view testing_cgatools-982e19c29ec0/cgatools/tools/cgatools_1.6/evidence2sam.xml @ 0:ef23f9cd599b draft default tip

Uploaded

<tool id="cg_evidence2sam" name="evidence2sam(beta) 1.6" version="1.0.0">
<!--
This tool creates a GUI for the evidence2sam function of cgatools from Complete Genomics, Inc.
written 8-31-2012 by [e-mail]
-->

  <description>converts evidence mappings to SAM format</description>
  
  <command>
<!-- print version of cgatools to STDOUT-->
cgatools | head -1;

<!-- print command lines to STDOUT-->
echo "cgatools evidence2sam --beta
--reference $crr.fields.path
--output $output
--evidence-dnbs $data_sources.input
--consistent-mapping-range $range
#if $region.selectregion == "yes"
--extract-genomic-region $region.coordinates
#end if
$duplicates
$mates
$intervals
$skip
$svcandidates
$unmapped
$primary
";

<!-- execute cgatools-->
cgatools evidence2sam --beta
--reference $crr.fields.path
--evidence-dnbs $data_sources.input
#if $region.selectregion == "yes"
	--extract-genomic-region $region.coordinates
#end if
$duplicates
$mates
$intervals
$skip
$svcandidates
$unmapped
$primary
--consistent-mapping-range $range
--output $output
  </command>

  <outputs>
    <data format="tabular" name="output" label="${tool.name} output"/>
  </outputs>
  
  <inputs>
		<!--form field to select crr file-->
		<param name="crr" type="select" label="Reference genome (.crr file)">
			<options from_data_table="cg_crr_files" />
		</param>
	
		<!--conditional to select input file-->
  	<conditional name="data_sources">
      <param name="data_source" type="select" label="Where is the input evidence file?">
        <option value="in">imported into Galaxy</option>
        <option value="out" selected="true">located outside Galaxy (data on server or mounted drive)</option>
      </param>
      
			<!--form field to select evidence files-->
      <when value="in">
				<param name="input" type="data" format="tabluar" label="EvidenceDnbs file">
					<validator type="dataset_ok_validator" />
					<validator type="dataset_metadata_in_file" filename="cg_crr_files.loc"
					 metadata_name="dbkey" metadata_column="1"
					 message="cgatools is not currently available for this build."/>
				</param>
			</when>
			
			<!--form field to enter external input file-->
      <when value="out">
				<param name="input" type="text" label="EvidenceDnbs file (/path/file)" size="40" help="e.g. /harddrive/GS00000XXXX-DID/GS00000YYYY-ASM/GS00123-DNA_G01_2000/ASM/EVIDENCE/evidenceDnbs-chr21-GS00000YYYY-ASM.tsv.bz2">
					<validator type="empty_field" message="You must supply an evidenceDnbs file"/>
				</param>
			</when>
		</conditional>

		<!--form field to select chromosomal region-->
		<conditional name="region">
			<param name="selectregion" type="select" label="Do you what to extract specific genomic region?">
				<option value="no" selected="true">no</option>
				<option value="yes">yes</option>
			</param>

			<when value="yes">
				<param name="coordinates" type="text" label="Enter genomic coordinates to avoid converting the entire file (chr,from,to)" size="40" help="Specify the region as a half-open interval chr,from,to (e.g. chrX,15203639,15412498)"/>
			</when>
		</conditional>
		
		<!--form field to select duplicate handling-->
		<param name="duplicates" type="select" label="Keep local duplicates of DNB mappings (default no)" help="All the output SAM records will be marked as 'not primary' if this option is used.">
			<option value="" selected="true">no</option>
			<option value="--keep-duplicates">yes</option>
		</param>

		<!--form field to generate mate sequence-->
		<param name="mates" type="select" label="Generate mate sequence (R2) and score (Q2) tags (default no)">
			<option value="" selected="true">no</option>
			<option value="--add-mate-sequence">yes</option>
		</param>

		<!--form field to generate interval ids-->
		<param name="intervals" type="select" label="Generate interval id (ZI:I) and allele id (ZA:I) tags (default no)">
			<option value="" selected="true">no</option>
			<option value="--add-allele-id">yes</option>
		</param>

