@@ -11,7 +11,7 @@

 #'

 #' @param datasetName single string GMQL dataset folder path

 #'

-#' @return GrangesList containing all GMQL sample In dataset

+#' @return GrangesList containing all GMQL samples in dataset

 #'

 #' @seealso \code{\link{exportGMQL.gdm}} \code{\link{exportGMQL.gtf}} \code{\link{importGMQL.gdm} }

 #'

@@ -72,7 +72,7 @@ importGMQL.gtf <- function(datasetName)

 #'

 #' @param datasetName single string GMQL dataset folder path

 #'

-#' @return GrangesList containing all GMQL sample In dataset

+#' @return GrangesList containing all GMQL samples in dataset

 #'

 #' @seealso \code{\link{exportGMQL.gdm}} \code{\link{exportGMQL.gtf}} \code{\link{importGMQL.gtf} }

 #'

@@ -14,7 +14,7 @@

 #' @param samples GrangesList

 #' @param dir_out folder path where create a folder and write all the sample files

 #'

-#' @return no value return

+#' @return None

 #'

 #' @seealso \code{\link{exportGMQL.gdm}} \code{\link{exportGMQL.gtf}} \code{\link{importGMQL.gtf}}

 #'

@@ -67,7 +67,7 @@ exportGMQL.gdm <- function(samples, dir_out)

 #' @param samples GrangesList

 #' @param dir_out folder path where create a folder and write all the sample files

 #'

-#' @return no value return

+#' @return None

 #'

 #'

 #' @seealso \code{\link{exportGMQL.gdm}} \code{\link{exportGMQL.gtf}} \code{\link{importGMQL.gdm} }

@@ -32,6 +32,34 @@

 #'

 #' @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.

+#' 

+#' 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,)

+#' 

+#' 

+#' \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.

+#' 

+#' initGMQL("gtf")

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

+#' DS_in = readDataset(test_path)

+#' DS_out = project(DS_in,regions=c("variant_classification", "variant_type"), 

+#' metadata=c("manually_curated__tissue_status","manually_curated__tumor_tag"))

+#' 

+#' }

+#' 

 #' @export

 #'

 #'

@@ -12,13 +12,13 @@

 #' @param predicate single string predicate made up by logical operation: AND,OR,NOT on metadata attribute

 #' @param region_predicate single string predicate made up by logical operation: AND,OR,NOT on schema region values

 #' @param semi_join list of CONDITION objects where every object contains the name of metadata to be used in semijoin,

-#' or simple string concatenation of name of metadata (e.g c("cell_type","attribute_tag","size") ) without declaring condition.

+#' or simple string concatenation of name of metadata, e.g c("cell_type","attribute_tag","size") without declaring condition.

 #' In the latter form all metadata are considered having DEF condition

 #' The CONDITION's available are:

 #' \itemize{

 #' \item{\code{\link{FULL}}: 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{DEF}}: Default evaluation, two attributes match if both end with value. }

+#' \item{\code{\link{DEF}}: Default evaluation, two attributes match if both end with value}

 #' \item{\code{\link{EXACT}}: Exact evaluation, only attributes exactly as value will match; no further prefixes are allowed. }

 #' }

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

@@ -44,7 +44,7 @@

 #' s=select(input,"Patient_age < 70")

 #' 

 #' 

-#' \dontrun {

+#' \dontrun{

 #' 

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

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

deleted file mode 100644

@@ -1,7 +0,0 @@

-read.R

-

-aggiungere data per grangeslist in example

-aggiugnere example con data

-

-

-//delete warning eventually

deleted file mode 120000

@@ -1 +0,0 @@

-/Users/simone/Documents/GMQL/GMQL-R/target/uber-GMQL-R-1.0.jar

\ No newline at end of file

new file mode 100644

Binary files /dev/null and b/inst/java/scala-2.11/GMQL.jar differ

@@ -12,7 +12,7 @@ exportGMQL.gdm(samples, dir_out)

 \item{dir_out}{folder path where create a folder and write all the sample files}

 }

 \value{

-no value return

+None

 }

 \description{

 It create GMQL dataset from GRangesList.

@@ -12,7 +12,7 @@ exportGMQL.gtf(samples, dir_out)

 \item{dir_out}{folder path where create a folder and write all the sample files}

 }

 \value{

-no value return

+None

 }

 \description{

 It create GMQL dataset from GRangesList.

