@@ -1,9 +1,8 @@

 Package: seqTools

 Type: Package

-Title: Analysis of nucleotide, sequence and quality content on fastq

-        files.

-Version: 1.9.0

-Date: 2013-10-14

+Title: Analysis of nucleotide, sequence and quality content on fastq files

+Version: 1.9.1

+Date: 2017-04-13

 Author: Wolfgang Kaisers

 Maintainer: Wolfgang Kaisers <kaisers@med.uni-duesseldorf.de>

 Description: Analyze read length, phred scores and alphabet frequency and DNA k-mers on uncompressed and compressed fastq files.

@@ -12,3 +11,5 @@ License: Artistic-2.0

 Depends: methods,utils,zlibbioc

 LinkingTo: zlibbioc

 Suggests: RUnit, BiocGenerics

+Packaged: 2016-11-02 14:54:43 UTC; kaisers

+NeedsCompilation: yes

@@ -2,8 +2,11 @@

 useDynLib(seqTools)

 import(methods)

 import(zlibbioc)

-importFrom(utils,head)

-importFrom(utils,tail)

+importFrom(utils,"head", "tail")

+importFrom("grDevices", "topo.colors")

+importFrom("graphics", "axis", "legend", "lines", "plot")

+importFrom("stats", "as.dist", "hclust")

+

 export(

     ascii2char,

     countDnaKmers,

@@ -34,9 +37,11 @@ exportMethods(

     collectDur,

     gcContent,

     gcContentMatrix,

+    getGCcontent,

     fileNames,

     getK,

     kmerCount,

+    kmerSvd,

     maxSeqLen,

     meltDownK,

     mergedPhred,

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

+CHANGES IN VERSION 1.9.1

+-------------------------

+

+NEW FEATURES

+

+    o (none)

+

+SIGNIFICANT USER-VISIBLE CHANGES

+

+    o (none)

+

+BUG FIXES

+

+    o Added entry in NAMESPACE

+

+

+

 CHANGES IN VERSION 0.99.42

 -------------------------

@@ -6,13 +6,17 @@

 \alias{gcContentMatrix-methods}

 \alias{gcContentMatrix,Fastqq-method}

 %

+\alias{getGCcontent}

+\alias{getGCcontent-methods}

+\alias{getGCcontent,Fastqq-method}

 \title{

 gcContentMatrix: Returns matrix with read counts for GC content.

 }

 % - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - %

 % Description

 % - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - %

-\description{Returns a matrix with read counts.}

+\description{Returns a matrix with read counts. getGCcontent returns a

+numeric vector with the GC contend (in percent) for each fastq file.}

 %

 \usage{

 gcContentMatrix(object)

@@ -23,7 +27,7 @@ gcContentMatrix(object)

 % - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - %

 % Details

 % - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - %

-\details{The matrix contains one column for each FASTQ file. Rows labeled 

+\details{The matrix contains one column for each FASTQ file. Rows labeled

     from 0 to 100 which represents percent (\%) GC content. The matrix contains

     numbers of reads with the respective proportion of GC (Row 2 contains

     number of reads with 2\% GC content).}

@@ -32,7 +36,7 @@ gcContentMatrix(object)

 %

 \references{

 Cock PJA, Fields CJ, Goto N, Heuer ML, Rice PM

-The sanger FASTQ file format for sequences with quality scores and 

+The sanger FASTQ file format for sequences with quality scores and

     the Solexa/Illumina FASTQ variants.

 Nucleic Acids Research 2010 Vol.38 No.6 1767-1771

 }

@@ -47,6 +51,7 @@ setwd(basedir)

 fq <- fastqq(c("g4_l101_n100.fq.gz", "g5_l101_n100.fq.gz"), k=4,

     probeLabel=c("g4","g5"))

 fqm<-gcContentMatrix(fq)

+getGCcontent(fq)

 }

 \seealso{gcContent}

 \keyword{gcContentMatrix}

@@ -4,24 +4,76 @@

 ## Load prerequisites

 ## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

-require(seqTools)

+library(seqTools)

 ## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

 ## Initialize example data

 ## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

 basedir<-system.file("extdata",package="seqTools")

-load(file.path(basedir,"test_res.RData"))

 ## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

 ## Run tests

 ## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

-source("test_seqTools.r")

+

+filename <- "test_seqTools.R"

+basedir <- system.file("extdata", package = "seqTools")

+load(file.path(basedir,"test_res.RData"))

+

+

+

+## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

+## kmerCount.fastqq

+## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

+

+fq <- fastqq(file.path(basedir, "test_l5_N.fq"), k = 2)

+if(!identical(kmerCount(fq), kmer_l5_N))

+    stop("[kmerCount.fastqq] Test 1 '", filename, "' FAILED!")

+

+fq<-fastqq(file.path(basedir, "test_l6.fq"), k = 2)

+if(!identical(kmerCount(fq), kmer_l6))

+    stop("[kmerCount.fastqq] Test 2 '", filename, "' FAILED!")

+

+fq<-fastqq(file.path(basedir, "test_l6_multi_line.fq"), k = 2)

+if(!identical(kmerCount(fq), kmer_l6_ml))

+    stop("[kmerCount.fastqq] Test 3 '", filename, "' FAILED!")

