diff rapidcluster.xml @ 0:12f2dd9ac1fd draft

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/rapidcluster.xml	Mon Dec 26 11:04:51 2016 -0500
@@ -0,0 +1,52 @@
+<tool id="rapidcluster_2" name="RapidCluster" version="2">
+
+	<description>Cluster closely-related sequences using Levenshtein edit distance filtering.</description>
+	
+	<version_command>rapidcluster -v</version_command>
+	
+	<command interpreter="perl">rapidcluster -i $input -o $output -d $distance -f $filter -c $max_clusters > $report
+	</command>
+
+	<inputs>
+		<param name="input" type="data" format="fasta" label="Input file"  help="Must use FASTA output from FASTAptamer-Count"></param>
+		<param name="distance" type="integer" label="Levenshtein Edit Distance" value="1" help="Minimum number of insertions, deletions, or substitutions required to transfer a sequence into another"></param>
+		<param name="filter" type="integer" label="Read Filter" optional="true" value="1" help="Only sequences with total reads greater than the value supplied will be clustered."></param> 
+		<param name="max_clusters" type="integer" label="Maximum number of clusters to find" optional="true" value="500" help="Script will stop after finding this much clusters"></param> 
+ 	</inputs>
+ 	
+    <outputs>
+    	<data name="output" format="fasta" label="$input RapidCluster output"></data>
+	<data name="report" format="txt" label="$input RapidCluster Report"></data>
+ 	</outputs>
+ 	
+    <help>
+
+.. class:: warningmark
+
+RapidCluster requires a FASTA formatted input file generated by FASTAptamer-Count.
+
+.. class:: warningmark
+
+RapidCluster uses an exhaustive approach to clustering and can take *several* hours to process. For faster processing utilize the "Read Filter" option to exclude low read sequences and define a reasonable number of clusters to find.
+
+------
+
+This version does not calculate exact Levenshtein distance for each pair of sequences, instead it simply checks if this distance is lower or greater than user-defined value. This makes script much faster for clustering highly-similar sequences.
+
+RapidCluster begins with the most abundant sequence in a population, referred to as the "seed sequence," and clusters with it every sequence in the file within an edit distance less than or equal to the specified edit distance (Cluster #1). The next most abundant unclustered sequence then serves as the next seed sequence for assembling the second cluster from the remaining sequences (Cluster #2), followed by the next most abundant unclustered sequence (Cluster #3), and so on. This process is iterated until every sequence is clustered.
+
+Output is FASTA formatted with the following information on the FASTA identifier line:
+
+	>Rank-Reads-RPM-Cluster#-RankWithinCluster-EditDistanceFromSeedSequence
+
+.. class:: infomark
+
+The "Read Filter" excludes from the clustering process sequences with a total number of reads less than or equal to the integer supplied. Because of the computational complexity of clustering large datasets, the default filter setting of 1 is designed to eliminate singleton sequences from clustering.
+
+------
+
+
+    </help>
+
+	
+</tool>