New Addition: ripples and general update to latest version of usher

tools/usher/macros.xml

@@ -1,6 +1,7 @@
 <macros>
-    <token name="@TOOL_VERSION@">0.2.1</token>
+    <token name="@TOOL_VERSION@">0.6.6</token>
     <token name="@GALAXY_TOOL_VERSION@">galaxy0</token>
+    <token name="@GALAXY_PROFILE@">23.2</token>
     <xml name="xrefs">
         <xrefs>
             <xref type="bio.tools">usher</xref>
@@ -15,15 +16,20 @@
         <citations>
             <citation type="doi">10.1101/2020.09.26.314971</citation>
             <citation type="doi">10.1101/2021.04.03.438321</citation>
+            <citation type="doi">10.1101/2021.08.04.455157</citation>
         </citations>
     </xml>
+    <xml name="version">
+        <version_command>usher --version</version_command>
+    </xml>
     <macro name="sanitize_string" >
         <sanitizer invalid_char="">
             <valid initial="string.letters,string.digits">
                 <add value="_"/>
                 <add value="-"/>
                 <add value="."/>
                 <add value=":"/>
+                <add value=","/>
             </valid>
         </sanitizer>
     </macro>

tools/usher/ripples.xml

@@ -0,0 +1,94 @@
+<tool id='usher_ripples' name='UShER RIPPLES' version='@TOOL_VERSION@+@GALAXY_TOOL_VERSION@' profile='@GALAXY_PROFILE@'>
+    <description>detect recombination events in large mutation annotated tree (MAT) files.</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="xrefs"/>
+    <expand macro='requirements' />
+    <expand macro="version"/>
+    <command detect_errors='exit_code'><![CDATA[
+   ## get correct extension filenames
+   ln -sf '$input_mat' '$input_mat.element_identifier' &&
+
+   ripples
+   --input-mat '$input_mat.element_identifier'
+
+   --branch-length $branch_length
+   --min-coordinate-range $min_coordinate_range
+   --max-coordinate-range $max_coordinate_range
+   --samples-filename '$samples_filename'
+   --parsimony-improvement $parsimony_improvement
+   --num-descendants $num_descendants
+
+   --outdir ./
+   --threads \${GALAXY_SLOTS:-1} > output_stdout.txt
+
+ ]]>    </command>
+    <inputs>
+        <param argument="--input-mat" type="data" format="protobuf3" label="Mutation-annotated tree object" help="Load a mutation annotated tree file, in protocol-buffers format (protobuf3)."/>
+        <param argument="--branch-length" type="integer" value="3" min="0" label="Minimum branch length" help="Minimum length of the branch to consider for recombination events. Default = 3." />
+        <param argument="--min-coordinate-range" type="integer" value="1000" min="0" label="Minimal coordinate range" help="Minimum range of the genomic coordinates of the mutations on the recombinant branch. Default = 1,000." />
+        <param argument="--max-coordinate-range" type="integer" value="10000000" min="0" label="Maximal coordinate range" help="Maximum range of the genomic coordinates of the mutations on the recombinant branch. Default = 10,000,000." />
+        <param argument="--samples-filename" type="data" format="txt" label="Sample restriction file" help="Restrict the search to the ancestors of the samples specified in the input file." />
+        <param argument="--parsimony-improvement" type="integer" value="3" min="0" label="Parsimony improvement" help="Minimum improvement in parsimony score of the recombinant sequences during the partial placement. Default = 3." />
+        <param argument="--num-descendants" type="integer" value="10" label="Number of descendants" help="Minimum number of leaves that node should have to be considered for recombinatino. Default = 10." />
+    </inputs>
+    <outputs>
+        <data name="recombination" format="tabular" from_work_dir='recombination.tsv' label="${tool.name} on ${on_string}: recombinations" >
+            <actions>
+                <action name="column_names" type="metadata" default="recomb_node_id,breakpoint-1_interval,breakpoint-2_interval,donor_node_id,donor_is_sibling,donor_parsimony,acceptor_node_id,acceptor_is_sibling,acceptor_parsimony,original_parsimony,min_starting_parsimony,recomb_parsimony" />
+            </actions>
+        </data>
