annotate SMART/galaxy/CompareOverlappingAdapt.xml @ 64:783e6ed4eb66

Minor bug correction. Added casts to str in Galaxy XML files. Also closed the writer in the Python script "changeTagName."

<tool id="CompareOverlappingAdapt" name="compare overlapping">
	<description>Provide the queries that overlap with a reference.</description>  
	<requirements>
		<requirement type="set_environment">PYTHONPATH</requirement>
	</requirements>
	<command interpreter="python">
		../Java/Python/CompareOverlappingAdapt.py -i $formatType.inputFileName1 -f $formatType.FormatInputFileName1 -j $formatType2.inputFileName2 -g $formatType2.FormatInputFileName2 -o $outputFileGff $InvertMatch $NotOverlapping -m $NbOverlap
		#if $OptionDistance.Dist == 'Yes':
			-d $OptionDistance.distance
		#end if
		#if str($OptionCA) == 'Collinear':
			-c 
		#elif str($OptionCA) == 'AntiSense':
			-a
		#end if	
	</command>

	<inputs>
		<conditional name="formatType">
			<param name="FormatInputFileName1" type="select" label="Input Query File Format">
				<option value="bed">bed</option>
				<option value="gff">gff</option>
				<option value="gff2">gff2</option>
				<option value="gff3">gff3</option>
				<option value="sam">sam</option>
				<option value="gtf">gtf</option>
			</param>
			<when value="bed">
				<param name="inputFileName1" format="bed" type="data" label="Input File 1"/>
			</when>
			<when value="gff">
				<param name="inputFileName1" format="gff" type="data" label="Input File 1"/>
			</when>
			<when value="gff2">
				<param name="inputFileName1" format="gff2" type="data" label="Input File 1"/>
			</when>
			<when value="gff3">
				<param name="inputFileName1" format="gff3" type="data" label="Input File 1"/>
			</when>
			<when value="sam">
				<param name="inputFileName1" format="sam" type="data" label="Input File 1"/>
			</when>
			<when value="gtf">
				<param name="inputFileName1" format="gtf" type="data" label="Input File 1"/>
								                        </when>
		</conditional>

		<conditional name="formatType2">
			<param name="FormatInputFileName2" type="select" label="Input Reference File Format">
				<option value="bed">bed</option>
				<option value="gff">gff</option>
				<option value="gff2">gff2</option>
				<option value="gff3">gff3</option>
				<option value="sam">sam</option>
				<option value="gtf">gtf</option>
			</param>
			<when value="bed">
				<param name="inputFileName2" format="bed" type="data" label="Input File 2"/>
			</when>
			<when value="gff">
				<param name="inputFileName2" format="gff" type="data" label="Input File 2"/>
			</when>
			<when value="gff2">
				<param name="inputFileName2" format="gff2" type="data" label="Input File 2"/>
			</when>
			<when value="gff3">
				<param name="inputFileName2" format="gff3" type="data" label="Input File 2"/>
			</when>
			<when value="sam">
				<param name="inputFileName2" format="sam" type="data" label="Input File 2"/>
			</when>
			<when value="gtf">
				<param name="inputFileName2" format="gtf" type="data" label="Input File 2"/>
			</when>
		</conditional>
		<conditional name="OptionDistance">
			<param name="Dist" type="select" label="Maximum Distance between two reads">
				<option value="Yes">Yes</option>
				<option value="No" selected="true">No</option>
			</param>
			<when value="Yes">
				<param name="distance" type="integer" value="0"/>
			</when>
			<when value="No">
			</when>
		</conditional>
		<param name="OptionCA" type="select" label="Collinear or anti-sense features only">
			<option value="Collinear">Collinear</option>
			<option value="AntiSense">AntiSense</option>
			<option value="All" selected="true">All</option>
		</param>
		<param name="InvertMatch" type="boolean" truevalue="-x" falsevalue="" checked="false" label="Invert match: the output file will contain all query elements which do NOT overlap"/>
		<param name="NotOverlapping" type="boolean" truevalue="-O" falsevalue="" checked="false" label="Also report the query data which do not overlap, with the nbOverlaps tag set to 0."/>
		<param name="NbOverlap" type="integer" value="1" label="Min. # of overlapping nt. to declare an overlap."/>
	</inputs>

	<outputs>
		<data name="outputFileGff" format="gff3"/>
	</outputs> 

	<help>
This script may be the most important one. It basically compares two sets of transcripts and keeps those from the first set which overlap with the second one. The first set is considered as the query set (basically, your data) and the second one is the reference set (RefSeq data, for example).
  
It is vital to understand that it will output the elements of the first file which overlap with the elements of the second one.

Various modifiers are also available:

-Invert selection (report those which do not overlap).

-Restrict to collinear / anti-sense overlapping data.

-Keep the query data even if they do not strictly overlap with the reference data, but are located not further away than *n* nucleotide from some reference data.

Some option reverses the selection. Put in other words, it performs the comparison as usual, and outputs all those query data which do not overlap.
	</help>
</tool>