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

 Package: bsseq

-Version: 0.7.0

+Version: 0.7.1

 Title: Analyze, manage and store bisulfite sequencing data

 Description: Tools for analyzing and visualizing bisulfite sequencing data

 Author: Kasper Daniel Hansen

@@ -193,6 +193,7 @@ setMethod("combine", signature(x = "BSseq", y = "BSseq"), function(x, y, ...) {

         stop("'x' and 'y' need to be smoothed on the same scale")

     phenoData <- combine(phenoData(x), phenoData(y))

     if(identical(granges(x), granges(y))) {

+        gr <- granges(x)

         M <- cbind(getBSseq(x, "M"), getBSseq(y, "M"))

         Cov <- cbind(getBSseq(x, "Cov"), getBSseq(y, "Cov"))

         if(!hasBeenSmoothed(x) || !hasBeenSmoothed(y)) {

@@ -60,6 +60,8 @@ getMeth <- function(BSseq, regions = NULL, type = c("smooth", "raw"),

     }

     stopifnot(is(BSseq, "BSseq"))

     type <- match.arg(type)

+    if(type == "smooth" & !hasBeenSmoothed(BSseq))

+        stop("'type=smooth' requires the object to have been smoothed.")

     what <- match.arg(what)

     z <- abs(qnorm((1 - alpha)/2, mean = 0, sd = 1))

     if(is.null(regions) && type == "smooth") {

@@ -336,7 +336,7 @@ read.umtab.chr <- function(files, sampleNames = NULL,

 read.bsmoothDirRaw <- function(dir, seqnames = NULL, keepCycle = FALSE, keepFilt = FALSE,

                                header = TRUE, verbose = TRUE) {

     dir <- normalizePath(dir)

-    inpattern <- "\\.cpg\\.tsv\\.gz$"

+    inpattern <- "\\.cpg\\.tsv(|\\.gz)$"

     if(length(dir) != 1 || !file.info(dir)$isdir)

         stop("argument 'dir' needs to be a single directory")

     allChrFiles <- list.files(dir, pattern = inpattern, full.names = TRUE)

@@ -347,8 +347,12 @@ read.bsmoothDirRaw <- function(dir, seqnames = NULL, keepCycle = FALSE, keepFilt

         return(NULL)

     }

     if(header) {

-        columnHeaders <- sapply(allChrFiles, function(file) {

-            out <- readLines(con <- gzfile(file), n = 1)

+        columnHeaders <- sapply(allChrFiles, function(thisfile) {

+            if(grepl("\\.gz$", thisfile))

+                con <- gzfile(thisfile)

+            else

+                con <- file(thisfile, open = "r")

+            out <- readLines(con, n = 1)

             close(con)

             out

         })

@@ -367,10 +371,14 @@ read.bsmoothDirRaw <- function(dir, seqnames = NULL, keepCycle = FALSE, keepFilt

         what0[c("Mcy", "Ucy")] <- replicate(2, NULL)

     if(!keepFilt) 

         what0[grep("^filt", names(what0))] <- replicate(length(grep("^filt", names(what0))), NULL)

-    outList <- lapply(allChrFiles, function(file) {

+    outList <- lapply(allChrFiles, function(thisfile) {

         if(verbose)

-            cat(sprintf("Reading '%s'\n", file))

-        out <- scan(con <- gzfile(file, open = "r"), skip = header, what = what0, sep = "\t",

+            cat(sprintf("Reading '%s'\n", thisfile))

+        if(grepl("\\.gz$", thisfile))

+            con <- gzfile(thisfile)

+        else

+            con <- file(thisfile)

+        out <- scan(con, skip = header, what = what0, sep = "\t",

                     quote = "", na.strings = "NA", quiet = TRUE)

         close(con)

         out

@@ -6,10 +6,11 @@ bibentry("Article",

          person(c("Rafael", "A."), "Irizarry")),

          journal = "Genome Biology",

          year = 2012,

-	 note = "In press",  

-         textVersion = 

-         paste("KD Hansen, B Langmead, and RA Irizarry",

-               "BSmooth: from whole genome bisulfite sequencing reads to differentially methylated regions", 

-"Genome Biology, In press (2012)")

+	 volume = "13",

+	 pages = "R83",

+  	 textVersion = 

+         paste("KD Hansen, B Langmead, and RA Irizarry.",

+               "BSmooth: from whole genome bisulfite sequencing reads to differentially methylated regions.", 

+"Genome Biology, 13:R83 (2012)")

 )

@@ -2,6 +2,20 @@

 \title{bsseq news}

 \encoding{UTF-8}

+\section{Version 0.7}{

+  \itemize{

+    \item Fixed a bug in getMeth, where type="raw" resulted in an error

+    for non-smoothed data objects.

+    \item Updated CITATION and citations in the vignettes.

+    \item Now read.bsmooth supports both gzipped and non-gzipped files,

+    whereas previously it assumed the output files to be gzipped.

