annotate kmc_tools_filter.xml @ 3:87ddc8ca7859 draft default tip

planemo upload for repository https://github.com/usegalaxy-au/tools-au/tree/master/tools/kmc commit 3be367228b531c346c10700f07d57ae44394be36-dirty

<tool id="kmc_filter" name="KMC filter" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>filtering KMC's database</description>
    <xrefs>
        <xref type='bio.tools'>kmc</xref>
    </xrefs>
    <macros>
	  <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <expand macro="version_command" /> 
    <command><![CDATA[
	    #for $f in $input_collection:
	    	#if '.kmc_suf' in str($f.element_identifier)
	    	    ln -s '${f}' db.kmc_suf &&
	        #else
	    	    ln -s '${f}' db.kmc_pre &&
	        #end if
	    #end for
	    kmc_tools 
	      filter
	      -t\${GALAXY_SLOTS:-2}
              #if $t:
                  '$t'
              #end if
              #if $hm:
                  '$hm'
              #end if
              db
              -ci'$min_kmer_occurrence'
	      -cx'$max_kmer_occurrence'
	      $input_read_file
              -f'$input_format'
              -ci'$exclude_length'
	      -cx'$exclude_kmer_occurence'
	      #if str($output_format) == 'q':
	         $filter_output_fastq
	      #else
		 $filter_output_fasta
	      #end if
              -f'$output_format'

	    ]]></command>
    <inputs>
	    <param name="input_collection" type="data_collection" collection_type="list" label="KMC db"/>
	    <param name="input_read_file" type="data" format="fastq,fasta" label="input read file" help="Input file format FASTQ/FASTA [default:FASTQ]"/>
            <expand macro="input_option"/>
            <param name="input_format" argument="-f" type="select" label="input read file format [default:FASTQ]">
                   <option value="q" selected="true">FASTQ</option>
                   <option value="a">FASTA</option>
            </param>
            <param argument="-t" type="boolean" truevalue="-t" falsevalue="" checked="false" label="trim reads" help="trim reads on first invalid k-mer instead of remove entirely"/>
            <param argument="-hm" type="boolean" truevalue="-hm" falsevalue="" checked="false" label="hard mask" help="hard mask invalid k-mers in a read"/>
            <expand macro="general_option"/>
            <param name="output_format" argument="-f" type="select" label="output read file format [default:FASTQ]">
                   <option value="q" selected="true">FASTQ</option>
                   <option value="a">FASTA</option>
            </param>
    </inputs>
    <outputs>
	    <data name="filter_output_fastq" format="fastq" label="${tool.name} on ${on_string}: filter">
		    <filter>'q' in output_format</filter>
	    </data>
	    <data name="filter_output_fasta" format="fasta" label="${tool.name} on ${on_string}: filter">
                    <filter>'a' in output_format</filter>
            </data>

    </outputs>
	
    <tests>
	 <test>
	     <!-- #1 test with common parameters -->
            <param name="input_collection">
                <collection type="list">
                    <element name="db.kmc_pre" value="filtered_kmers1.kmc_pre" dbkey="89"/>
                    <element name="db.kmc_suf" value="filtered_kmers1.kmc_suf" dbkey="89"/>
                </collection>
            </param>
	    <param name="input_read_file" value="Illumina.1.fastq" ftype="fastq"/>
            <param name="min_kmer_occurrence" value="3" />
            <param name="exclude_length" value="2" />
            <param name="exclude_kmer_occurence" value="10" />
            <output name="filtered_1.fastq" file="filtered_1.fastq" ftype="fastq" />
        </test>
         <test>
             <!-- #2 test with common parameters -->
            <param name="input_collection">
                <collection type="list">
                    <element name="db.kmc_pre" value="filtered_kmers2.kmc_pre" dbkey="89"/>
		    <element name="db.kmc_suf" value="filtered_kmers2.kmc_suf" dbkey="89"/>
                </collection>
            </param>
            <param name="input_read_file" value="Illumina.2.fastq" ftype="fastq"/>
            <param name="exclude_length" value="10" />
            <param name="exclude_kmer_occurence" value="100" />
            <output name="filtered_2.fastq" file="filtered_2.fastq" ftype="fastq" />
        </test>

    </tests>
    <help><![CDATA[

.. class:: infomark

**What it does**
	    
*K-mer Counter is a utility designed for counting k-mers (sequences of consecutive k symbols) in a set of reads from genome sequencing projects.*
	    
**Input**
	    
- input file - FASTA, FASTQ and BAM. Also, gipped versions of FASTA and FASTQ. 

**Command line Example:**

- kmc_tools filter kmc_db -ci3 input.fastq -ci0.5 -cx1.0 filtered_1.fastq
- kmc_tools filter kmc_db input.fastq -ci10 -cx100 filtered_2.fastq

**Output**

- filtered_1.fastq
- filtered_2.fastq

 
.. class:: infomark
	    
**References**

More information are available on `website <http://sun.aei.polsl.pl/REFRESH/index.php?page=projects&project=kmc&subpage=about>`_.
	]]></help>
     <citations>
        <citation type="doi">DOI: 10.1093/bioinformatics/btx304</citation>
	<citation type="doi">DOI: 10.1093/bioinformatics/btv022</citation>
	<citation type="doi">DOI: 10.1186/1471-2105-14-160</citation>
    </citations>
</tool>