@@ -19,8 +19,9 @@ Suggests: igraph, Gviz,

 	 RUnit

 Collate: utils.R

 	 SplicingGraphs-class.R

-	 sgdf-methods.R

+	 sgedges-methods.R

 	 sgraph-methods.R

+	 bubbles-methods.R

 	 countReads.R

 	 toy_data.R

 biocViews: Genetics, Annotation, HighThroughputSequencing

@@ -39,8 +39,8 @@ exportMethods(

 ###

 export(

-    ## sgdf-methods.R:

-    sgdf2,

+    ## sgedges-methods.R:

+    sgedges2,

     ## sgraph-methods.R:

     sgraph2,

@@ -67,10 +67,10 @@ export(

     ## SplicingGraphs-class.R:

     SplicingGraphs,

-    ## sgdf-methods.R:

+    ## sgedges-methods.R:

     spath,

     UATXHcount,

-    sgdf,

+    sgedges,

     uninformativeSSids,

     ## sgraph-methods.R:

@@ -82,7 +82,7 @@ exportMethods(

     SplicingGraphs,

     spath,

     UATXHcount,

-    sgdf,

+    sgedges,

     uninformativeSSids,

     sgraph

 )

new file mode 100644

@@ -0,0 +1,13 @@

+

+.make_spath_matrix_from_spath <- function(spath)

+{

+    nodes <- c("R", sort(unique(unlist(spath))), "L")

+}

+

+findBubbles <- function(x, gene_id=NA)

+{

+    spath <- spath(sg, gene_id=gene_id)

+    spath_mat <- .make_spath_matrix_from_spath(spath)

+    spath_mat

+}

+

similarity index 84%

rename from R/sgdf-methods.R

rename to R/sgedges-methods.R

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

 ### =========================================================================

-### sgdf (and related) methods

+### sgedges (and related) methods

 ### -------------------------------------------------------------------------

@@ -124,7 +124,7 @@ setMethod(".hits", "GRangesList",

 ### - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

-### sgdf() extractor

+### sgedges() extractor

 ###

 ### Returns the splicing graph in a DataFrame with 1 row per edge.

 ###

@@ -133,7 +133,7 @@ setMethod(".hits", "GRangesList",

 ### given gene. Should have been obtained thru the spath() accessor.

 ### Returns a 4-col (or 5-col if 'UATXHcount' is supplied) data.frame

 ### representing the splicing graph.

-.make_sgdf0_from_spath <- function(spath, UATXHcount=NULL)

+.make_sgedges0_from_spath <- function(spath, UATXHcount=NULL)

 {

     if (!is.null(UATXHcount)) {

         if (!is.integer(UATXHcount))

@@ -142,7 +142,7 @@ setMethod(".hits", "GRangesList",

             stop("when not NULL, 'UATXHcount' must have ",

                  "the same length as 'spath'")

     }

-    sgdf0s <- lapply(seq_along(spath),

+    sgedges0s <- lapply(seq_along(spath),

                      function(i) {

                          SSids <- spath[[i]]

                          from <- c("R", SSids)

@@ -169,48 +169,48 @@ setMethod(".hits", "GRangesList",

                                     ex_or_in=ex_or_in,

                                     stringsAsFactors=FALSE)

                      })

-    nedges_per_tx <- sapply(sgdf0s, nrow)

-    sgdf0 <- do.call(rbind, sgdf0s)

+    nedges_per_tx <- sapply(sgedges0s, nrow)

+    sgedges0 <- do.call(rbind, sgedges0s)

     tx_id <- names(spath)

     if (is.null(tx_id))

         tx_id <- seq_along(spath)

     tx_id <- rep.int(factor(tx_id, levels=tx_id), nedges_per_tx)

-    sgdf0$tx_id <- tx_id

+    sgedges0$tx_id <- tx_id

     if (!is.null(UATXHcount))

-        sgdf0$UATXHcount <- rep.int(UATXHcount, nedges_per_tx)

-    sgdf0

+        sgedges0$UATXHcount <- rep.int(UATXHcount, nedges_per_tx)

+    sgedges0

 }

-### Collapse the duplicated edges in 'sgdf0' into a DataFrame.

+### Collapse the duplicated edges in 'sgedges0' into a DataFrame.

