diff preprocessing.xml @ 0:3eb088816194 draft

planemo upload for repository https://github.com/eteriSokhoyan/galaxytools/tree/branchForIterations/tools/GraphClust commit 21aaee40723b5341b4236edeb0e72995c2054053

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/preprocessing.xml	Fri Dec 16 07:36:58 2016 -0500
@@ -0,0 +1,85 @@
+<tool id="preproc" name="Preprocessing" version="0.1">
+  <requirements>
+    <requirement type="package" version="0.1">graphclust-wrappers</requirement>
+  </requirements>
+    <stdio>
+        <exit_code range="1:" />
+    </stdio>
+    <command>
+		<![CDATA[
+
+    'preprocessing.pl'
+    '$fastaFile'  $max_length $in_winShift $min_seq_length
+
+]]>
+	</command>
+    <inputs>
+        <param type="data" name="fastaFile" format="fasta" />
+        <param name="max_length" type="integer" value="10000" size="5" label="window size"/>
+        <param name="in_winShift" type="integer" value="100" size="5" label="window shift in percent"/>
+        <param name="min_seq_length" type="integer" value="5" size="5" label="minimum sequence length"/>
+    </inputs>
+
+    <outputs>
+        <data name="data.fasta" format="fasta" from_work_dir="FASTA/data.fasta" label="data.fasta"/>
+        <data name="data.map" format="txt" from_work_dir="FASTA/data.map" label="data.map"/>
+        <data name="data.names" format="txt" from_work_dir="FASTA/data.names" label="data.names"/>
+        <data name="data.fasta.scan" format="fasta" from_work_dir="FASTA/data.fasta.scan" label="data.fasta.scan"/>
+        <data name="FASTA" format="zip" from_work_dir="FASTA.zip" label="FASTA.ZIP"/>
+    </outputs>
+
+
+    <tests>
+    <test>
+        <param name="fastaFile" value="input.fa"/>
+        <param name="max_length" value="10000"/>
+        <param name="in_winShift" value="100"/>
+        <param name="min_seq_length" value="5"/>
+        <output name="data.fasta" file="FASTA/data.fasta"/>
+        <output name="data.map" file="FASTA/data.map" />
+        <output name="data.names" file="FASTA/data.names"/>
+        <output name="data.fasta.scan" file="FASTA/data.fasta.scan" />
+    </test>
+</tests>
+
+    <help>
+<![CDATA[
+
+**What it does**
+
+The tool takes as an input file of sequences in Fasta format and creates the final input for GraphCLust based on given parameters.
+
+**Parameters**
+
++ **window size** : All input sequences are splitted into fragments of this length.
+  The shift of the sliding window can be defined via option *window shift in percent*.
+  This paramter reflects the expected length of signals to be found.
+  Slightly larger windows are usually ok. Too small windows can disturb existing signals.
+
+
+
+
++ **window shift in percent** : Relative window size in % for window shift during input preprocessing.
+  Please note that a small shift results in much more fragments for clustering. The benefit is that RNA
+  motifs/structures are not destroyed by arbitrary split points. Smaller
+  shifts usually increase the cluster quality. Too small shifts (<20) are not
+  recommended as a dense center is "polluted" by overlapping fragments and
+  no other occurences in the dataset can be found.
+
+
+
+
+
++ **minimum sequence length** : Minimal length of input sequences.
+  Every input sequence below that length is ignored completely during clustering.
+
+
+    ]]></help>
+
+
+    <citations>
+        <citation type="doi">10.1093/bioinformatics/bts224</citation>
+    </citations>
+
+
+</tool>