annotate SMART/galaxy/mapperAnalyzer.xml @ 36:44d5973c188c

Uploaded

<tool id="mapperAnalyzer" name="mapper analyzer">
	<description>Read the output of an aligner, print statistics and possibly translate into GFF, BED or GBrowse formats. </description>
	<command interpreter="python">
		../Java/Python/mapperAnalyzer.py -i $formatType.inputFileName1
		#if $formatType.FormatInputFileName1 == 'bed':
			-f bed
		#elif $formatType.FormatInputFileName1 == 'gff3':
			-f gff3	
		#elif $formatType.FormatInputFileName1 == 'sam':
			-f sam
		#elif $formatType.FormatInputFileName1 == 'bam':
			-f bam
		#elif $formatType.FormatInputFileName1 == 'seqmap':
			-f seqmap
		#end if
			
		-q $formatType2.inputFileName2
		#if $formatType2.FormatInputFileName2 == 'fasta':
			-k fasta
		#elif $formatType2.FormatInputFileName2 == 'fastq':
			-k fastq	
		#end if
		

		#if $optionnumber.number == 'Yes':
			-n $optionnumber.numberVal
		#end if
		#if $optionsize.size == 'Yes':
			-s $optionsize.sizeVal
		#end if
		#if $optionidentity.identity == 'Yes':
			-d $optionidentity.identityVal
		#end if
		#if $optionmismatch.mismatch == 'Yes':
			-m $optionmismatch.mismatchVal
		#end if
		#if $optiongap.gap == 'Yes':
			-p $optiongap.gapVal
		#end if		
		#if $optiontitle.title == 'Yes':
			-t $optiontitle.titleVal
		#end if	
		#if $optionappend.append == 'Yes':
			-a $optionappend.appendfile
		#end if	
			
		$merge
		$remove
		$remain
		-o $outputFileGFF
	</command>

	<inputs>
		<conditional name="formatType">
			<param name="FormatInputFileName1" type="select" label="Input File mapping Format">
				<option value="bed">bed</option>
				<option value="gff3">gff3</option>
				<option value="sam">sam</option>
				<option value="bam">bam</option>
				<option value="seqmap" selected="true">seqmap</option>
			</param>
			<when value="bed">
				<param name="inputFileName1" format="bed" type="data" label="Input File"/>
			</when>
			<when value="gff3">
				<param name="inputFileName1" format="gff3" type="data" label="Input File"/>
			</when>
			<when value="sam">
				<param name="inputFileName1" format="sam" type="data" label="Input File"/>
			</when>
			<when value="bam">
				<param name="inputFileName1" format="bam" type="data" label="Input File"/>
			</when>
			<when value="seqmap">
				<param name="inputFileName1" format="seqmap" type="data" label="Input File"/>
			</when>
		</conditional>

		<conditional name="formatType2">
			<param name="FormatInputFileName2" type="select" label="Reference sequence File Format">
				<option value="fasta" selected="true">fasta</option>
				<option value="fastq">fastq</option>
			</param>
			<when value="fasta">
				<param name="inputFileName2" format="fasta" type="data" label="Reference sequence File Format"/>
			</when>
			<when value="fastq">
				<param name="inputFileName2" format="fastq" type="data" label="Reference sequence File Format"/>
			</when>
		</conditional>

		<conditional name="optionnumber">
			<param name="number" type="select" label="max. number of occurrences of a sequence">
					<option value="Yes">Yes</option>
					<option value="No" selected="true">No</option>
			</param>
			<when value="Yes">
				<param name="numberVal" type="integer" value="0"/>
			</when>
			<when value="No">
			</when>
		</conditional>
		
		<conditional name="optionsize">
			<param name="size" type="select" label="minimum pourcentage of size ">
				<option value="Yes">Yes</option>
				<option value="No" selected="true">No</option>
			</param>
			<when value="Yes">
				<param name="sizeVal" type="integer" value="0"/>
			</when>
			<when value="No">
			</when>
		</conditional>

		<conditional name="optionidentity">
			<param name="identity" type="select" label="minimum pourcentage of identity ">
				<option value="Yes">Yes</option>
				<option value="No" selected="true">No</option>
			</param>
			<when value="Yes">
				<param name="identityVal" type="integer" value="0"/>
			</when>
			<when value="No">
			</when>
		</conditional>

		<conditional name="optionmismatch">
			<param name="mismatch" type="select" label="maximum number of mismatches">
					<option value="Yes">Yes</option>
					<option value="No" selected="true">No</option>
			</param>
			<when value="Yes">
				<param name="mismatchVal" type="integer" value="0"/>
			</when>
			<when value="No">
			</when>
		</conditional>

		<conditional name="optiongap">
			<param name="gap" type="select" label="maximum number of gaps">
				<option value="Yes">Yes</option>
				<option value="No" selected="true">No</option>
			</param>
			<when value="Yes">
				<param name="gapVal" type="integer" value="0"/>
			</when>
			<when value="No">
			</when>
		</conditional>

		<conditional name="optiontitle">
			<param name="title" type="select" label="title of the plots ">
					<option value="Yes">Yes</option>
					<option value="No" selected="true">No</option>
			</param>
			<when value="Yes">
				<param name="titleVal" type="text" value="title of the UCSC track" />
			</when>
			<when value="No">
			</when>
		</conditional>
		
		<conditional name="optionappend">
			<param name="append" type="select" label="append to GFF3 file">
					<option value="Yes">Yes</option>
					<option value="No" selected="true">No</option>
			</param>
			<when value="Yes">
				<param name="appendfile" type="data" format="gff3" label="append a file"/>
			</when>
			<when value="No">
			</when>
		</conditional>
		
		<param name="merge" type="boolean" truevalue="-e" falsevalue="" checked="false" label="merge exons when introns are short "/>
		<param name="remove" type="boolean" truevalue="-x" falsevalue="" checked="false" label="remove transcripts when exons are short"/>
		<param name="remain" type="boolean" truevalue="-r" falsevalue="" checked="false" label="print the unmatched sequences "/>
	</inputs>

	<outputs>
		<data name="outputFileGFF" format="gff3" label="[mapperAnalyzer] out file"/>
	</outputs> 
	
	<help>
Maybe the first program you may use. It reads a set of mapping given by the tool you have used to map your data on the reference genome and translate it to a set of genomic coordinates. You also have the possibility to extract only those that you are interested in (few matches in the genome, few errors in the mapping, etc.). You can also select those reads which map less than a given of times in the genome. Moreover, you can output the data in various different formats, which you can use to visualize them *via* UCSC genome browser or GBrowse. Unmatched reads can be written in an other file, in case you would like to try to map them with another tool (may sometimes work!).

You can filter your data according to:

- number of errors in the mapping

- number of occurrences of the mapping in the genome

- size of the read mapped

- number of gaps in the mapping

The script needs an input file (your mapped reads) together with its format and the read sequences file together with its format (FASTA or FASTQ). If you want, you can also append the results of this script to another GFF3 file. This is useful when the GFF3 file is the result of the mapping using another tool.

By default, any gap in the alignment to the reference sequence is treated like an exon. You can decide to remove this feature by merging short introns (actually, gaps).
	</help>
</tool>