@@ -9,6 +9,6 @@ Description: not yet

 Depends: R (>= 3.1.0), GenomicRanges, ggplot2, reshape2, mclust

 Imports: IRanges, Rsamtools, Biostrings, GenomicAlignments, grid, preseqR, ggdendro, foreach, doParallel

 Suggests:

-License: GPL

+License: GPLv3

 LazyLoad: yes

-Packaged: 2014-02-13 13:29:00 CET+1; Taudt

+Packaged: 2015-09-19 13:29:00 CET+1; Taudt

@@ -1,21 +1,15 @@

-The MIT License (MIT)

+aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+Copyright (C) 2015  Aaron Taudt

-Copyright (c) 2014, Aaron Taudt and David Porubsky

+This program is free software: you can redistribute it and/or modify

+it under the terms of the GNU General Public License as published by

+the Free Software Foundation, either version 3 of the License, or

+(at your option) any later version.

-Permission is hereby granted, free of charge, to any person obtaining a copy

-of this software and associated documentation files (the "Software"), to deal

-in the Software without restriction, including without limitation the rights

-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell

-copies of the Software, and to permit persons to whom the Software is

-furnished to do so, subject to the following conditions:

+This program is distributed in the hope that it will be useful,

+but WITHOUT ANY WARRANTY; without even the implied warranty of

+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+GNU General Public License for more details.

-The above copyright notice and this permission notice shall be included in all

-copies or substantial portions of the Software.

-

-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR

-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,

-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE

-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER

-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,

-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE

-SOFTWARE.

+You should have received a copy of the GNU General Public License

+along with this program.  If not, see <http://www.gnu.org/licenses/>.

@@ -4,6 +4,7 @@ S3method(plot,GRanges)

 S3method(plot,aneuBiHMM)

 S3method(plot,aneuHMM)

 S3method(plot,character)

+export(Aneufinder)

 export(bam2binned)

 export(bed2GRanges)

 export(bed2binned)

@@ -11,7 +12,6 @@ export(bedGraph2binned)

 export(clusterByQuality)

 export(correctGC)

 export(correctMappability)

-export(easyAneufinder)

 export(exportCNVs)

 export(exportReadCounts)

 export(filterSegments)

@@ -24,6 +24,7 @@ export(heatmapGenomewide)

 export(karyotypeMeasures)

 export(loadBinnedFromFiles)

 export(loadHmmsFromFiles)

+export(makeConfig)

 export(readConfig)

 export(stateColors)

 import(GenomicRanges)

old mode 100755

new mode 100644

similarity index 81%

rename from R/easyAneufinder.R

rename to R/Aneufinder.R

@@ -1,15 +1,32 @@

+# aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+# Copyright (C) 2015  Aaron Taudt

+# 

+# This program is free software: you can redistribute it and/or modify

+# it under the terms of the GNU General Public License as published by

+# the Free Software Foundation, either version 3 of the License, or

+# (at your option) any later version.

+# 

+# This program is distributed in the hope that it will be useful,

+# but WITHOUT ANY WARRANTY; without even the implied warranty of

+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+# GNU General Public License for more details.

+# 

+# You should have received a copy of the GNU General Public License

+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

+

+

 #' Wrapper function for the aneufinder package

 #'

 #' This function is an easy-to-use wrapper to \link[aneufinder:binning]{bin the data}, \link[aneufinder:findCNVs]{find copy-number-variations}, \link[aneufinder:findSCEs]{find sister-chromatid-exchange} events and plot the results.

 #'

-#' @param inputfolder Folder with BAM files.

-#' @param configfile A file with parameters that are used by the various functions.

-#' @param outputfolder Folder to put the results. If it does not exist it will be created.

+#' @param inputfolder Folder with either BAM or BED files.

+#' @param outputfolder Folder to output the results. If it does not exist it will be created.

+#' @param config A file with parameters that are used by the various subfunctions. Alternatively a list with parameters created by \code{\link{makeConfig}}.

 #' @author Aaron Taudt

 #' @import foreach

 #' @import doParallel

 #' @export

-easyAneufinder <- function(inputfolder, configfile, outputfolder) {

+Aneufinder <- function(inputfolder, outputfolder, config=makeConfig()) {

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

 ### Helper functions ###

@@ -21,16 +38,26 @@ as.object <- function(x) {

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

 ### General variables ###

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

-## Read config file ##

-tC <- tryCatch({

-	config <- readConfig(configfile)

-}, error = function(err) {

-	message("Error: Could not read configuration file ",configfile)

-})

+if (is.character(config)) {

+	## Read config file ##

+	errstring <- tryCatch({

+		conf <- readConfig(config)

+		errstring <- ''

+	}, error = function(err) {

+		errstring <- paste0("Could not read configuration file ",config)

+	})

+	if (errstring!='') {

+		stop(errstring)

+	}

+	## Make a copy of the conf file ##

+	temp <- file.copy(from=config, to=file.path(outputfolder, basename(config)), overwrite=TRUE)

+} else {

+	conf <- config

+}

 ## Helpers

-binsizes <- config$Binning$binsizes

-reads.per.bins <- config$Binning$reads.per.bin

+binsizes <- conf$Binning$binsizes

+reads.per.bins <- conf$Binning$reads.per.bin

 patterns <- c(paste0('reads.per.bin_',reads.per.bins,'_'), paste0('binsize_',format(binsizes, scientific=F, trim=T),'_'))

 patterns <- setdiff(patterns, c('reads.per.bin__','binsize__'))

@@ -43,7 +70,7 @@ SCEpath <- file.path(outputfolder,'SCE_results')

 SCEplotpath <- file.path(outputfolder,'SCE_plots')

 SCEbrowserpath <- file.path(outputfolder,'SCE_browser_files')

 ## Delete old directory if desired ##

-if (config$General$reuse.existing.files==FALSE) {

+if (conf$General$reuse.existing.files==FALSE) {

 	if (file.exists(outputfolder)) {

 		message("Deleting old directory ",outputfolder)

 		unlink(outputfolder, recursive=T)

@@ -52,12 +79,10 @@ if (config$General$reuse.existing.files==FALSE) {

 if (!file.exists(outputfolder)) {

 	dir.create(outputfolder)

 }

-## Make a copy of the config file ##

-temp <- file.copy(configfile, file.path(outputfolder, basename(configfile)))

 ## Parallelization ##

-message("Using ",config$General$numCPU," CPUs")

-cl <- makeCluster(config$General$numCPU)

+message("Using ",conf$General$numCPU," CPUs")

+cl <- makeCluster(conf$General$numCPU)

 doParallel::registerDoParallel(cl)

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

@@ -66,14 +91,14 @@ doParallel::registerDoParallel(cl)

 message("Binning the data ...", appendLF=F); ptm <- proc.time()

 if (!file.exists(binpath.uncorrected)) { dir.create(binpath.uncorrected) }

 ## Prepare parameter list ##

-paramlist <- config$Binning

+paramlist <- conf$Binning

 paramlist$outputfolder <- binpath.uncorrected

 paramlist$save.as.RData <- TRUE

 paramlist$format <- NULL

 paramlist$GC.correction.bsgenome.string <- NULL

-files <- list.files(inputfolder, full=T, recursive=T, pattern='.bam$')

-temp <- foreach (file = files, .packages=c('aneufinder',config$Binning$GC.correction.bsgenome.string)) %dopar% {

+files <- list.files(inputfolder, full=T, recursive=T, pattern=paste0('.',conf$Binning$format,'$'))

+temp <- foreach (file = files, .packages=c('aneufinder',conf$Binning$GC.correction.bsgenome.string)) %dopar% {

 	message(file)

 	## Check for existing files ##

 	existing.binfiles <- grep(basename(file), list.files(binpath.uncorrected), value=T)

@@ -85,11 +110,11 @@ temp <- foreach (file = files, .packages=c('aneufinder',config$Binning$GC.correc

 		# Make paramter list

 		paramlist$binsizes <- binsizes.todo

 		paramlist$reads.per.bin <- rpbin.todo

-		if (config$Binning$format=='bam') {

+		if (conf$Binning$format=='bam') {

 			paramlist$bamfile <- file

 			do.call('bam2binned', paramlist)

 		} else {

-			warning("Unknown file format ",config$Binning$format)

+			warning("Unknown file format ",conf$Binning$format)

 		}

 	}

 }

@@ -98,16 +123,16 @@ time <- proc.time() - ptm; message(" ",round(time[3],2),"s")

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

 ### Correction ###

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

-if (!is.null(config$Correction$method)) {

+if (!is.null(conf$Correction$method)) {

-	message(paste0(config$Correction$method," correction ..."), appendLF=F); ptm <- proc.time()

-	if (config$Correction$method=='GC') {

+	message(paste0(conf$Correction$method," correction ..."), appendLF=F); ptm <- proc.time()

+	if (conf$Correction$method=='GC') {

 		binpath.corrected <- file.path(outputfolder,'binned_GC-corrected')

 		if (!file.exists(binpath.corrected)) { dir.create(binpath.corrected) }

 		## Load BSgenome

-		suppressPackageStartupMessages(library(config$Correction$GC.bsgenome, character.only=T))

-		config$Correction$GC.bsgenome.string <- config$Correction$GC.bsgenome

-		config$Correction$GC.bsgenome <- as.object(config$Correction$GC.bsgenome.string) # replacing string by object

+		suppressPackageStartupMessages(library(conf$Correction$GC.bsgenome, character.only=T))

+		conf$Correction$GC.bsgenome.string <- conf$Correction$GC.bsgenome

+		conf$Correction$GC.bsgenome <- as.object(conf$Correction$GC.bsgenome.string) # replacing string by object

 		## Go through patterns

 		temp <- foreach (pattern = patterns, .packages=c('aneufinder')) %dopar% {

@@ -119,9 +144,9 @@ if (!is.null(config$Correction$method)) {

 			if (length(binfiles.todo)>0) {

 				binfiles.todo <- paste0(binpath.uncorrected,.Platform$file.sep,binfiles.todo)

 				if (grepl('binsize',pattern)) {

-					binned.data.list <- suppressMessages(correctGC(binfiles.todo,config$Correction$GC.bsgenome, same.GC.content=TRUE))

+					binned.data.list <- suppressMessages(correctGC(binfiles.todo,conf$Correction$GC.bsgenome, same.GC.content=TRUE))

 				} else {

-					binned.data.list <- suppressMessages(correctGC(binfiles.todo,config$Correction$GC.bsgenome))

+					binned.data.list <- suppressMessages(correctGC(binfiles.todo,conf$Correction$GC.bsgenome))

 				}

 				for (i1 in 1:length(binned.data.list)) {

 					binned.data <- binned.data.list[[i1]]

@@ -130,9 +155,9 @@ if (!is.null(config$Correction$method)) {

 				}

 			}

 		}

+		binpath <- binpath.corrected

 	}

 	time <- proc.time() - ptm; message(" ",round(time[3],2),"s")

-	binpath <- binpath.corrected

 } else {

 	binpath <- binpath.uncorrected

@@ -141,12 +166,12 @@ if (!is.null(config$Correction$method)) {

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

 ### findCNVs ###

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

-if (config$CNV$findCNVs==TRUE) {

+if (conf$CNV$findCNVs==TRUE) {

 	message("Finding CNVs ...", appendLF=F); ptm <- proc.time()

 	if (!file.exists(CNVpath)) { dir.create(CNVpath) }

 	## Prepare parameter list ##

-	paramlist <- config$CNV

+	paramlist <- conf$CNV

 	paramlist$findCNVs <- NULL

 	files <- list.files(binpath, full=T, recursive=T, pattern='.RData$')

@@ -155,7 +180,6 @@ if (config$CNV$findCNVs==TRUE) {

 		if (!file.exists(savename)) {

 			# Make parameter list

 			paramlist$binned.data <- file

-			paramlist$ID <- basename(file)

 			model <- do.call('findCNVs', paramlist)

 			save(model, file=savename)

