diff NSPDK_sparseVect.xml @ 0:165fe96228be draft

planemo upload for repository https://github.com/eteriSokhoyan/galaxytools/tree/branchForIterations/tools/GraphClust/NSPDK commit 21aaee40723b5341b4236edeb0e72995c2054053
author rnateam
date Fri, 16 Dec 2016 07:36:07 -0500
parents
children 90a4a2e7d876
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/NSPDK_sparseVect.xml	Fri Dec 16 07:36:07 2016 -0500
@@ -0,0 +1,66 @@
+<tool id="nspdk_sparse" name="NSPDK_sparseVect" version="9.2">
+	<requirements>
+			<requirement type="package" version="0.1">graphclust-wrappers</requirement>
+			<requirement type="package" version="9.2">nspdk</requirement>
+	</requirements>
+	<stdio>
+		<exit_code range="1:" />
+	</stdio>
+	<command>
+		<![CDATA[
+
+
+      'NSPDK_sparseVect.pl' '$data_fasta' '$gspan_file'  $max_rad $max_dist_relations
+
+]]>
+	</command>
+	<inputs>
+		<param type="data" name="gspan_file" format="searchgui_archive"  />
+		<param type="data" name="data_fasta" format="fasta" />
+		<param name="max_rad" type="integer" value="3" size="5" label="maximum radius " help="-R"/>
+		<param name="max_dist_relations" type="integer" value="3" size="5" label="maximum distance relations" help="-D"/>
+	</inputs>
+	<outputs>
+		<data name="data_svector" format="zip" from_work_dir="SVECTOR/data.svector" label="data_svector"/>
+	</outputs>
+	<tests>
+		<test>
+			<param name="data_fasta" value="data.fasta"/>
+			<param name="gspan_file" value="1.group.gspan.bz2" ftype="searchgui_archive"/>
+			<param name="max_rad" value="3"/>
+			<param name="max_dist_relations" value="3"/>
+			<output name="data_svector" file="SVECTOR/data.svector" ftype="zip" />
+		</test>
+	</tests>
+	<help>
+		<![CDATA[
+
+**What it does**
+
+Produces an explicit sparse feature encoding.
+Integer code for the invariant graph encoding is used as a feature indicator. In this way,
+the integer associated to each feature (i.e. each pair or neighborhood subgraphs of radius r whose
+roots are at distance d) can be interpreted as the feature key and the (normalized) count of occurrences as its value.
+This allows to obtain an explicit feature encoding for a given graph G as a sparse vector in ℝ^m (with a very high dimension m).
+
+**Parameters**
+
++	**-R** <max radius> (default: 1)
++	**-D** <max distance relations> (default: 4)
+
+
+    ]]>
+	</help>
+	<citations>
+		<citation type="doi">10.1093/bioinformatics/bts224</citation>
+		<citation type="bibtex">@inproceedings{costa2010fast,
+      title={Fast neighborhood subgraph pairwise distance kernel},
+      author={Costa, Fabrizio and De Grave, Kurt},
+      booktitle={Proceedings of the 26th International Conference on Machine Learning},
+      pages={255--262},
+      year={2010},
+      organization={Omnipress}
+    }
+	</citation>
+	</citations>
+</tool>