view noisy.xml @ 0:ab2cf9c6c4f1 draft

Imported from capsule None

<tool id="noisy" name="Noisy" version="1.5.12.1">
    <description>Cleaning aligned sequences</description>
    <requirements>
        <requirement type="package" version="1.5.12">noisy</requirement>
    </requirements>
    <command><![CDATA[ 
                noisy $input
                
                 #if $sequence.seqtype == 'cfg' :
	                 ## Automatic sequence detection
	                 ## read an info file to choose which option set 
	                 #set $info = open( str($input_info) ).read()
	                 #if 'dna' in $info:
	                        --seqtype D
	                 #else if 'protein' in $info :
	                        --seqtype P
	                 #end if
	                 
                 #else :
                    --seqtype $sequence.seqtype
                 #end if 
                 
                 --cutoff $cutoff
                 --distance $distance
                 #if $usematrix.matrix == "true":
                    --matrix $usematrix.matrixfile
                 #end if
                 #if $missingchar.setmissingchar == "true":
                    --missing $missingchar.chars
                 #end if
                 --ordering
                 #if $orderingmethode.ordering == "rand":
                   RAND[,$orderingmethode.randpermut]
                 #else if $orderingmethode.ordering == "list":
                   $orderingmethode.randpermutlist
                 #else:
                   $orderingmethode.ordering
                 #end if
                 
                 $constant
                 $gap
                 
                 --shuffles $shuffles
                 --smooth $smooth
                 --silent
                 
                 ]]>
    </command>
	<inputs>
		<param name="input" type="data" format="fasta" label="Source file" help="Fasta format" />
		<conditional name="sequence">
			<param name="seqtype" type="select" label="Sequence Coding">
				<option value="D">DNA</option>
				<option value="P">Protein</option>
				<option value="R">RNA</option>
				<option value="cfg">Config file</option>
			</param>
			<when value="D"></when>
			<when value="P"></when>
			<when value="R"></when>
			<when value="auto">
                <param name="input_info" type="data" format="txt" label="info" help="Precompute file containning sequence description (dna or protein)" />
            </when>	
		</conditional>   
		<param name="cutoff" type="float" value="0.8" min="0" max="1" label="cut-off  [ 0-1 ]" help="Columns with a score below FLOAT are removed from the output alignment." />
		<param name="distance" type="select" label="Distance methode used by NeighbotNet">
		    <option value="HAMMING">HAMMING</option>
            <option value="GTR">GTR</option>
        </param>
        <conditional name="usematrix">
         <param name="matrix" type="boolean"  truevalue="true" falsevalue="" checked="False" label="Use matrix file" help="default is calculate distances with nnet"/>
         <when value=""/>
         <when value="true">
            <param name="matrixfile" format="text" type="data" label="matrix file"/>
         </when>
        </conditional>
        <conditional name="missingchar">
            <param name="setmissingchar" type="boolean" truevalue="true" falsevalue="" checked="False" label="Set list of missing chars" />
            <when value=""/>
            <when value="true">
                <param name="chars" type="text" label="Missing chars list"/>
            </when>
        </conditional>
        <conditional name="orderingmethode">
	        <param name="ordering" type="select" display="radio" label="Choose ordering method">
	            <option value="nnet">NeighborNet</option>
	            <option value="qnet">QNet</option>
	            <option value="rand">Sample INT random permutation</option>
	            <option value="list">List of index MSA ordering</option>
	            <option value="all">All permutations</option>
	         </param>
            <when value="nnet"/>
            <when value="qnet"/>
            <option value="all"/>
            <when value="rand">
                <param name="randpermut" type="integer" value="1000" label="random permutation"/>
            </when>
            <when value="list">
                <param name="randpermutlist" type="text" label="Comma-seperated string of INT"/>
            </when>
         </conditional>
         <param name="constant" type="boolean" truevalue="" falsevalue="--noconstant" checked="True" label="Constant columns in output alignment" />
         <param name="gap" type="boolean" truevalue="" falsevalue="--nogap" checked="True" label="Count gap symbol as character state"/>
         <param name="smooth" type="integer" value="1" min="0" max="1000" label="Running average over INT columns" help="Calculate a running average over the reliability score of INT columns and use this smoothed values to remove unreliable columns from the MAS.s" />
         <param name="shuffles" type="integer" value="0" min="0" max="1000" label="Perform INT random shuffles per column of the MSA"/>
	</inputs>
	<outputs>
		<data name="output1" format="fasta" label="Noisy Cleaned sequencies"  from_work_dir="*_out.fas" />
		<data name="output2" format="eps" label="Noisy Cleaned sequencies image"  from_work_dir="*_typ.eps" />
		<data name="output3" format="txt" label="Noisy Cleaned sequencies information"  from_work_dir="*_sta.gr" />
	</outputs>
	<tests>
        <test>
	        <param name="input" value="aln.fasta" />
	        <output name="output1" file="aln_out.fas" />  
        </test>
	</tests>
	
<help>
<![CDATA[ 
Usage::

 noisy [OPTIONS] MultiFastaAlignment

Options::

 --cutoff FLOAT     Set cutoff value to FLOAT. Columns with a score below FLOAT are removed from the output alignment.
                     (default is >0.80<)
 --distance STRING  Distance methode used by NeighbotNet.
                     (default is >HAMMING< [HAMMING|GTR])
 -h, --help         Print usage message for noisy.
 --matrix FILE      Use distance matrix for NeighbotNet from FILE.
                     (default is >calculate distances with nnet<)
 --missing STRING   Set list of missing characters to STRING.
                     (default is >N<)
 --nogap            Don't count gap symbol as character state.
                     (default is >0<)
 --noconstant       Ignore constant columns in output alignment.
                     (default is >0<)
 --ordering STRING
                    Choose ordering method.
                     (default is >nnet<)
                    nnet         NeighborNet
                    qnet         QNet algorithm is O(n^4) both in time and memory, be careful when you use this option.
                    rand[,INT]   sample INT random permutation. With rand a random sample of all possible orderings of the TAXA can be specified for which the reliability score is calculated
                                (default is >1000<)
                    INT,INT,...  provide ordering explicitly as comma-seperated list of TAXA indices in the range (e.g 3,0,4,1,2 as ordering for the 5 TAXA in the input MSA).
                    all          all permutations, If all is used than for all possible permutations of the TAXA the reliability score is calculated (Note that for more than 8 TAXA this can become rather time consuming!).

 --shuffles INT     Perform INT random shuffles per column.
                     (default is >0<)
 -s, --silent       Turn off status bar
                     (default is >0<)
 --smooth INT       Running avarage over INT columns.
                     (default is >1<)
 --seqtype CHAR     Set sequence type of input alignment to CHAR
                     (default is >D<) [D=DNA, P=Protein, R=RNA]
 -v, --verbose      Verbose mode. Causes noisy to print debugging
                    messages about its progress.
]]>
</help>
    <citations>
        <citation type="doi">10.1186/1748-7188-3-7</citation>
        <citation type="doi">10.1093/molbev/msl180</citation>
        <citation type="doi">10.1093/molbev/msh018s</citation>
    </citations>
</tool>