 		}

@@ -197,7 +221,7 @@ if (config$CNV$findCNVs==TRUE) {

 		ifiles <- grep(pattern, ifiles, value=T)

 		savename=file.path(CNVplotpath,paste0('genomeHeatmap_',sub('_$','',pattern),'.pdf'))

 		if (!file.exists(savename)) {

-			suppressMessages(heatmapGenomewide(ifiles, file=savename, plot.SCE=F, cluster=config$Plotting$cluster))

+			suppressMessages(heatmapGenomewide(ifiles, file=savename, plot.SCE=F, cluster=conf$Plotting$cluster))

 		}

 	}

 	temp <- foreach (pattern = patterns, .packages=c('aneufinder')) %dopar% {

@@ -206,7 +230,7 @@ if (config$CNV$findCNVs==TRUE) {

 		savename=file.path(CNVplotpath,paste0('aneuploidyHeatmap_',sub('_$','',pattern),'.pdf'))

 		if (!file.exists(savename)) {

 			pdf(savename, width=30, height=0.3*length(ifiles))

-			ggplt <- suppressMessages(heatmapAneuploidies(ifiles, cluster=config$Plotting$cluster))

+			ggplt <- suppressMessages(heatmapAneuploidies(ifiles, cluster=conf$Plotting$cluster))

 			print(ggplt)

 			d <- dev.off()

 		}

@@ -258,7 +282,7 @@ if (config$CNV$findCNVs==TRUE) {

 		if (!file.exists(paste0(savename,'.bed.gz'))) {

 			ifiles <- list.files(CNVpath, pattern='RData$', full=T)

 			ifiles <- grep(pattern, ifiles, value=T)

-			exportCNVs(ifiles, filename=savename, cluster=config$Plotting$cluster, export.CNV=TRUE, export.SCE=FALSE)

+			exportCNVs(ifiles, filename=savename, cluster=conf$Plotting$cluster, export.CNV=TRUE, export.SCE=FALSE)

 		}

 	}

 	time <- proc.time() - ptm; message(" ",round(time[3],2),"s")

@@ -267,12 +291,12 @@ if (config$CNV$findCNVs==TRUE) {

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

 ### findSCEs ###

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

-if (config$SCE$findSCEs==TRUE) {

+if (conf$SCE$findSCEs==TRUE) {

 	message("Finding SCEs ...", appendLF=F); ptm <- proc.time()

 	if (!file.exists(SCEpath)) { dir.create(SCEpath) }

 	## Prepare parameter list ##

-	paramlist <- config$SCE

+	paramlist <- conf$SCE

 	paramlist$findSCEs <- NULL

 	files <- list.files(binpath, full=T, recursive=T, pattern='.RData$')

@@ -281,7 +305,6 @@ if (config$SCE$findSCEs==TRUE) {

 		if (!file.exists(savename)) {

 			# Make parameter list

 			paramlist$binned.data <- file

-			paramlist$ID <- basename(file)

 			model <- do.call('findSCEs', paramlist)

 			save(model, file=savename)

 		}

@@ -323,7 +346,7 @@ if (config$SCE$findSCEs==TRUE) {

 		ifiles <- grep(pattern, ifiles, value=T)

 		savename=file.path(SCEplotpath,paste0('genomeHeatmap_',sub('_$','',pattern),'.pdf'))

 		if (!file.exists(savename)) {

-			suppressMessages(heatmapGenomewide(ifiles, file=savename, plot.SCE=T, cluster=config$Plotting$cluster))

+			suppressMessages(heatmapGenomewide(ifiles, file=savename, plot.SCE=T, cluster=conf$Plotting$cluster))

 		}

 	}

 	temp <- foreach (pattern = patterns, .packages=c('aneufinder')) %dopar% {

@@ -332,7 +355,7 @@ if (config$SCE$findSCEs==TRUE) {

 		savename=file.path(SCEplotpath,paste0('aneuploidyHeatmap_',sub('_$','',pattern),'.pdf'))

 		if (!file.exists(savename)) {

 			pdf(savename, width=30, height=0.3*length(ifiles))

-			ggplt <- suppressMessages(heatmapAneuploidies(ifiles, cluster=config$Plotting$cluster))

+			ggplt <- suppressMessages(heatmapAneuploidies(ifiles, cluster=conf$Plotting$cluster))

 			print(ggplt)

 			d <- dev.off()

 		}

@@ -384,7 +407,7 @@ if (config$SCE$findSCEs==TRUE) {

 		if (!file.exists(paste0(savename,'.bed.gz'))) {

 			ifiles <- list.files(SCEpath, pattern='RData$', full=T)

 			ifiles <- grep(pattern, ifiles, value=T)

-			exportCNVs(ifiles, filename=savename, cluster=config$Plotting$cluster, export.CNV=TRUE, export.SCE=TRUE)

+			exportCNVs(ifiles, filename=savename, cluster=conf$Plotting$cluster, export.CNV=TRUE, export.SCE=TRUE)

 		}

 	}

 	time <- proc.time() - ptm; message(" ",round(time[3],2),"s")

@@ -1,3 +1,20 @@

+# aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+# Copyright (C) 2015  Aaron Taudt

+# 

+# This program is free software: you can redistribute it and/or modify

+# it under the terms of the GNU General Public License as published by

+# the Free Software Foundation, either version 3 of the License, or

+# (at your option) any later version.

+# 

+# This program is distributed in the hope that it will be useful,

+# but WITHOUT ANY WARRANTY; without even the implied warranty of

+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+# GNU General Public License for more details.

+# 

+# You should have received a copy of the GNU General Public License

+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

+

+

 bait.loadSCE <- function(filename) {

   data <- read.table(filename, header=FALSE)

@@ -1,3 +1,20 @@

+# aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+# Copyright (C) 2015  Aaron Taudt

+# 

+# This program is free software: you can redistribute it and/or modify

+# it under the terms of the GNU General Public License as published by

+# the Free Software Foundation, either version 3 of the License, or

+# (at your option) any later version.

+# 

+# This program is distributed in the hope that it will be useful,

+# but WITHOUT ANY WARRANTY; without even the implied warranty of

+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+# GNU General Public License for more details.