 ### We use a DataFrame instead of a data.frame because we want to store

 ### the tx_id col in a CompressedFactorList (even though this container

 ### doesn't formally exist and a CompressedIntegerList is actually what's

 ### being used).

-.make_sgdf_from_sgdf0 <- function(sgdf0, ex_hits=NULL, in_hits=NULL)

+.make_sgedges_from_sgedges0 <- function(sgedges0, ex_hits=NULL, in_hits=NULL)

 {

-    from <- sgdf0[ , "from"]

-    to <- sgdf0[ , "to"]

-    ex_or_in <- sgdf0[ , "ex_or_in"]

-    tx_id <- sgdf0[ , "tx_id"]

+    from <- sgedges0[ , "from"]

+    to <- sgedges0[ , "to"]

+    ex_or_in <- sgedges0[ , "ex_or_in"]

+    tx_id <- sgedges0[ , "tx_id"]

     edges <- paste(from, to, sep="~")

     sm <- match(edges, edges)

     if (!all(ex_or_in == ex_or_in[sm]))

         stop("invalid splicing graph")

     is_not_dup <- sm == seq_along(sm)

-    sgdf <- DataFrame(sgdf0[is_not_dup, , drop=FALSE])

-    sgdf$tx_id <- splitAsList(tx_id, sm)

-    UATXHcount <- sgdf$UATXHcount

+    sgedges <- DataFrame(sgedges0[is_not_dup, , drop=FALSE])

+    sgedges$tx_id <- splitAsList(tx_id, sm)

+    UATXHcount <- sgedges$UATXHcount

     if (!is.null(UATXHcount))

-        sgdf$UATXHcount <- sum(splitAsList(sgdf0$UATXHcount, sm))

+        sgedges$UATXHcount <- sum(splitAsList(sgedges0$UATXHcount, sm))

     if (is.null(ex_hits) && is.null(in_hits))

-        return(sgdf)

+        return(sgedges)

     hits <- relist(character(0), PartitioningByEnd(NG=length(sm)))

     if (!is.null(ex_hits)) {

         if (!is(ex_hits, "CharacterList"))

             stop("'ex_hits' must be a CharacterList object")

         ex_idx <- which(ex_or_in == "ex")

         if (length(ex_idx) != length(ex_hits))

-            stop("'ex_hits' is incompatible with 'sgdf0'")

+            stop("'ex_hits' is incompatible with 'sgedges0'")

         hits[ex_idx] <- ex_hits

     }

     if (!is.null(in_hits)) {

@@ -218,24 +218,24 @@ setMethod(".hits", "GRangesList",

             stop("'in_hits' must be a CharacterList object")

         in_idx <- which(ex_or_in == "in")

         if (length(in_idx) != length(in_hits))

-            stop("'in_hits' is incompatible with 'sgdf0'")

+            stop("'in_hits' is incompatible with 'sgedges0'")

         hits[in_idx] <- in_hits

     }

     ## TODO: This is quite inefficient. Improve it.

     for (i in which(!is_not_dup))

         hits[[sm[i]]] <- unique(hits[[sm[i]]], hits[[i]])

-    sgdf$hits <- hits[is_not_dup]

-    sgdf$nhits <- elementLengths(sgdf$hits)

-    sgdf

+    sgedges$hits <- hits[is_not_dup]

+    sgedges$nhits <- elementLengths(sgedges$hits)

+    sgedges

 }

-setGeneric("sgdf", signature="x",

+setGeneric("sgedges", signature="x",

     function(x, gene_id=NA, UATXHcount=NULL, in_by_tx=NULL,

              keep.dup.edges=FALSE)

-        standardGeneric("sgdf")

+        standardGeneric("sgedges")

 )

-setMethod("sgdf", "ANY",

+setMethod("sgedges", "ANY",

     function(x, gene_id=NA, UATXHcount=NULL, in_by_tx=NULL,

              keep.dup.edges=FALSE)

     {

@@ -243,7 +243,7 @@ setMethod("sgdf", "ANY",

         if (is.null(UATXHcount))

             UATXHcount <- UATXHcount(x, gene_id=gene_id)

         if (is.null(in_by_tx))

-            return(sgdf(spath, UATXHcount=UATXHcount,

+            return(sgedges(spath, UATXHcount=UATXHcount,

                                keep.dup.edges=keep.dup.edges))

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

             stop("'in_by_tx' must be NULL or a GRangesList object")

@@ -257,8 +257,8 @@ setMethod("sgdf", "ANY",

                  "with the shape of 'x'")

         if (!identical(keep.dup.edges, FALSE))

             stop("'keep.dup.edges' must be FALSE when 'in_by_tx' is supplied")

-        sgdf0 <- sgdf(spath, UATXHcount=UATXHcount, keep.dup.edges=TRUE)

-        ex_or_in <- sgdf0[ , "ex_or_in"]

+        sgedges0 <- sgedges(spath, UATXHcount=UATXHcount, keep.dup.edges=TRUE)

+        ex_or_in <- sgedges0[ , "ex_or_in"]

         ex_hits <- .hits(x@tx, gene_id=gene_id)

         if (is.null(ex_hits))

             stop("'x' must have a \"hits\" inner metadata column ",

@@ -268,11 +268,11 @@ setMethod("sgdf", "ANY",

         if (is.null(in_hits))

             stop("'in_by_tx' has no \"hits\" inner metadata column. May be ",

                  "you forgot to pass it thru assignSubfeatureHits()?")