+    Thanks to Andreas Schoenegger for reporting this problem.

+    \item Fixed a bug in combine() that also resulted in a bug in

+    read.bsmooth when multiple input directories were specified.  Bug

+    reported by Andreas Schoenegger.

+  }

+}

+

 \section{Version 0.4}{

   \itemize{

     \item Improved combine and fixed a bug.  Also added a non-exported

@@ -33,6 +33,10 @@ read.bsmooth(dirs, sampleNames = NULL, seqnames = NULL,

   \item{verbose}{Make the function verbose.}

 }

 \note{

+  Input files can either be gzipped or not.  Gzipping the input files

+  results in much greater speed of reading (and saves space), so it is

+  recommended.

+  

   We are working on making this function faster and less memory hungry.

 }

 \value{

@@ -19,10 +19,11 @@ options(width=70)

 \newcommand{\Rpackage}[1]{{\texttt{#1}}}

 \newcommand{\software}[1]{\textsf{#1}}

 \newcommand{\R}{\software{R}}

+\newcommand{\bold}[1]{\textbf{#1}}

 \title{The bsseq user's guide}

 \author{Kasper Daniel Hansen \\ \texttt{khansen@jhsph.edu}}

-\date{Modified: June 20, 2011.  Compiled: \today}

+\date{Modified: October 13, 2012.  Compiled: \today}

 \begin{document}

 \setlength{\parskip}{1\baselineskip}

 \setlength{\parindent}{0pt}

@@ -103,6 +104,14 @@ methylation (methylation that is higher in one condition/sample than in another)

 (methylation that is lower in one condition/sample than in another), and finally differentially

 methylated position (DMP) referring to a single loci.

+\subsubsection*{Citation}

+

+If you use this package, please cite our BSmooth paper:

+

+<<citation,echo=FALSE,results=tex>>=

+print(citation("bsseq"), style = "latex")

+@ 

+

 \section{Overview}

 The package assumes that the following data has been extracted from alignments:

@@ -288,12 +297,12 @@ computed for region-level summary estimates.  Examples

 <<getMeth>>=

 getMeth(BS.chr22, regions, type = "raw")

-getMeth(BS.chr22, regions[2], type = "smooth", what = "perBase")

+getMeth(BS.chr22, regions[2], type = "raw", what = "perBase")

 @ 

 \section{Reading data}

-\subsubsection{Alignment output from the BSmooth alignment suite}

+\subsubsection*{Alignment output from the BSmooth alignment suite}

 It is straightforward to read output files (summarized evidence) from the BSmooth alignment suite,

 using \Rcode{read.bsmooth}.  This function takes as argument a number of directories, usually

@@ -301,12 +310,13 @@ corresponding to samples, with the alignment output.  Sometimes, one might want

 chromosomes, which can be accomplished by the \Rcode{seqnames} argument.  Also, the default values

 of \Rcode{qualityCutoff = 20} ensures that we do not use methylation evidence with a base quality

 strictly lower than 20 (since we may not be confident whether the read really supports methylation

-or not).

+or not).  The function \Rcode{read.bsmooth} allows for both gzipped and non-gzipped input files. It

+is faster to read gzipped files, so we recommend gzipping post-alignment.

 During the development of BSmooth we experimented with a number of different output formats.  These

 legacy formats can be read with \Rcode{read.umtab} and \Rcode{read.umtab2}.

-\subsubsection{Alignment output from other aligners}

+\subsubsection*{Alignment output from other aligners}

 We are interested in adding additional parsers to the package; if your favorite alignment software

 is not supported, feel free to get in touch.

@@ -339,7 +349,7 @@ file may be found by

 system.file("scripts", "get_BS.chr22.R", package = "bsseq")

 @ 

-\section{Analysis}

+\section*{Analysis}

 Computing smoothed methylation levels is simple.  We subset \Rcode{BS.chr22} so we only smooth 1

 sample, for run-time purpose

@@ -4,7 +4,11 @@

                   methylated regions}},

   journal =	 {Genome Biology},

   year =	 {2012},

-  note =	 {In press}

+  volume =	 {13},

+  number =	 {10},

+  pages =	 {R83},

+  doi =		 {10.1186/gb-2012-13-10-r83},

+  pubmed =	 {23034175}

 }

@@ -25,7 +25,7 @@ options(width=70)

 \title{Analyzing WGBS with the bsseq package}

 \author{Kasper Daniel Hansen\\ \texttt{khansen@jhsph.edu}}

-\date{Modified: June 26, 2011.  Compiled: \today}

+\date{Modified: October 13, 2012.  Compiled: \today}

 \begin{document}

 \maketitle

@@ -62,6 +62,11 @@ BS.cancer.ex

 pData(BS.cancer.ex)

 @ 

+If you use this package, please cite our BSmooth paper

+<<citation,echo=FALSE,results=tex>>=

+print(citation("bsseq"), style = "latex")

+@

+

 \section*{Smoothing}

 The first step of the analysis is to smooth the data