+# 

+# You should have received a copy of the GNU General Public License

+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

+

+

 #' Analysis of Aneuploidies and Copy Number Variation in Single-Cell-Sequencing Data

 #'

 #' TODO

@@ -1,3 +1,20 @@

+# aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+# Copyright (C) 2015  Aaron Taudt

+# 

+# This program is free software: you can redistribute it and/or modify

+# it under the terms of the GNU General Public License as published by

+# the Free Software Foundation, either version 3 of the License, or

+# (at your option) any later version.

+# 

+# This program is distributed in the hope that it will be useful,

+# but WITHOUT ANY WARRANTY; without even the implied warranty of

+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+# GNU General Public License for more details.

+# 

+# You should have received a copy of the GNU General Public License

+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

+

+

 #' Convert aligned reads from various file formats into read counts in equidistant bins

 #'

 #' Convert aligned reads in .bam or .bed format into read counts in equidistant windows. Convert signal values in .bedGraph format to signal counts in equidistant windows.

@@ -19,13 +36,13 @@ NULL

 #' @param bamfile A file in BAM format.

 #' @param bamindex BAM index file. Can be specified without the .bai ending. If the index file does not exist it will be created and a warning is issued.

 #' @export

-bam2binned <- function(bamfile, bamindex=bamfile, pairedEndReads=FALSE, outputfolder="binned_data", binsizes=NULL, reads.per.bin=NULL, numbins=NULL, chromosomes=NULL, save.as.RData=FALSE, calc.complexity=TRUE, min.mapq=10, remove.duplicate.reads=TRUE, outputfolder.fragments=NULL, return.fragments=FALSE) {

+bam2binned <- function(bamfile, bamindex=bamfile, ID=basename(bamfile), pairedEndReads=FALSE, outputfolder="binned_data", binsizes=NULL, reads.per.bin=NULL, numbins=NULL, chromosomes=NULL, save.as.RData=FALSE, calc.complexity=TRUE, min.mapq=10, remove.duplicate.reads=TRUE, outputfolder.fragments=NULL, return.fragments=FALSE) {

 	call <- match.call()

 	underline <- paste0(rep('=',sum(nchar(call[[1]]))+3), collapse='')

 	message("\n",call[[1]],"():")

 	message(underline)

 	ptm <- proc.time()

-	binned.data <- align2binned(bamfile, format="bam", bamindex=bamindex, pairedEndReads=pairedEndReads, outputfolder=outputfolder, binsizes=binsizes, reads.per.bin=reads.per.bin, numbins=numbins, chromosomes=chromosomes, save.as.RData=save.as.RData, calc.complexity=calc.complexity, min.mapq=min.mapq, remove.duplicate.reads=remove.duplicate.reads, call=call, outputfolder.fragments=outputfolder.fragments, return.fragments=return.fragments)

+	binned.data <- align2binned(bamfile, format="bam", ID=ID, bamindex=bamindex, pairedEndReads=pairedEndReads, outputfolder=outputfolder, binsizes=binsizes, reads.per.bin=reads.per.bin, numbins=numbins, chromosomes=chromosomes, save.as.RData=save.as.RData, calc.complexity=calc.complexity, min.mapq=min.mapq, remove.duplicate.reads=remove.duplicate.reads, call=call, outputfolder.fragments=outputfolder.fragments, return.fragments=return.fragments)

 	time <- proc.time() - ptm

 	message("Time spent in ", call[[1]],"(): ",round(time[3],2),"s")

 	return(binned.data)

@@ -35,13 +52,13 @@ bam2binned <- function(bamfile, bamindex=bamfile, pairedEndReads=FALSE, outputfo

 #' @inheritParams align2binned

 #' @param bedfile A file in BED format.

 #' @export

-bed2binned <- function(bedfile, chrom.length.file, outputfolder="binned_data", binsizes=NULL, reads.per.bin=NULL, numbins=NULL, chromosomes=NULL, save.as.RData=FALSE, calc.complexity=TRUE, min.mapq=10, remove.duplicate.reads=TRUE, outputfolder.fragments=NULL, return.fragments=FALSE) {

+bed2binned <- function(bedfile, chrom.length.file, ID=basename(bedfile), outputfolder="binned_data", binsizes=NULL, reads.per.bin=NULL, numbins=NULL, chromosomes=NULL, save.as.RData=FALSE, calc.complexity=TRUE, min.mapq=10, remove.duplicate.reads=TRUE, outputfolder.fragments=NULL, return.fragments=FALSE) {

 	call <- match.call()

 	underline <- paste0(rep('=',sum(nchar(call[[1]]))+3), collapse='')

 	message("\n",call[[1]],"():")

 	message(underline)

 	ptm <- proc.time()

-	binned.data <- align2binned(bedfile, format="bed", chrom.length.file=chrom.length.file, outputfolder=outputfolder, binsizes=binsizes, reads.per.bin=reads.per.bin, numbins=numbins, chromosomes=chromosomes, save.as.RData=save.as.RData, calc.complexity=calc.complexity, min.mapq=min.mapq, remove.duplicate.reads=remove.duplicate.reads, call=call, outputfolder.fragments=outputfolder.fragments, return.fragments=return.fragments)

+	binned.data <- align2binned(bedfile, format="bed", ID=ID, chrom.length.file=chrom.length.file, outputfolder=outputfolder, binsizes=binsizes, reads.per.bin=reads.per.bin, numbins=numbins, chromosomes=chromosomes, save.as.RData=save.as.RData, calc.complexity=calc.complexity, min.mapq=min.mapq, remove.duplicate.reads=remove.duplicate.reads, call=call, outputfolder.fragments=outputfolder.fragments, return.fragments=return.fragments)

 	time <- proc.time() - ptm

 	message("Time spent in ", call[[1]],"(): ",round(time[3],2),"s")

 	return(binned.data)

@@ -51,13 +68,13 @@ bed2binned <- function(bedfile, chrom.length.file, outputfolder="binned_data", b

 #' @inheritParams align2binned

 #' @param bedGraphfile A file in bedGraph format.

