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

 Package: RGMQL

 Type: Package

 Title: GenoMetric Query Language for R/Bioconductor

-Version: 0.99.30

+Version: 0.99.31

 Author: Simone Pallotta, Marco Masseroli

 Maintainer: Simone Pallotta <simonepallotta@hotmail.com>

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

@@ -30,6 +30,7 @@ export(SUM)

 export(UP)

 export(compile_query)

 export(compile_query_fromfile)

+export(cover)

 export(delete_dataset)

 export(download_as_GRangesList)

 export(download_dataset)

@@ -1,7 +1,3 @@

-

-

-

-

 #' GMQL Operation: COVER

 #'

 #' It takes as input a dataset containing one or more samples and returns 

@@ -134,11 +130,10 @@

 #' }

 #' 

 #' 

-#' @name cover

-#' @rdname cover-methods

-#' @aliases cover, cover-methods

+#' @rdname GMQLDataset-class

+#' @aliases cover, GMQLDataset--method

 #' 

-#' @exportMethod cover

+#' @export

 #' 

 setGeneric("cover", function(data, minAcc, maxAcc, ...)

 {

@@ -148,12 +143,11 @@ setGeneric("cover", function(data, minAcc, maxAcc, ...)

     min <- .check_cover_param(minAcc,TRUE)

     max <- .check_cover_param(maxAcc,FALSE)

-    gmql_cover(data,minAcc,maxAcc)

+    gmql_cover(data,min,max,NULL,NULL,"COVER")

 })

-#' @name cover

-#' @rdname cover-methods

-#' @aliases cover, cover-methods

+#' @rdname GMQLDataset-class

+#' @aliases cover, GMQLDataset--method

 #' @export

 setMethod("cover", "GMQLDataset",

             function(data, minAcc, maxAcc, groupBy = NULL, aggregates = NULL, 

@@ -166,12 +160,12 @@ setMethod("cover", "GMQLDataset",

                 max <- .check_cover_param(maxAcc,FALSE)

                 flag = toupper(variation)

-                gmql_cover(data@value, minAcc, maxAcc, groupBy, aggregates, 

-                                flag)

+                gmql_cover(data@value, min, max, groupBy, aggregates, 

+                           flag)

             })

-gmql_cover <- function(input_data, minAcc, maxAcc, groupBy = NULL, 

-                        aggregates = NULL, flag = "cover")

+gmql_cover <- function(data, minAcc, maxAcc, groupBy = NULL, 

+                        aggregates = NULL, flag)

 {

     if(!is.null(groupBy))

         join_condition_matrix <- .jarray(.join_condition(groupBy),

@@ -188,14 +182,13 @@ gmql_cover <- function(input_data, minAcc, maxAcc, groupBy = NULL,

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

     response <- switch(flag,

                 "COVER" = WrappeR$cover(minAcc, maxAcc, join_condition_matrix,

-                                    metadata_matrix, input_data),

+                                    metadata_matrix, data),

                 "FLAT" = WrappeR$flat(minAcc, maxAcc, join_condition_matrix,

-                                    metadata_matrix,input_data),

+                                    metadata_matrix, data),

                 "SUMMIT" = WrappeR$summit(minAcc,maxAcc, join_condition_matrix,

-                                    metadata_matrix, input_data),

+                                    metadata_matrix, data),

                 "HISTOGRAM" = WrappeR$histogram(minAcc, maxAcc, 

-                                join_condition_matrix, metadata_matrix,

-                                input_data))

+                                join_condition_matrix, metadata_matrix, data))

     if(is.null(response))

         stop("no admissible variation: cover, flat, summit, histogram")

@@ -42,9 +42,10 @@

 #' 

 #' res <- union(data1, data2)

 #' 

-#' @rdname GMQLDataset-class

-#' @aliases union, GMQLDataset-method

+#' @rdname union-method

+#' @aliases union, union-method

 #' @export

+#' 

 setMethod("union", c("GMQLDataset","GMQLDataset"),

             function(x, y)

