@@ -4,5 +4,4 @@

 .Rproj.user/**

 .Rapp.history

 .RData

-

-

+.R.zip

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

 Package: RGMQL

 Type: Package

-Title: GMQL function

-Version: 0.99.0

+Title: GenoMetric Query Language for R/Bioconductor

+Version: 0.99.1

 Author: Simone Pallotta, Marco Masseroli

 Maintainer: Simone Pallotta <simonepallotta@hotmail.com>

 Description: This package brings GMQL functionalities into R environemnt.

@@ -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, stats

+Imports: httr, rJava,GenomicRanges, rtracklayer, data.table, utils, plyr, xml2, methods, S4Vectors, dplyr, stats

 Depends: R(>= 3.3.2)

 VignetteBuilder: knitr

 Suggests: BiocStyle, knitr, rmarkdown

@@ -1,78 +1,34 @@

 # Generated by roxygen2: do not edit by hand

-export(ASC)

-export(AVG)

-export(BAG)

-export(COUNT)

-export(DEF)

-export(DESC)

-export(DGE)

-export(DLE)

-export(DOWN)

-export(EXACT)

-export(FULL)

-export(MAX)

-export(MD)

-export(MEDIAN)

-export(MIN)

-export(Q1)

-export(Q2)

-export(Q3)

-export(STD)

-export(SUM)

 export(TFARMatrix)

 export(TFARMemAtrix)

-export(UP)

-export(compileQuery)

-export(compileQuery.fromfile)

-export(cover)

 export(deleteDataset)

-export(difference)

 export(downloadDataset)

 export(downloadDatasetToGrangesList)

-export(execute)

 export(exportGMQL.gdm)

 export(exportGMQL.gtf)

 export(extend)

-export(flat)

-export(histogram)

 export(importGMQL.gdm)

 export(importGMQL.gtf)

 export(initGMQL)

-export(join)

 export(login.GMQL)

 export(logout.GMQL)

-export(map)

-export(materialize)

-export(merge)

 export(metadataFromSample)

-export(order)

-export(project)

 export(read)

 export(readDataset)

 export(regionFromSample)

 export(register.GMQL)

 export(remote_processing)

-export(runQuery)

-export(runQuery.fromfile)

 export(saveQuery)

 export(saveQuery.fromfile)

-export(select)

 export(showDatasets)

-export(showJobLog)

-export(showJobs)

 export(showQueries)

 export(showSamplesFromDataset)

 export(showSchemaFromDataset)

-export(stopJob)

-export(summit)

-export(take)

-export(traceJob)

-export(union)

 export(uploadSamples)

 import(GenomicRanges)

 import(httr)

-import(rscala)

+import(rJava)

 import(xml2)

 importClassesFrom(GenomicRanges,GRangesList)

 importFrom(GenomicRanges,makeGRangesFromDataFrame)

@@ -81,9 +37,11 @@ importFrom(data.table,fread)

 importFrom(dplyr,bind_cols)

 importFrom(methods,is)

 importFrom(plyr,revalue)

+importFrom(rJava,.jinit)

+importFrom(rJava,.jnew)

+importFrom(rJava,.jpackage)

 importFrom(rtracklayer,export)

 importFrom(rtracklayer,import)

-importFrom(stats,setNames)

 importFrom(utils,read.delim)

 importFrom(utils,unzip)

 importFrom(utils,write.table)

deleted file mode 100644

@@ -1,348 +0,0 @@

-#' GMQL Operation: COVER

-#'

-#' it takes as input a dataset and returns another dataset (with a single sample, if no \emph{groupby} option is specified)

-#' by “collapsing” the input dataset samples and their regions according to certain rules specified by the input parameters.

-#' The attributes of the output genomic regions are only the region coordinates, and Jaccard indexes (JaccardIntersect and JaccardResult).

-#' Jaccard Indexes are standard measures of similarity of the contributing regions, added as default region attributes.

