# HG changeset patch
# User hammock
# Date 1453726712 18000
# Node ID 4db310b7e37c3d21d61bbe5d9b2fa7360f9c619d
# Parent  d90f4809ccc6292bc9970160d0f9e2856fdcac89
Uploaded

diff -r d90f4809ccc6 -r 4db310b7e37c Hammock/dist/Hammock.jar
Binary file Hammock/dist/Hammock.jar has changed
diff -r d90f4809ccc6 -r 4db310b7e37c hammock.xml
--- a/hammock.xml	Fri Aug 28 07:38:12 2015 -0400
+++ b/hammock.xml	Mon Jan 25 07:58:32 2016 -0500
@@ -1,9 +1,9 @@
-<tool id="hammock_1.0" name="Hammock - cluster peptides" version="1.0.2" hidden="false">
+<tool id="hammock_1.0" name="Hammock - cluster peptides" version="1.0.4" hidden="false">
 
     <description>Clusters short peptide sequences</description>
 
     <command interpreter="bash">
-wrapper.sh \$HAMMOCK_JAR full --galaxy -t \${GALAXY_SLOTS:-4} -i $input --goc $output_clusters --gos $output_sequences
+wrapper.sh \$HAMMOCK_JAR full --galaxy -t \${GALAXY_SLOTS:-4} -i $input --goc $output_clusters --gos $output_sequences --goo $output_sequences_ordered
 
 	   #if $label_params.set_labels == "set":
                 #for $s in $label_params.round_labels:
@@ -242,8 +242,9 @@
 </inputs>
 
    <outputs>  
-       <data format="csv" name="output_clusters" />
-	<data format="csv" name="output_sequences" />
+       <data format="tsv" name="output_clusters" />
+	<data format="tsv" name="output_sequences" />
+	<data format="tsv" name="output_sequences_ordered" />
    </outputs>
 
   <requirements>
@@ -252,7 +253,7 @@
 		<requirement type="set_environment">MATRIX_PATH</requirement>
 		<requirement type="package" version="1.6.0">java</requirement>
 		<requirement type="package" version="1.2.0">clustalomega</requirement>
-		<requirement type="package" version="3.1b1">hmmer</requirement>
+		<requirement type="package" version="3.1b2">hmmer</requirement>
 		<requirement type="package" version="2.0.16">hhsuite</requirement>
   </requirements>
 
@@ -278,6 +279,8 @@
 <help>
 
 
+**HAMMOCK version 1.0.4**
+
 **Hammock overview**
 
 Hammock performs peptide sequence clustering. It is able to identify clusters of sequences sharing a sequence motif within big datasets. For news, documentation and other available versions, see http://www.recamo.cz/en/software/hammock-cluster-peptides/
@@ -289,7 +292,7 @@
 **Citation**
 Please cite: 
 
-Krejci A, et al. *in preparation* 
+Krejci, Adam, et al. "Hammock: a hidden Markov model-based peptide clustering algorithm to identify protein-interaction consensus motifs in large datasets." Bioinformatics 32.1 (2016): 9-16.
 
 ------
 
@@ -312,7 +315,7 @@
 
 **Outputs**
 
-Hammock returns two files, both are semicolon-separated tables.
+Hammock returns three files, all of them are tab-separated tables.
 
 The first is the cluster overview file. It contains one line for each resulting cluster plus header. Columns are: 
 
@@ -324,7 +327,9 @@
   | label1, label2 etc. Counts of sequences with particular labels
 
 
-The second file provides more detailed information. It contains one line for each clustered sequence plus header. Columns are: 
+The second file provides more detailed information. It contains one line for each clustered (unique) sequence plus header. The sequences are ordered according to their presence in clusters, from the largest cluster and within a cluster, from the most abundant sequence.
+
+Columns are: 
 
 cluster_id sequence alignment sum label1 label2 label3 ...
 
@@ -334,10 +339,13 @@
   | sum: Total count of copies of this sequence (sum over all labels)
   | label1, label2 etc. Counts of copies with particular labels
 
+
+The third file is the same as the second file, with two differences: it also contains sequences not belonging to any cluster (these have "NA" in the cluster_id column) and the order of the sequences in this file is the same as their order in the input fasta file.
+
 ------
 
 **Parameters**
-Default and auto-detected parameters have been carefully tuned and tested to work well with several datasets, they are especially suited for short peptides from Phage display experiments. Neverheless, there is no such thing as universal rules suitable for every dataset - parameter understanding and tuning may be needed. For more detailed description of parameters, see the documentation_.
+Default and auto-detected parameters have been carefully tuned and tested to work well with several datasets, they are especially suited for short peptides from phage display experiments. Neverheless, there is no such thing as universal rules suitable for every dataset - parameter understanding and tuning may be needed. For more detailed description of parameters, see the documentation_.
 
 .. _documentation: http://www.recamo.cz/userfiles/file/Software/Hammock/Hammock-manual.pdf
 
diff -r d90f4809ccc6 -r 4db310b7e37c tool_dependencies.xml
--- a/tool_dependencies.xml	Fri Aug 28 07:38:12 2015 -0400
+++ b/tool_dependencies.xml	Mon Jan 25 07:58:32 2016 -0500
@@ -25,11 +25,11 @@
 			</install>
 		</package>
 
-        <package name="hmmer" version="3.1b1">
+        <package name="hmmer" version="3.1b2">
             <install version="1.0">
 				<actions_group>
                     <actions architecture="x86_64" os="linux">
-                        <action type="download_by_url">http://selab.janelia.org/software/hmmer3/3.1b1/hmmer-3.1b1-linux-intel-x86_64.tar.gz</action>
+                        <action type="download_by_url">http://eddylab.org/software/hmmer3/3.1b2/hmmer-3.1b2-linux-intel-x86_64.tar.gz</action>
 						<action type="move_file">
                     		<source>binaries/hmmbuild</source>
                     		<destination>$INSTALL_DIR</destination>