+

+fq<-fastqq(file.path(basedir, "test_l10_20_40.fq"),k = 2)

+if(!identical(kmerCount(fq), kmer_l10_20))

+    stop("[kmerCount.fastqq] Test 4 '", filename, "' FAILED!")

+

+fq<-fastqq(file.path(basedir, "test_l10_atcg.fq"), k = 2)

+if(!identical(kmerCount(fq), kmer_l10_atcg))

+    stop("[kmerCount.fastqq] Test 5 '", filename, "' FAILED!")

+

+fq<-fastqq(file.path(basedir, "test_l10_ATCGN.fq"), k = 2)

+if(!identical(kmerCount(fq), kmer_l10_ATCGN))

+    stop("[kmerCount.fastqq] Test 6 '", filename, "' FAILED!")

+

+# Counting k-mers on linux ('\n') and equal windows ('\r\n')

+# formatted FASTQ file should give equal results

+# fq<-fastqq(file.path(basedir, c("test_l4.fq", "test_win.fq")), k = 2)

+# kc <- kmerCount(fq)

+# if(!all(kc[,1]==kc[,2]))

+#     stop("[kmerCount.fastqq] test_l4: kmerCount unequal to test_win.fq")

 ## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

-## Cleanup

+## ascii2char, char2ascii

 ## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

+if(!identical(ascii2char(97:101, multiple = FALSE), "abcde"))

+    stop("[ascii2char] Test 1 '", filename, "' FAILED!")

+

+if(!identical(ascii2char(97:101, multiple = TRUE), letters[1:5]))

+    stop("[ascii2char] Test 2 '", filename, "' FAILED!")

+

+if(!identical(ascii2char(char2ascii("abcde")), "abcde"))

+    stop("[ascii2char] Test 3 '", filename, "' FAILED!")

+

+if(!identical(char2ascii("abcde"), 97:101))

+    stop("[char2ascii] Test 1 '", filename, "' FAILED!")

+

 ## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

 ## END OF FILE

 ## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

+

@@ -1,8 +1,24 @@

+## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

+## Load prerequisites

+## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

+

 library(seqTools)

-filename <- "test_seqTools.r"

+## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

+## Initialize example data

+## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

+

+basedir<-system.file("extdata",package="seqTools")

+

+## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

+## Run tests

+## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

+

+filename <- "test_seqTools.R"

 basedir <- system.file("extdata", package = "seqTools")

+load(file.path(basedir,"test_res.RData"))

+

 ## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

 ## countDnaKmers

@@ -10,7 +26,7 @@ basedir <- system.file("extdata", package = "seqTools")

 if(!identical(countDnaKmers("ACGT", k = 1, start = 3:1, width = 1), cdk_ACGT))

     stop("[countDnaKmers] Test 1 '", filename, "' FAILED!")

-   

+

 if(!identical(countDnaKmers("ACGT", k = 1, start = 3, width = 1), cdk_ACGT_one))

     stop("[countDnaKmers] Test 2 '", filename, "' FAILED!")

@@ -27,49 +43,6 @@ if(!identical(

     stop("[revCountDnaKmers] Test 1 '", filename, "' FAILED!")

-## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

-## kmerCount.fastqq

-## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

-

-fq <- fastqq(file.path(basedir, "test_l5_N.fq"), k = 2)

-if(!identical(kmerCount(fq), kmer_l5_N))

-    stop("[kmerCount.fastqq] Test 1 '", filename, "' FAILED!")

-

-fq<-fastqq(file.path(basedir, "test_l6.fq"), k = 2)

-if(!identical(kmerCount(fq), kmer_l6))

-    stop("[kmerCount.fastqq] Test 2 '", filename, "' FAILED!")

-

-fq<-fastqq(file.path(basedir, "test_l6_multi_line.fq"), k = 2)

-if(!identical(kmerCount(fq), kmer_l6_ml))

-    stop("[kmerCount.fastqq] Test 3 '", filename, "' FAILED!")

-

-fq<-fastqq(file.path(basedir, "test_l10_20_40.fq"),k = 2)

-if(!identical(kmerCount(fq), kmer_l10_20))

-    stop("[kmerCount.fastqq] Test 4 '", filename, "' FAILED!")

-

-fq<-fastqq(file.path(basedir, "test_l10_atcg.fq"), k = 2)

-if(!identical(kmerCount(fq), kmer_l10_atcg))

-    stop("[kmerCount.fastqq] Test 5 '", filename, "' FAILED!")

-

-fq<-fastqq(file.path(basedir, "test_l10_ATCGN.fq"), k = 2)

-if(!identical(kmerCount(fq), kmer_l10_ATCGN))

-    stop("[kmerCount.fastqq] Test 6 '", filename, "' FAILED!")

-

-## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

-## ascii2char, char2ascii

-## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

-

-if(!identical(ascii2char(97:101, multiple = FALSE), "abcde"))

-    stop("[ascii2char] Test 1 '", filename, "' FAILED!")

-

-if(!identical(ascii2char(97:101, multiple = TRUE), letters[1:5]))

-    stop("[ascii2char] Test 2 '", filename, "' FAILED!")

-

-if(!identical(ascii2char(char2ascii("abcde")), "abcde"))

-    stop("[ascii2char] Test 3 '", filename, "' FAILED!")

-

-if(!identical(char2ascii("abcde"), 97:101))

-    stop("[char2ascii] Test 1 '", filename, "' FAILED!")

 ## + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##

 ## END OF FILE