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

-#' and of the union of the contributing regions; the JaccardResult index is calculated as the ratio

-#' between the lengths of region and the union of the contributing regions.

-#' If aggregate functions are specified, new attributes are added.

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

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

-#' each with distinct values of the grouping metadata attributes, and the 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 are disregarded.

-#'

-#' @importFrom methods is

-#' 

-#' @param input_data returned object from any GMQL function

-#' @param minAcc minimum number of overlapping regions to be considered during executio.n

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

-#' minAcc accept ALL and string like (ALL+N)/K as special keyword 

-#' ALL sets the minimum to the number of samples in the input dataset

-#' @param maxAcc maximum number of overlapping regions to be considered during execution.

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

-#' maxAcc accept ALL, ANY and string like (ALL+N)/K as special keyword 

-#' ALL sets the maximum to the number of samples in the input dataset

-#' ANY acts as a wildcard, consider all areas defined to any amount of overlapping 

-#' @param groupBy list of CONDITION objects, or simple string concatenation 

-#' (i.e c("cell_type","attribute_tag","size")).

-#' Every object contains the name of metadata to be used in \emph{groupby}.

-#' For details of CONDITION objects see:

-#' \code{\link{DEF}}, \code{\link{FULL}}, \code{\link{EXACT}}

-#' 

-#' Every condition accepts only one string value. (e.g. DEF("cell_type") )

-#' In case of single concatenation with no CONDITION, all metadata are considering as DEF

-#' 

-#' @param aggregates list of element in the form \emph{key} = \emph{function_aggregate}.

-#' The \emph{function_aggregate} is an object of class OPERATOR

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

-#' \code{\link{SUM}}, \code{\link{BAG}}, \code{\link{AVG}}, \code{\link{COUNT}},

-#' \code{\link{STD}}, \code{\link{MEDIAN}}, \code{\link{Q1}}, \code{\link{Q2}}, 

-#' \code{\link{Q3}}.

-#' Every operator accepts a string value, execet for COUNT that cannot have a value.

-#' Argument of 'function_aggregate' must exist in schema

-#' Two style are allowed:

-#' \itemize{

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

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

-#' }

-#' "mixed style" is not allowed

-#'

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

-#' as input for the subsequent GMQL function

-#' 

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

-#'

-#' @seealso  \code{\link{summit}} \code{\link{flat}} \code{\link{histogram}}

-#'

-#' @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.

-#' 

-#' initGMQL("gtf")

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

-#' 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).

-#' 

-#' 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")))

-#' }

-#' @export

-#'

-cover <- function(input_data, minAcc, maxAcc, groupBy = NULL, aggregates = NULL)

-{

-  .doVariant("COVER",minAcc,maxAcc,groupBy,aggregates,input_data)

-}

-

-#' GMQL Operation: HISTOGRAM

-#'

-#' returns the non-overlapping regions contributing to the cover,

-#' each with its accumulation index value, which is assigned to the AccIndex region attribute.

-#'

-#' @importFrom methods is

-#'

-#' @param input_data returned object from any GMQL function

-#' @param minAcc minimum number of overlapping regions to be considered during execution

-#' normally is a single integer number, declared also as string.

-#' minAcc accept ALL and string like (ALL+N)/K as special keyword 

-#' ALL sets the minimum to the number of samples in the input dataset

-#' @param maxAcc maximum number of overlapping regions to be considered during execution

-#' normally is a single integer number, declared also as string.

-#' maxAcc accept ALL, ANY and string like (ALL+N)/K as special keyword 

-#' ALL sets the maximum to the number of samples in the input dataset

-#' ANY acts as a wildcard, consider all areas defined to any amount of overlapping 

-#' @param groupBy list of CONDITION objects, or simple string concatenation 

-#' (i.e c("cell_type","attribute_tag","size")).

-#' Every object contains the name of metadata to be used in \emph{groupby}.