 #' @export

-bedGraph2binned <- function(bedGraphfile, chrom.length.file, outputfolder="binned_data", binsizes=NULL, reads.per.bin=NULL, numbins=NULL, chromosomes=NULL, save.as.RData=FALSE, calc.complexity=TRUE, min.mapq=10, remove.duplicate.reads=TRUE, outputfolder.fragments=NULL, return.fragments=FALSE) {

+bedGraph2binned <- function(bedGraphfile, chrom.length.file, ID=basename(bedGraphfile), outputfolder="binned_data", binsizes=NULL, reads.per.bin=NULL, numbins=NULL, chromosomes=NULL, save.as.RData=FALSE, calc.complexity=TRUE, min.mapq=10, remove.duplicate.reads=TRUE, outputfolder.fragments=NULL, return.fragments=FALSE) {

 	call <- match.call()

 	underline <- paste0(rep('=',sum(nchar(call[[1]]))+3), collapse='')

 	message("\n",call[[1]],"():")

 	message(underline)

 	ptm <- proc.time()

-	binned.data <- align2binned(bedGraphfile, format="bedGraph", chrom.length.file=chrom.length.file, outputfolder=outputfolder, binsizes=binsizes, reads.per.bin=reads.per.bin, numbins=numbins, chromosomes=chromosomes, save.as.RData=save.as.RData, calc.complexity=calc.complexity, min.mapq=min.mapq, remove.duplicate.reads=remove.duplicate.reads, call=call, outputfolder.fragments=outputfolder.fragments, return.fragments=return.fragments)

+	binned.data <- align2binned(bedGraphfile, format="bedGraph", ID=ID, chrom.length.file=chrom.length.file, outputfolder=outputfolder, binsizes=binsizes, reads.per.bin=reads.per.bin, numbins=numbins, chromosomes=chromosomes, save.as.RData=save.as.RData, calc.complexity=calc.complexity, min.mapq=min.mapq, remove.duplicate.reads=remove.duplicate.reads, call=call, outputfolder.fragments=outputfolder.fragments, return.fragments=return.fragments)

 	time <- proc.time() - ptm

 	message("Time spent in ", call[[1]],"(): ",round(time[3],2),"s")

 	return(binned.data)

@@ -69,6 +86,7 @@ bedGraph2binned <- function(bedGraphfile, chrom.length.file, outputfolder="binne

 #'

 #' @param file A file with aligned reads.

 #' @param format One of \code{c('bam', 'bed', 'bedGraph')}.

+#' @param ID An identifier that will be used to identify the file throughout the workflow and in plotting.

 #' @param bamindex Index file if \code{format='bam'} with or without the .bai ending. If this file does not exist it will be created and a warning is issued.

 #' @param pairedEndReads Set to \code{TRUE} if you have paired-end reads in your file.

 #' @param chrom.length.file A file which contains the chromosome lengths in basepairs. The first column contains the chromosome name and the second column the length (see also \code{\link{chrom.length.file}}.

@@ -88,7 +106,7 @@ bedGraph2binned <- function(bedGraphfile, chrom.length.file, outputfolder="binne

 #' @importFrom Rsamtools indexBam scanBamHeader ScanBamParam scanBamFlag

 #' @importFrom GenomicAlignments readGAlignmentPairsFromBam readGAlignmentsFromBam first

 #' @import preseqR

-align2binned <- function(file, format, bamindex=file, pairedEndReads=FALSE, chrom.length.file, outputfolder="binned_data", binsizes=200000, reads.per.bin=NULL, numbins=NULL, chromosomes=NULL, save.as.RData=FALSE, calc.complexity=TRUE, min.mapq=10, remove.duplicate.reads=TRUE, call=match.call(), outputfolder.fragments=NULL, return.fragments=FALSE) {

+align2binned <- function(file, format, ID=basename(file), bamindex=file, pairedEndReads=FALSE, chrom.length.file, outputfolder="binned_data", binsizes=200000, reads.per.bin=NULL, numbins=NULL, chromosomes=NULL, save.as.RData=FALSE, calc.complexity=TRUE, min.mapq=10, remove.duplicate.reads=TRUE, call=match.call(), outputfolder.fragments=NULL, return.fragments=FALSE) {

 	## Check user input

 	if (is.null(binsizes) & is.null(reads.per.bin)) {

@@ -433,6 +451,9 @@ align2binned <- function(file, format, bamindex=file, pairedEndReads=FALSE, chro

 		## Shannon entropy

 		attr(binned.data, 'shannon.entropy') <- qc.entropy(binned.data$reads)

+		### ID ###

+		attr(binned.data, 'ID') <- ID

+

 		### Save or return the binned data ###

 		if (save.as.RData==TRUE) {

 			# Save to file

@@ -1,3 +1,20 @@

+# aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+# Copyright (C) 2015  Aaron Taudt

+# 

+# This program is free software: you can redistribute it and/or modify

+# it under the terms of the GNU General Public License as published by

+# the Free Software Foundation, either version 3 of the License, or

+# (at your option) any later version.

+# 

+# This program is distributed in the hope that it will be useful,

+# but WITHOUT ANY WARRANTY; without even the implied warranty of

+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+# GNU General Public License for more details.

+# 

+# You should have received a copy of the GNU General Public License

+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

+

+

 check.positive.integer = function(testvar) {

 	if (!is(testvar,"numeric") & !is(testvar,"integer")) return(1)

 	if (length(testvar)>1) return(2)

@@ -1,3 +1,20 @@

+# aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+# Copyright (C) 2015  Aaron Taudt

+# 

+# This program is free software: you can redistribute it and/or modify

+# it under the terms of the GNU General Public License as published by

+# the Free Software Foundation, either version 3 of the License, or

+# (at your option) any later version.

+# 

+# This program is distributed in the hope that it will be useful,

+# but WITHOUT ANY WARRANTY; without even the implied warranty of

+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+# GNU General Public License for more details.

+# 

+# You should have received a copy of the GNU General Public License

+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

+

+

 #' Collapse consecutive bins

 #'

 #' The function will collapse consecutive bins which have, for example, the same CNV-state.

