view cd_hit_est.xml @ 1:2f0a6f227f87 draft

planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 5c45ed58045ce1686aa069403f8a9426ea20bac5-dirty

<tool id="cd_hit_est" name="CD-HIT-EST" version="1.2">
  <description>Cluster a nucleotide dataset into representative sequences</description>

  <macros>
    <import>cdhit_macros.xml</import>
  </macros>

  <requirements>
    <requirement type="package" version="4.6.1">cd-hit</requirement>
  </requirements>

  <command><![CDATA[
    cd-hit-est
      -i "$fasta_in" 
      -o rep_seq 
      -c $similarity 
      -n $wordsize $strand
   
      #include source=$common_cdhit_options#
      #include source=$runtime_tuning#
  ]]></command>
  
  <inputs>
    <param name="fasta_in" type="data" format="fasta" label="EST Sequences to cluster"/>
    <param name="similarity" type="float" value="0.9"  label="similarity threshold: .75 - 1.0, default is .9">
      <validator type="in_range" message="sequence similarity threshold should be .75 - 1.0" min=".75" max="1.0"/>
    </param>
    <param name="wordsize" type="integer" value="8"  label="word size">
      <help> Suggested word size:
             8,9,10 for thresholds 0.90 ~ 1.0
             7      for thresholds 0.88 ~ 0.9
             6      for thresholds 0.85 ~ 0.88
             5      for thresholds 0.80 ~ 0.85
             4      for thresholds 0.75 ~ 0.8 
      </help>
      <validator type="in_range" message="word size should be between 4 and 10" min="4" max="10"/>
    </param>
    <param name="strand" type="boolean" truevalue="-r 1" falsevalue="" checked="false" label="Compare both strands"/>
    <expand macro="common_cdhit_options" />
    <expand macro="runtime_tuning" />
  </inputs>

  <outputs>
    <data format="txt" name="clusters_out" label="${tool.name} on ${on_string}: clusters" from_work_dir="rep_seq.clstr"/>
    <data format="fasta" name="fasta_out" label="${tool.name} on ${on_string}: representatives.fasta" from_work_dir="rep_seq"/>
  </outputs>
  
  <tests>
   <test>
     <!-- Expect 3 clusters: 0,1,2 -->
     <param name="fasta_in" value="cd_hit_est_in.fa" />
     <param name="similarity" value="0.9"/>
     <param name="wordsize" value="8"/>
     <param name="strand" value="true"/>
     <!-- conditionals in macros -->
     <param name="settings" value="no"/>
     <param name="tuning" value="default"/>
     <output name="clusters_out">
         <assert_contents>
             <has_text text=">Cluster 0" />
             <!-- There should not be a Cluster 3 -->
             <not_has_text text="Cluster 3" />
             <has_text_matching expression="F12Fcsw_481739" />
         </assert_contents>
     </output>
     <output name="fasta_out">
         <assert_contents>
             <has_text_matching expression="^>[MF]\d\dFcsw_\d*" />
         </assert_contents>
     </output>
   </test>
   <test>
     <!-- tighter constraints should yield more clusters -->
     <param name="fasta_in" value="cd_hit_est_in.fa" />
     <param name="similarity" value="0.95"/>
     <param name="wordsize" value="9"/>
     <param name="strand" value="true"/>
     <!-- conditionals in macros -->
     <param name="settings" value="no"/>
     <param name="tuning" value="default"/>
     <output name="clusters_out">
         <assert_contents>
             <has_text text=">Cluster 4" />
             <has_text_matching expression=">F12Fcsw_481739" />
         </assert_contents>
     </output>
     <output name="fasta_out">
         <assert_contents>
             <has_text_matching expression="^>[MF]\d\dFcsw_\d*" />
         </assert_contents>
     </output>
   </test>
  </tests>

  <help><![CDATA[
**What it does**

CD-HIT_ stands for Cluster Database at High Identity with Tolerance. The program (cd-hit) takes a fasta format sequence database as input and produces a set of 'non-redundant' (nr) representative sequences as output. In addition cd-hit outputs a cluster file, documenting the sequence 'groupies' for each nr sequence representative. The idea is to reduce the overall size of the database without removing any sequence information by only removing 'redundant' (or highly similar) sequences. This is why the resulting database is called non-redundant (nr). Essentially, cd-hit produces a set of closely related protein families from a given fasta sequence database.

.. _CD-HIT: http://www.bioinformatics.org/cd-hit/

------

**Inputs**

cd-hit-est requires a fasta dataset as input.
 
------

**Outputs**

A fasta datasets containing representative sequences.

A text file listing the mapping of sequences to the representative sequences::

	>Cluster 0
	0 2799aa, >PF04998.6|RPOC2_CHLRE/275-3073... *
	>Cluster 1
	0 2214aa, >PF06317.1|Q6Y625_9VIRU/1-2214... at 80%
	1 2215aa, >PF06317.1|O09705_9VIRU/1-2215... at 84%
	2 2217aa, >PF06317.1|Q6Y630_9VIRU/1-2217... *
	3 2216aa, >PF06317.1|Q6GWS6_9VIRU/1-2216... at 84%
	4 527aa, >PF06317.1|Q67E14_9VIRU/6-532... at 63%
	>Cluster 2
	0 2202aa, >PF06317.1|Q6UY61_9VIRU/8-2209... at 60%
	1 2208aa, >PF06317.1|Q6IVU4_JUNIN/1-2208... *
	2 2207aa, >PF06317.1|Q6IVU0_MACHU/1-2207... at 73%
	3 2208aa, >PF06317.1|RRPO_TACV/1-2208... at 69%


  ]]></help>

  <citations>
    <citation type="doi">10.1093/bioinformatics/btl158</citation>
    <citation type="doi">10.1093/bioinformatics/bts565</citation>
  </citations>
</tool>