-        .make_sgdf_from_sgdf0(sgdf0, ex_hits=ex_hits, in_hits=in_hits)

+        .make_sgedges_from_sgedges0(sgedges0, ex_hits=ex_hits, in_hits=in_hits)

     }

 )

-setMethod("sgdf", "IntegerList",

+setMethod("sgedges", "IntegerList",

     function(x, gene_id=NA, UATXHcount=NULL, in_by_tx=NULL,

              keep.dup.edges=FALSE)

     {

@@ -282,12 +282,12 @@ setMethod("sgdf", "IntegerList",

         if (!is.null(in_by_tx))

             stop("the 'in_by_tx' arg is not supported ",

                  "when 'x' is an IntegerList")

-        sgdf0 <- .make_sgdf0_from_spath(x, UATXHcount=UATXHcount)

-        sgdf(sgdf0, keep.dup.edges=keep.dup.edges)

+        sgedges0 <- .make_sgedges0_from_spath(x, UATXHcount=UATXHcount)

+        sgedges(sgedges0, keep.dup.edges=keep.dup.edges)

     }

 )

-setMethod("sgdf", "data.frame",

+setMethod("sgedges", "data.frame",

     function(x, gene_id=NA, UATXHcount=NULL, in_by_tx=NULL,

              keep.dup.edges=FALSE)

     {

@@ -304,7 +304,7 @@ setMethod("sgdf", "data.frame",

             stop("'keep.dup.edges' must be TRUE or FALSE")

         if (keep.dup.edges)

             return(x)  # no-op

-        .make_sgdf_from_sgdf0(x)

+        .make_sgedges_from_sgedges0(x)

     }

 )

@@ -320,7 +320,7 @@ setGeneric("uninformativeSSids", signature="x",

 setMethod("uninformativeSSids", "ANY",

     function(x, gene_id=NA)

     {

-        x <- sgdf(x, gene_id=gene_id)

+        x <- sgedges(x, gene_id=gene_id)

         uninformativeSSids(x)

     }

 )

@@ -341,30 +341,30 @@ setMethod("uninformativeSSids", "DataFrame",

 ### - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

-### sgdf2() extractor

+### sgedges2() extractor

 ###

-### Same as sgdf() except that uninformative nodes (i.e. SSids) are removed.

+### Same as sgedges() except that uninformative nodes (i.e. SSids) are removed.

 ###

-### 'sgdf' must be a DataFrame as returned by:

-###     sgdf( , keep.dup.edges=FALSE)

-.remove_uninformative_SSids <- function(sgdf)

+### 'sgedges' must be a DataFrame as returned by:

+###     sgedges( , keep.dup.edges=FALSE)

+.remove_uninformative_SSids <- function(sgedges)

 {

-    ex_or_in <- sgdf[ , "ex_or_in"]

+    ex_or_in <- sgedges[ , "ex_or_in"]

     ex_or_in_levels <- levels(ex_or_in)

     if (!identical(ex_or_in_levels, EX_OR_IN_LEVELS))

         stop("Malformed input.\n",

              "  In the input data.frame (or DataFrame) representing the ",

              "original splicing graph, the \"ex_or_in\" column has invalid ",

              "levels. Could it be that it was obtained by a previous call ",

-             "to sgdf2()?")

+             "to sgedges2()?")

     levels(ex_or_in) <- EX_OR_IN_LEVELS2

-    uninformative_SSids <- uninformativeSSids(sgdf)

+    uninformative_SSids <- uninformativeSSids(sgedges)

     if (length(uninformative_SSids) == 0L)

-        return(sgdf)

-    from <- sgdf[ , "from"]

-    to <- sgdf[ , "to"]

-    tx_id <- sgdf[ , "tx_id"]

+        return(sgedges)

+    from <- sgedges[ , "from"]

+    to <- sgedges[ , "to"]

+    tx_id <- sgedges[ , "tx_id"]

     idx1 <- match(uninformative_SSids, from)

     idx2 <- match(uninformative_SSids, to)

     ## 2 sanity checks.

@@ -375,7 +375,7 @@ setMethod("uninformativeSSids", "DataFrame",

              "uninformative splicing site id must contain the same tx_id.",

              "Could it be that the \"tx_id\" column was manually altered ",

              "before the data.frame (or DataFrame) was passed to ",

-             "sgdf2()?")

