.field = "left",

+                                                         end.field = "right",

+                                                         strand.field="strand")

+      }

     unlink(temp)

     return(samples)

   }

@@ -53,17 +53,17 @@ 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 120K bases and joined TSS and HM samples are obtained 

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

+#' ## 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,