annotate kmc.xml @ 1:c7fda6e88567 draft

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

<tool id="kmc" name="KMC Counter" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>K-mer counting and filtering of reads</description>
    <macros>
          <import>macros.xml</import>
    </macros>
    <xrefs>
        <xref type='bio.tools'>kmc</xref>
    </xrefs> 
    <expand macro="requirements" />
    <expand macro="stdio" />
    <expand macro="version_command" /> 
    <command><![CDATA[
          mkdir output &&
	  #if $data_type.select == 'individual'
	    #for $input_file in $data_type.individual_file
	     #if $input_file.is_of_type("fastq","fastq.gz","fastqsanger.gz"):
                #if $input_file.ext.endswith(".gz")
                    #set $ext='.fastq.gz'
                #else
                    #set $ext='.fastq'
                #end if
                ln -s '$input_file' 'in$ext' &&
            #elif $input_file.is_of_type("fasta","fasta.gz"):
                #if $input_file.ext.endswith(".gz")
                   #set $ext='.fasta.gz'
                #else
                   #set $ext='.fasta'
                #end if
                ln -s '$input_file' 'in$ext' &&
            #elif $input_file.is_of_type("bam"):
                ln -s '$input_file' in.bam &&
            #elif $input_file.is_of_type("kmc_suf"):
                #if $input_file.ext.endswith(".kmc_suf")
                    #set $suf_ext='.kmc_suf'
                #end if
                #if $input_file.ext.endswith(".kmc_pre")
                    #set $pre_ext='.kmc_pre'
                #end if
                ln -s '$input_file' 'in$suf_ext' &&
                ln -s '$input_file' 'in$pre_ext' &&
	    #end if
	    #end for
	  #else    
	    	mkdir input_dir &&
		#import re
	    	#for $input_file in $data_type.collection_file
		  #if $input_file.is_of_type("fastq","fastq.gz","fastqsanger.gz"):
                     #if $input_file.ext.endswith(".gz")
                        #set $ext='.fastq.gz'
                     #else
                        #set $ext='.fastq'
                     #end if
        	     #set $identifier = re.sub('[^\s\w\-\\.]', '_', str($input_file.element_identifier))
	    	     ln -s '$input_file' 'input_dir/${identifier}' &&
		  #elif $input_file.is_of_type("fasta","fasta.gz"):
	    	     #if $input_file.ext.endswith(".gz")
	    	     	#set $ext='.fasta.gz'
	    	     #else
	    		#set $ext='.fasta'
	    	     #end if
	    	     #set $identifier = re.sub('[^\s\w\-\\.]', '_', str($input_file.element_identifier))
	    	     ln -s '$input_file' 'input_dir/${identifier}' &&
	    	  #elif $input_file.is_of_type("bam"):
	    	     #set $identifier = re.sub('[^\s\w\-\\.]', '_', str($input_file.element_identifier))
	    	     ln -s '$input_file' 'input_dir/${identifier}' &&
		  #elif $input_file.is_of_type("kmc_suf"):
	    	     #if $input_file.ext.endswith(".kmc_suf")
	    		#set $suf_ext='.kmc_suf'
	    	     #end if
	    	     #if $input_file.ext.endswith(".kmc_pre")
	    		#set $pre_ext='.kmc_pre'
	    	     #end if
	    	     #set $identifier = re.sub('[^\s\w\-\\.]', '_', str($input_file.element_identifier))
	    	     ln -s '$input_file' 'input_dir/${identifier}' &&
	    	     ln -s '$input_file' 'input_dir/${identifier}' &&
		  #end if
	    	#end for
	    	ls -ld input_dir/* | awk '{print $9}' >> files.list &&
	   #end if

	   kmc
	    -t\${GALAXY_SLOTS:-4}
	    #if $params.k:
	    	-k'$params.k'		
	    #end if
	    -m\${GALAXY_MEMORY_GB:-4}
	    #if $params.j:
	       -j'$statistic'
	    #end if
	    #if $params.p:
	       -p'$params.p'
	    #end if
	    #if $params.ci:
	       -ci'$params.ci'
	    #end if
	    #if $params.cs:
	       -cs'$params.cs'
	    #end if
	    #if $params.cx:
	       -cx'$params.cx'
	    #end if
            #if $input_file.is_of_type("fastq","fastq.gz","fastqsanger.gz"):
	    	-fq
	    #elif $input_file.is_of_type("fasta","fasta.gz"):
	    	#if $data_type.select == "individual":
	    	    -fa
	    	#else
	    	    -fm
	    	#end if
            #elif $input_file.is_of_type("bam"):
	    	-fbam 
            #elif $input_file.is_of_type("kmc_suf"):
	    	-fkmc
	    #end if

	    #if $input_file.is_of_type('fastq.gz','fasta.gz','fastqsanger.gz'):
                -f
            #end if

	    #if $data_type.select == 'individual'
	    	#if $input_file.is_of_type("fastq","fastq.gz","fastqsanger.gz"):
	    	    #if $input_file.ext.endswith(".gz")
		    	in.fastq.gz
	    	    #else
		    	in.fastq
	    	    #end if
	    	#elif $input_file.is_of_type("fasta","fasta.gz"):
	    	    #if $input_file.ext.endswith(".gz")
		        in.fasta.gz
	            #else
	    	    	in.fasta
		    #end if
	    	#elif $input_file.is_of_type("bam"):
	    	     in.bam
	    	#end if
	     #else
	       @files.list
	     #end if
	     output/kmer_"$params.k"
	     .  