@@ -10,7 +10,7 @@ importGMQL.gdm(datasetName)

 \item{datasetName}{single string GMQL dataset folder path}

 }

 \value{

-GrangesList containing all GMQL sample In dataset

+GrangesList containing all GMQL samples in dataset

 }

 \description{

 It create a GrangesList from GMQL samples in dataset

@@ -10,7 +10,7 @@ importGMQL.gtf(datasetName)

 \item{datasetName}{single string GMQL dataset folder path}

 }

 \value{

-GrangesList containing all GMQL sample In dataset

+GrangesList containing all GMQL samples in dataset

 }

 \description{

 It create a GrangesList from GMQL samples in dataset

@@ -5,26 +5,33 @@

 \title{GMQL Operation: PROJECT}

 \usage{

 project(input_data, metadata = NULL, metadata_update = NULL,

-  regions = NULL, regions_update = NULL, all_but = FALSE)

+  all_but_meta = FALSE, regions = NULL, regions_update = NULL,

+  all_but_reg = FALSE)

 }

 \arguments{

 \item{input_data}{string pointer taken from GMQL function}

 \item{metadata}{vector of string made up by metadata attribute}

-\item{metadata_update}{single string predicate}

+\item{metadata_update}{single string predicate made up by operation on metadata attribute}

-\item{regions_update}{single string predicate}

+\item{all_but_meta}{logical value indicating which metadata you want to exclude.

+If FALSE only the metadata you choose is kept in the output of the project operation,

+if TRUE the metadata are all except ones include in region parameter.

+if metadata is not defined \emph{all_but_meta} is not considerd.}

-\item{all_but}{logical value indicating which schema filed attribute you want to exclude.

+\item{regions_update}{single string predicate made up by operation on schema field attribute}

+

+\item{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.

-if regions is not defined all_but is not considerd.}

+if regions is not defined \emph{all_but_reg} is not considerd.}

 \item{region}{vector of string made up by schema field attribute}

 }

 \value{

-"url-like" string

+DAGgraph class object. It contains the value associated to the graph used 

+as input for the subsequent GMQL function#'

 }

 \description{

 It creates, from an existing dataset, a new dataset with all the samples from input dataset

@@ -38,25 +45,35 @@ It allows to:

 }

 }

 \examples{

-\dontrun{

+

+## 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.

 initGMQL("gtf")

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

-r = read(test_path)

+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,)

+

-### preserving all region attributes and creating a new region attribute called length

-p = project(input_data = r,regions_update="length AS right - left")

+\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.

-### preserving all region attributes apart from  score, and creating a new region attribute called new_score

-p = project(input_data = r, regions = "score" regions_update="length AS right - left", all_but=TRUE)

+initGMQL("gtf")

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

+DS_in = readDataset(test_path)

+DS_out = project(DS_in,regions=c("variant_classification", "variant_type"), 

+metadata=c("manually_curated__tissue_status","manually_curated__tumor_tag"))

-### 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 and as metadata attributes only the specified ones

-p = project(input_data = r, regions = c("variant_classification", "variant_type"),

-metadata = c("manually_curated","tissue_status", "tumor_ta") )

 }

-""

+

 }

 \references{

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

@@ -15,13 +15,13 @@ select(input_data, predicate = NULL, region_predicate = NULL,

 \item{region_predicate}{single string predicate made up by logical operation: AND,OR,NOT on schema region values}

 \item{semi_join}{list of CONDITION objects where every object contains the name of metadata to be used in semijoin,

-or simple string concatenation of name of metadata (e.g c("cell_type","attribute_tag","size") ) without declaring condition.

+or simple string concatenation of name of metadata, e.g c("cell_type","attribute_tag","size") without declaring condition.

 In the latter form all metadata are considered having DEF condition

 The CONDITION's available are:

 \itemize{

 \item{\code{\link{FULL}}: 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{DEF}}: Default evaluation, two attributes match if both end with value. }

+\item{\code{\link{DEF}}: Default evaluation, two attributes match if both end with value}

 \item{\code{\link{EXACT}}: Exact evaluation, only attributes exactly as value will match; no further prefixes are allowed. }

 }

 Every condition accepts only one string value. (e.g. FULL("cell_type") )}

@@ -56,7 +56,7 @@ input = readDataset(test_path)

 s=select(input,"Patient_age < 70")

-\dontrun {

+\dontrun{

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

 regions from the existing 'data' dataset such that: