<tool id="vsearch_clustering" name="VSearch clustering" version="@VERSION@.1">
    <description></description>
    <macros>
        <import>vsearch_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <expand macro="version_command" />
    <command>
<![CDATA[
    vsearch
        @GENERAL@
	
	#if $clustering_mode.clustering_mode_select == 'cluster_fast':
            --cluster_fast "$infile"
	#else if $clustering_mode.clustering_mode_select == 'cluster_smallmem':
            --cluster_smallmem "$infile"
        #end if
        ##--clusters STRING            output each cluster to a separate FASTA file

        #if $maxrejects:
            --maxrejects $maxrejects
        #end if
        #if $maxaccepts:
            --maxaccepts $maxaccepts
        #end if

        $cons_truncate
        --id $id
        --iddef $iddef

        #if '--msaout' in str($outputs):
            --msaout $msaout
        #end if
        #if '--consout' in str($outputs):
            --consout $consout
        #end if
        #if '--centroids' in str($outputs):
            --centroids $centroids
        #end if
        #if '--alnout' in str($outputs):
            --alnout $alnout
        #end if
        #if '--blast6out' in str($outputs):
            --blast6out $blast6out
        #end if
        #if '--notmatched' in str($outputs):
            --notmatched $notmatched
        #end if
        #if '--fastapairs' in str($outputs):
            --fastapairs $fastapairs
        #end if
        #if '--matched' in str($outputs):
            --matched $matched
        #end if
        #if $qmask != 'no':
            --qmask $qmask
        #end if
        $sizein
        $sizeout
        --strand $strand
	$usersort
	#if $uc:
            --uc "$uc_outfile"
	#end if

]]>
    </command>
    <inputs>
        <param name="infile" type="data" format="fasta" label="Select your input FASTA file" help="" />
        <conditional name="clustering_mode">
            <param name="clustering_mode_select" type="select" label="Choose sorting method to use before clustering" help="">
                <option value="cluster_fast" default="True">Cluster sequences after sorting by length (--cluster-fast)</option>
                <option value="cluster_smallmem">Cluster already sorted sequences (--cluster-smallmem)</option>
            </param>
            <when value="cluster_fast">
            </when>
            <when value="cluster_smallmem">
          </when>
        </conditional>
        <param name="usersort" type="boolean" truevalue="--usersort" falsevalue="" checked="False" 
            label="Indicate that input sequences are not presorted by length" help="(--usersort)"/>
        <expand macro="id_and_iddef" />
        <param name="cons_truncate" type="boolean" truevalue="--cons_truncate" falsevalue="" checked="False" 
            label="Do not ignore terminal gaps in MSA for consensus" help="(--cons_truncate)"/>
        <expand macro="qmask" />
        <expand macro="sizein" />
        <expand macro="sizeout" />
        <expand macro="strand" />
        <expand macro="maxrejects" />
        <expand macro="maxaccepts" />
        <expand macro="general_output">
            <option value="--msaout">Multiple sequence alignments</option>
            <option value="--consout">Cluster consensus sequences</option>
            <option value="--centroids">Centroid sequences</option>
            <option value="--notmatched">Write non-matching query sequences to separate file</option>
            <option value="--matched">Write matching query sequences to separate file</option>
        </expand>
        <expand macro="uclust_like_output" />

