Mercurial > repos > bebatut > cdhit

changeset 1:2f0a6f227f87 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/cdhit/ commit 5c45ed58045ce1686aa069403f8a9426ea20bac5-dirty
author bebatut
date Tue, 12 Apr 2016 02:54:39 -0400
parents 617a5f3baf7f
children aa923171e225
files cd_hit_est.xml cd_hit_protein.xml
diffstat 2 files changed, 186 insertions(+), 154 deletions(-) [+]
line wrap: on
line diff
--- a/cd_hit_est.xml	Mon Dec 14 04:19:46 2015 -0500
+++ b/cd_hit_est.xml	Tue Apr 12 02:54:39 2016 -0400
@@ -1,87 +1,99 @@
 <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>
+  <description>Cluster a nucleotide dataset into representative sequences</description>
+
   <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=$runtime_tuning#
- </command>
- <inputs>
-  <param name="fasta_in" type="data" format="fasta" label="EST Sequences to cluster"/>
-  <param name="similarity" type="float" value="0.9"  label="similarity threshold: .75 - 1.0, default is .9">
-    <validator type="in_range" message="sequence similarity threshold should be .75 - 1.0" min=".75" max="1.0"/>
-  </param>
-  <param name="wordsize" type="integer" value="8"  label="word size">
-    <help> Suggested word size:
-          8,9,10 for thresholds 0.90 ~ 1.0
-          7      for thresholds 0.88 ~ 0.9
-          6      for thresholds 0.85 ~ 0.88
-          5      for thresholds 0.80 ~ 0.85
-          4      for thresholds 0.75 ~ 0.8 
-    </help>
-    <validator type="in_range" message="word size should be between 4 and 10" min="4" max="10"/>
-  </param>
-  <param name="strand" type="boolean" truevalue="-r 1" falsevalue="" checked="false" label="Compare both strands"/>
-  <expand macro="common_cdhit_options" />
-  <expand macro="runtime_tuning" />
- </inputs>
- <outputs>
-  <data format="txt" name="clusters_out" label="${tool.name} on ${on_string}: clusters" from_work_dir="rep_seq.clstr"/>
-  <data format="fasta" name="fasta_out" label="${tool.name} on ${on_string}: representatives.fasta" from_work_dir="rep_seq"/>
- </outputs>
- <tests>
-  <test>
-    <!-- Expect 3 clusters: 0,1,2 -->
-    <param name="fasta_in" value="cd_hit_est_in.fa" />
-    <param name="similarity" value="0.9"/>
-    <param name="wordsize" value="8"/>
-    <param name="strand" value="true"/>
-    <!-- conditionals in macros -->
-    <param name="settings" value="no"/>
-    <param name="tuning" value="default"/>
-    <output name="clusters_out">
-        <assert_contents>
-            <has_text text=">Cluster 0" />
-            <!-- There should not be a Cluster 3 -->
-            <not_has_text text="Cluster 3" />
-            <has_text_matching expression="F12Fcsw_481739" />
-        </assert_contents>
-    </output>
-    <output name="fasta_out">
-        <assert_contents>
-            <has_text_matching expression="^>[MF]\d\dFcsw_\d*" />
-        </assert_contents>
-    </output>
-  </test>
-  <test>
-    <!-- tighter constraints should yield more clusters -->
-    <param name="fasta_in" value="cd_hit_est_in.fa" />
-    <param name="similarity" value="0.95"/>
-    <param name="wordsize" value="9"/>
-    <param name="strand" value="true"/>
-    <!-- conditionals in macros -->
-    <param name="settings" value="no"/>
-    <param name="tuning" value="default"/>
-    <output name="clusters_out">
-        <assert_contents>
-            <has_text text=">Cluster 4" />
-            <has_text_matching expression=">F12Fcsw_481739" />
-        </assert_contents>
-    </output>
-    <output name="fasta_out">
-        <assert_contents>
-            <has_text_matching expression="^>[MF]\d\dFcsw_\d*" />
-        </assert_contents>
-    </output>
-  </test>
- </tests>
- <help>
-**CD-HIT-EST**
+
+  <requirements>
+    <requirement type="package" version="4.6.1">cd-hit</requirement>
+  </requirements>
+
+  <command><![CDATA[
+    cd-hit-est
+      -i "$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.
 