             {

@@ -1,25 +1,107 @@

 % Generated by roxygen2: do not edit by hand

-% Please edit documentation in R/Dataset-class.R, R/Select.R, R/Union.R

-\docType{class}

-\name{GMQLDataset-class}

+% Please edit documentation in R/Cover.R, R/Dataset-class.R, R/Select.R

+\docType{methods}

+\name{cover}

+\alias{cover}

+\alias{cover,}

+\alias{GMQLDataset--method}

+\alias{cover,GMQLDataset-method}

+\alias{cover,}

+\alias{GMQLDataset--method}

 \alias{GMQLDataset-class}

 \alias{GMQLDataset}

 \alias{filter}

 \alias{filter,}

 \alias{filter-methods}

-\alias{union}

-\alias{union,}

-\alias{GMQLDataset-method}

-\title{Class GMQLDataset}

+\title{GMQL Operation: COVER}

 \usage{

+cover(data, minAcc, maxAcc, ...)

+

+\S4method{cover}{GMQLDataset}(data, minAcc, maxAcc, groupBy = NULL,

+  aggregates = NULL, variation = "cover")

+

 GMQLDataset(value)

 filter(data, m_predicate = NULL, r_predicate = NULL, semi_join = NULL,

   semi_join_negation = FALSE, semi_join_dataset = NULL)

-

-\S4method{union}{GMQLDataset,GMQLDataset}(x, y)

 }

 \arguments{

+\item{data}{GMQLDataset class object}

+

+\item{minAcc}{minimum number of overlapping regions to be considered 

+during execution

+Is a integer number, declared also as string.

+minAcc accept also:

+\itemize{

+\item{PARAMETER class object: \code{\link{ALL}} that represents the number 

+of samples in the input dataset}

+\item{and expression built using PARAMETER object: (ALL() + N) / K or

+ALL() / K }

+}}

+

+\item{maxAcc}{maximum number of overlapping regions to be considered 

+during execution

+Is a integer number, declared also as string.

+maxAcc accept also:

+\itemize{

+\item{PARAMETER class object: \code{\link{ALL}} that represents the number 

+of samples in the input dataset}

+\item{PARAMETER calss object: \code{\link{ANY}}} that acts as a wildcard, 

+considering any amount of overlapping.

+\item{and expression built using PARAMETER object: (ALL() + N) / K or

+ALL() / K }

+}}

+

+\item{groupBy}{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.

+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{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") )

+In case of single concatenation with no CONDITION or list with some value 

+without conditon, the metadata are considered having default 

+evaluation: the two attributes match if both end with value.}

+

+\item{aggregates}{list of element in the form \emph{key} = \emph{aggregate}.

+The \emph{aggregate} is an object of class AGGREGATES

+The aggregate functions available are: \code{\link{SUM}}, 

+\code{\link{COUNT}}, \code{\link{MIN}}, \code{\link{MAX}}, 

+\code{\link{AVG}}, \code{\link{MEDIAN}}, \code{\link{STD}}, 

+\code{\link{BAG}}, \code{\link{BAGD}}, \code{\link{Q1}}, 

+\code{\link{Q2}}, \code{\link{Q3}}.

+Every aggregate accepts a string value, execet for COUNT, which does not 

+have any value.

+Argument of 'aggregate function' must exist in schema, i.e. among region 

+attributes. Two style are allowed:

+\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}

+

+\item{variation}{string identifying the cover GMQL function variation.

+The admissible string are:

+\itemize{

+\item{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 \emph{cover}.}

+\item{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.}

+\item{histogram: returns the non-overlapping regions contributing to 

+the cover, each with its accumulation index value, which is assigned to 

+the AccIndex region attribute.}

+\item{cover: default value.}

+}}

+

 \item{value}{value associated to GMQL dataset}

 \item{m_predicate}{logical predicate made up by R logical operation 

@@ -53,10 +135,6 @@ considering semi_join IN semi_join_dataset}

 \item{semi_join_dataset}{GMQLDataset class object}

-\item{x}{GMQLDataset class object}

-

-\item{y}{GMQLDataset class object}

-

 \item{x}{GMQLDataset class object}

 }

 \value{

@@ -67,6 +145,28 @@ GMQLDataset class object. It contains the value to use as input

 for the subsequent GMQL function

 }

 \description{

+It takes as input a dataset containing one or more samples and returns 

+another dataset (with a single sample, if no \emph{groupby} option is 

+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 the result and the union of the contributing regions.