-#' For details of CONDITION objects see:

-#' \code{\link{DEF}}, \code{\link{FULL}}, \code{\link{EXACT}}

-#' 

-#' Every condition accepts only one string value. (e.g. DEF("cell_type") )

-#' In case of single concatenation with no CONDITION, all metadata are considering as DEF

-#' 

-#' @param aggregates list of element in the form \emph{key} = \emph{function_aggregate}.

-#' The \emph{function_aggregate} is an object of class OPERATOR

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

-#' \code{\link{SUM}}, \code{\link{BAG}}, \code{\link{AVG}}, \code{\link{COUNT}},

-#' \code{\link{STD}}, \code{\link{MEDIAN}}, \code{\link{Q1}}, \code{\link{Q2}}, 

-#' \code{\link{Q3}}.

-#' Every operator accepts a string value, execet for COUNT that cannot have a value.

-#' Argument of 'function_aggregate' must exist in schema

-#' Two style are allowed:

-#' \itemize{

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

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

-#' }

-#' "mixed style" is not allowed

-#'

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

-#' as input for the subsequent GMQL function

-#' 

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

-#' @seealso \code{\link{flat}} \code{\link{cover}} \code{\link{summit}}

-#'

-#' @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;

-#'

-#' initGMQL("gtf")

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

-#' exp = readDataset(test_path)

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

-#' 

-#' @export

-#'

-histogram <- function(input_data, minAcc, maxAcc, groupBy = NULL, aggregates = NULL)

-{

-  .doVariant("HISTOGRAM",minAcc,maxAcc,groupBy,aggregates,input_data)

-}

-

-#' GMQL Operation: SUMMIT

-#'

-#' returns regions that start from a position

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

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

-#' or it violates the max accumulation index).

-#'

-#' @importFrom methods is

-#'

-#' @param input_data returned object from any GMQL function

-#' @param minAcc minimum number of overlapping regions to be considered during execution

-#' normally is a single integer number, declared also as string.

-#' minAcc accept ALL and string like (ALL+N)/K as special keyword 

-#' ALL sets the minimum to the number of samples in the input dataset

-#' @param maxAcc maximum number of overlapping regions to be considered during execution

-#' normally is a single integer number, declared also as string.

-#' maxAcc accept ALL, ANY and string like (ALL+N)/K as special keyword 

-#' ALL sets the maximum to the number of samples in the input dataset

-#' ANY acts as a wildcard, consider all areas defined to any amount of overlapping 

-#' @param groupBy list of CONDITION objects, or simple string concatenation 

-#' (i.e c("cell_type","attribute_tag","size")).

-#' Every object contains the name of metadata to be used in \emph{groupby}.

-#' For details of CONDITION objects see:

-#' \code{\link{DEF}}, \code{\link{FULL}}, \code{\link{EXACT}}

-#' 

-#' Every condition accepts only one string value. (e.g. DEF("cell_type") )

-#' In case of single concatenation with no CONDITION, all metadata are considering as DEF

-#' 

-#' @param aggregates list of element in the form \emph{key} = \emph{function_aggregate}.

-#' The \emph{function_aggregate} is an object of class OPERATOR

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

-#' \code{\link{SUM}}, \code{\link{BAG}}, \code{\link{AVG}}, \code{\link{COUNT}},

-#' \code{\link{STD}}, \code{\link{MEDIAN}}, \code{\link{Q1}}, \code{\link{Q2}}, 

-#' \code{\link{Q3}}.

-#' Every operator accepts a string value, execet for COUNT that cannot have a value.

-#' Argument of 'function_aggregate' must exist in schema

-#' Two style are allowed:

-#' \itemize{

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

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

-#' }

-#' "mixed style" is not allowed

-#'

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

-#' as input for the subsequent GMQL function

-#' 

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

-#' @seealso \code{\link{flat}} \code{\link{cover}} \code{\link{histogram}}

-#'

-#' @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;

-#'

-#'

-#' initGMQL("gtf")

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

-#' exp = readDataset(test_path)

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

-#' 

-#' @export

-#'

-summit <- function(input_data, minAcc, maxAcc, groupBy = NULL, aggregates = NULL)

-{

-  .doVariant("SUMMIT",minAcc,maxAcc,groupBy,aggregates,input_data)

-}

-

-#' GMQL Operation: FLAT

-#'

-#' returns the contiguous region that starts from the first end and stops at

-#' the last end of the regions which would contribute to each region of the COVER

-#'

-#' @importFrom methods is

-#'

-#' @param input_data returned object from any GMQL function

-#' @param minAcc minimum number of overlapping regions to be considered during execution

-#' normally is a single integer number, declared also as string.

-#' minAcc accept ALL and string like (ALL+N)/K as special keyword 

-#' ALL sets the minimum to the number of samples in the input dataset

-#' @param maxAcc maximum number of overlapping regions to be considered during execution

-#' normally is a single integer number, declared also as string.

-#' maxAcc accept ALL, ANY and string like (ALL+N)/K as special keyword 

-#' ALL sets the maximum to the number of samples in the input dataset

-#' ANY acts as a wildcard, consider all areas defined to any amount of overlapping 

-#' @param groupBy list of CONDITION objects, or simple string concatenation 

-#' (i.e c("cell_type","attribute_tag","size")).

-#' Every object contains the name of metadata to be used in \emph{groupBy}.

-#' For details of CONDITION objects see:

-#' \code{\link{DEF}}, \code{\link{FULL}}, \code{\link{EXACT}}

-#' 

-#' Every condition accepts only one string value. (e.g. DEF("cell_type") )

-#' In case of single concatenation with no CONDITION, all metadata are considering as DEF

-#' 

-#' @param aggregates list of element in the form \emph{key} = \emph{function_aggregate}.

-#' The \emph{function_aggregate} is an object of class OPERATOR

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

-#' \code{\link{SUM}}, \code{\link{BAG}}, \code{\link{AVG}}, \code{\link{COUNT}},

-#' \code{\link{STD}}, \code{\link{MEDIAN}}, \code{\link{Q1}}, \code{\link{Q2}}, 

-#' \code{\link{Q3}}.

-#' Every operator accepts a string value, execet for COUNT that cannot have a value.

-#' Argument of 'function_aggregate' must exist in schema

-#' Two style are allowed:

-#' \itemize{

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

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

-#' }

-#' "mixed style" is not allowed

-#'

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

-#' as input for the subsequent GMQL function

-#' 

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

-#' @seealso \code{\link{summit}} \code{\link{cover}} \code{\link{histogram}}

-#'

-#' @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; 

-#' 

-#' initGMQL("gtf")

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

-#' exp = readDataset(test_path)

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

-#'

-#' @export

-#'

-flat <- function(input_data, minAcc, maxAcc, groupBy = NULL, aggregates = NULL)

-{

-  .doVariant("FLAT",minAcc,maxAcc,groupBy,aggregates,input_data)

-}

-

-.doVariant <- function(flag,minAcc,maxAcc,groupBy,aggregates,input_data)

-{

-  min <- .check_cover_param(minAcc,TRUE)

-  max <- .check_cover_param(maxAcc,FALSE)

-

-  if(!is.null(groupBy))

-    join_condition_matrix <- .join_condition(groupBy)

-  else

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

-  

-  if(!is.null(aggregates))

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

-  else

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

-

-

-  response <- switch(flag,

-                "COVER" = WrappeR$cover(min,max,join_condition_matrix,metadata_matrix,input_data$value),

-                "FLAT" = WrappeR$flat(min,max,join_condition_matrix,metadata_matrix,input_data$value),

-                "SUMMIT" = WrappeR$summit(min,max,join_condition_matrix,metadata_matrix,input_data$value),

-                "HISTOGRAM" = WrappeR$histogram(min,max,join_condition_matrix,metadata_matrix,input_data$value))