@@ -1,3 +1,20 @@

+# aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+# Copyright (C) 2015  Aaron Taudt

+# 

+# This program is free software: you can redistribute it and/or modify

+# it under the terms of the GNU General Public License as published by

+# the Free Software Foundation, either version 3 of the License, or

+# (at your option) any later version.

+# 

+# This program is distributed in the hope that it will be useful,

+# but WITHOUT ANY WARRANTY; without even the implied warranty of

+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+# GNU General Public License for more details.

+# 

+# You should have received a copy of the GNU General Public License

+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

+

+

 #' Read bed-file into GRanges

 #'

 #' This is a simple convenience function to read a (compressed) bed-file into a \code{\link{GRanges}} object. The bed-file is expected to have the following fields: \code{chrom, chromStart, chromEnd, name, score, strand}.

@@ -1,16 +1,34 @@

+# aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+# Copyright (C) 2015  Aaron Taudt

+# 

+# This program is free software: you can redistribute it and/or modify

+# it under the terms of the GNU General Public License as published by

+# the Free Software Foundation, either version 3 of the License, or

+# (at your option) any later version.

+# 

+# This program is distributed in the hope that it will be useful,

+# but WITHOUT ANY WARRANTY; without even the implied warranty of

+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+# GNU General Public License for more details.

+# 

+# You should have received a copy of the GNU General Public License

+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

+

+

 #' GC correction

 #'

 #' Correct a list of \code{\link{binned.data}} by GC content

 #'

 #' @param binned.data.list A \code{list()} with \code{\link{binned.data}} objects or a list of filenames containing such objects.

-#' @param bsgenome A \code{BSgenome} object which contains the DNA sequence that is used for the GC correction.

+#' @param GC.bsgenome A \code{BSgenome} object which contains the DNA sequence that is used for the GC correction.

 #' @param same.GC.content If \code{TRUE} the GC content will only be calculated once. Set this to \code{TRUE} if all \code{\link{binned.data}} objects describe the same genome at the same binsize.

 #' @author Aaron Taudt

 #' @importFrom Biostrings Views alphabetFrequency

 #' @export

-correctGC <- function(binned.data.list, bsgenome, same.GC.content=FALSE) {

+correctGC <- function(binned.data.list, GC.bsgenome, same.GC.content=FALSE) {

 	binned.data.list <- loadBinnedFromFiles(binned.data.list)

+	same.GC.calculated <- FALSE

 	for (i1 in 1:length(binned.data.list)) {

 		binned.data <- binned.data.list[[i1]]

@@ -22,13 +40,15 @@ correctGC <- function(binned.data.list, bsgenome, same.GC.content=FALSE) {

 		chroms[mask] <- paste0('chr',chroms[mask])

 		names(chromlengths) <- chroms

 		# Compare

-		compare <- chromlengths[chroms] == seqlengths(bsgenome)[chroms]

+		compare <- chromlengths[chroms] == seqlengths(GC.bsgenome)[chroms]

 		if (any(compare==FALSE, na.rm=T)) {

-			stop("Chromosome lengths differ between binned data and 'bsgenome'. Use the correct genome for option 'bsgenome'")

+			warning(paste0(attr(binned.data,'ID'),": Chromosome lengths differ between binned data and 'GC.bsgenome'. GC correction skipped. Please use the correct genome for option 'GC.bsgenome'"))

+			binned.data.list[[i1]] <- binned.data

+			next

 		}

 		## Calculate GC content per bin

-		if (same.GC.content & i1==1 | !same.GC.content) {

+		if (same.GC.content & !same.GC.calculated | !same.GC.content) {

 			message("Calculating GC content per bin ...", appendLF=F); ptm <- proc.time()

 			GC.content <- list()

 			for (chrom in seqlevels(binned.data)) {

@@ -37,7 +57,7 @@ correctGC <- function(binned.data.list, bsgenome, same.GC.content=FALSE) {

 				} else {

 					chr <- chrom

 				}

-				view <- Biostrings::Views(bsgenome[[chr]], ranges(binned.data)[seqnames(binned.data)==chrom])

+				view <- Biostrings::Views(GC.bsgenome[[chr]], ranges(binned.data)[seqnames(binned.data)==chrom])

 				freq <- Biostrings::alphabetFrequency(view, as.prob = T, baseOnly=T)

 				if (nrow(freq) > 1) {

 					GC.content[[as.character(chrom)]] <- rowSums(freq[, c("G","C")])

@@ -46,6 +66,7 @@ correctGC <- function(binned.data.list, bsgenome, same.GC.content=FALSE) {

 				}

 			}

 			GC.content <- unlist(GC.content)

+			same.GC.calculated <- TRUE

 			time <- proc.time() - ptm; message(" ",round(time[3],2),"s")

 		}

 		binned.data$GC <- GC.content

@@ -1,3 +1,20 @@

+# aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+# Copyright (C) 2015  Aaron Taudt

+# 

+# This program is free software: you can redistribute it and/or modify

+# it under the terms of the GNU General Public License as published by

+# the Free Software Foundation, either version 3 of the License, or

+# (at your option) any later version.

+# 

+# This program is distributed in the hope that it will be useful,

+# but WITHOUT ANY WARRANTY; without even the implied warranty of

+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+# GNU General Public License for more details.

+# 

+# You should have received a copy of the GNU General Public License

+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

+

+

 #' Binned read counts

 #'

 #' A \link{GRanges} object which contains binned read counts as meta data column \code{reads}. It is output of the various \link{binning} functions.#' @name binned.data

@@ -1,3 +1,20 @@

+# aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+# Copyright (C) 2015  Aaron Taudt

+# 

+# This program is free software: you can redistribute it and/or modify

+# it under the terms of the GNU General Public License as published by

+# the Free Software Foundation, either version 3 of the License, or

+# (at your option) any later version.

+# 

+# This program is distributed in the hope that it will be useful,

+# but WITHOUT ANY WARRANTY; without even the implied warranty of

+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+# GNU General Public License for more details.

