@@ -9,7 +9,7 @@ Description: GSNAP and GMAP are a pair of tools to align short-read

         methods to work with GMAP and GSNAP from within R. In addition,

         it provides methods to tally alignment results on a

         per-nucleotide basis using the bam_tally tool.

-Version: 1.13.5

+Version: 1.13.6

 Depends: R (>= 2.15.0), methods, GenomeInfoDb (>= 1.1.3),

         GenomicRanges (>= 1.17.12)

 Imports: S4Vectors, IRanges, Rsamtools (>= 1.17.8), rtracklayer (>= 1.31.2),

@@ -17,12 +17,13 @@ importFrom(Biostrings, getSeq, readDNAStringSet, DNAStringSet)

 importMethodsFrom(GenomicRanges, seqnames, strand)

 importMethodsFrom(Rsamtools, asBam)

 importClassesFrom(GenomicFeatures, TxDb)

-importFrom(GenomicFeatures, transcripts, exons)

+importFrom(GenomicFeatures, transcripts, exons, exonsBy)

 importClassesFrom(rtracklayer, RTLFile, FastaFile, RTLFileList)

-importFrom(rtracklayer, "referenceSequence<-", import, export, FastaFile)

+importFrom(rtracklayer, "referenceSequence<-", import, export, FastaFile,

+           FileForFormat)

 importMethodsFrom(rtracklayer, export)

 importFrom(VariantAnnotation, readVcf, ScanVcfParam, fixed, VRanges, ref, alt,

-           "ref<-", "alt<-", altDepth, refDepth)

+           "ref<-", "alt<-", altDepth, refDepth, "vcfWhich<-")

 importClassesFrom(VariantAnnotation, "VCF", "VRanges")

 importFrom(BSgenome, getSeq, providerVersion)

 importFrom(GenomicAlignments, readGAlignments)

@@ -73,7 +73,7 @@ setMethod("normArgCdsIIT", "GmapGenome", function(exon_iit, genome, BPPARAM) {

         stop("No map matching the pattern 'genes.iit' found for this GmapGenome")

     if(length(exon_iit) > 1)

         stop("Multipe map matching the pattern 'genes.iit' found for this GmapGenome")

-    normArgsCdsIIT(exon_iit)

+    normArgCdsIIT(exon_iit)

 })

 .makeCdsIIT <- function(exons,

@@ -203,7 +203,7 @@ setAs("GsnapParam", "list", function(from) {

           to

       })

-as.list.GmapAlignerParam <- function(x) as(x, "list")

+as.list.GmapAlignerParam <- function(x, ...) as(x, "list")

 setAs("ANY", "characterORNULL", function(from) {

   if (is.null(from))

@@ -38,7 +38,7 @@ GeneGenome <- function(gene) {

 exonsToGene <- range

 getExons <- function(txdb, orgdb, gene) {

-  eg <- select(orgdb, gene, "ENTREZID", "SYMBOL")$ENTREZID

+  eg <- AnnotationDbi::select(orgdb, gene, "ENTREZID", "SYMBOL")$ENTREZID

   exons(txdb, vals = list(gene_id=eg))

 }

@@ -21,7 +21,7 @@ setMethod("get_genome", "GmapGenome",

               snpsdir <- directory(snps)

             }

             tmpfile <- file.path(tempdir(), "get_genome.fasta")

-            .get_genome(path(directory(db)), genome(db), snpsdir = snpsdir,

+            .get_genome(path(directory(x)), genome(x), snpsdir = snpsdir,

                         usesnps = usesnps, snpformat = "2", ...,

                         .range = range, .redirect = tmpfile)

             readDNAStringSet(tmpfile)

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

 ### High-level wrapper

 ###

-setGeneric("iit_store", function(x, dest, BPPARAM=MulticoreParam(1), ...) standardGeneric("iit_store"))

+setGeneric("iit_store", function(x, dest, BPPARAM=MulticoreParam(1), ...)

+    standardGeneric("iit_store"))

 gmapRange <- function(x) {

   pos <- strand(x) == "+"

@@ -28,7 +29,8 @@ gmapRange <- function(x) {

     strtpos = if(pos) min(strts) else max(ends)

     endpos = if(!pos) min(strts) else max(ends)

-    hdr = paste0(">", name, " ", runValue(seqnames(grange))[1], ":", strtpos, "..", endpos )

+    hdr = paste0(">", name, " ", runValue(seqnames(grange))[1], ":", strtpos,

+        "..", endpos)

     datline = paste(name, name, "NA")

     rngst = if(pos) strts[o] else ends[o]

@@ -69,7 +71,7 @@ setMethod("iit_store", c("character"),

                    label = if (gff) "ID" else NULL)