+If aggregate functions are specified, a new attributes is added for 

+each aggregate function specified.

+Output metadata are the union of the input ones.

+If \emph{groupby} clause is specified, the input samples are partitioned 

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

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

+yielding to one sample in the result for each group.

+Input samples that do not satisfy the \emph{groupby} condition 

+are disregarded.

+

 Abstract class representing GMQL dataset

 It returns all the samples satisfying the predicate on metadata.

@@ -78,25 +178,6 @@ attribute defined in semijoin clause with at least one metadata value

 in common with semi join dataset.

 If no metadata in common between input dataset and semi join dataset, 

 no sample is extracted.

-

-It is used to integrate homogeneous or heterogeneous samples of two datasets 

-within a single dataset; for each sample of either input dataset, 

-a result sample is created as follows:

-\itemize{

-\item {Metadata are the same as in the original sample.}

-\item {Resulting schema is obtained by projecting the schema 

-of the right dataset over the schema of the left one

-(more properly, it will be performed by adding to the schema of the 

-left dataset the region attributes of the right dataset which are not 

-identical to those of the left dataset)}

-\item {Regions are the same (in coordinates and attribute values) 

-as in the original sample.

-Region attributes which are missing in an input dataset sample 

-w.r.t. the merged schema are set to null.}

-}

-For what concerns metadata, attributes of samples from the left (right) 

-input dataset are prefixed with the strings LEFT (RIGHT), so as to trace 

-the dataset to which they originally belonged.

 }

 \section{Slots}{

@@ -106,6 +187,32 @@ the dataset to which they originally belonged.

 \examples{

+## This 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.

+

+init_gmql()

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

+exp = read_dataset(test_path)

+res = cover(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", "DATASET", package = "RGMQL")

+exp = read_dataset(test_path)

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

+}

+

+

+

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

 ## based on filtering on sample metadata attribute Patient_age

@@ -140,18 +247,4 @@ TRUE, semi_join_dataset = join_data )

 }

-

-## It creates a dataset called full which contains all samples from the 

-## datasets data1 and data2 whose schema is defined by merging the two 

-## dataset schemas.

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

-

-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)

-

-res <- union(data1, data2)

-

 }

deleted file mode 100644

@@ -1,149 +0,0 @@

-% Generated by roxygen2: do not edit by hand

-% Please edit documentation in R/Cover.R

-\docType{methods}

-\name{cover}

-\alias{cover}

-\alias{cover,}

-\alias{cover-methods}

-\alias{cover}

-\alias{cover,}

-\alias{cover-methods}

-\title{GMQL Operation: COVER}

-\usage{

-cover(data, minAcc, maxAcc, ...)

-

-\S4method{cover}{GMQLDataset}(data, minAcc, maxAcc, groupBy = NULL,

-  aggregates = NULL, variation = "cover")

-}

-\arguments{

-\item{data}{GMQLDataset class object}

-

-\item{minAcc}{minimum number of overlapping regions to be considered 

-during execution

-Is a integer number, declared also as string.

-minAcc accept also:

-\itemize{

-\item{PARAMETER class object: \code{\link{ALL}} that represents the number 

-of samples in the input dataset}

-\item{and expression built using PARAMETER object: (ALL() + N) / K or

-ALL() / K }

-}}

-

-\item{maxAcc}{maximum number of overlapping regions to be considered 

-during execution

-Is a integer number, declared also as string.

-maxAcc accept also:

-\itemize{

-\item{PARAMETER class object: \code{\link{ALL}} that represents the number 

-of samples in the input dataset}

-\item{PARAMETER calss object: \code{\link{ANY}}} that acts as a wildcard, 

-considering any amount of overlapping.