    </inputs>
    <outputs>
        <data name="msaout" format="fasta" label="${tool.name} on ${on_string}: Multiple Sequence Alignments">
            <filter>'--msaout' in outputs</filter>
        </data>
        <data name="consout" format="fasta" label="${tool.name} on ${on_string}: Consensus Sequences">
            <filter>'--consout' in outputs</filter>
        </data>
        <data name="centroids" format="fasta" label="${tool.name} on ${on_string}: Cluster centroids">
            <filter>'--centroids' in outputs</filter>
        </data>
        <data name="alnout" format="fasta" label="${tool.name} on ${on_string}: Alignment">
            <filter>'--alnout' in outputs</filter>
        </data>
        <data name="notmatched" format="fasta" label="${tool.name} on ${on_string}: Non-matched queries">
            <filter>'--notmatched' in outputs</filter>
        </data>
        <data name="matched" format="fasta" label="${tool.name} on ${on_string}: Matching query sequences">
            <filter>'--matched' in outputs</filter>
        </data>
        <data name="blast6out" format="tabular" label="${tool.name} on ${on_string}: BLAST like tabular">
            <filter>'--blast6out' in outputs</filter>
        </data>
        <data name="fastapairs" format="fasta" label="${tool.name} on ${on_string}: Query/Target sequences">
            <filter>'--fastapairs' in outputs</filter>
        </data>
        <data name="uc_outfile" format="tabular" label="${tool.name} on ${on_string}: UCLUST like output">
            <filter>uc is True</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="infile" value="BioMarKs5k.fsa.bz2" ftype="fasta" />
            <param name="id" value="0.99"/>
            <param name="maxaccepts" value="1"/>
            <param name="maxrejects" value="2"/>
            <param name="sizeout" value=""/>
            <param name="outputs" value="--centroids,--alnout,--blast6out,--notmatched" />
            <output name="centroids" file="clustering_centroids_result1.fasta" ftype="fasta" />
            <output name="blast6out" file="clustering_blast6out_result1.tab" ftype="tabular" />
            <output name="notmatched" file="clustering_notmatched_result1.fasta" ftype="fasta" />
            <!-- The result following result files would be too big -->
            <!--output name="matched" file="clustering_matched_result1.fasta" ftype="fasta" /-->
            <!--output name="alnout" file="clustering_alnout_result1.fasta" lines_diff="2" ftype="fasta" /-->
            <!--output name="fastapairs" file="clustering_fastapairs_result1.fasta" ftype="fasta" /-->
            <!--output name="msaout" file="clustering_msaout_result1.fasta" ftype="fasta" /-->
        </test>
        <test>
            <param name="infile" value="BioMarKs5k.fsa.bz2" ftype="fasta" />
            <param name="clustering_mode_select" value="cluster_smallmem"/>
            <param name="usersort" value="--usersort"/>
            <param name="id" value="0.99"/>
            <param name="maxaccepts" value="1"/>
            <param name="maxrejects" value="2"/>
            <param name="sizeout" value="--sizeout"/>
            <param name="outputs" value="--centroids,--blast6out,--notmatched" />
            <output name="centroids" file="clustering_centroids_result2.fasta" ftype="fasta" />
            <output name="blast6out" file="clustering_blast6out_result2.tab" ftype="tabular" />
            <output name="notmatched" file="clustering_notmatched_result2.fasta" ftype="fasta" />
        </test>
	<test>
            <param name="infile" value="BioMarKs5k.fsa.bz2" ftype="fasta" />
            <param name="clustering_mode_select" value="cluster_smallmem"/>
            <param name="usersort" value="--usersort"/>
            <param name="id" value="0.99"/>
            <param name="maxaccepts" value="1"/>
            <param name="maxrejects" value="2"/>
            <param name="sizeout" value="--sizeout"/>
            <param name="outputs" value="--centroids" />
            <param name="uc" value="--uc"/>
            <output name="centroids" file="clustering_centroids_result2.fasta" ftype="fasta" />
            <output name="uc_outfile" file="clustering_uc_result3.uc" ftype="tabular" />
        </test>
	<test>
            <param name="infile" value="BioMarKs5k.fsa.bz2" ftype="fasta" />
            <param name="clustering_mode_select" value="cluster_smallmem"/>
            <param name="usersort" value="--usersort"/>
            <param name="id" value="0.99"/>
            <param name="maxaccepts" value="1"/>
            <param name="maxrejects" value="2"/>
            <param name="sizeout" value="--sizeout"/>
            <param name="outputs" value="--centroids" />
            <param name="iddef" value="0"/>
            <output name="centroids" file="clustering_centroids_result4.fasta" ftype="fasta" />
        </test>
	<test>
            <param name="infile" value="BioMarKs5k.fsa.bz2" ftype="fasta" />
            <param name="clustering_mode_select" value="cluster_fast"/>
            <param name="usersort" value="--usersort"/>
            <param name="id" value="0.99"/>
            <param name="maxaccepts" value="1"/>
            <param name="maxrejects" value="2"/>
            <param name="sizeout" value=""/>
            <param name="outputs" value="--centroids" />
            <param name="qmask" value="none"/>
            <output name="centroids" file="clustering_centroids_result1.fasta" ftype="fasta" />
        </test>
    </tests>
    <help>
<![CDATA[
**What it does**

vsearch implements a single-pass, greedy star-clustering algorithm, similar to the algorithms
implemented in usearch, DNAclust and sumaclust for example.


Clustering options (most searching options also apply)
  --centroids FILENAME         output centroid sequences to FASTA file
  --cluster_fast FILENAME      cluster sequences after sorting by length
  --cluster_size FILENAME      cluster sequences after sorting by abundance
  --cluster_smallmem FILENAME  cluster already sorted sequences (see -usersort)
  --clusters STRING            output each cluster to a separate FASTA file
  --consout FILENAME           output cluster consensus sequences to FASTA file
  --cons_truncate              do not ignore terminal gaps in MSA for consensus
  --id REAL                    reject if identity lower
  --iddef INT                  id definition, 0-4=CD-HIT,all,int,MBL,BLAST (2)
  --msaout FILENAME            output multiple seq. alignments to FASTA file
  --qmask                      seqs with dust, soft or no method (dust)
  --sizein                     propagate abundance annotation from input
  --sizeout                    write cluster abundances to centroid file
  --strand                     cluster using plus or both strands (plus)
  --uc FILENAME                filename for UCLUST-like output
  --usersort                   indicate sequences not presorted by length


@EXTERNAL_DOCUMENTATION@

-------

@REFERENCES@


]]>
    </help>
    <expand macro="citations" />
</tool>