+# 

+# You should have received a copy of the GNU General Public License

+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

+

+

 #' Export genome browser viewable files

 #'

 #' Export copy-number-variation state or read counts as genome browser viewable file

@@ -1,3 +1,20 @@

+# aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+# Copyright (C) 2015  Aaron Taudt

+# 

+# This program is free software: you can redistribute it and/or modify

+# it under the terms of the GNU General Public License as published by

+# the Free Software Foundation, either version 3 of the License, or

+# (at your option) any later version.

+# 

+# This program is distributed in the hope that it will be useful,

+# but WITHOUT ANY WARRANTY; without even the implied warranty of

+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+# GNU General Public License for more details.

+# 

+# You should have received a copy of the GNU General Public License

+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

+

+

 #' Find copy number variations

 #'

 #' \code{findCNVs} classifies the binned read counts into several states which represent copy-number-variation.

@@ -12,11 +29,11 @@

 #'## Bin the BAM file into bin size 200000bp

 #'binned.data <- bam2binned(bamfile, binsize=200000, chromosomes=c(1:22,'X','Y'), save.as.RData=FALSE)

 #'## Fit the Hidden Markov Model

-#'model <- findCNVs(binned.data, ID=basename(bamfile), eps=0.1, max.time=60)

+#'model <- findCNVs(binned.data, eps=0.1, max.time=60)

 #'## Check the fit

 #'plot(model, type='histogram')

 #' @export

-findCNVs <- function(binned.data, ID, method='univariate', eps=0.001, init="standard", max.time=-1, max.iter=-1, num.trials=15, eps.try=10*eps, num.threads=1, read.cutoff.quantile=0.999, strand='*', states=c("zero-inflation","monosomy","disomy","trisomy","tetrasomy","multisomy"), most.frequent.state="disomy") {

+findCNVs <- function(binned.data, ID=NULL, method='univariate', eps=0.1, init="standard", max.time=-1, max.iter=1000, num.trials=15, eps.try=10*eps, num.threads=1, read.cutoff.quantile=0.999, strand='*', states=c("zero-inflation","monosomy","disomy","trisomy","tetrasomy","multisomy"), most.frequent.state="disomy") {

 	call <- match.call()

 	underline <- paste0(rep('=',sum(nchar(call[[1]]))+3), collapse='')

@@ -59,17 +76,19 @@ findCNVs <- function(binned.data, ID, method='univariate', eps=0.001, init="stan

 #' @param states A subset or all of \code{c("zero-inflation","nullsomy","monosomy","disomy","trisomy","tetrasomy","multisomy")}. This vector defines the states that are used in the Hidden Markov Model. The order of the entries should not be changed.

 #' @param most.frequent.state One of the states that were given in \code{states} or 'none'. The specified state is assumed to be the most frequent one. This can help the fitting procedure to converge into the correct fit. If set to 'none', no state is assumed to be most frequent.

 #' @return An \code{\link{aneuHMM}} object.

-univariate.findCNVs <- function(binned.data, ID, eps=0.001, init="standard", max.time=-1, max.iter=-1, num.trials=1, eps.try=NULL, num.threads=1, read.cutoff.quantile=0.999, strand='*', states=c("zero-inflation","monosomy","disomy","trisomy","tetrasomy","multisomy"), most.frequent.state="disomy") {

+univariate.findCNVs <- function(binned.data, ID=NULL, eps=0.1, init="standard", max.time=-1, max.iter=-1, num.trials=1, eps.try=NULL, num.threads=1, read.cutoff.quantile=0.999, strand='*', states=c("zero-inflation","monosomy","disomy","trisomy","tetrasomy","multisomy"), most.frequent.state="disomy") {

 	### Define cleanup behaviour ###

 	on.exit(.C("R_univariate_cleanup"))

 	## Intercept user input

-	IDcheck <- ID  #trigger error if not defined

 	if (class(binned.data) != 'GRanges') {

 		binned.data <- get(load(binned.data))

 		if (class(binned.data) != 'GRanges') stop("argument 'binned.data' expects a GRanges with meta-column 'reads' or a file that contains such an object")

 	}

+	if (is.null(ID)) {

+		ID <- attr(binned.data, 'ID')

+	}

 	if (check.positive(eps)!=0) stop("argument 'eps' expects a positive numeric")

 	if (check.integer(max.time)!=0) stop("argument 'max.time' expects an integer")

 	if (check.integer(max.iter)!=0) stop("argument 'max.iter' expects an integer")

@@ -1,3 +1,20 @@

+# aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+# Copyright (C) 2015  Aaron Taudt

+# 

+# This program is free software: you can redistribute it and/or modify

+# it under the terms of the GNU General Public License as published by

+# the Free Software Foundation, either version 3 of the License, or

+# (at your option) any later version.

+# 

+# This program is distributed in the hope that it will be useful,

+# but WITHOUT ANY WARRANTY; without even the implied warranty of

+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+# GNU General Public License for more details.

+# 

+# You should have received a copy of the GNU General Public License

+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

+

+

 #' Find sister chromatid exchanges

 #'

 #' \code{findSCEs} classifies the binned read counts into several states which represent the number of chromatids on each strand.

@@ -17,7 +34,7 @@

 #'## Check the fit

 #'plot(model, type='histogram')

 #' @export

-findSCEs <- function(binned.data, ID, eps=0.001, init="standard", max.time=-1, max.iter=-1, num.trials=15, eps.try=10*eps, num.threads=1, read.cutoff.quantile=0.999, strand='*', allow.odd.states=TRUE, states=c("zero-inflation","nullsomy","monosomy","disomy","trisomy","tetrasomy","multisomy"), most.frequent.state="monosomy") {

+findSCEs <- function(binned.data, ID=NULL, eps=0.1, init="standard", max.time=-1, max.iter=1000, num.trials=15, eps.try=10*eps, num.threads=1, read.cutoff.quantile=0.999, strand='*', allow.odd.states=TRUE, states=c("zero-inflation","nullsomy","monosomy","disomy","trisomy","tetrasomy","multisomy"), most.frequent.state="monosomy") {

 	call <- match.call()

 	underline <- paste0(rep('=',sum(nchar(call[[1]]))+3), collapse='')

@@ -60,17 +77,19 @@ findSCEs <- function(binned.data, ID, eps=0.001, init="standard", max.time=-1, m

 #' @param states A subset or all of \code{c("zero-inflation","nullsomy","monosomy","disomy","trisomy","tetrasomy","multisomy")}. This vector defines the states that are used in the Hidden Markov Model. The order of the entries should not be changed.

