Wrapper function for ctk's ctk_tag2profile

ctk_tag2profile(
  filesToRun,
  outFile = paste0(file_path_sans_ext(filesToRun), ".out"),
  outFile2 = NULL,
  sb = "tag2profile.pl",
  perl = "perl",
  PATHTOPERLLIB = NULL,
  bigFile = FALSE,
  weight = FALSE,
  weightAvg = FALSE,
  ss = TRUE,
  exact = TRUE,
  nz = FALSE,
  ext5 = NULL,
  ext3 = NULL,
  chromLen = NULL,
  region = NULL,
  minBlockSize = 2e+06,
  windowSize = 100,
  stepSize = 20,
  outputFormat = "bedgraph",
  normalization = "none",
  stderr = file.path(dirname(fileToRun), paste0(basename(fileToRun),
    "_ctk_tag2profile_stderr.txt")),
  stdout = file.path(dirname(fileToRun), paste0(basename(fileToRun),
    "_ctk_tag2profile_stdout.txt")),
  useClipRConda = ifelse(is.null(getOption("CLIPflexR.condaEnv")), FALSE, TRUE),
  additional_Args = NULL,
  verbose = FALSE,
  writelog = T
)

Arguments

filesToRun: path to file to process (BED).
outFile: path to output file (BED).
outFile2: path to output 2 file (BED; specify two output files to separate strands).
sb: path to tag2profile.pl from CTK.
perl: path to PERL
PATHTOPERLLIB: path to PERL5LIB.
bigFile: TRUE when working with a big file, TRUE or FALSE (default).
weight: weight counts according to the score of each tag, TRUE or FALSE (default).
weightAvg: weight average the score of each tag, TRUE or FALSE (default).
ss: separate strand, TRUE (default) or FALSE.
exact: exact count at each nucleotide, TRUE (default) or FALSE.
nz: don't print zeroes (works for sgr and bed), TRUE or FALSE (default).
ext5: extension of tags at the 5' end, default is NULL (set to integer to specify).
ext3: extension of tags at the 3' end, default is NULL (set to integer to specify).
chromLen: chrom length file, default is NULL (set file path to specify).
region: a bed file with regions to count tag numbers; if not specified (NULL), count in moving windows
minBlockSize: minimum number of lines to read in each block for a big file, default is 2000000.
windowSize: window size, default is 100.
stepSize: step size, default is 20.
outputFormat: output format, "bed" or "bedgraph" (default) or "sgr".
normalization: normalization, "none" (default) or "rpkm" or multiply=1.3).
stderr: path to stdout file.
stdout: path to stdout file.
useClipRConda: use conda environment installed by Herper, TRUE (default) or FALSE.
additional_Args: Additional arguments to be passed to system call.
verbose: print messages, TRUE or FALSE (default).
writelog: write stderr/stdout logs, TRUE (default) or FALSE.

Value

path to BED file.

Author

Kathryn Rozen-Gagnon

Examples

testFasta <- system.file("extdata/hg19Small.fa",package="CLIPflexR")
myIndex <-suppressWarnings(bowtie2_index(testFasta, overwrite = TRUE))
testFQ <- system.file("extdata/Fox3_Std_small.fq.gz",package="CLIPflexR")
FqFile_FF <- ctk_fastqFilter(testFQ,qsFilter="mean:0-29:20",verbose=TRUE)
#> fastq_filter.pl command is /Users/runner/Library/r-miniconda/envs/CLIPflexR_0.1.20/bin/ctk/fastq_filter.pl
#> fastq_filter.pl arguments are /Users/runner/Library/r-miniconda/envs/CLIPflexR_0.1.20/bin/ctk/fastq_filter.pl  -if sanger  -of fastq  -f mean:0-29:20  /Users/runner/work/_temp/Library/CLIPflexR/extdata/Fox3_Std_small.fq.gz  /Users/runner/work/_temp/Library/CLIPflexR/extdata/FF_Fox3_Std_small.fq.gz 
FqFile <- decompress(FqFile_FF,overwrite=TRUE)
FqFile_clipped <- fastx_clipper(FqFile,length=20)
FqFile_QF <- fastq_quality_trimmer(FqFile_clipped)
FqFile_Col <- ctk_fastq2collapse(FqFile_QF,verbose=TRUE)
#> fastq_filter.pl command is /Users/runner/Library/r-miniconda/envs/CLIPflexR_0.1.20/bin/ctk/fastq2collapse.pl
#> fastq_filter.pl arguments are /Users/runner/Library/r-miniconda/envs/CLIPflexR_0.1.20/bin/ctk/fastq2collapse.pl  /Users/runner/work/_temp/Library/CLIPflexR/extdata/QT_FF_Fox3_Std_small_clip.fq  /Users/runner/work/_temp/Library/CLIPflexR/extdata/Collapsed_QT_FF_Fox3_Std_small_clip.fq 
FqFile_QFColStripped <- ctk_stripBarcode(FqFile_Col,linkerlength=5,inputFormat="fastq")
bam <- suppressWarnings(bowtie_align(FqFile_QFColStripped,myIndex, 
overwrite=TRUE, inputFormat="fastq"))
parsedAlignment <- ctk_parseAlignment(bam)
myCollaped <- ctk_tag2collapse(parsedAlignment,weight=FALSE,randomBarcode=FALSE,
weightInName=FALSE,verbose=TRUE)
#> tag2collapse.pl command is /Users/runner/Library/r-miniconda/envs/CLIPflexR_0.1.20/bin/ctk/tag2collapse.pl
#> tag2collapse.pl arguments are /Users/runner/Library/r-miniconda/envs/CLIPflexR_0.1.20/bin/ctk/tag2collapse.pl  --keep-tag-name   --keep-max-score   -EM -1  --seq-error-model em-local  /Users/runner/work/_temp/Library/CLIPflexR/extdata/Collapsed_QT_FF_Fox3_Std_small_clip_rm5.bed  /Users/runner/work/_temp/Library/CLIPflexR/extdata/TC_Collapsed_QT_FF_Fox3_Std_small_clip_rm5.bed 
myrgbBed <- ctk_bed2rgb(myCollaped,col="128,0,0")
ctk_tag2profile(myrgbBed,verbose=TRUE)
#> tag2profile.pl command is /Users/runner/Library/r-miniconda/envs/CLIPflexR_0.1.20/bin/ctk/tag2profile.pl
#> tag2profile.pl arguments are /Users/runner/Library/r-miniconda/envs/CLIPflexR_0.1.20/bin/ctk/tag2profile.pl  -ss   -exact   -minBlockSize 2000000  -w 100  -s 20  -of bedgraph  -normalize none  /Users/runner/work/_temp/Library/CLIPflexR/extdata/TC_Collapsed_QT_FF_Fox3_Std_small_clip_rm5.RGB.bed  /Users/runner/work/_temp/Library/CLIPflexR/extdata/TC_Collapsed_QT_FF_Fox3_Std_small_clip_rm5.RGB.out 
#> [1] "/Users/runner/work/_temp/Library/CLIPflexR/extdata/TC_Collapsed_QT_FF_Fox3_Std_small_clip_rm5.RGB.out"