-\item{and expression built using PARAMETER object: (ALL() + N) / K or

-ALL() / K }

-}}

-

-\item{groupBy}{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.

-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{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") )

-In case of single concatenation with no CONDITION or list with some value 

-without conditon, the metadata are considered having default 

-evaluation: the two attributes match if both end with value.}

-

-\item{aggregates}{list of element in the form \emph{key} = \emph{aggregate}.

-The \emph{aggregate} is an object of class AGGREGATES

-The aggregate functions available are: \code{\link{SUM}}, 

-\code{\link{COUNT}}, \code{\link{MIN}}, \code{\link{MAX}}, 

-\code{\link{AVG}}, \code{\link{MEDIAN}}, \code{\link{STD}}, 

-\code{\link{BAG}}, \code{\link{BAGD}}, \code{\link{Q1}}, 

-\code{\link{Q2}}, \code{\link{Q3}}.

-Every aggregate accepts a string value, execet for COUNT, which does not 

-have any value.

-Argument of 'aggregate function' must exist in schema, i.e. among region 

-attributes. Two style are allowed:

-\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}

-

-\item{variation}{string identifying the cover GMQL function variation.

-The admissible string are:

-\itemize{

-\item{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 \emph{cover}.}

-\item{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.}

-\item{histogram: returns the non-overlapping regions contributing to 

-the cover, each with its accumulation index value, which is assigned to 

-the AccIndex region attribute.}

-\item{cover: default value.}

-}}

-}

-\value{

-GMQLDataset class object. It contains the value to use as input 

-for the subsequent GMQL function

-}

-\description{

-It takes as input a dataset containing one or more samples and returns 

-another dataset (with a single sample, if no \emph{groupby} option is 

-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 the result and the union of the contributing regions.

-If aggregate functions are specified, a new attributes is added for 

-each aggregate function specified.

-Output metadata are the union of the input ones.

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

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

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

-yielding to one sample in the result for each group.

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

-are disregarded.

-}

-\examples{

-

-## This 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.

-

-init_gmql()

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

-exp = read_dataset(test_path)

-res = cover(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", "DATASET", package = "RGMQL")

-exp = read_dataset(test_path)

-res = cover(exp, 2, 3, c("cell"), list(min_pValue = MIN("pvalue")))

-}

-

-

-}

new file mode 100644

@@ -0,0 +1,56 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/Union.R

+\docType{methods}

+\name{union,GMQLDataset,GMQLDataset-method}

+\alias{union,GMQLDataset,GMQLDataset-method}

+\alias{union,}

+\alias{union-method}

+\title{GMQL Operation: UNION}

+\usage{

+\S4method{union}{GMQLDataset,GMQLDataset}(x, y)

+}

+\arguments{

+\item{x}{GMQLDataset class object}

+

+\item{y}{GMQLDataset class object}

+}

+\value{

+GMQLDataset class object. It contains the value to use as input 

+for the subsequent GMQL function

+}

+\description{

+It is used to integrate homogeneous or heterogeneous samples of two datasets 

+within a single dataset; for each sample of either input dataset, 

+a result sample is created as follows:

+\itemize{

+\item {Metadata are the same as in the original sample.}

+\item {Resulting schema is obtained by projecting the schema 

+of the right dataset over the schema of the left one

+(more properly, it will be performed by adding to the schema of the 

+left dataset the region attributes of the right dataset which are not 

+identical to those of the left dataset)}

+\item {Regions are the same (in coordinates and attribute values) 

+as in the original sample.

+Region attributes which are missing in an input dataset sample 

+w.r.t. the merged schema are set to null.}

+}

+For what concerns metadata, attributes of samples from the left (right) 

+input dataset are prefixed with the strings LEFT (RIGHT), so as to trace 

+the dataset to which they originally belonged.

+}

+\examples{

+

+## It creates a dataset called full which contains all samples from the 

+## datasets data1 and data2 whose schema is defined by merging the two 

+## dataset schemas.

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

+

+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)

+

+res <- union(data1, data2)

+

+}