<tool id="shm_csr" name="SHM &amp; CSR pipeline" version="1.0">
	<description></description>
	<command interpreter="bash">
		wrapper.sh $in_file custom $out_file $out_file.files_path ${in_file.name} "-" $functionality $unique $naive_output_ca $naive_output_cg $naive_output_cm $naive_output_ce $filter_uniques $class_filter $empty_region_filter $fast
	</command>
	<inputs>
		<param name="in_file" type="data" label="IMGT zip file to be analysed" />
		<param name="empty_region_filter" type="select" label="Sequence starts at" help="" >
			<option value="leader" selected="true">Leader: include FR1, CDR1, FR2, CDR2, FR3 in filters</option>
			<option value="FR1" selected="true">FR1: include CDR1,FR2,CDR2,FR3 in filters</option>
			<option value="CDR1">CDR1: include FR2,CDR2,FR3 in filters</option>
			<option value="FR2">FR2: include CDR2,FR3 in filters</option>
		</param>
		<param name="functionality" type="select" label="Functionality filter" help="" >
			<option value="productive" selected="true">Productive (Productive and Productive see comment)</option>
			<option value="unproductive">Unproductive (Unproductive and Unproductive see comment)</option>
			<option value="remove_unknown">Productive and Unproductive (Productive, Productive see comment, Unproductive, Unproductive and Unproductive see comment)</option>
		</param>
		<param name="filter_uniques" type="select" label="Filter unique sequences" help="See below for an example.">
			<option value="remove" selected="true">Remove uniques (Based on nucleotide sequence + C)</option>
			<option value="keep">Keep uniques (Based on nucleotide sequence + C)</option>
			<option value="no">No</option>
		</param>
		<param name="unique" type="select" label="Remove duplicates based on" help="" >
			<option value="VGene,CDR3.IMGT.AA,best_match_class">Top.V.Gene, CDR3 (AA), C region</option>
			<option value="VGene,CDR3.IMGT.AA">Top.V.Gene, CDR3 (AA)</option>
			<option value="CDR3.IMGT.AA,best_match_class">CDR3 (AA), C region</option>
			<option value="CDR3.IMGT.AA">CDR3 (AA)</option>
			
			<option value="VGene,CDR3.IMGT.seq,best_match_class">Top.V.Gene, CDR3.nt.Seq, C region</option>
			<option value="VGene,CDR3.IMGT.seq">Top.V.Gene, CDR3 (nt)</option>
			<option value="CDR3.IMGT.seq,best_match_class">CDR3 (nt), C region</option>
			<option value="CDR3.IMGT.seq">CDR3 (nt)</option>
			<option value="Sequence.ID" selected="true">Don't remove duplicates</option>
		</param>
		<param name="class_filter" type="select" label="Human Class/Subclass filter" help="" >
			<option value="70_70" selected="true">>70% class and >70% subclass</option>
			<option value="60_55">>60% class and >55% subclass</option>
			<option value="70_0">>70% class</option>
			<option value="60_0">>60% class</option>
			<option value="101_101">Do not assign (sub)class</option>
		</param>
		<conditional name="naive_output_cond">
			<param name="naive_output" type="select" label="Output new IMGT archives per class into your history?">
				<option value="yes">Yes</option>
				<option value="no" selected="true">No</option>
			</param>
		</conditional>
		
		
		<param name="fast" type="select" label="Fast" help="Skips generating the new ZIP files and Change-O/Baseline" >
			<option value="yes">Yes</option>
			<option value="no" selected="true">No</option>
		</param>
		
		
	</inputs>
	<outputs>
		<data format="html" name="out_file" label = "SHM &amp; CSR on ${in_file.name}"/>
		<data format="imgt_archive" name="naive_output_ca" label = "Naive CA input data from ${in_file.name}" >
		    <filter>naive_output_cond['naive_output'] == "yes"</filter>
		</data>
		<data format="imgt_archive" name="naive_output_cg" label = "Naive CG input data from ${in_file.name}" >
		    <filter>naive_output_cond['naive_output'] == "yes"</filter>
		</data>
		<data format="imgt_archive" name="naive_output_cm" label = "Naive CM input data from ${in_file.name}" >
		    <filter>naive_output_cond['naive_output'] == "yes"</filter>
		</data>
		<data format="imgt_archive" name="naive_output_ce" label = "Naive CE input data from ${in_file.name}" >
		    <filter>naive_output_cond['naive_output'] == "yes"</filter>
		</data>
	</outputs>
	<citations>
		<citation type="doi">10.1093/nar/gks457</citation>
		<citation type="doi">10.1093/bioinformatics/btv359</citation>
	</citations>
	<help>
		Takes an IMGT zip (http://www.imgt.org/HighV-QUEST/search.action) file and creates a summarization of the mutation analysis.  
		
		+--------------------------+
		|       unique filter      |
		+--------+--------+--------+
		| values | remove | keep   |
		+--------+--------+--------+
		|   A    |   A    |   A    |
		+--------+--------+--------+
		|   A    |   B    |   B    |
		+--------+--------+--------+
		|   B    |   D    |   C    |
		+--------+--------+--------+
		|   B    |        |   D    |
		+--------+--------+--------+
		|   C    |        |        |
		+--------+--------+--------+
		|   D    |        |        |
		+--------+--------+--------+
		|   D    |        |        |
		+--------+--------+--------+
		
	</help>
</tool>