		<!--form field to skip not mapped reads-->
		<param name="skip" type="select" label="Skip not mapped records (default no)">
			<option value="" selected="true">no</option>
			<option value="--skip-not-mapped">yes</option>
		</param>

		<!--form field to skip not mapped reads-->
		<param name="svcandidates" type="select" label="Mate unique single arm mappings in SAM including those on different stands and chromosomes (default no)">
			<option value="" selected="true">no</option>
			<option value="--mate-sv-candidates">yes</option>
		</param>

		<!--form field to skip not mapped reads-->
		<param name="unmapped" type="select" label="Generate mate sequence and score tags for inconsistent mappings only (default no)">
			<option value="" selected="true">no</option>
			<option value="--add-unmapped-mate-info">yes</option>
		</param>

		<!--form field to skip not mapped reads-->
		<param name="primary" type="select" label="Use primary mappings only (default no)" help="Report only the best mappings">
			<option value="" selected="true">no</option>
			<option value="--primary-mappings-only">yes</option>
		</param>

		<param name="range" type="integer" value="1300" label="Maximum distance between consistent mates (default 1300)">
			<validator type="empty_field" message="You must enter a value, the default is 1300" />
		</param>
  </inputs>

	<stdio>
		<regex match="failed" source="stderr" level="fatal"/>
		<regex match="error" source="stderr" level="fatal"/>
		<regex match="Export the sequence:" source="stderr" level="warning" description="Finished:" />
	</stdio>

  <help>
  
**What it does**

This tool uses cgatools evidence2sam to convert Complete Genomics evidence mappings to SAM format

**cgatools 1.6.0 Documentation**

Userguide: http://cgatools.sourceforge.net/docs/1.6.0/cgatools-user-guide.pdf

Release notes: http://cgatools.sourceforge.net/docs/1.6.0/cgatools-release-notes.pdf

**Command line reference**::

		COMMAND NAME
				evidence2sam - Converts CGI variant evidence data into SAM format.
		
		DESCRIPTION
				The evidence2sam converter takes as input evidence mapping files 
				(evidenceDnbs-*) and generates one SAM file as an output. The output is 
				sent into stdout by default. By default, all the evidence mapping records 
				from the input are converted into a pair of corresponding SAM records - one
				record for each HalfDNB. The negative gaps in CGI mappings are represented 
				using GS/GQ/GC tags.
		
		OPTIONS
			-h [ --help ] 
						Print this help message.
		
			--beta 
						This is a beta command. To run this command, you must pass the --beta 
						flag.
		
			-e [ --evidence-dnbs ] arg
						Input evidence dnbs file.
		
			-s [ --reference ] arg
						Reference file.
		
			-o [ --output ] arg (=STDOUT)
						The output SAM file (may be omitted for stdout).
		
			-r [ --extract-genomic-region ] arg
						defines a region as a half-open interval 'chr,from,to'.
		
			--keep-duplicates 
						Keep local duplicates of DNB mappings.All the output SAM records will 
						be marked as not primary if this option is used.
		
			--add-allele-id 
						Generate interval id and allele id tags.
		
			--skip-not-mapped 
						Skip not mapped records
		
			--add-mate-sequence 
						Generate mate sequence and score tags.
		
			--mate-sv-candidates 
						Inconsistent mappings are normally converted as single arm mappings 
						with no mate information provided. If the option is used map2sam will 
						mate unique single arm mappings in SAM including those on different 
						stands and chromosomes. To distinguish these "artificially" mated 
						records a tag "XS:i:1" is used. The MAPQ provided for these records is 
						a single arm mapping weight.
		
			--add-unmapped-mate-info 
						works like add-mate-sequence, but is applied to inconsistent mappings 
						only
		
			--primary-mappings-only 
						report only the best mappings
		
			--consistent-mapping-range arg (=1300)
						limit the maximum distance between consistent mates
		
		
		SUPPORTED FORMAT_VERSION
				0.3 or later
  </help>
</tool>