<tool id="segemehl" name="segemehl" version="0.2.0.3">
  <description>short read mapping with gaps</description>
  <requirements>
    <requirement type="package" version="0.2.0">segemehl</requirement>
  </requirements>
  <stdio>
    <regex match="Exit forced"
           source="both"
           level="fatal"
           description="Execution halted." />
  </stdio>
  <command>
    <![CDATA[
        ## prepare segemehl index if no reference genome is supplied
        #if $refGenomeSource.genomeSource == "history":
            mkdir ./temp_index/ &&
            #set $temp_index = './temp_index/temp.idx'
            segemehl.x -x $temp_index -d $refGenomeSource.own_reference_genome &&
        #else:
            #set $temp_index = $refGenomeSource.index.fields.index_path
        #end if
        
        ## execute segemehl
            segemehl.x
        
        ## number of threads
            -t "\${GALAXY_SLOTS:-12}"
        
        #if $refGenomeSource.genomeSource == "history":
            -d $refGenomeSource.own_reference_genome
        #else:
            -d ${refGenomeSource.index.fields.db_path}
        #end if
        
        -i $temp_index
        
        ## check for single/pair-end
        #if str( $library.type ) == "single":
            #set $query_list = list()
        ## prepare inputs
        #for $fastq in $library.input_query:
            $query_list.append('%s' % $fastq )
        #end for
        -q "#echo ' '.join( $query_list )#"
        #else
            ## prepare inputs        
            #set $mate1 = list()
            #set $mate2 = list()
            #for $mate_pair in $library.mate_list:
                $mate1.append( str($mate_pair.first_strand_query) )
                $mate2.append( str($mate_pair.second_strand_query) )
            #end for
        
            -q #echo ','.join($mate1)
            -p #echo ','.join($mate2)
        
            -I $library.maxinsertsize
        #end if
        -m $minsize
        -A $accuracy
        -H $hitstrategy
        #if str( $prime5 ).strip():
            -P "$prime5"
        #end if
        #if str( $prime3 ).strip():
            -Q "$prime3"
        #end if
            $polyA
            $autoclip
            $hardclip
            $order
        #if $maxout:
            --maxout $maxout
        #end if
        #if str( $splitreads.splits ) == "splits":
            --splits
            --minsplicecover $splitreads.minsplicecover
            --minfragscore $splitreads.minfragscore
            --minfraglen $splitreads.minfraglen
            --splicescorescale $splitreads.splicescorescale
        #end if
        -M $maxinterval
        -E $evalue
        -D $differences
        -s
        -o '$segemehl_out'
    ]]>
  </command>
  <inputs>
    <conditional name="refGenomeSource">
      <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options">
        <option value="indexed">Use a built-in index</option>
        <option value="history">Use one from the history</option>
      </param>
      <when value="indexed">
        <param name="index" type="select" label="Select a reference genome" help="If your genome of interest is not listed, contact your Galaxy admin">
          <options from_data_table="segemehl_indexes">
            <column name="value" index="0"/>
            <column name="dbkey" index="1"/>
            <column name="name" index="2"/>
            <column name="db_path" index="3"/>
            <column name="index_path" index="4"/>
            <filter type="sort_by" column="2"/>
            <validator type="no_options" message="No indexes are available for the selected input dataset"/>
          </options>
        </param>
      </when>  <!-- build-in -->
      <when value="history">
        <param name="own_reference_genome" type="data" format="fasta" label="Select the reference genome" />
      </when>  <!-- history -->
    </conditional>  <!-- refGenomeSource -->

    <conditional name="library">
      <param name="type" type="select" label="Is this library paired-end?">
        <option value="single">Single-end</option>
        <option value="paired">Paired-end</option>
      </param>
      <when value="single">
        <param name="input_query" type="data" multiple="True" format="fastqsanger,fastqillumina,fastq,fasta" label="Reads in FASTQ/FASTA files" />
      </when>
      <when value="paired">
        <!-- ToDo paired coolections -->
        <repeat name="mate_list" title="Paired End Pairs" min="1">
          <param name="first_strand_query" type="data" format="fastqsanger,fastqillumina,fastq,fasta" label="Reads from first strand" />
          <param name="second_strand_query" type="data" format="fastqsanger,fastqillumina,fastq,fasta" label="Reads from second strand" />
        </repeat>
        <param name="maxinsertsize" type="integer" value="5000" label="Maximum size of the inserts (paired end)" help="default: 5000 (-I)" />
      </when>
    </conditional>

