view makeTagDirectory.xml @ 24:b3b65304ee72 draft

Uploaded
author kevyin
date Thu, 20 Dec 2012 17:52:56 -0500
parents 687df269e597
children
line wrap: on
line source

<tool id="homer_makeTagDirectory" name="homer_makeTagDirectory" version="1.0.1">
    <requirements>
        <requirement type="package" version="4.1">homer</requirement>
    </requirements>
    <description>Simple wrapper for makeTagDirectory. Used by findPeaks</description>
    <!--<version_command></version_command>-->
    <command interpreter="python">makeTagDirectory.py ${tagDir.files_path} 
        #for $alignF in $alignmentFiles
          $alignF.file -f $alignF.file.ext
        #end for
          -o $tagDir
        2&gt; $out_log || echo "Error running homer_makeTagDirectory." >&amp;2

    </command>
    <inputs>
        <param name="title" label="Name for the output tag directory" type="text" default="Homer TagDirectory" />
        <param type="text" name="options" label="Extra options" value="" help="See below for more options">
          <sanitizer>
            <valid initial="string.printable">
             <remove value="&apos;"/>
             <remove value="/"/>
            </valid>
            <mapping initial="none">
              <add source="&apos;" target="__sq__"/>
            </mapping>
          </sanitizer>
        </param>
        <repeat name="alignmentFiles" title="Alignment Files">
          <param name="file" label="Add file" type="data" format="sam,bed" help="Alignments in SAM or BED format" />
        </repeat>
    </inputs>
    <outputs>
        <!--<data format="homerTagDirectory" name="tagDir" label="${title} tag directory" />-->
        <data format="html" name="tagDir" label="${title} tag directory" />
        <data format="txt" name="out_log" label="${title}.log" />
        <!--<data format="html" name="html_outfile" label="index" />-->
        <!--<data format="html" hidden="True" name="html_outfile" label="index.html" />-->
    </outputs>


    <tests>
        <!--<test>-->
            <!--<param name="input_file" value="extract_genomic_dna.fa" />-->
            <!--<output name="html_file" file="sample_output.html" ftype="html" />-->
        <!--</test>-->
    </tests>

    <help>

  .. 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 &lt;directory&gt; &lt;alignment file 1&gt; [file 2] ... [options]

	Creates a platform-independent &apos;tag directory&apos; 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 &quot;-update&quot;

	Options:
		-fragLength &lt;# | given&gt; (Set estimated fragment length - given: use read lengths)
			By default treats the sample as a single read ChIP-Seq experiment
		-format &lt;X&gt; 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 &lt;#&gt; (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 &lt;#&gt; (minimum number of reads to report mC/C ratios, default: 10)
				-mCcontext &lt;CG|CHG|CHH|all&gt; (only use C&apos;s in this context, default: CG)
			HiCsummary - minimal paired-end read mapping information
				(1:readname,2:chr1,3:5&apos;pos1,4:strand1,5:chr2,6:5&apos;pos2,7:strand2)
		-force5th (5th column of BED file contains # of reads mapping to position)
		-d &lt;tag directory&gt; [tag directory 2] ... (add Tag directory to new tag directory)
		-t &lt;tag file&gt; [tag file 2] ... (add tag file i.e. *.tags.tsv to new tag directory)
		-single (Create a single tags.tsv file for all &quot;chromosomes&quot; - i.e. if &gt;100 chromosomes)
		-update (Use current tag directory for QC/processing, do not parse new alignment files)
		-tbp &lt;#&gt; (Maximum tags per bp, default: no maximum)
		-precision &lt;1|2|3&gt; (number of decimal places to use for tag totals, default: 1)

		GC-bias options:
		-genome &lt;genome version&gt; (To see available genomes, use &quot;-genome list&quot;)
			-or- (for custom genomes):
		-genome &lt;path-to-FASTA file or directory of FASTA files&gt;

		-checkGC (check Sequence bias, requires &quot;-genome&quot;)
			-freqStart &lt;#&gt; (offset to start calculating frequency, default: -50)
			-freqEnd &lt;#&gt; (distance past fragment length to calculate frequency, default: +50)
			-oligoStart &lt;#&gt; (oligo bias start)
			-oligoEnd &lt;#&gt; (oligo bias end)
		-normGC &lt;target GC profile file&gt; (i.e. tagGCcontent.txt file from control experiment)
			Use &quot;-normGC default&quot; to match the genomic GC distribution
		-normFixedOligo &lt;oligoFreqFile&gt; (normalize 5&apos; end bias, &quot;-normFixedOligo default&quot; ok)
		-minNormRatio &lt;#&gt; (Minimum deflation ratio of tag counts, default: 0.25)
		-maxNormRatio &lt;#&gt; (Maximum inflation ratio of tag counts, default: 2.0)
		-iterNorm &lt;#&gt; (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 &lt;#&gt; (remove PE  reads facing on another within this distance, default: 1.5x fragLen)
		-restrictionSite &lt;seq&gt; (i.e. AAGCTT for HindIII, assign data &lt; 1.5x fragment length to sites)
			Must specify genome sequence directory too. (-rsmis &lt;#&gt; 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 &lt;#&gt; (maximum distance from restriction site, default: 1.5x fragLen)
		-removeSpikes &lt;size bp&gt; &lt;#&gt; (remove tags from regions with &gt; than # times
			the average tags per size bp, suggest &quot;-removeSpikes 10000 5&quot;)


    </help>
</tool>