+             "sgedges2()?")

     if (!all(idx1 == idx2 + 1L))

         stop("Malformed input.\n",

              "  In the input data.frame (or DataFrame) representing the ",

@@ -383,7 +383,7 @@ setMethod("uninformativeSSids", "DataFrame",

              "id must appear in 2 consecutive rows (first in the \"to\" ",

              "column, then in the \"from\" column. Could it be that the ",

              "rows were subsetted before the data.frame (or DataFrame) ",

-             "was passed to sgdf2()?")

+             "was passed to sgedges2()?")

     from <- from[-idx1]

     to <- to[-idx2]

     ex_or_in[idx1] <- EX_OR_IN_LEVELS2[4L]

@@ -392,10 +392,10 @@ setMethod("uninformativeSSids", "DataFrame",

     DataFrame(from=from, to=to, ex_or_in=ex_or_in, tx_id=tx_id)

 }

-sgdf2 <- function(x, gene_id=NA)

+sgedges2 <- function(x, gene_id=NA)

 {

     if (!is(x, "DataFrame"))

-        x <- sgdf(x, gene_id=gene_id)

+        x <- sgedges(x, gene_id=gene_id)

     .remove_uninformative_SSids(x)

 }

@@ -9,23 +9,23 @@ setOldClass("igraph")

 ### - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

-### .make_igraph_from_sgdf()

+### .make_igraph_from_sgedges()

 ###

-### 'sgdf' must be a data.frame as returned by:

-###     sgdf( , keep.dup.edges=TRUE)

+### 'sgedges' must be a data.frame as returned by:

+###     sgedges( , keep.dup.edges=TRUE)

 ### or a DataFrame as returned by:

-###     sgdf( , keep.dup.edges=FALSE)

+###     sgedges( , keep.dup.edges=FALSE)

 ### Valid extra cols are: "label", "label.color", "lty", "color", "width"

 ### and "UATXHcount". They are used to set graphical parameters on the edges.

-.precook_igraph_edges_from_sgdf <- function(sgdf)

+.precook_igraph_edges_from_sgedges <- function(sgedges)

 {

     required_colnames <- c("from", "to", "ex_or_in", "tx_id")

     extra_colnames <- c("label", "label.color", "lty", "color",

                         "width", "UATXHcount")

     extract_colnames <- c(required_colnames,

-                          intersect(extra_colnames, colnames(sgdf)))

-    ans <- sgdf[ , extract_colnames, drop=FALSE]

+                          intersect(extra_colnames, colnames(sgedges)))

+    ans <- sgedges[ , extract_colnames, drop=FALSE]

     ex_or_in <- ans[ , "ex_or_in"]

     ex_or_in_levels <- levels(ex_or_in)

     if (!identical(ex_or_in_levels, EX_OR_IN_LEVELS2)

@@ -83,33 +83,33 @@ setOldClass("igraph")

     g

 }

-### 'sgdf0' must be a data.frame as returned by:

-###     sgdf( , keep.dup.edges=TRUE)

-.make_igraph_from_sgdf0 <- function(sgdf0, gene_id=NA,

-                                    tx_id.as.edge.label=FALSE)

+### 'sgedges0' must be a data.frame as returned by:

+###     sgedges( , keep.dup.edges=TRUE)

+.make_igraph_from_sgedges0 <- function(sgedges0, gene_id=NA,

+                                       tx_id.as.edge.label=FALSE)

 {

-    if (!is.data.frame(sgdf0))

-        stop("'sgdf0' must be a data.frame")

+    if (!is.data.frame(sgedges0))

+        stop("'sgedges0' must be a data.frame")

     if (!isTRUEorFALSE(tx_id.as.edge.label))

         stop("'tx_id.as.edge.label' must be TRUE or FALSE")

-    d <- .precook_igraph_edges_from_sgdf(sgdf0)

+    d <- .precook_igraph_edges_from_sgedges(sgedges0)

     if (tx_id.as.edge.label)

         d$label <- d$tx_id

     .make_igraph(d)

 }

-### 'sgdf' must be a DataFrame as returned by:

-###     sgdf( , keep.dup.edges=FALSE)

+### 'sgedges' must be a DataFrame as returned by:

+###     sgedges( , keep.dup.edges=FALSE)

 ### or by:

-###     sgdf2( )

-.make_igraph_from_sgdf <- function(sgdf, gene_id=NA,

-                                   tx_id.as.edge.label=FALSE)

+###     sgedges2( )

+.make_igraph_from_sgedges <- function(sgedges, gene_id=NA,

+                                      tx_id.as.edge.label=FALSE)

 {

-    if (!is(sgdf, "DataFrame"))

-        stop("'sgdf' must be a DataFrame")

+    if (!is(sgedges, "DataFrame"))

+        stop("'sgedges' must be a DataFrame")

     if (!isTRUEorFALSE(tx_id.as.edge.label))

         stop("'tx_id.as.edge.label' must be TRUE or FALSE")

-    d <- .precook_igraph_edges_from_sgdf(sgdf)

+    d <- .precook_igraph_edges_from_sgedges(sgedges)

     if (tx_id.as.edge.label)

         d$label <- sapply(d$tx_id, paste, collapse=",")

     d$tx_id <- NULL

@@ -137,9 +137,9 @@ setMethod("sgraph", "ANY",

     function(x, gene_id=NA, keep.dup.edges=FALSE,

              tx_id.as.edge.label=FALSE, as.igraph=FALSE)

     {

-        sgdf <- sgdf(x, gene_id=gene_id, keep.dup.edges=keep.dup.edges)

-        sgraph(sgdf, tx_id.as.edge.label=tx_id.as.edge.label,

-                     as.igraph=as.igraph)

+        sgedges <- sgedges(x, gene_id=gene_id, keep.dup.edges=keep.dup.edges)

+        sgraph(sgedges, tx_id.as.edge.label=tx_id.as.edge.label,

+                        as.igraph=as.igraph)

     }

 )

@@ -153,7 +153,7 @@ setMethod("sgraph", "data.frame",

         if (!identical(keep.dup.edges, FALSE))

             stop("the 'keep.dup.edges' arg is not supported ",

                  "when 'x' is a data.frame")

-        igraph <- .make_igraph_from_sgdf0(x,

+        igraph <- .make_igraph_from_sgedges0(x,

                       tx_id.as.edge.label=tx_id.as.edge.label)

         sgraph(igraph, as.igraph=as.igraph)

     }

@@ -169,7 +169,7 @@ setMethod("sgraph", "DataFrame",

         if (!identical(keep.dup.edges, FALSE))

             stop("the 'keep.dup.edges' arg is not supported ",

                  "when 'x' is a DataFrame")

-        igraph <- .make_igraph_from_sgdf(x,

+        igraph <- .make_igraph_from_sgedges(x,

                       tx_id.as.edge.label=tx_id.as.edge.label)

         sgraph(igraph, as.igraph=as.igraph)

     }

@@ -209,7 +209,7 @@ setMethod("sgraph", "igraph",

 sgraph2 <- function(x, gene_id=NA, tx_id.as.edge.label=FALSE, as.igraph=FALSE)

 {

-    sgraph(sgdf2(x, gene_id=gene_id),

+    sgraph(sgedges2(x, gene_id=gene_id),

            tx_id.as.edge.label=tx_id.as.edge.label, as.igraph=as.igraph)

 }

@@ -259,7 +259,7 @@ package.

 First we load the selected \Rclass{TranscriptDb} object.

 <<loadTxdb>>=

-library("TxDb.Mmusculus.UCSC.mm9.knownGene")

+library(TxDb.Mmusculus.UCSC.mm9.knownGene)

 txdb <- TxDb.Mmusculus.UCSC.mm9.knownGene

 @

@@ -290,46 +290,32 @@ the modified \Rclass{TranscriptDb} object.

 <<loadGenomicFeatures>>=

 library(SplicingGraphs)

 sg <- SplicingGraphs(txdb)

+sg

+@

+

+\Rcode{sg} is a \Rclass{SplicingGraphs} object. It has 1 element per

+transcript, and each transcript is assigned a name that is the id of the

+gene it belongs to. All the transcripts belonging to the same gene are

+guaranteed to be consecutive elements in \Rcode{sg}:

+

+<<>>=

+head(names(sg))

 @

 \end{document}

-The \Rfunction{spliceGraphs} function returns the

-collapsed edges with their associated disjoined exons and provides information

-about the underlying splicing mechanisms represented as splicing codes.

-Additionally the object contains mapping of edges to the

-individual bubbles and bubble parts.

-Lets have a look onto the resulting object. The provided

-\Rclass{GrangesList} contains the edge IDs as list names.