           {

             .iit_store(gff = gff, label = label, sort = "none",

-                       output = dest, inputfile = x)

+                       output = dest, .inputfile = x)

           })

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

@@ -1,48 +1 @@

-.test <- function(dir, pattern = "^test_.*\\.R$")

-{

-    .failure_details <- function(result) {

-        res <- result[[1L]]

-        if (res$nFail > 0 || res$nErr > 0) {

-            Filter(function(x) length(x) > 0,

-                   lapply(res$sourceFileResults,

-                          function(fileRes) {

-                              names(Filter(function(x) x$kind != "success",

-                                           fileRes))

-                          }))

-        } else list()

-    }

-

-    if (missing(dir)) {

-        dir <- system.file("unitTests", package="gmapR")

-        if (!length(dir)) {

-            dir <- system.file("UnitTests", package="gmapR")

-            if (!length(dir))

-                stop("unable to find unit tests, no 'unitTests' dir")

-        }

-    }

-    require("RUnit", quietly=TRUE) || stop("RUnit package not found")

-    RUnit_opts <- getOption("RUnit", list())

-    RUnit_opts$verbose <- 0L

-    RUnit_opts$silent <- TRUE

-    RUnit_opts$verbose_fail_msg <- TRUE

-    options(RUnit = RUnit_opts)

-    suite <- defineTestSuite(name="gmapR RUnit Tests", dirs=dir,

-                             testFileRegexp=pattern,

-                             rngKind="default",

-                             rngNormalKind="default")

-    result <- runTestSuite(suite)

-    cat("\n\n")

-    printTextProtocol(result, showDetails=FALSE)

-    if (length(details <- .failure_details(result)) >0) {

-        cat("\nTest files with failing tests\n")

-        for (i in seq_along(details)) {

-            cat("\n  ", basename(names(details)[[i]]), "\n")

-            for (j in seq_along(details[[i]])) {

-                cat("    ", details[[i]][[j]], "\n")

-            }

-        }

-        cat("\n\n")

-        stop("unit tests failed for package gmapR")

-    }

-    result

-}

+.test <- function() BiocGenerics:::testPackage("gmapR")

@@ -10,7 +10,9 @@ test_BamTallyParam <- function() {

                primary_only = FALSE, ignore_duplicates = FALSE,

                min_depth = 0L, variant_strand = 0L,

                ignore_query_Ns = FALSE,

-               indels = FALSE, include_soft_clips = 0L)

+               indels = FALSE, include_soft_clips = 0L,

+               xs = FALSE, read_pos = FALSE, min_base_quality = 0L,

+               noncovered = FALSE, nm = FALSE)

   which <- TP53Which()

   wicked.which <- renameSeqlevels(which, c(TP53 = "chr1"))

@@ -49,6 +49,7 @@ test_GmapGenome_accessors <- function() {

   if (file.exists(genomeDir)) unlink(genomeDir, recursive=TRUE)

   dir.create(genomeDir, recursive=TRUE)

   on.exit(unlink(genomeDir, recursive=TRUE))

+  genomeDir <- normalizePath(genomeDir)

   gmapGenome <- GmapGenome(genome=dna, directory=genomeDir,

                            name=genomeName, create=FALSE, k=12)

   checkIdentical(path(gmapGenome), file.path(genomeDir, genomeName))

@@ -10,16 +10,5 @@ test_GmapGenomeDirectory <- function() {

   ##test methods

   checkIdentical(genome(ggd), character(0))

-

-  ##for compatibility with Macs

-  .unSymLink <- function(d) {

-    pieces <- unlist(strsplit(d, "/"))

-    unSymed <- Sys.readlink(file.path(pieces[1], pieces[2]))

-    if (unSymed != "") {

-      pieces[2] <- sub("^/", "", unSymed)

-      d <- paste(pieces, collapse="/")

-    }

-    return(d)

-  }

-  checkIdentical(.unSymLink(path(ggd)), .unSymLink(genomeDir))

+  checkIdentical(path(ggd), normalizePath(genomeDir))

 }

@@ -22,7 +22,9 @@

                 min_depth = 0L, variant_strand = 0L,

                 ignore_query_Ns = FALSE,

                 indels = FALSE, include_soft_clips = 0L,

-                exon_iit = NULL, IIT_BPPARAM = NULL)

+                exon_iit = NULL, IIT_BPPARAM = NULL,

+                xs = FALSE, read_pos = FALSE,

+                min_base_quality = 0L, noncovered = FALSE, nm = FALSE)

 }

 \arguments{

   \item{genome}{A \code{GmapGenome} object, or something coercible to one.}

@@ -74,6 +76,20 @@

     generating the iit file from an R object. Ignored if \code{exon_iit}

     is a character vector or \code{NULL}

   }

+  \item{xs}{Whether to tabulate reads by XS tag, the aligner's best

+    guess about the strand of transcription.

