annotate cgatools/tools/cgatools_1.5/junctiondiff.xml @ 0:182426b32995 draft default tip

Uploaded

<tool id="cg_junctiondiff" name="junctiondiff(beta) 1.5" version="1.0.0">
<!--
This tool creates a GUI for the junctiondiff function of cgatools from Complete Genomics, Inc.
written 6-18-2012 by [e-mail]
-->

  <description>reports difference between junction calls</description> <!--adds description in toolbar-->

  <requirements>
  	<requirement type="binary">cgatools</requirement>
  </requirements>

  <command> <!--run executable-->
  	cgatools | head -1;
  	cgatools junctiondiff --beta 
  	--reference $crr.fields.path 
  	--junctionsA $data_sources.inputA 
  	--junctionsB $data_sources.inputB 
  	--scoreThresholdA $scoreA
  	--scoreThresholdB $scoreB
  	--distance $distance
  	--minlength $minlength
    $stat  
  	--output-prefix cg_ 
  	;
  	mv cg_diff-*tsv cg_diff.tsv
  </command>

  <outputs>
  	<data format="tabular" name="output1" from_work_dir="cg_diff.tsv" label="${tool.name} on ${on_string}: diff"/>
		<data format="tabular" name="output2" from_work_dir="cg_report.tsv" label="${tool.name} on ${on_string}: report">
			<filter>(stat == '--statout')</filter>
		</data>
  </outputs>
  
  <inputs>
		<!--form field to select crr file-->
		<param name="crr" type="select" label="Reference genome (.crr file)">
			<options from_data_table="cg_crr_files" />
		</param>
	
		<!--conditional to select variant file input-->
  	<conditional name="data_sources">
      <param name="data_source" type="select" label="Where are the input junction files?">
        <option value="in" selected="true">imported into Galaxy</option>
        <option value="out">located outside Galaxy (available only for local Galaxy instances)</option>
      </param>
      <when value="in">
				<!--form field to select variant files-->
				<param name="inputA" type="data" format="tabluar" label="Junction file A">
					<validator type="unspecified_build" />
					<validator type="dataset_metadata_in_file" filename="cg_crr_files.loc"
					 metadata_name="dbkey" metadata_column="1"
					 message="cgatools is not currently available for this build."/>
				</param>
				<param name="inputB" type="data" format="tabluar" label="Junction file B">
					<validator type="unspecified_build" />
					<validator type="dataset_metadata_in_file" filename="cg_crr_files.loc"
					 metadata_name="dbkey" metadata_column="1"
					 message="cgatools is not currently available for this build."/>
				</param>
			</when>
      <when value="out">
				<!--form field to enter external input files-->
				<param name="inputA" type="text" label="Junction file A (/path/junction_file)" size="40" help="e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01_2000/ASM/SV/allJunctionsBeta-GS00000YYYY-ASM.tsv"/>
				<param name="inputB" type="text" label="Junction file B (/path/junction_file)" size="40" help="e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01_2000/ASM/SV/allJunctionsBeta-GS00000YYYY-ASM.tsv"/>
			</when>
		</conditional>
		
		<!--form field to select stats output-->
		<param name="stat" type="select" label="Print input file stats">
			<option value="">no</option>
			<option value="--statout">yes</option>
		</param>

		<param name="scoreA" type="integer" label="Score threshold value for input file A (default 10)" value="10"/>
		<param name="scoreB" type="integer" label="Score threshold value for input file B (default 0)" value="0"/>
		<param name="distance" type="integer" label="Max distance between coordinates of potentially compatible junctions (default 200)" value="200"/>
		<param name="minlength" type="integer" label="Minimum deletion junction length to be included into the difference file (default 500)" value="500"/>
  </inputs>


  <help>
  
**What it does**

This tool reports difference between junction calls of Complete Genomics junctions files

**cgatools 1.5.0 Documentation**

Userguide: http://cgatools.sourceforge.net/docs/1.5.0/cgatools-user-guide.pdf

Release notes: http://cgatools.sourceforge.net/docs/1.5.0/cgatools-release-notes.pdf

**Command line reference**::

		COMMAND NAME
		  junctiondiff - Reports difference between junction calls of Complete Genomics junctions files.
		
		DESCRIPTION
		  junctiondiff takes two junction files A and B as input and produces the 
		  following output:
		    - "diff-inputFileName" - the junctions from an input file A that are not 
		      present in input file B.
		    - "report.txt" - a brief summary report (if --statout is used)
				
		  Two junctions are considered equivalent if:
		    - they come from different files
		    - left and right positions of one junction are not more than "--distance"
		      bases apart from the corresponding positions of another junction
		    - the junction scores are equal or above the scoreThreshold
		    - they are on the same strands
		
		OPTIONS
		  -h [ --help ] 
		      Print this help message.
		
		  --beta 
		      This is a beta command. To run this command, you must pass the --beta 
		      flag.
		
		  -s [ --reference ] arg
		      Reference file.
		
		  -a [ --junctionsA ] arg
		      input junction file A.
		
		  -b [ --junctionsB ] arg
		      input junction file B.
		
		  -A [ --scoreThresholdA ] arg (=10)
		      score threshold value for the input file A.
		
		  -B [ --scoreThresholdB ] arg (=0)
		      score threshold value for the input file B.
		
		  -d [ --distance ] arg (=200)
		      Max distance between coordinates of potentially compatible junctions.
		
		  -l [ --minlength ] arg (=500)
		      Minimum deletion junction length to be included into the difference 
		      file.
		
		  -o [ --output-prefix ] arg
		      The path prefix for all the output reports.
		
		  -S [ --statout ] 
		      (Debug) Report various input file statistics. Experimental feature.
		
		SUPPORTED FORMAT_VERSION
		  1.5 or later
  </help>
</tool>