annotate genMutModel.xml @ 9:441103f02a11 draft

planemo upload commit e96b43f96afce6a7b7dfd4499933aad7d05c955e-dirty

<tool id="genMutModel"
      name="genMutModel"
      version="1.0.0"
	  profile="16.04">
  <description>generates a mutation model based on provided mutations. Creates model file for use in NEAT-genReads</description>
  <requirements>
    <requirement type="package">numpy</requirement>
    <requirement type="package">matplotlib</requirement>
  </requirements>
  <command detect_errors="exit_code">
    <![CDATA[
	## Filenames and extensions are important, so make some links to make life easier downstream
	ln -s $mutation_file mutation_file.vcf;
	#if $in_type.input_type == "built-in":
	ln -s ${in_type.reference.fields.path} reference.fa;
	#else:
	ln -s ${in_type.reference} reference.fa;
	#end if
    python2 $__tool_directory__/utilities/genMutModel.py
		-r reference.fa
		-m mutation_file.vcf
		-o $genMutModel_modelfile
		#if $misc.include_file:
		  -bi $misc.include_file
		#end if
		#if $misc.exclude_file:
		  -be $misc.exclude_file
		#end if
		$misc.save_trinuc
		$misc.no_whitelist
		$misc.skip_common
	]]>
  </command>
  <inputs>

    <param name="mutation_file"
	       type="data"
		   format="vcf"
		   label="The VCF file to use as the definition of errors in the sequence [-m]"
		   help="Trinucleotides are identified in the reference genome and the variant file. Frequencies of each trinucleotide transition are calculated and output as a pickle (.p) file" 
	/>
	
	<conditional name="in_type">
	  <param name="input_type" type="select" label="Use a built-in FASTA file or one from the history?">
		<option value="built-in">Built-in</option>
		<option value="history">History file</option>
	  </param>
	  <when value="built-in">
		<param name="reference"
			   type="select"
			   label="Select a built-in reference sequence"
			   help="The reference sequence that will be used as the basis for the simulated reads">
		  <options from_data_table="all_fasta" />
		</param>
	  </when>
	  <when value="history">
		<param name="reference"
			   type="data"
			   format="fasta"
			   label="The reference sequence (FASTA format)"
			   help="The reference sequence that will be used as the basis for the simulated reads"
		/>
	  </when>
	</conditional>

	<section name="misc"
			 title="Miscellanous settings"
			 expanded="false"
			 help="Miscellanous settings. In/Exclude regions and other settings"
	>
		<param name="include_file"
			   optional="true"
			   type="data"
			   format="bed"
			   label="Only use mutations falling inside this region [-bi]"
			   help="" 
		/>
		
		<param name="exclude_file"
			   optional="true"
			   type="data"
			   format="bed"
			   label="Exlude mutations falling inside this region [-be]"
			   help="Trinucleotides are identified in the reference genome and the variant file. Frequencies of each trinucleotide transition are calculated and output as a pickle (.p) file" 
		/>

		<param name="save_trinuc"
			   type="boolean"
			   checked="false"
			   truevalue="--save-trinuc"
			   falsevalue=""
			   label="Save the trinulceotide counts for ref [--save-trinuc]"
			   help=""
		/>
		
		<param name="no_whitelist"
			   type="boolean"
			   checked="false"
			   truevalue="--no-whitelist"
			   falsevalue=""
			   label="Allow any non-standard reference [--no-whitelist]"
			   help=""
		/>
		
		<param name="skip_common"
			   type="boolean"
			   checked="false"
			   truevalue="--skip-common"
			   falsevalue=""
			   label="Do not save common SNPs and high mutation regions"
			   help=""
		/>
	</section>
  </inputs>
  <outputs>
	<data format="txt"
		  name="genMutModel_modelfile"
		  label="${os.path.splitext(str($mutation_file.name))[0]}_genMutModel.p"
		  metadata_source="in_type.reference">
	</data>
	
	<data format="simple"
	      name="trinuc_file"
		  from_work_dir="reference.fa.trinucCounts"
	      label="${os.path.splitext(str($mutation_file.name))[0]}_trinucCounts.tsv"
	      metadata_source="in_type.reference">
		  <filter>misc['save_trinuc']</filter>
	</data>

  </outputs>
  <help>
  </help>
	<tests>
		
		<test>
			<conditional name="in_type">
				<param name="input_type" value="history"/>
			  <param name="reference" value="chrMT.fa" format="fasta"/>
			</conditional>
			<param name="mutation_file" value="chrMT-PE-VCF-BAM.vcf"/>
			<output name="genMutModel_modelfile" value="chrMT-PE-VCF-BAM-genMutModel.p" compare="diff"/>
		</test>

		<test>
			<conditional name="in_type">
				<param name="input_type" value="history"/>
			  <param name="reference" value="chrMT.fa" format="fasta"/>
			</conditional>
			<param name="mutation_file" value="chrMT-PE-VCF-BAM.vcf"/>
			<section name="misc">
				<param name="include_file" value="chrMT-Targets.bed"/>
			</section>
			<output name="genMutModel_modelfile" value="chrMT-PE-VCF-BAM-INCLUDELIST-genMutModel.p" compare="diff"/>
		</test>

		<test>
			<conditional name="in_type">
				<param name="input_type" value="history"/>
			  <param name="reference" value="chrMT.fa" format="fasta"/>
			</conditional>
			<param name="mutation_file" value="chrMT-PE-VCF-BAM.vcf"/>
			<section name="misc">
				<param name="exclude_file" value="chrMT-Targets.bed"/>
			</section>
			<output name="genMutModel_modelfile" value="chrMT-PE-VCF-BAM-EXCLUDELIST-genMutModel.p" compare="diff"/>
		</test>

		<test>
			<conditional name="in_type">
				<param name="input_type" value="history"/>
			  <param name="reference" value="chrMT.fa" format="fasta"/>
			</conditional>
			<param name="mutation_file" value="chrMT-PE-VCF-BAM.vcf"/>
			<section name="misc">
				<param name="save_trinuc" value="true"/>
				<param name="no_whitelist" value="true"/>
				<param name="skip_common" value="true"/>
			</section>
			<output name="genMutModel_modelfile" value="chrMT-PE-VCF-BAM-BOOLEANS-genMutModel.p" compare="diff"/>
			<output name="trinuc_file" value="chrMT.fa.trinucCounts" compare="diff"/>
		</test>

	</tests>
</tool>