<tool id="1_create_conf" name="1_create_conf" version="0.1"> 
    <description> : Create configuration file and chromosome tab file for Scaffremodler</description>  
    <stdio>
        <exit_code range="1:" />
    </stdio>
    <command>
		source $__tool_directory__/include_scaffremodler.sh ;
        python $__tool_directory__/1_create_conf.py
		--tool $tool
        #if str($reference_genome.source) == "history":
            --ref $reference_genome.own_file  
        #else:
            --ref $reference_genome.genome.fields.path
        #end if 
		--q1 $q1
		--q2 $q2
		--orient $orient
		--qual $qual
		--mini $mini
		--maxi $maxi
		--index $index
		--rmindex $rmindex
		--mini_dis $mini_dis
		--mult_max_cov $mult_max_cov
		--mult_min_cov $mult_min_cov
		--min_zone $min_zone
		--min_gap $min_gap
		--thread $thread
		--msd $msd
		--max_dist_merge $max_dist_merge
		--YiS $YiS
		--MiS $MiS
		--YiC $YiC
		--MiC $MiC
		--min_score $min_score
		--ploid $ploid
		--restimate $restimate 
		--output $config_file
		--chr $chromosome_information
		
    </command>
    <inputs>
		<param name="tool" type="select" label="Mapping tool">
			<option selected="true" value="bowtie2_single">bowtie2_single</option>
			<option value="bowtie">bowtie</option>
			<option value="bowtie2">bowtie2</option>
			<option value="bwa">bwa</option>
			<option value="bwa_mem">bwa_mem</option>
		</param>
		
        <conditional name="reference_genome">
        	<param name="source" 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. See `Indexes` section of help below">
            	<option value="indexed">Use a built-in genome index</option>
            	<option value="history">Use a genome from the history and build index</option>
          	</param>
          	<when value="indexed">
            	<param name="genome" type="select" label="Select reference genome" help="If your genome of interest is not listed, contact the South Green team">
					
					<options from_data_table="scaffremodler">
						<filter type="sort_by" column="1"/>
						<validator type="no_options" message="No indexes are available for the selected input dataset"/>
					</options> 
            	</param>
          	</when>
          	<when value="history">
            	<param name="own_file" type="data" format="fasta"  label="Select reference genome" />
          	</when>
        </conditional>		 
		<param name="q1" type="data" format="fastq,fastqsanger" label="Mate1 fastq file" />
		<param name="q2" type="data" format="fastq,fastqsanger" label="Mate2 fastq file" />
		<param name="orient" type="select" label="The upstream/downstream mate orientation for valid paired-end alignment against the forward reference strand">
			<option value="rf">RF</option>
			<option value="fr">FR</option>
		</param>
		<param name="qual" type="select" label="Fastq file quality encoding 33 or 64">
			<option selected="true" value="33">33</option>
			<option value="64">64</option>
		</param>
    	<param name="mini" type="integer" value="2500" label="minimum good fragment length" />
    	<param name="maxi" type="integer" value="7500" label="maximum good fragment length" />
		<param name="index" type="select" label="Create index if reference not indexed">
			<option selected="true" value="y">y</option>
			<option value="n">n</option>
		</param>
		<param name="rmindex" type="select" label="Remove index">
			<option selected="true" value="y">y</option>
			<option value="n">n</option>
		</param>
		<param name="mini_dis" type="integer" value="10000" label="Minimal distance between mate to keep discordant mate (should be higher than 2 fold expected insert)" />
		<param name="mult_max_cov" type="float" value="10" label="Multiplicator of median coverage for maximal median coverage to keep a zone" />
		<param name="mult_min_cov" type="float" value="0.25" label="Multiplicator of median coverage for maximal median coverage to keep a zone" />
		<param name="min_zone" type="integer" value="500" label="Minimal number of covered sites in a zone to be considered" />
		<param name="min_gap" type="integer" value="300" label="Maximal number of contiguous uncovered sites in a zone to be considered as a single zone" />
		<param name="thread" type="integer" value="1" label="Thread number used for mapping" />
		<param name="msd" type="float" value="3" label="Multiplicator of standard deviation for discordant zone identification" />
		<param name="max_dist_merge" type="float" value="1000" label="Maximal distance between two discordant zone to merge" />
		<param name="YiS" type="float" value="0" label="Y-intercept of the linear function for zone size that will give the first component of product giving the score" />
		<param name="MiS" type="float" value="0.5" label="Multiplicator of median insert size for calculating minimal zone size for which the first component of product giving the score will be maximal" />
		<param name="YiC" type="float" value="0" label="Y-intercept of the linear function for coverage that will give the second component of product giving the score" />
		<param name="MiC" type="float" value="0.25" label="Multiplicator of median coverage for calculating  minimal zone coverage for which the second component of product giving the score will be maximal" />
		<param name="min_score" type="integer" value="70" label="minimal score for a discordant zone to be identified as passed (0 to 100)" />
		<param name="ploid" type="float" value="0.66" label="Multiplicator for coverage variation detection in SV identification (ex : If homozygous duplication expected in diploid: expected = coverage + coverage*1; if heterozygous duplication expected in diploid => expected = coverage + coverage*0.5). Choose a value lower than the expected one" />
		<param name="restimate" type="select" label="Re-estimate --mini and --maxi parameters">
			<option selected="true" value="y">y</option>
			<option value="n">n</option>
		</param>  
    </inputs>
    <outputs>
        <data format="txt" name="config_file" label="${tool.name} : Configuration file" />
        <data format="data" name="chromosome_information" label="${tool.name} : Chromosome information" />
    </outputs>
    <tests>
        <test>
            <param name="q1" value="reads_mate1_SV.fq"/>
            <param name="q2" value="reads_mate2_SV.fq"/>
			<param name="orient" value="rf"/>
			<param name="index" value="y"/>
			<param name="rmindex" value="y"/>
            <param name="source" value="history" />
            <param name="own_file" value="Ref_for_SV_detection.fasta" />
            <output name="config_file" file="config_file.txt" compare="sim_size"/>  
            <output name="chromosome_information" file="chromosome_information.txt"/> 
        </test>
    </tests>
    <help>
    
**Overview**

This program generate a configuration file that will be used by all other programs that begin with a number.

-----

.. class:: infomark

**Galaxy integration** Martin Guillaume (CIRAD), Droc Gaetan (CIRAD).

.. class:: infomark

**Support** For any questions about Galaxy integration, please send an e-mail to galaxy-dev-southgreen@cirad.fr

.. class:: infomark

**Program encapsulated in Galaxy by South Green**

	</help>
	<citations>
        <citation type="doi">10.1186/s12864-016-2579-4</citation> 
    </citations>
</tool>