Files created by makeTagDirectory
\n']
-
- flist.sort()
- for i,f in enumerate(flist):
- if not(os.path.isdir(f)):
- fn = os.path.split(f)[-1]
- res.append('%s |
\n' % (fn,getFileString(fn, dr)))
-
- res.append('
\n')
-
- return res
-
-if __name__ == '__main__':
- op = optparse.OptionParser()
- op.add_option('-e', '--executable', default='makeTagDirectory')
- op.add_option('-o', '--htmloutput', default=None)
- op.add_option('-f', '--format', default="sam")
- opts, args = op.parse_args()
- #assert os.path.isfile(opts.executable),'## makeTagDirectory.py error - cannot find executable %s' % opts.executable
-
- #if not os.path.exists(opts.outputdir):
- #os.makedirs(opts.outputdir)
- f = makeTagDirectory(opts, args)
-
- html,retval = f.run_makeTagDirectory()
- f = open(opts.htmloutput, 'w')
- f.write(''.join(html))
- f.close()
- if retval <> 0:
- print >> sys.stderr, serr # indicate failure
-
-
-
diff -r 6f1302d12a38 -r 251442d07ef8 makeTagDirectory.xml
--- a/makeTagDirectory.xml Wed Dec 19 20:09:58 2012 -0500
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,146 +0,0 @@
-
-
- homer
-
- Simple wrapper for makeTagDirectory. Used by findPeaks
-
- makeTagDirectory.py ${tagDir.files_path}
- #for $alignF in $alignmentFiles
- $alignF.file -f $alignF.file.ext
- #end for
- -o $tagDir
- 2> $out_log || echo "Error running homer_makeTagDirectory." >&2
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- .. class:: infomark
-
- **Homer makeTagDirectory**
-
- For more options, look under: "Command line options"
-
- http://biowhat.ucsd.edu/homer/ngs/tagDir.html
-
-**Parameter list**
-
-Command line options (not all of them are supported)::
-
- Usage: makeTagDirectory <directory> <alignment file 1> [file 2] ... [options]
-
- Creates a platform-independent 'tag directory' for later analysis.
- Currently BED, eland, bowtie, and sam files are accepted. The program will try to
- automatically detect the alignment format if not specified. Program will also
- unzip *.gz, *.bz2, and *.zip files and convert *.bam to sam files on the fly
- Existing tag directories can be added or combined to make a new one using -d/-t
- If more than one format is needed and the program cannot auto-detect it properly,
- make separate tag directories by running the program separately, then combine them.
- To perform QC/manipulations on an existing tag directory, add "-update"
-
- Options:
- -fragLength <# | given> (Set estimated fragment length - given: use read lengths)
- By default treats the sample as a single read ChIP-Seq experiment
- -format <X> where X can be: (with column specifications underneath)
- bed - BED format files:
- (1:chr,2:start,3:end,4:+/- or read name,5:# tags,6:+/-)
- -force5th (5th column of BED file contains # of reads mapping to position)
- sam - SAM formatted files (use samTools to covert BAMs into SAM if you have BAM)
- -unique (keep if there is a single best alignment based on mapq)
- -mapq <#> (Minimum mapq for -unique, default: 10, set negative to use AS:i:/XS:i:)
- -keepOne (keep one of the best alignments even if others exist)
- -keepAll (include all alignments in SAM file)
- -mis (Maximum allowed mismatches, default: no limit, uses MD:Z: tag)
- bowtie - output from bowtie (run with --best -k 2 options)
- (1:read name,2:+/-,3:chr,4:position,5:seq,6:quality,7:NA,8:misInfo)
- eland_result - output from basic eland
- (1:read name,2:seq,3:code,4:#zeroMM,5:#oneMM,6:#twoMM,7:chr,
- 8:position,9:F/R,10-:mismatches
- eland_export - output from illumina pipeline (22 columns total)
- (1-5:read name info,9:sequence,10:quality,11:chr,13:position,14:strand)
- eland_extended - output from illumina pipeline (4 columns total)
- (1:read name,2:sequence,3:match stats,4:positions[,])
- mCpGbed - encode style mCpG reporting in extended BED format, no auto-detect
- (1:chr,2:start,3:end,4:name,5:,6:+/-,7:,8:,9:,10:#C,11:#mC)