 #' @param most.frequent.state One of the states that were given in \code{states} or 'none'. The specified state is assumed to be the most frequent one. This can help the fitting procedure to converge into the correct fit. If set to 'none', no state is assumed to be most frequent.

 #' @return An \code{\link{aneuHMM}} object.

-univariate.findSCEs <- function(binned.data, ID, eps=0.001, init="standard", max.time=-1, max.iter=-1, num.trials=1, eps.try=NULL, num.threads=1, read.cutoff.quantile=0.999, strand='*', states=c("zero-inflation","nullsomy","monosomy","disomy","trisomy","tetrasomy","multisomy"), most.frequent.state="monosomy") {

+univariate.findSCEs <- function(binned.data, ID=NULL, eps=0.1, init="standard", max.time=-1, max.iter=-1, num.trials=1, eps.try=NULL, num.threads=1, read.cutoff.quantile=0.999, strand='*', states=c("zero-inflation","nullsomy","monosomy","disomy","trisomy","tetrasomy","multisomy"), most.frequent.state="monosomy") {

 	### Define cleanup behaviour ###

 	on.exit(.C("R_univariate_cleanup"))

 	## Intercept user input

-	IDcheck <- ID  #trigger error if not defined

 	if (class(binned.data) != 'GRanges') {

 		binned.data <- get(load(binned.data))

 		if (class(binned.data) != 'GRanges') stop("argument 'binned.data' expects a GRanges with meta-column 'reads' or a file that contains such an object")

 	}

+	if (is.null(ID)) {

+		ID <- attr(binned.data, 'ID')

+	}

 	if (check.positive(eps)!=0) stop("argument 'eps' expects a positive numeric")

 	if (check.integer(max.time)!=0) stop("argument 'max.time' expects an integer")

 	if (check.integer(max.iter)!=0) stop("argument 'max.iter' expects an integer")

@@ -388,7 +407,7 @@ univariate.findSCEs <- function(binned.data, ID, eps=0.001, init="standard", max

 #'

 #' @inheritParams univariate.findSCEs

 #' @param allow.odd.states If set to \code{TRUE}, all states are allowed. If \code{FALSE}, only states which have an even multiplicity (plus nullsomy-monosomy states) are allowed, e.g. disomy-disomy, monosomy-trisomy.

-bivariate.findSCEs <- function(binned.data, ID, eps=0.001, init="standard", max.time=-1, max.iter=-1, num.trials=1, eps.try=NULL, num.threads=1, read.cutoff.quantile=0.999, allow.odd.states=TRUE, states=c("zero-inflation","nullsomy","monosomy","disomy","trisomy","tetrasomy","multisomy"), most.frequent.state="monosomy") {

+bivariate.findSCEs <- function(binned.data, ID, eps=0.1, init="standard", max.time=-1, max.iter=-1, num.trials=1, eps.try=NULL, num.threads=1, read.cutoff.quantile=0.999, allow.odd.states=TRUE, states=c("zero-inflation","nullsomy","monosomy","disomy","trisomy","tetrasomy","multisomy"), most.frequent.state="monosomy") {

 	## Intercept user input

 	IDcheck <- ID  #trigger error if not defined

@@ -1,3 +1,20 @@

+# aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+# Copyright (C) 2015  Aaron Taudt

+# 

+# This program is free software: you can redistribute it and/or modify

+# it under the terms of the GNU General Public License as published by

+# the Free Software Foundation, either version 3 of the License, or

+# (at your option) any later version.

+# 

+# This program is distributed in the hope that it will be useful,

+# but WITHOUT ANY WARRANTY; without even the implied warranty of

+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+# GNU General Public License for more details.

+# 

+# You should have received a copy of the GNU General Public License

+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

+

+

 #' Chromosome lengths for different assemblies

 #'

 #' Get the chromosome lengths of different common assemblies. Only the standard chromosomes (no chrN_random) will be returned.

@@ -1,3 +1,20 @@

+# aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+# Copyright (C) 2015  Aaron Taudt

+# 

+# This program is free software: you can redistribute it and/or modify

+# it under the terms of the GNU General Public License as published by

+# the Free Software Foundation, either version 3 of the License, or

+# (at your option) any later version.

+# 

+# This program is distributed in the hope that it will be useful,

+# but WITHOUT ANY WARRANTY; without even the implied warranty of

+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+# GNU General Public License for more details.

+# 

+# You should have received a copy of the GNU General Public License

+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

+

+

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

 # Extraction of segments and clustering

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

@@ -1,3 +1,20 @@

+# aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+# Copyright (C) 2015  Aaron Taudt

+# 

+# This program is free software: you can redistribute it and/or modify

+# it under the terms of the GNU General Public License as published by

+# the Free Software Foundation, either version 3 of the License, or

+# (at your option) any later version.

+# 

+# This program is distributed in the hope that it will be useful,

+# but WITHOUT ANY WARRANTY; without even the implied warranty of

+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+# GNU General Public License for more details.

+# 

+# You should have received a copy of the GNU General Public License

+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

+

+

 #' @useDynLib aneufinder

 #' @import GenomicRanges

 #' @import IRanges

@@ -1,3 +1,20 @@

+# aneufinder - An R-package for CNV detection in whole-genome single cell sequencing data

+# Copyright (C) 2015  Aaron Taudt

+# 

+# This program is free software: you can redistribute it and/or modify

+# it under the terms of the GNU General Public License as published by

+# the Free Software Foundation, either version 3 of the License, or

+# (at your option) any later version.

+# 

+# This program is distributed in the hope that it will be useful,

+# but WITHOUT ANY WARRANTY; without even the implied warranty of

+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

+# GNU General Public License for more details.

+# 

+# You should have received a copy of the GNU General Public License

+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

+