-

-  error <- strtoi(response[1])

-  data <- response[2]

-  

-  if(error!=0)

-    stop(data)

-  else

-    DAGgraph(data)

-}

-

-.check_cover_param <- function(param,is_min)

-{

-  if(length(param)>1)

-    stop("length > 1")

-

-  if(is.numeric(param))

-  {

-    if(param<=0)

-      stop("No negative value")

-    else

-      return(as.integer(param))

-  }

-  else if(is.character(param))

-  {

-    if(is_min && identical(param,"ANY"))

-      stop("min cannot assume ANY as value")

-    return(param)

-  }

-  else

-    stop("invalid input data")

-}

-

-

deleted file mode 100644

@@ -1,79 +0,0 @@

-#' GMQL Operation: DIFFERENCE

-#'

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

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

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

-#' in the right operand sample.

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

-#' from the cartesian product of two dataset \emph{left_input_data} x \emph{right_input_data}

-#' on which to apply the DIFFERENCE operator:

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

-#' are considered when performing the difference.

-#'

-#'

-#' @param right_input_data returned object from any GMQL function

-#' @param left_input_data returned object from any GMQL function

-#' @param joinBy list of CONDITION objects, or simple string concatenation 

-#' (i.e c("cell_type","attribute_tag","size")).

-#' Every object contains the name of metadata to be used in \emph{groupby}.

-#' For details of CONDITION objects see:

-#' \code{\link{DEF}}, \code{\link{FULL}}, \code{\link{EXACT}}

-#' 

-#' Every condition accepts only one string value (e.g. DEF("cell_type") )

-#' In case of single concatenation with no CONDITION, all metadata are considering as DEF

-#' 

-#' @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; 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).

-#'

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

-#' as input for the subsequent GMQL function

-#'

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

-#'

-#' @examples

-#'

-#' ## 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")

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

-#' r_left = readDataset(test_path)

-#' r_right = readDataset(test_path2)

-#' 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.

-#' 

-#' initGMQL("gtf")

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

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

-#' exp1 = readDataset(test_path)

-#' exp2 = readDataset(test_path2)

-#' out = difference(exp1,exp2, c("antibody_target"))

-#'

-#' }

-#'

-#' @export

-#'

-difference <- function(left_input_data, right_input_data, joinBy = NULL,is_exact = FALSE)

-{

-  if(!is.null(joinBy))

-    join_condition_matrix <- .join_condition(joinBy)

-  else

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

-  

-  response <- WrappeR$difference(join_condition_matrix,right_input_data$value,left_input_data$value,is_exact)

-  error <- strtoi(response[1])

-  data <- response[2]

-  if(error!=0)

-    stop(data)

-  else

-    DAGgraph(data)

-}

-

@@ -27,7 +27,7 @@

 #' @examples

 #'

 #' initGMQL("gtf")

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

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

 #' r = readDataset(test_path)

 #'

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

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

 #' \dontrun{

 #' 

 #' initGMQL("gtf")

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

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

 #' exp = readDataset(test_path)

 #'

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

@@ -56,8 +56,9 @@ extend <-function(input_data, metadata = NULL)

   if(!is.null(metadata))

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

   else

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

-

+    metadata_matrix <- .jnull("java/lang/String")

+  

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

   response <- WrappeR$extend(metadata_matrix,input_data$value)

   error <- strtoi(response[1])

   data <- response[2]

@@ -24,7 +24,7 @@

 #'

 #' @examples

 #'

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

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

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

 #'

 #' @export

@@ -98,7 +98,7 @@ TFARMatrix <- function(GMQL_dataset_path, metadata = NULL,metadata_prefix = NULL

 #' @examples

 #'

 #'

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

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

 #' grl <- importGMQL.gtf(test_path)

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

 #'

@@ -18,7 +18,7 @@

 #'

 #' @examples

 #'

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

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

 #' grl = importGMQL.gtf(test_path)

 #'

 #'