@@ -116,5 +128,10 @@
 	3 2208aa, >PF06317.1|RRPO_TACV/1-2208... at 69%
 
 
- </help>
+  ]]></help>
+
+  <citations>
+    <citation type="doi">10.1093/bioinformatics/btl158</citation>
+    <citation type="doi">10.1093/bioinformatics/bts565</citation>
+  </citations>
 </tool>
--- a/cd_hit_protein.xml	Mon Dec 14 04:19:46 2015 -0500
+++ b/cd_hit_protein.xml	Tue Apr 12 02:54:39 2016 -0400
@@ -1,82 +1,92 @@
 <tool id="cd_hit_protein" name="CD-HIT PROTEIN" version="1.2">
- <description>Cluster a protein dataset into representative sequences</description>
- <requirements>
-  <requirement type="package" version="4.6.1">cd-hit</requirement>
- </requirements>
+  <description>Cluster a protein dataset into representative sequences</description>
+
   <macros>
     <import>cdhit_macros.xml</import>
   </macros>
- <command>
-  cd-hit -i "$fasta_in" -o rep_seq -c $similarity -n $wordsize 
-  #include source=$common_cdhit_options#
-  #include source=$runtime_tuning#
- </command>
- <inputs>
-  <param name="fasta_in" type="data" format="fasta" label="Protein Sequences to cluster"/>
-  <param name="similarity" type="float" value="0.9"  label="similarity threshold: .4 - 1.0 (default .9)">
-    <validator type="in_range" message="sequence similarity threshold should be .4 - 1.0" min=".4" max="1.0"/>
-  </param>
-  <param name="wordsize" type="integer" value="5"  label="word size (default 5)">
-    <help> Suggested word size:
-          5    for thresholds 0.7 ~ 1.0; 
-          4    for thresholds 0.6 ~ 0.7; 
-          3    for thresholds 0.5 ~ 0.6; 
-          2    for thresholds 0.4 ~ 0.5; 
-    </help>
-    <validator type="in_range" message="word size should be between 2 and 5" min="2" max="5"/>
-  </param>
-  <expand macro="common_cdhit_options" />
-  <expand macro="runtime_tuning" />
- </inputs>
- <outputs>
-  <data format="txt" name="clusters_out" label="${tool.name} on ${on_string}: clusters" from_work_dir="rep_seq.clstr"/>
-  <data format="fasta" name="fasta_out" label="${tool.name} on ${on_string}: representatives.fasta" from_work_dir="rep_seq"/>
- </outputs>
- <tests>
-  <test>
-    <param name="fasta_in" value="cd_hit_protein_in.fasta" />
-    <param name="similarity" value="0.9"/>
-    <param name="wordsize" value="5"/>
-    <!-- conditionals in macros -->
-    <param name="settings" value="no"/>
-    <param name="tuning" value="default"/>
-    <output name="clusters_out">
+
+  <requirements>
+    <requirement type="package" version="4.6.1">cd-hit</requirement>
+  </requirements>
+
+  <command><![CDATA[
+    cd-hit 
+      -i "$fasta_in" 
+      -o rep_seq 
+      -c $similarity 
+      -n $wordsize 
+      #include source=$common_cdhit_options#
+      #include source=$runtime_tuning#
+  ]]></command>
+
+  <inputs>
+    <param name="fasta_in" type="data" format="fasta" label="Protein Sequences to cluster"/>
+    <param name="similarity" type="float" value="0.9"  label="similarity threshold: .4 - 1.0 (default .9)">
+      <validator type="in_range" message="sequence similarity threshold should be .4 - 1.0" min=".4" max="1.0"/>
+    </param>
+    <param name="wordsize" type="integer" value="5"  label="word size (default 5)">
+      <help> Suggested word size:
+           5    for thresholds 0.7 ~ 1.0; 
+           4    for thresholds 0.6 ~ 0.7; 
+           3    for thresholds 0.5 ~ 0.6; 
+           2    for thresholds 0.4 ~ 0.5; 
+      </help>
+      <validator type="in_range" message="word size should be between 2 and 5" min="2" max="5"/>
+    </param>
+    <expand macro="common_cdhit_options" />
+    <expand macro="runtime_tuning" />
+  </inputs>
+
+  <outputs>
+    <data format="txt" name="clusters_out" label="${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>
+       <param name="fasta_in" value="cd_hit_protein_in.fasta" />
+       <param name="similarity" value="0.9"/>
+       <param name="wordsize" value="5"/>
+       <!-- conditionals in macros -->
+       <param name="settings" value="no"/>
+       <param name="tuning" value="default"/>
+       <output name="clusters_out">
+           <assert_contents>
+               <has_text text="Cluster 0" />
+               <!--
+               <has_text_matching expression=">sp.P00338-2.LDHA_HU" />
+               -->
+           </assert_contents>
+       </output>
+       <output name="fasta_out">
+           <assert_contents>
+               <has_text_matching expression=">sp.P19858.LDHA_BOVIN" />
+           </assert_contents>
+       </output>
+    </test>
+    <test>
+      <param name="fasta_in" value="cd_hit_protein_in.fasta" />
+      <param name="similarity" value="0.8" />
+      <param name="wordsize" value="5" />
+     <!-- conditionals in macros -->
+      <param name="settings" value="no"/>
+      <param name="tuning" value="default"/>
+      <output name="clusters_out">
         <assert_contents>
-            <has_text text="Cluster 0" />
-            <!--
-            <has_text_matching expression=">sp.P00338-2.LDHA_HU" />
-            -->
-        </assert_contents>
-    </output>
-    <output name="fasta_out">
-        <assert_contents>
-            <has_text_matching expression=">sp.P19858.LDHA_BOVIN" />
+      <has_text text="Cluster 0" />
+      <not_has_text text="Cluster 4" />
         </assert_contents>
-    </output>
-  </test>
-  <test>
-    <param name="fasta_in" value="cd_hit_protein_in.fasta" />
-    <param name="similarity" value="0.8" />
-    <param name="wordsize" value="5" />
-    <!-- conditionals in macros -->
-    <param name="settings" value="no"/>
-    <param name="tuning" value="default"/>
-    <output name="clusters_out">
-      <assert_contents>
-	<has_text text="Cluster 0" />
-	<not_has_text text="Cluster 4" />
-      </assert_contents>
-    </output>
-    <output name="fasta_out">
-      <assert_contents>
-	<has_text_matching expression=">sp.P00340.LDHA_CHICK" />
-      </assert_contents>
-    </output>
-  </test>
- </tests>
+      </output>
+      <output name="fasta_out">
+        <assert_contents>
+        <has_text_matching expression=">sp.P00340.LDHA_CHICK" />
+        </assert_contents>
+      </output>
+    </test>
+  </tests>
 
- <help>
-**CD-HIT**
+  <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.
 
@@ -111,5 +121,10 @@
 	3 2208aa, >PF06317.1|RRPO_TACV/1-2208... at 69%
 
 
- </help>
+  ]]></help>
+
+  <citations>
+    <citation type="doi">10.1093/bioinformatics/btl158</citation>
+    <citation type="doi">10.1093/bioinformatics/bts565</citation>
+  </citations>
 </tool>