<?xml version="1.0"?>
<tool id="mdust" name="mdust" version="1.0">
	<description>fast and symmetric DUST implementation to mask low-complexity DNA sequences</description>
	 <requirements>
		 <requirement type="package" version="1.0">mdust</requirement>
	 </requirements>
	<command interpreter="python">
		mdust_wrapper.py -i ${input_file} -v ${cutoff} -w ${wsize} -m ${masking_letter.masking_letter_selector} -f ${output_type.output_type_selector}
		
		#if str( $output_type.output_type_selector) == "default"
			-o ${output_masked_fasta}
		#end if

		#if str( $output_type.output_type_selector) == "tab"
			-o ${output_tab}
		#end if

		#if str( $output_type.output_type_selector) == "bed"
			-o ${output_bed}
		#end if
	</command>
	<inputs>
		<param name="input_file" type="data" format="fasta" label="Input fasta file" help=""/>
		<param name="cutoff" type="integer" value="28" label="cutt-off" help="cut-off" />
		<param name="wsize" type="integer" value="3" label="set maximum word size" help="word-size" />
		<conditional name="masking_letter">
			<param name="masking_letter_selector" type="select" label="Choose your masking type" help="Select the masking letter (N,X or lowercase)" >
				<option value="N" selected="True">N (default)</option>
				<option value="X">X</option>
				<option value="L">lowercase</option>
			</param>
		</conditional>
		<conditional name="output_type">
			<param name="output_type_selector" type="select" label="Choose your output type" help="select your output">
				<option value="default" selected="True">masked file (default)</option>
				<option value="tab">output masking coordinates only (tab delimited)</option>
				<option value="bed">output masking coordinates only (bed format)</option>
			</param>
		</conditional>
	</inputs>
	<outputs>
		<data format="fasta" name="output_masked_fasta" label="masked.${input_file.name}">
			<filter>( output_type['output_type_selector'] == 'default' )</filter>
		</data>
		<data format="tabular" name="output_tab" label="${input_file.name}.tab">
			<filter>( output_type['output_type_selector'] == 'tab' )</filter>
		</data>
		<data format="bed" name="output_bed" label="${input_file.name}.bed">
			<filter>( output_type['output_type_selector'] == 'bed' )</filter>
		</data>
	</outputs>
	<tests>
		<test>
			<param name="input_file" value="seq-mdust.fsa" />
			<output name="output_masked_fasta" file="masked-seq-mdust.fsa" ftype="fasta" />
		</test>
	</tests>
	 <help><![CDATA[
mdust new implementation of the DUST module that uses the same function to assign a complexity score to a sequence, but uses a different rule by which high-scoring sequences are masked.

-----

**Usage:** ::

	mdust [<fasta-file>] [-w <wsize>] [-v <cut-off>] [-m N|X|L] [-c] 
	  if no <fasta-file> is given, a multi-fasta stream is expected at stdin
	  -v default <cut-off> value is 28 (lower values might mask more, 
	  but possibly still useful sequence; > 64 will rarely mask poly-triplets)
	  -w set maximum word size to <wsize> (default 3)
	  -m if fasta output is not disabled by -c, set the masking letter type:
	     N ('N', default), X ('X'), L (make lowercase)
	  -c output masking coordinates only: 
	     seq_name, seqlength, mask_start, mask_end  (tab delimited)

-----

**Reference:** ::

  A fast and symmetric DUST implementation to mask low-complexity DNA sequences.
  Morgulis A, Gertz EM, Schäffer AA, Agarwala R.
  J Comput Biol. 2006 Jun;13(5):1028-40.
  PMID:16796549


]]>
	</help>	 
</tool>