- allC - Lister style output files detailing the read information about all cytosines
- (1:chr,2:pos,3:strand,4:context,#mC,#totalC,#C
- -minCounts <#> (minimum number of reads to report mC/C ratios, default: 10)
- -mCcontext <CG|CHG|CHH|all> (only use C's in this context, default: CG)
- HiCsummary - minimal paired-end read mapping information
- (1:readname,2:chr1,3:5'pos1,4:strand1,5:chr2,6:5'pos2,7:strand2)
- -force5th (5th column of BED file contains # of reads mapping to position)
- -d <tag directory> [tag directory 2] ... (add Tag directory to new tag directory)
- -t <tag file> [tag file 2] ... (add tag file i.e. *.tags.tsv to new tag directory)
- -single (Create a single tags.tsv file for all "chromosomes" - i.e. if >100 chromosomes)
- -update (Use current tag directory for QC/processing, do not parse new alignment files)
- -tbp <#> (Maximum tags per bp, default: no maximum)
- -precision <1|2|3> (number of decimal places to use for tag totals, default: 1)
-
- GC-bias options:
- -genome <genome version> (To see available genomes, use "-genome list")
- -or- (for custom genomes):
- -genome <path-to-FASTA file or directory of FASTA files>
-
- -checkGC (check Sequence bias, requires "-genome")
- -freqStart <#> (offset to start calculating frequency, default: -50)
- -freqEnd <#> (distance past fragment length to calculate frequency, default: +50)
- -oligoStart <#> (oligo bias start)
- -oligoEnd <#> (oligo bias end)
- -normGC <target GC profile file> (i.e. tagGCcontent.txt file from control experiment)
- Use "-normGC default" to match the genomic GC distribution
- -normFixedOligo <oligoFreqFile> (normalize 5' end bias, "-normFixedOligo default" ok)
- -minNormRatio <#> (Minimum deflation ratio of tag counts, default: 0.25)
- -maxNormRatio <#> (Maximum inflation ratio of tag counts, default: 2.0)
- -iterNorm <#> (Sets -max/minNormRatio to 1 and 0, iteratively normalizes such that the
- resulting distrubtion is no more than #% different than target, i.e. 0.1,default: off)
-
- Paired-end/HiC options
- -illuminaPE (when matching PE reads, assumes last character of read name is 0 or 1)
- -removePEbg (remove paired end tags within 1.5x fragment length on same chr)
- -PEbgLength <#> (remove PE reads facing on another within this distance, default: 1.5x fragLen)
- -restrictionSite <seq> (i.e. AAGCTT for HindIII, assign data < 1.5x fragment length to sites)
- Must specify genome sequence directory too. (-rsmis <#> to specify mismatches, def: 0)
- -both, -one, -onlyOne, -none (Keeps reads near restriction sites, default: keep all)
- -removeSelfLigation (removes reads linking same restriction fragment)
- -removeRestrictionEnds (removes reads starting on a restriction fragment)
- -assignMidPoint (will place reads in the middle of HindIII fragments)
- -restrictionSiteLength <#> (maximum distance from restriction site, default: 1.5x fragLen)
- -removeSpikes <size bp> <#> (remove tags from regions with > than # times
- the average tags per size bp, suggest "-removeSpikes 10000 5")
-
-
-
-
-
diff -r 6f1302d12a38 -r 251442d07ef8 pos2bed.xml
--- a/pos2bed.xml Wed Dec 19 20:09:58 2012 -0500
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,37 +0,0 @@
-
-
- homer
-
-
-
-
- pos2bed.pl $input_peak 1> $out_bed
- 2> $out_log || echo "Error running pos2bed." >&2
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- .. class:: infomark
-
- Converts: homer peak positions -(to)-> BED format
-
- **Homer pos2bed.pl**
-
- http://biowhat.ucsd.edu/homer/ngs/miscellaneous.html
-
-
-
diff -r 6f1302d12a38 -r 251442d07ef8 tool_dependencies.xml
--- a/tool_dependencies.xml Wed Dec 19 20:09:58 2012 -0500
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,23 +0,0 @@
-
-
-
-
-
- http://biowhat.ucsd.edu/homer/configureHomer.pl
-
-
-
- ./
- $INSTALL_DIR
-
-
- $INSTALL_DIR/bin
-
-
-
-
- Installs homer
-
-
-
-