diff qiime_vsearch_cluster-features-closed-reference.xml @ 0:09b7bcb72fa7 draft

Uploaded
author florianbegusch
date Thu, 24 May 2018 02:11:44 -0400
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/qiime_vsearch_cluster-features-closed-reference.xml	Thu May 24 02:11:44 2018 -0400
@@ -0,0 +1,97 @@
+<?xml version="1.0" ?>
+<tool id="qiime_vsearch_cluster-features-closed-reference" name="qiime vsearch cluster-features-closed-reference" version="2018.4">
+	<description> -  Closed-reference clustering of features.</description>
+	<requirements>
+		<requirement type="package" version="2018.4">qiime2</requirement>
+	</requirements>
+	<command>
+	<![CDATA[
+	qiime vsearch cluster-features-closed-reference --p-perc-identity="$ppercidentity" --i-table=$itable --i-sequences=$isequences --i-reference-sequences=$ireferencesequences --o-unmatched-sequences=ounmatchedsequences
+
+	#if str($cmdconfig) != 'None':
+	 --cmd-config=$cmdconfig
+	#end if
+	 --o-clustered-table=oclusteredtable
+	#if str($pstrand) != 'None':
+	 --p-strand=$pstrand
+	#end if
+	 --o-clustered-sequences=oclusteredsequences
+	#set $pthreads = '${GALAXY_SLOTS:-4}'
+
+	#if str($pthreads):
+	 --p-threads="$pthreads"
+	#end if
+	;
+	cp ounmatchedsequences.qza $ounmatchedsequences;
+	cp oclusteredtable.qza $oclusteredtable;
+	cp oclusteredsequences.qza $oclusteredsequences
+	]]>
+	</command>
+	<inputs>
+		<param format="qza,no_unzip.zip" label="--i-sequences: FeatureData[Sequence] The sequences corresponding to the features in table.  [required]" name="isequences" optional="False" type="data"/>
+		<param format="qza,no_unzip.zip" label="--i-table: FeatureTable[Frequency] The feature table to be clustered. [required]" name="itable" optional="False" type="data"/>
+		<param format="qza,no_unzip.zip" label="--i-reference-sequences: FeatureData[Sequence] The sequences to use as cluster centroids. [required]" name="ireferencesequences" optional="False" type="data"/>
+
+		<param label="--p-perc-identity: The percent identity at which clustering should be performed. This parameter maps to vsearch's --id parameter.  [required]" name="ppercidentity" optional="False" type="text"/>
+
+		<param label="--p-strand: Search plus (i.e., forward) or both (i.e.,
+                                  forward and reverse complement) strands.
+                                  [default: plus]" name="pstrand" optional="True" type="select">
+			<option selected="True" value="None">Selection is Optional</option>
+			<option value="both">both</option>
+			<option value="plus">plus</option>
+		</param>
+
+		<param label="--cmd-config: Use config file for command options" name="cmdconfig" optional="True" type="data"/>
+	</inputs>
+	<outputs>
+		<data format="qza" label="${tool.name} on ${on_string}: unmatched-sequences.qza" name="ounmatchedsequences"/>
+		<data format="qza" label="${tool.name} on ${on_string}: clustered-table.qza" name="oclusteredtable"/>
+		<data format="qza" label="${tool.name} on ${on_string}: clustered-sequences.qza" name="oclusteredsequences"/>
+	</outputs>
+	<help>
+		<![CDATA[
+Closed-reference clustering of features.
+-----------------------------------------
+
+Given a feature table and the associated feature sequences, cluster the
+features against a reference database based on user-specified percent
+identity threshold of their sequences. This is not a general-purpose
+closed-reference clustering method, but rather is intended to be used for
+clustering the results of quality-filtering/dereplication methods, such as
+DADA2, or for re-clustering a FeatureTable at a lower percent identity than
+it was originally clustered at. When a group of features in the input table
+are clustered into a single feature, the frequency of that single feature
+in a given sample is the sum of the frequencies of the features that were
+clustered in that sample. Feature identifiers will be inherited from the
+centroid feature of each cluster. See the vsearch documentation for details
+on how sequence clustering is performed.
+
+Parameters
+----------
+sequences : FeatureData[Sequence]
+    The sequences corresponding to the features in table.
+table : FeatureTable[Frequency]
+    The feature table to be clustered.
+reference_sequences : FeatureData[Sequence]
+    The sequences to use as cluster centroids.
+perc_identity : Float % Range(0, 1, inclusive_start=False, inclusive_end=True)
+    The percent identity at which clustering should be performed. This
+    parameter maps to vsearch's --id parameter.
+strand : Str % Choices({'both', 'plus'}), optional
+    Search plus (i.e., forward) or both (i.e., forward and reverse
+    complement) strands.
+
+Returns
+-------
+clustered_table : FeatureTable[Frequency]
+    The table following clustering of features.
+clustered_sequences : FeatureData[Sequence]
+    The sequences representing clustered features, relabeled by the
+    reference IDs.
+unmatched_sequences : FeatureData[Sequence]
+    The sequences which failed to match any reference sequences. This
+    output maps to vsearch's --notmatched parameter.
+    ]]>
+	</help>
+</tool>