view masscomb_fasta_validator.xml @ 6:2864d8797260

new experimental tool

<tool name="Fasta Validator" id="masscomb_fastavalidator" version="1.0.1">
	<description>Basic FASTA file validation</description>
	<!-- 
	   For remote debugging start you listener on port 8000 and use the following as command interpreter:
	       java -jar -Xdebug -Xrunjdwp:transport=dt_socket,address=D0100564.wurnet.nl:8000 
	-->    
	<command interpreter="java -jar">
	    MassComb.jar 
	    -action FASTAVALIDATOR 
	    -fastaFile $inputFile 
	    -outputFile $outputFile 
	    -expressions "$expressions"
	    -maxLengthSequenceLine $maxLengthSequenceLine
	    </command>
<inputs>
	<param name="inputFile" type="data" format="" label="Fasta file to validate"/>
    
	<param name="expressions" type="select" display="checkboxes" multiple="true" label="Error patterns to search for in each line" help="">
      	<option value="description=White space in SEQUENCE;regex=^[a-zA-Z]+SLASHs[a-zA-Z]">White space in SEQUENCE (^[a-zA-Z]+\s[a-zA-Z])</option>
      	<option value="description=Numbers in SEQUENCE;regex=^[0-9]PIPE^[a-zA-Z]+.*[0-9]">Numbers in SEQUENCE (^[0-9]|^[a-zA-Z]+.*[0-9])</option>
      	<option value="description=Line starting with white space followed by alpha numeric characters;regex=^SLASHs[a-zA-Z0-9]+">Line starting with white space followed by alpha numeric characters (^\s[a-zA-Z0-9]+)</option>
      	<option value="description=Line ending with white space;regex=.*SLASHsDOLLAR">Line ending with white space (.*\s$)</option>
      	<option value="description=Sequence lines with non-Amino Acid characters;regex=(^[SLASHwAMPAMP[^ARNDCEQGHILKMFPSTWYV]])PIPE(^[ARNDCEQGHILKMFPSTWYV]+[SLASHwAMPAMP[^ARNDCEQGHILKMFPSTWYV]]+)">Sequence lines with non-Amino Acid characters ((^[\w&amp;&amp;[^ARNDCEQGHILKMFPSTWYV]])|(^[ARNDCEQGHILKMFPSTWYV]+[\w&amp;&amp;[^ARNDCEQGHILKMFPSTWYV]]+))</option>
      	<option value="description=Hyphen in accession numbers;regex=^SLASHS*-">Hyphen in accession numbers (^\S*-)</option>
      	<option value="description=Lines with stretches of X;regex=XX+">Lines with stretches of X (XX+)</option>
    </param>

	<param name="maxLengthSequenceLine" type="integer" size="10" value="0" label="Max length sequence line " 
	help="(Optional) the maximum line width in the protein sequence part. Leave to 0 (zero) for no restrictions "/>

</inputs>
<outputs>
	<data format="txt" name="outputFile" />
</outputs>
<tests>
	<test>
	</test>
</tests>
<help>

</help>
</tool>