@@ -39,7 +39,7 @@

 #' gr2 <- GRanges(seqnames = c("chr1", "chr1"),

 #' ranges = IRanges(c(7,13), width = 3), strand = c("+", "-"), score = 3:4, GC = c(0.3, 0.5))

 #' grl = GRangesList(gr1,gr2)

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

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

 #' exportGMQL.gdm(grl,test_out_path)

 #'

 #'

@@ -92,7 +92,7 @@ exportGMQL.gdm <- function(samples, dir_out)

 #' gr2 <- GRanges(seqnames = c("chr1", "chr1"),

 #' ranges = IRanges(c(7,13), width = 3), strand = c("+", "-"), score = 3:4, GC = c(0.3, 0.5))

 #' grl = GRangesList(gr1,gr2)

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

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

 #' exportGMQL.gtf(grl,test_out_path)

 #'

 #' @export

deleted file mode 100644

@@ -1,117 +0,0 @@

-#' GMQL Operation: JOIN

-#'

-#' It takes in input two datasets, respectively known as nchor (left) and experiment (right) and returns

-#' a dataset of samples consisting of regions extracted from the operands according to the specified condition

-#' (a.k.a genometric_predicate).

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

-#' in the anchor and in the experiment dataset (if joinBy is not specified).

-#' The output metadata are the union of the input metadata, with their attribute names prefixed with

-#' left or right respectively.

-#'

-#'

-#' @param left_input_data returned object from any GMQL function

-#' @param right_input_data returned object from any GMQL function

-#' @param genometric_predicate is a list of lists of DISTAL object by means of logical ANDs

-#' For details of DISTAL objects see:

-#' \code{\link{DLE}}, \code{\link{DGE}}, \code{\link{MD}}, \code{\link{UP}}, \code{\link{DOWN}}

-#' 

-#' @param joinBy list of CONDITION objects, or simple string concatenation 

-#' (i.e c("cell_type","attribute_tag","size")).

-#' Every object contains the name of metadata to be used in \emph{groupby}.

-#' For details of CONDITION objects see:

-#' \code{\link{DEF}}, \code{\link{FULL}}, \code{\link{EXACT}}

-#' 

-#' Every condition accepts only one string value. (e.g. DEF("cell_type") )

-#' In case of single concatenation with no CONDITION, all metadata are considering as DEF

-#' 

-#' @param region_output single string that declare which region is given in output for each input pair of left dataset

-#' right dataset regions satisfying the genometric predicate:

-#' \itemize{

-#' \item{left: outputs the anchor regions from left_input_data that satisfy the genometric predicate}

-#' \item{right: outputs the experiment regions from right_input_data that satisfy the genometric predicate}

-#' \item{int (intersection): outputs the overlapping part (intersection) of the left_input_data and right_input_data

-#' regions that satisfy the genometric predicate; if the intersection is empty, no output is produced}

-#' \item{contig: outputs the concatenation between the left_input_data and right_input_data regions that satisfy

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

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

-#' regions satisfying the genometric predicate)}

-#' }

-#'

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

-#' as input for the subsequent GMQL function

-#'

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

-#'

-#'

-#' @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).

-#' 

-#' 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")

-#'

-#' @export

-#'

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

-                 joinBy = NULL, region_output="contig")

-{

-  

-  if(!is.null(genometric_predicate))

-  {

-    if(!is.list(genometric_predicate))

-      stop("genometric_predicate must be list of lists")

-    

-    if(!all(sapply(genometric_predicate, function(x) is.list(x) )))

-      stop("genometric_predicate must be list of lists")

-    

-    lapply(genometric_predicate, function(list_pred) {

-      if(length(list_pred)>4)

-      {

-        warning("only 4 element per list, we cut the rest")

-        length(list_pred)=4

-      }

-      

-      if(!all(sapply(list_pred, function(x) {is(x,"DISTAL")} )))

-        stop("All elements should be DISTAL object")