-The exons in the \Rclass{Granges} objects are not the original

-exons provided by the \Rclass{TranscriptDb} object, since the gene

-model became modified internally.

-As mentioned in the previous section during the splicing graph 

-construction overlapping exons within a gene get disjoined and

-new exons with new exon ids which differ in

-size compared to the original exons are produced.

-

-The original exon ids associated with the new exon ids

-can be found in the metadata column of the individual list elements

-and is called \Rfunction{exon\_ids}. Each element of the

-column is a \Rclass{CharacterList} containing the original exon ids.

-The new disjoined exon ids can be retrieved

-directly from  the metadata column called \Rfunction{disJ\_exon\_ids}.

+\Rcode{sg} contains information about the underlying splicing mechanisms

+represented as splicing codes. Additionally the object contains mapping

+of edges to the individual bubbles and bubble parts.

+

+Lets have a look at the resulting object.

+

 As already mentioned in the introduction there is also information

 provided about the splicing events generating the individual

 transcript variants. This information is stored in the metadata slot

 of the \Rclass{GrangesList} object and can be accessed by using the 

 \Rfunction{metadata} function.

-Below an example edge of the object returned by the \Rfunction{spliceGraphs}

-function is shown. This edge consist of multiple exons.

-

-\begin{scriptsize}

-<<exbyedges>>=

-sG

-@ 

-\end{scriptsize}

-

 In the code chunk below we access the information about the type of

 splicing events and try to quantify them later on.

deleted file mode 100644

Binary files a/inst/extdata/TSPCsgdfs/BAI1sgdf.rda and /dev/null differ

deleted file mode 100644

Binary files a/inst/extdata/TSPCsgdfs/CYB561sgdf.rda and /dev/null differ

deleted file mode 100644

Binary files a/inst/extdata/TSPCsgdfs/DAPL1sgdf.rda and /dev/null differ

deleted file mode 100644

Binary files a/inst/extdata/TSPCsgdfs/ITGB8sgdf.rda and /dev/null differ

deleted file mode 100644

Binary files a/inst/extdata/TSPCsgdfs/KIAA0319Lsgdf.rda and /dev/null differ

deleted file mode 100644

Binary files a/inst/extdata/TSPCsgdfs/LGSNsgdf.rda and /dev/null differ

deleted file mode 100644

Binary files a/inst/extdata/TSPCsgdfs/MKRN3sgdf.rda and /dev/null differ

deleted file mode 100644

Binary files a/inst/extdata/TSPCsgdfs/ST14sgdf.rda and /dev/null differ

deleted file mode 100644

Binary files a/inst/extdata/TSPCsgdfs/TREM2sgdf.rda and /dev/null differ

new file mode 100644

Binary files /dev/null and b/inst/extdata/TSPCsgraphs/BAI1sgedges.rda differ

new file mode 100644

Binary files /dev/null and b/inst/extdata/TSPCsgraphs/CYB561sgedges.rda differ

new file mode 100644

Binary files /dev/null and b/inst/extdata/TSPCsgraphs/DAPL1sgedges.rda differ

new file mode 100644

Binary files /dev/null and b/inst/extdata/TSPCsgraphs/ITGB8sgedges.rda differ

new file mode 100644

Binary files /dev/null and b/inst/extdata/TSPCsgraphs/KIAA0319Lsgedges.rda differ

new file mode 100644

Binary files /dev/null and b/inst/extdata/TSPCsgraphs/LGSNsgedges.rda differ

new file mode 100644

Binary files /dev/null and b/inst/extdata/TSPCsgraphs/MKRN3sgedges.rda differ

new file mode 100644

Binary files /dev/null and b/inst/extdata/TSPCsgraphs/ST14sgedges.rda differ

new file mode 100644

Binary files /dev/null and b/inst/extdata/TSPCsgraphs/TREM2sgedges.rda differ

@@ -20,24 +20,24 @@ source(TSPC_utils_path)

 ### Make a TSPC splicing graph data frame and save it in the current working

 ### directory.

-makeAndSaveTSPCsgdf <- function(subdir_path)

+makeAndSaveTSPCsgedges <- function(subdir_path)

 {

     subdir_basename <- basename(subdir_path)

-    objname <- paste0(subdir_basename, "sgdf")

+    objname <- paste0(subdir_basename, "sgedges")

     filename <- paste0(objname, ".rda")

-    sgdf <- makeTSPCsgdf(subdir_path)

+    sgedges <- makeTSPCsgedges(subdir_path)

     message("Saving ", objname, " to ", filename, " ... ", appendLF=FALSE)