    <conditional name="splitreads">
      <param name="splits" type="select" label="Detect split/spliced reads" help="(--splits)">
        <option value="nosplit">No splits</option>
        <option value="splits">Split reads</option>
      </param>
      <when value="splits">
        <param name="minsplicecover" type="integer" value="80" label="Min coverage for spliced transcripts" help="(--minsplicecover)" />
        <param name="minfragscore" type="integer" value="18" label="Min coverage for spliced transcripts" help="(--minfragscore)" />
        <param name="minfraglen" type="integer" value="20" label="Min length of a spliced fragment" help="(--minfraglen)" />
        <param name="splicescorescale" type="float" value="1.0" label="Report spliced alignment with score greater than this scale times the score"
               help="Report only if this value x score is larger than next best spliced alignment (--splicescorescale)" />
        <param name="sevalue" type="float" min="0" value="50.000000" label="max split evalue" help="(--maxsplitevalue)"/>
      </when>
      <when value="nosplit">
      </when>     
    </conditional>
    
    <param name="minsize" type="integer" value="12" min="1" label="Minimum size of queries" help="(-m)" />
    <param name="maxout" type="integer" min="0" value="0" optional="True" 
           label="Maximum number of alignments that will be reported" help="(--maxout)" />
    <param name="accuracy" type="integer" value="85" min="1" max="100" label="Min percentage of matches per read in semi-global alignment" help="(-A)" />
    <param name="hitstrategy" type="select" label="Hits to report?" help="(-H)">
      <option value="1">report only best scoring hits</option>
      <option value="0">report all scoring hits</option>
    </param>
    <param name="prime5" type="text" label="add 5' adapter" help="default: none (-Q)" />
    <param name="prime3" type="text" label="add 3' adapter" help="default: none (-P)"/>
    <param name="polyA" type="boolean" truevalue="--polyA" falsevalue="" checked="false" label="Clip polyA tail" help="(-T)"/>
    <param name="autoclip" type="boolean" truevalue="--autoclip" falsevalue="" checked="false" label="Autoclip unknown 3prime adapter" help="(-Y)"/>
    <param name="hardclip" type="boolean" truevalue="--hardclip" falsevalue="" checked="false" label="Enable hard clipping" help="(-C)"/>
    <param name="order" type="boolean" truevalue="--order" falsevalue="" checked="false" label="Sorts the output by chromsome and position" help="(-O)"/>
    <param name="differences" type="integer" min="0" value="1" label="search seeds initially with n differences" help="(--differences)"/>
    <param name="evalue" type="float" min="0" value="5.000000" label="max evalue" help="(--evalue)"/>
    <param name="maxinterval" type="integer" min="1" value="100" label="maximum width of a suffix array interval, i.e. a query seed will be omitted if it matches more than n times" help="(--maxinterval)"/>
  </inputs>
  <outputs>
    <data format="sam" name="segemehl_out" label="Read alignments on ${on_string}"/>
  </outputs>
  <tests>
    <test>
      <param name="genomeSource" value="history" />
      <param name="own_reference_genome" value="chr1.fa" />
      <param name="library" value="single" />
      <param name="input_query" value="test.fastq" />   
      <param name="splits" value="nosplit" />
      <output name="segemehl_out" file="testmap.sam" lines_diff="2" />
    </test>
    <test>
      <param name="genomeSource" value="history" />
      <param name="own_reference_genome" value="chr1.fa" />
      <param name="library" value="single" />
      <param name="input_query" value="test.fastq" />   
      <param name="splits" value="splits" />
	  <param name="minsplicecover" value="40" />
      <output name="segemehl_out" file="testmap2.sam" lines_diff="2" />
    </test>
  </tests>
  <help>
    <![CDATA[

.. class:: infomark

**What it does**

Segemehl_ is a short read mapper with gaps.

Segemehl_ is a software to map short sequencer reads to reference genomes.
Unlike other methods, segemehl is able to detect not only mismatches but also insertions and deletions.
Furthermore, segemehl is not limited to a specific read length and is able to mapprimer- or polyadenylation contaminated reads correctly.
segemehl implements a matching strategy based on enhanced suffix arrays (ESA). Segemehl_ allows bisulfite sequencing mapping and split read mapping.

.. _Segemehl: http://www.bioinf.uni-leipzig.de/Software/segemehl/


    ]]>
  </help>
  <citations>
    <citation type="doi">10.1371/journal.pcbi.1000502</citation>
  </citations>
</tool>