+  }

+  \item{read_pos}{Whether to tabulate by read position.

+  }

+  \item{min_base_quality}{Minimum base quality cutoff. Calls of lower

+    quality are not counted, except in the total raw depth.

+  }

+  \item{noncovered}{

+    Whether to report zero tallies, where there is no coverage.

+  }

+  \item{nm}{

+    Whether to tally by NM tag, the number of mismatches for a read.

+  }

 }

 \seealso{

   \code{\link{bam_tally}}

@@ -19,8 +19,9 @@

 \usage{

 \S4method{bam_tally}{BamFile}(x, param, ...)

 \S4method{bam_tally}{character}(x, param, ...)

-variantSummary(x, read_pos_breaks = NULL, high_base_quality = 0L,

-               keep_ref_rows = FALSE, read_length = NA_integer_)

+variantSummary(x, read_pos_breaks = NULL,

+               keep_ref_rows = FALSE, read_length = NA_integer_,

+               high_nm_score = NA_integer_)

 }

 \arguments{

@@ -30,8 +31,6 @@ variantSummary(x, read_pos_breaks = NULL, high_base_quality = 0L,

   \item{read_pos_breaks}{The breaks, like those passed to \code{\link{cut}}

     for aggregating the per-read position counts. If \code{NULL}, no per-cycle

     counts are returned.}

-  \item{high_base_quality}{The minimum mapping quality for a

-    read to be counted as high quality.}

   \item{keep_ref_rows}{Whether to keep the rows describing only the

     reference calls, i.e., where ref and alt are the same. These are

     useful when one needs the reference counts even when there are no

@@ -39,6 +38,7 @@ variantSummary(x, read_pos_breaks = NULL, high_base_quality = 0L,

   \item{read_length}{The expected read length. If the read length is NA,

     the MDFNE (median distance from nearest end) statistic will NOT be

     calculated.}

+  \item{high_nm_score}{The value at which an NM value is considered high.}

   \item{...}{Arguments that override settings in \code{param}.}

 }

@@ -55,15 +55,8 @@ variantSummary(x, read_pos_breaks = NULL, high_base_quality = 0L,

   columns are also present:

   \item{n.read.pos}{The number of unique read positions for the alt allele.}

   \item{n.read.pos.ref}{The number of unique read positions for the ref allele.}

-  \item{raw.count}{The number of reads with the alternate allele,

-    \code{NA} for the reference allele row.}

-  \item{raw.count.ref}{The number of reads with the reference allele.}

   \item{raw.count.total}{The total number of reads at that position,

     including reference and all alternates.}

-  \item{mean.quality}{The mean base quality for the alt allele,

-    truncated at \code{high_base_quality}.}

-  \item{mean.quality.ref}{The mean base quality for the ref allele,

-    truncated at \code{high_base_quality}.}

   \item{count.plus}{The number of positive strand reads for the alternate

     allele, \code{NA} for the reference allele row.}

   \item{count.plus.ref}{The number of positive strand reads for the reference

@@ -72,12 +65,28 @@ variantSummary(x, read_pos_breaks = NULL, high_base_quality = 0L,

     allele, \code{NA} for the reference allele row.}

   \item{count.minus.ref}{The number of negative strand reads for the reference

     allele.}

+  \item{count.del.plus}{The plus strand deletion count over the

+    position.}

+  \item{count.del.minus}{The minus strand deletion count over the

+    position.}

   \item{read.pos.mean}{Mean read position for the alt allele.}

   \item{read.pos.mean.ref}{Mean read position for the ref allele.}

   \item{read.pos.var}{Variance in the read positions for the alt allele.}

   \item{read.pos.var.ref}{Variance in the read positions for the ref allele.}

   \item{mdfne}{Median distance from nearest end for the alt allele.}

   \item{mdfne.ref}{Median distance from nearest end for the ref allele.}

+  \item{count.high.nm}{The number of alt reads with an NM value at or above the

+    \code{high_nm_score} cutoff.}

+  \item{count.high.nm.ref}{The number of ref reads with an NM value at

+    or above the \code{high_nm_score} cutoff.}

+  

+  If codon counting was enabled, there will be a column giving the codon

+  strand: \code{codon.strand}.

+  

+  If the \code{xs} parameter was \code{TRUE}, there will be four

+  additional columns giving the counts by aligner-determined

+  strand: \code{count.xs.plus}, \code{count.xs.plus.ref},

+  \code{count.xs.minus}, and \code{count.xs.minus.ref}.

   An additional column is present for each bin formed by

   the \code{read_pos_breaks} parameter, with the read count for that bin.