	    ]]></command>
    <inputs>
	    <expand macro="macro_input" />
	    <section name="params" title="parameter" expanded="false">
                    <param argument="-k" type="integer" value="25" label="k-mer length (k from 1 to 256; default: 25)" />
		    <param argument="-p" type="integer" value="9" label="signature length (5, 6, 7, 8, 9, 10, 11); default: 9"/>
		    <param argument="-ci" type="integer" value="2" label="exclude k-mers occurring less than [value] times (default: 2)"/>
		    <param argument="-cs" type="integer" value="255" label="maximal value of a counter (default: 255)"/>
		    <param argument="-cx" type="integer" value="1000000000" label="xclude k-mers occurring more of than [value] times (default: 1e9)"/>
		    <param argument="-j" type="boolean" truevalue="-j" falsevalue="" checked="True" label="file name with execution summary in JSON format"/>
	    </section>
    </inputs>
    <outputs>
	  <data name="statistic" format="json" label="${tool.name} on ${on_string}">
		 <filter>params['j']</filter>
	  </data>
	  <collection name="kmc_db" type="list" label="${tool.name} on ${on_string}: kmc db">
		<discover_datasets pattern="(?P&lt;designation&gt;.+)" directory="output" format="binary" />
	  </collection>
    </outputs>
    <tests>
        <test expect_num_outputs="2">
            <!-- #1 test individual fasta file -->
            <param name="individual_file" value="test.fasta.gz" ftype="fasta.gz"/>
            <param name="k" value="27" />
            <param name="ci" value="2" />
            <param name="cs" value="255" />
            <output_collection name="kmc_db" type="list">
                <element name="kmer_27.kmc_pre" file="kmer_27.kmc_pre" ftype="binary" />
                <element name="kmer_27.kmc_suf" file="kmer_27.kmc_suf" ftype="binary" />
            </output_collection>
            <output name="statistic" ftype="json">
                    <assert_contents>
                        <has_text text="1st_stage"/>
                        <has_text text="2nd_stage"/>
                        <has_text text="Stats"/>
                    </assert_contents>
            </output>
        </test>
	 <!-- output file is too large for testing; comment out to test on local machine with update_test_data option -->   
	 <!--  <test expect_num_outputs="2"> -->
            <!-- #2 test individual fastq file -->
	 <!--   <param name="individual_file" value="filtered_1.fastq" ftype="fastq"/>
            <param name="k" value="25" />
	    <param name="p" value="9" />
	    <param name="ci" value="2" />
	    <param name="cs" value="255" />
	    <output_collection name="kmc_db" type="list">
	    	<element name="kmer_25.kmc_pre" file="kmer_25.kmc_pre" ftype="binary" />
	    	<element name="kmer_25.kmc_suf" file="kmer_25.kmc_suf" ftype="binary" />
	    </output_collection>
	     <output name="statistic" ftype="json">
		 <assert_contents>
                      <has_text text="1st_stage"/>
                      <has_text text="2nd_stage"/>
                      <has_text text="Stats"/>
		 </assert_contents>				 
	    </output>
    	</test> -->
	<!-- output file is too large for testing; comment out to test on local machine -->
        <!-- <test expect_num_outputs="2"> -->
            <!-- #3 test collection fastq with common parameters -->
        <!--    <param name="k" value="29" />
            <param name="m" value="12" />
            <param name="p" value="9" />
            <param name="ci" value="2" />
            <param name="cs" value="255" />
            <conditional name="data_type">
              <param name="select" value="collection"/>
                <param name="collection_file">
                 <collection type="list">
                     <element name="filtered_1.fastq" value="filtered_1.fastq" ftype="fastq"/>
                     <element name="filtered_2.fastq" value="filtered_2.fastq" ftype="fastq"/>
                 </collection>
                </param>
            </conditional>
            <output_collection name="kmc_db">
                <element name="kmer_29.kmc_suf" file="kmer_29.kmc_suf" ftype="binary" />
                <element name="kmer_29.kmc_pre" file="kmer_29.kmc_pre" ftype="binary" />
            </output_collection>
	    <output name="statistic" ftype="json">
                    <assert_contents>
                        <has_text text="1st_stage"/>
                        <has_text text="2nd_stage"/>
                        <has_text text="Stats"/>
                    </assert_contents>
            </output>
    	</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. 

**Example:**

- kmc -k27 -m24 NA19238.fastq NA.res /data/kmc_tmp_dir/
- kmc -k27 -m24 @files.lst NA.res /data/kmc_tmp_dir/

**Output**

- filename.res.kmc_suf
- filename.res.kmc_pre

 
.. 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>