annotate mothur/tools/mothur/get.lineage.xml @ 36:040410b8167e default tip

Fixed reference to legacy blast repository in tool_dependencies.xml. Updated README with author information.

<tool id="mothur_get_lineage" name="Get.lineage" version="1.21.0">
 <description>Picks by taxon</description>
 <command interpreter="python">
  mothur_wrapper.py 
  #import re, os.path
  #set results = ["'^mothur.\S+\.logfile$:'" + $logfile.__str__]
  ## adds .pick before the last extension to the input file
  --cmd='get.lineage'
	#if $file.filetype.__str__ == "usetaxonomy"
		--taxonomy=$file.taxonomy
		#set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($taxonomy.__str__)) + ":'" + $taxonomy_out.__str__]
	#else
		--constaxonomy=$file.constaxonomy
		--shared=$file.shared
		--list=$file.list
		#set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($constaxonomy.__str__)) + ":'" + $taxonomy_out.__str__]
	#end if
  --outputdir='$logfile.extra_files_path'
  --taxon="'$re.sub('(\s|,)+',',',$re.sub('\(\d+\)','',$taxon.value.__str__))'"
  #if $fasta_in.__str__ != "None" and len($fasta_in.__str__) > 0:
   --fasta=$fasta_in
   #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($fasta_in.__str__)) + ":'" + $fasta_out.__str__]
  #end if
  #if $group_in.__str__ != "None" and len($group_in.__str__) > 0:
   --group=$group_in
   #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($group_in.__str__)) + ":'" + $group_out.__str__]
  #end if
  #if $alignreport_in.__str__ != "None" and len($alignreport_in.__str__) > 0:
   --alignreport=$alignreport_in
   #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)$',r'\1.pick.align.report',$os.path.basename($alignreport_in.__str__)) + ":'" + $alignreport_out.__str__]
  #end if
  #if $list_in.__str__ != "None" and len($list_in.__str__) > 0:
   --list=$list_in
   #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($list_in.__str__)) + ":'" + $list_out.__str__]
  #end if
  #if $name_in.__str__ != "None" and len($name_in.__str__) > 0:
   --name=$name_in
   #set results = $results + ["'" + $re.sub(r'(^.*)\.(.*?)',r'\1.pick.\2',$os.path.basename($name_in.__str__)) + ":'" + $name_out.__str__]
   $dups
	 #end if
	#if $count.__str__ != "None" and len($count.__str__) > 0:
		--count=$count
	#end if
  --result=#echo ','.join($results)
 </command>
 <inputs>
	 <conditional name ="file">
	 <param name = "filetype" type = "select" label="choose which file is used">
		 <option value = "usetaxonomy" selected = "true">taxonomy</option>
		 <option value = "useconstaxonomy">constaxonomy</option>
	 </param>
	 <when value = "usetaxonomy">
		<param name="taxonomy" type="data" format="seq.taxonomy" label="taxonomy - Taxonomy"/>
	 </when>
	 <when value = "useconstaxonomy">
		<param name="constaxonomy" type="data" format="cons.taxonomy" label="constaxonomy - Constaxonomy file. Provide either a constaxonomy file or a taxonomy file"/>
		<param name="shared" type="data" format="shared" label="shared - shared file" optional="true"/>
		<param name="list" type="data" format="list" label="list - list file" optional="true"/>
	 </when>
 </conditional>

  <!--
  <param name="taxons" type="select" size="120" multiple="true" label="Browse Taxons from Taxonomy">
   <options from_dataset="taxonomy">
    <column name="name" index="1"/>
    <column name="value" index="1"/>
    <filter type="unique_value" name="unique_taxon" column="1" />
    <filter type="sort_by" name="sorted_taxon" column="1" />
   </options>
  </param>
  -->
  <param name="taxon" type="text" area="True" size="5x120" label="taxon - Select Taxons for filtering" help="Enter 1 or more taxons separated by whitespace or commas"/>
  <param name="fasta_in" type="data" format="fasta" optional="true" label="fasta - Fasta Sequences"/>
  <param name="group_in" type="data" format="groups" optional="true" label="group - Groups"/>
  <param name="alignreport_in" type="data" format="align.report" optional="true" label="alignreport - Align Report"/>
  <param name="list_in" type="data" format="list" optional="true" label="list - OTU List"/>
  <param name="name_in" type="data" format="names" optional="true" label="name - Sequences Name reference"/>
	<param name="dups" type="boolean" truevalue="" falsevalue="--dups=false" checked="true" label="dups - Apply to duplicate names"/>
	<param name = "count" type="data" format="count_table" optional="true" help ="The count file is similar to the name file in that it is used to represent the number of duplicate sequences for a given representative sequence. It can also contain group information"/>
 </inputs>
 <outputs>
  <data format="html" name="logfile" label="${tool.name} on ${on_string}: logfile" />
  <data format="seq.taxonomy" name="taxonomy_out" label="${tool.name} on ${on_string}: pick.taxonomy"/>
  <data format_source="fasta_in" name="fasta_out" label="${tool.name} on ${on_string}: pick.fasta">
   <filter>fasta_in != None</filter>
  </data>
  <data format="groups" name="group_out" label="${tool.name} on ${on_string}: pick.group">
   <filter>group_in != None</filter>
  </data>
  <data format="list" name="list_out" label="${tool.name} on ${on_string}: pick.list">
   <filter>list_in != None</filter>
  </data>
  <data format="names" name="name_out" label="${tool.name} on ${on_string}: pick.name">
   <filter>name_in != None</filter>
  </data>
  <data format="align.report" name="alignreport_out" label="${tool.name} on ${on_string}: pick.align.report">
   <filter>alignreport_in != None</filter>
  </data>
 </outputs>
 <requirements>
  <requirement type="package" version="1.33">mothur</requirement>
 </requirements>
 <tests>
 </tests>
 <help>
**Mothur Overview**

Mothur_, initiated by Dr. Patrick Schloss and his software development team
in the Department of Microbiology and Immunology at The University of Michigan,
provides bioinformatics for the microbial ecology community.

.. _Mothur: http://www.mothur.org/wiki/Main_Page

**Command Documenation**

The get.lineage_ command reads a taxonomy_ file and a taxon and generates a new file that contains only the sequences in the that are from that taxon. You may also include either a fasta, name_, group_, list_, or align.report_ file to this command and mothur will generate new files for each of those containing only the selected sequences.

.. _taxonomy: http://www.mothur.org/wiki/Taxonomy_outline
.. _name: http://www.mothur.org/wiki/Name_file
.. _group: http://www.mothur.org/wiki/Group_file
.. _list: http://www.mothur.org/wiki/List_file
.. _align.report: http://www.mothur.org/wiki/Align.seqs
.. _get.lineage: http://www.mothur.org/wiki/Get.lineage


 </help>
</tool>