-

-    })

-    

-    genomatrix <- t(sapply(genometric_predicate, function(list_pred) {

-      dist_array <- sapply(list_pred, function(x) {

-        new_value = as.character(x)

-        array <- c(new_value)

-      })

-      dist_array = c(dist_array,c("NA","NA"),c("NA","NA"),c("NA","NA"))

-      length(dist_array) = 8

-      dist_array

-    }))

-  }

-  else

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

-      

-  if(!is.null(joinBy))

-    join_condition_matrix <- .join_condition(joinBy)

-  else

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

-  

-  ouput <- toupper(region_output)

-  if(!identical(ouput,"CONTIG") && !identical(ouput,"LEFT") && !identical(ouput,"RIGHT")

-     && !identical(ouput,"INT"))

-    stop("region_output must be contig,left,right or int (intersection)")

-  

-  response <- WrappeR$join(genomatrix,join_condition_matrix, ouput,right_input_data$value, left_input_data$value)

-  error <- strtoi(response[1])

-  data <- response[2]

-  if(error!=0)

-    stop(data)

-  else

-    DAGgraph(data)

-}

deleted file mode 100644

@@ -1,87 +0,0 @@

-#' GMQL Operation: MAP

-#'

-#' It computes, for each sample in the right dataset, aggregates over the values of the right regions

-#' that intersect with a region in a left sample, for each region of each sample in the left dataset;

-#' The number of generated output samples is the Cartesian product of the samples in the two input datasets;

-#' each output sample has the same regions as the related input left sample, with their attributes and values,

-#' plus the attributes computed as aggregates over right region values.

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

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

-#'

-#' When the joinby clause is present, only pairs of samples of left_input_data and of right_input_data with

-#' metadata M1 and M2 respectively that satisfy the joinby condition are considered.

-#'

-#' The clause consists of a list of metadata attribute names that must be present with equal values

-#' in both M1 and  M2

-#'

-#'

-#' @param left_input_data returned object from any GMQL function

-#' @param right_input_data returned object from any GMQL function

-#' @param aggregates list of element in the form \emph{key} = \emph{function_aggregate}.

-#' The \emph{function_aggregate} is an object of class OPERATOR

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

-#' \code{\link{SUM}}, \code{\link{BAG}}, \code{\link{AVG}}, \code{\link{COUNT}},

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

-#' Every operator accepts a string value, execet for COUNT that cannot have a value.

-#' Argument of 'function_aggregate' must exist in schema

-#' Two style are allowed:

-#' \itemize{

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

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

-#' }

-#' "mixed style" is not allowed

-#'

-#' @param joinBy list of CONDITION objects, or simple string concatenation 

-#' (i.e c("cell_type","attribute_tag","size")).

-#' Every object contains the name of metadata to be used in \emph{groupby}.

-#' For details of CONDITION objects see:

-#' \code{\link{DEF}}, \code{\link{FULL}}, \code{\link{EXACT}}

-#' 

-#' Every condition accepts only one string value. (e.g. DEF("cell_type") )

-#' In case of single concatenation with no CONDITION, all metadata are considering as DEF

-#' 

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

-#' as input for the subsequent GMQL function

-#'

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

-#'

-#' @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.

-#' 

-#' 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 = readDataset(test_path)

-#' ref = readDataset(test_path2)

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

-#' 

-#' 

-#' @export

-#'

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

-{

-  if(!is.null(aggregates))

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

-  else

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

-

-  if(!is.null(joinBy))

-    join_condition_matrix <- .join_condition(joinBy)

-  else

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

-

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

-  error <- strtoi(response[1])

-  data <- response[2]

-  if(error!=0)

-    stop(data)

-  else

-    DAGgraph(data)

-}

deleted file mode 100644

@@ -1,189 +0,0 @@

-#' GMQL Function: EXECUTE

-#'

-#' execute GMQL query.

-#' The function works only after invoking at least one materialize

-#'

-#' @details