-    assign(objname, sgdf, envir=.GlobalEnv)

+    assign(objname, sgedges, envir=.GlobalEnv)

     save(list=objname, file=filename, envir=.GlobalEnv)

     message("OK")

 }

-makeAndSaveAllTSPCsgdfs <- function(subdir_paths)

+makeAndSaveAllTSPCsgedges <- function(subdir_paths)

 {

     for (subdir_path in subdir_paths)

-        makeAndSaveTSPCsgdf(subdir_path)

+        makeAndSaveTSPCsgedges(subdir_path)

 }

 ### Run this to make and save all the TSPC splicing graph data frames:

-#makeAndSaveAllTSPCsgdfs(subdir_paths)

+#makeAndSaveAllTSPCsgedges(subdir_paths)

@@ -27,7 +27,7 @@ loadModels <- function(models_path, check.transcripts=TRUE)

 ### It's questionable whether this does the right thing on paired-end reads.

 ### I guess not...

-makeSgdfWithHits <- function(grl, sg)

+makeSgedgesWithHits <- function(grl, sg)

 {

     ov0 <- findOverlaps(grl, sg@tx, ignore.strand=TRUE)

     ovenc0 <- encodeOverlaps(grl, sg@tx, hits=ov0,

@@ -37,10 +37,10 @@ makeSgdfWithHits <- function(grl, sg)

     sg@tx <- assignSubfeatureHits(grl, sg@tx, ov1, ignore.strand=TRUE)

     in_by_tx <- psetdiff(range(sg@tx), sg@tx)

     in_by_tx <- assignSubfeatureHits(grl, in_by_tx, ov1, ignore.strand=TRUE)

-    sgdf(sg, in_by_tx=in_by_tx)

+    sgedges(sg, in_by_tx=in_by_tx)

 }

-makeTSPCsgdf <- function(subdir_path)

+makeTSPCsgedges <- function(subdir_path)

 {

     subdir_basename <- basename(subdir_path)

     filenames <- list.files(subdir_path)

@@ -56,7 +56,7 @@ makeTSPCsgdf <- function(subdir_path)

     ## Compute the splicing graph.

     sg <- SplicingGraphs(ex_by_tx)

-    ans <- sgdf(sg)

+    ans <- sgedges(sg)

     ## Find the BAM files.

     suffixes <- substr(filenames, filenames_nchar-3L, filenames_nchar)

@@ -101,9 +101,9 @@ makeTSPCsgdf <- function(subdir_path)

                                              param=param0)

             grl <- grglist(galp, order.as.in.query=TRUE)

         }

-        sgdf <- makeSgdfWithHits(grl, sg)

+        sgedges <- makeSgedgesWithHits(grl, sg)

         message("OK")

-        sgdf[ , "nhits"]

+        sgedges[ , "nhits"]

     })

     cbind(ans, DataFrame(nhits))

 }

@@ -139,9 +139,10 @@ SplicingGraphs(x, grouping=NULL, check.introns=TRUE)

     \item The \link[IRanges]{IntegerList}, \link[IRanges]{CharacterList},

           and \link[IRanges]{DataFrame} classes in the IRanges package.

-    \item \code{\link{sgdf}} and \code{\link{sgraph}} for extracting

-          a splicing graph as a data frame or as a plottable graph-like

-          object.

+    \item \code{\link{sgedges}} for extracting the edges of a splicing graph.

+

+    \item \code{\link{sgraph}} for extracting a splicing graph as a plottable

+          graph-like object.

   }

 }

similarity index 61%

rename from man/TSPCsgdfs.Rd

rename to man/TSPCsgraphs.Rd

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

-\name{TSPCsgdfs}

+\name{TSPCsgraphs}

-\alias{TSPCsgdfs}

+\alias{TSPCsgraphs}

 \alias{TSPC}

 \title{

@@ -15,36 +15,36 @@

 ## 1 splicing graph data frame per gene, except for gene MUC16.

 ## Transcripts T-4 and T-5 in gene MUC16 both have their 2nd exon included

 ## in their 3rd exon ==> splicing graph theory doesn't apply.

-filepaths <- list.files(system.file("extdata", "TSPCsgdfs",

+filepaths <- list.files(system.file("extdata", "TSPCsgraphs",

                                     package="SplicingGraphs"),

                         full.names=TRUE)

 for (filepath in filepaths)

     load(filepath)

-dim(BAI1sgdf)

+dim(BAI1sgedges)

