view micomplete.xml @ 1:609b98cf0f9f draft default tip

Uploaded tool_data_table_conf.xml.sample
author lionelguy
date Thu, 17 Oct 2013 08:44:01 -0400
parents 23e768cddc7d
children
line wrap: on
line source

<tool id="micomplete" name="micomplete" version="0.1">
  <description>Using hmm profiles of conserved proteins, reports how much complete a (single-cell amplified) genome is</description>
  <requirements>
    <requirement type="package" version="3.1b1">hmmer</requirement>
  </requirements>
  <command interpreter="perl">micomplete.pl 
  #if $hmm_source.hmm_source_type == "cached"
  --hmm "${ hmm_source.profiles.fields.hmms }"
  --weights "${ hmm_source.profiles.fields.weights }"
  #else
  --hmm "${ hmm_source.own_profiles }"
    #if $hmm_source.weights.use_weights
    --weights "${ hmm_source.weights.own_weights }"
    #end if
  #end if
  --proteome $proteome
  --cut-off $cutoff
  #if $evalue
  --evalue 
  #end if
  #if $save_hmm_tab
  --save-hmm-tab $hmm_tab
  #end if
  #if $save_hmm_alignments
  --save-hmm-alignments $hmm_alignments
  #end if
  #if $save_res_tab
  --save-result-tab $res_tab
  #end if
  --threads $threads > $output
  </command>
  <inputs>
    <param name="proteome" type="data" format="fasta" label="Proteome file" />
    <conditional name="hmm_source">
      <param name="hmm_source_type" type="select" label="HMM file from history or from built-in profile?">
	<option value="cached">Use a built-in profile</option>
	<option value="history">Use a profile from the history</option>
      </param>
      <when value="cached">
	<param name="profiles" type="select" label="Select a reference set">
	  <options from_data_table="micomplete_hmms">
	    <filter type="sort_by" column="2" />
	  </options>
	</param>
      </when>
      <when value="history">
	<param name="own_profiles" type="data" format="text" label="Select a HMM set in the history" />
	<conditional name="weights">
	  <param name="use_weights" type="boolean" checked="false" truevalue="True" falsevalue="False" label="Use weights?" />
	  <when value="True">
	    <param name="own_weights" type="data" format="tabular" label="Select a weight file (optional)" help="There should be exactly one weight for each profile in the profiles file"/>
	  </when>
	</conditional>
      </when>
    </conditional>
    <param name="cutoff" type="float" value="1e-10" label="E-value cutoff to include hits" />
    <param name="evalue" type="boolean" checked="true" truevalue="True" falsevalue="False" label="Show E-values on the output instead of 0/1?" />
    <param name="save_res_tab" type="boolean" checked="true" truevalue="True" falsevalue="False" label="Save per marker result tabular file?" />
    <param name="save_hmm_tab" type="boolean" checked="false" truevalue="True" falsevalue="False" label="Save HMM tab result file?" />
    <param name="save_hmm_alignments" type="boolean" checked="false" truevalue="True" falsevalue="False" label="Save HMM alignments result file?" />
    <param name="threads" type="integer" value="15" min="1" label="Number of threads to use" />
  </inputs>
  <outputs>
    <data format="txt" name="output" label="Completeness report" />
    <data format="tabular" name="res_tab" label="HMM report, tabular format"> 
      <filter>save_res_tab is True</filter>
    </data>
    <data format="tabular" name="hmm_tab" label="HMM report, tabular format"> 
      <filter>save_hmm_tab is True</filter>
    </data>
    <data format="txt" name="hmm_alignments" label="HMM alignments"> 
      <filter>save_hmm_alignments is True</filter>
    </data>
  </outputs>
  <help>
***What it does***

Micomplete estimates the level of completion of a genome. This is particularly useful for single-cell amplified genomes. It aligns a proteome to a set of "markers" or conserved proteins, represented by a collection of HMM profiles, possibly with weights. It uses hmmsearch (http://hmmer.janelia.org/, see for example S.R Eddy, PLOS Comp Biol 2011, 7:e1002195) to align proteins

Weights are used to alleviate the effect of having/not having a specific contig which would contain many markers that are generally clustering together. Typically, ribosomal proteins, often used are markers, are often organized in operons. Thus, the impact of having/not having these operons is very important, and should be downplayed to get a more correct estimate.

**License**

This wrapper is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.

This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.

You should have received a copy of the GNU General Public License along with this program.  If not, see http://www.gnu.org/licenses/.
  </help>
</tool>