comparison cd_hit_est.xml @ 11:75fde37f69e5

Add cd-hit to protein fastas

10:211ca88ce047

<tool id="cd_hit_est" name="CD-HIT-EST" version="1.1">
 <description>Cluster a nucleotide dataset into representative sequences</description>
 <requirements>
  <requirement type="package" version="4.6.1">cd-hit</requirement>
 </requirements>
 <command>
  cd-hit-est -i $fasta_in -o rep_seq -c $similarity -n $wordsize $strand
 </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"/>

          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"/>
 </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>
    <param name="fasta_in" value="cd_hit_est_in.fa" />
    <param name="similarity" value="0.9"/>
    <param name="wordsize" value="8"/>
    <output name="clusters_out">
        <assert_contents>
            <has_text text=">Cluster" />
            <has_text_matching expression=">F12Fcsw_481739" />
        </assert_contents>
    </output>
    <output name="fasta_out">
        <assert_contents>

11:75fde37f69e5

<tool id="cd_hit_est" name="CD-HIT-EST" version="1.2">
 <description>Cluster a nucleotide dataset into representative sequences</description>
 <requirements>
  <requirement type="package" version="4.6.1">cd-hit</requirement>
 </requirements>
  <macros>
    <import>cdhit_macros.xml</import>
  </macros>
 <command>
  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"/>

          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>