 ## All the data frames have 1 row per edge in the graph, and the first 4

 ## cols are always "from", "to", "ex_or_in", and "tx_id". Note that there

 ## can be more than 1 transcript associated with a given edge.

-LGSNsgdf[ , 1:4]

+LGSNsgedges[ , 1:4]

 ## There is 1 additional column per sample:

-LGSNsgdf[ , 5:8]

+LGSNsgedges[ , 5:8]

-## 'KIAA0319Lsgdf' and 'TREM2sgdf' have no additional cols because there

+## 'KIAA0319Lsgedges' and 'TREM2sgedges' have no additional cols because there

 ## was no BAM files for those genes:

-dim(KIAA0319Lsgdf)

-dim(TREM2sgdf)

+dim(KIAA0319Lsgedges)

+dim(TREM2sgedges)

 ## Plot the splicing graphs:

 library(Rgraphviz)

-plot(sgraph(BAI1sgdf))

-plot(sgraph(CYB561sgdf))

-plot(sgraph(DAPL1sgdf))

-plot(sgraph(ITGB8sgdf))

-plot(sgraph(KIAA0319Lsgdf))

-plot(sgraph(LGSNsgdf))

-plot(sgraph(MKRN3sgdf))

-plot(sgraph(ST14sgdf))

-plot(sgraph(TREM2sgdf))

+plot(sgraph(BAI1sgedges))

+plot(sgraph(CYB561sgedges))

+plot(sgraph(DAPL1sgedges))

+plot(sgraph(ITGB8sgedges))

+plot(sgraph(KIAA0319Lsgedges))

+plot(sgraph(LGSNsgedges))

+plot(sgraph(MKRN3sgedges))

+plot(sgraph(ST14sgedges))

+plot(sgraph(TREM2sgedges))

 }

@@ -106,5 +106,5 @@ sg@tx <- assignSubfeatureHits(grl, sg@tx, ov1, ignore.strand=TRUE)

 in_by_tx <- psetdiff(range(sg@tx), sg@tx)

 in_by_tx <- assignSubfeatureHits(grl, in_by_tx, ov1, ignore.strand=TRUE)

-sgdf(sg, gene_id="geneA", in_by_tx=in_by_tx)

+sgedges(sg, gene_id="geneA", in_by_tx=in_by_tx)

 }

similarity index 69%

rename from man/sgdf-methods.Rd

rename to man/sgedges-methods.Rd

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

-\name{sgdf-methods}

+\name{sgedges-methods}

-\alias{sgdf-methods}

+\alias{sgedges-methods}

 \alias{spath}

 \alias{spath,SplicingGraphs-method}

@@ -8,30 +8,30 @@

 \alias{UATXHcount}

 \alias{UATXHcount,SplicingGraphs-method}

-\alias{sgdf}

-\alias{sgdf,ANY-method}

-\alias{sgdf,IntegerList-method}

-\alias{sgdf,data.frame-method}

+\alias{sgedges}

+\alias{sgedges,ANY-method}

+\alias{sgedges,IntegerList-method}

+\alias{sgedges,data.frame-method}

 \alias{uninformativeSSids}

 \alias{uninformativeSSids,ANY-method}

 \alias{uninformativeSSids,DataFrame-method}

-\alias{sgdf2}

+\alias{sgedges2}

 \title{

-  Extract a splicing graph as a data frame

+  Extract the edges of a splicing graph

 }

 \description{

-  Extract the splicing graph for a given gene from a \link{SplicingGraphs}

-  object and return it as a \link[IRanges]{DataFrame}.

+  Extract the edges of the splicing graph of a given gene from a

+  \link{SplicingGraphs} object and return it as a \link[IRanges]{DataFrame}.

 }

 \usage{

-sgdf(x, gene_id=NA, UATXHcount=NULL, in_by_tx=NULL, keep.dup.edges=FALSE)

-sgdf2(x, gene_id=NA)

+sgedges(x, gene_id=NA, UATXHcount=NULL, in_by_tx=NULL, keep.dup.edges=FALSE)

+sgedges2(x, gene_id=NA)

 ## Related utilities:

@@ -89,5 +89,5 @@ sg

 ## consecutive elements in 'sg'.

 names(sg)

-sgdf(sg, gene_id="geneA")

+sgedges(sg, gene_id="geneA")

 }

@@ -72,8 +72,7 @@ slideshow(x)

   \itemize{

     \item The \link{SplicingGraphs} class.

-    \item \code{\link{sgdf}} for extracting a splicing graph as a

-          data frame.

+    \item \code{\link{sgedges}} for extracting the edges of a splicing graph.

   }

 }