+        <data name="descendants" format="tabular" from_work_dir='descendants.tsv' label="${tool.name} on ${on_string}: descendants" >
+            <actions>
+                <action name="column_names" type="metadata" default="node_id,descendants" />
+            </actions>
+        </data>
+
+    </outputs>
+    <tests>
+        <test expect_num_outputs="2">
+            <param name="input_mat" value="mutation_annotation.pb" ftype="protobuf3"/>
+            <param name="samples_filename" value="sample_names.txt" ftype="txt"/>
+            <output name="descendants" file="test_26_descendants.tabular" ftype="tabular"/>
+            <output name="recombination" file="test_26_recombination.tabular" ftype="tabular"/>
+        </test>
+        <test expect_num_outputs="2">
+            <param name="input_mat" value="mutation_annotation.pb" ftype="protobuf3"/>
+            <param name="samples_filename" value="sample_names.txt" ftype="txt"/>
+            <param name="num_descendants" value="20" />
+            <param name="parsimony_improvement" value="5" />
+            <param name="branch_length" value="2" />
+            <output name="descendants" file="test_27_descendants.tabular" ftype="tabular"/>
+            <output name="recombination" file="test_27_recombination.tabular" ftype="tabular"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+
+.. class:: infomark
+
+**Purpose**
+
+RIPPLES (Recombination Inference using Phylogenetic PLacEmentS) is a program used to detect recombination events in large mutation annotated tree (MAT) files.
+
+----
+
+RIPPLES is a program to rapidly and sensitively detect recombinant nodes and their ancestors in a mutation-annotated tree (MAT). RIPPLES exploits the fact that recombinant lineages arising from diverse genomes will often be found on “long branches” which result from accommodating the divergent evolutionary histories of the two parental haplotypes. Therefore, RIPPLES first identifies long branches in a MAT. RIPPLES then exhaustively breaks the potential recombinant sequence into distinct segments that are differentiated by mutations on the recombinant sequence and separated by up to two breakpoints. For each set of breakpoints, RIPPLES places each of its corresponding segments using maximum parsimony to find the two parental nodes – a donor and an acceptor – that result in the highest parsimony score improvement relative to the original placement on the global phylogeny. The nodes for which a set of breakpoints along with two parental nodes can be identified that provide a parsimony score improvement above a user-specified threshold are reported as recombinants.
+
+.. class:: infomark
+
+**RIPPLES Common Options**
+
+ - input-mat: Input mutation-annotated tree file [REQUIRED]. If only this argument is set, print the count of samples and nodes in the tree.
+ - branch-length (-l): Minimum length of the branch to consider for recombination events. Default = 3.
+ - min-coordinate-range (-r): Minimum range of the genomic coordinates of the mutations on the recombinant branch. Default = 1,000.
+ - max-coordinate-range (-R): Maximum range of the genomic coordinates of the mutations on the recombinant branch. Default = 10,000,000.
+ - samples-filename (-s): Restrict the search to the ancestors of the samples specified in the input file.
+ - parsimony-improvement (-p): Minimum improvement in parsimony score of the recombinant sequences during the partial placement. Default = 3.
+ - num-descendants (-n): Minimum number of leaves that node should have to be considered for recombinatino. Default = 10.
+
+You can find more information in the `RIPPLES official documentation page <https://usher-wiki.readthedocs.io/en/latest/ripples.html>`_.
+
+    ]]>    </help>
+    <expand macro="citations" />
+</tool>

tools/usher/test-data/rename_samples.tabular

@@ -1,4 +1,4 @@
-England/BRIS-1853249/2020|20-04-02	Spain/BRIS-1853249/2020|20-04-02
-Wales/PHWC-25B04/2020|20-03-24	Spain/BRIS-1853249/2020|20-04-02
-NPL/61-TW/2020|MT072688.1|20-01-13	Spain/BRIS-1853249/2020|20-04-02
-Wales/LIVE-A6831/2020|20-03-16	Spain/BRIS-1853249/2020|20-04-02
+England/BRIS-1853249/2020|20-04-02	Spain/BRIS-1853249/2020|20-04-02_A
+Wales/PHWC-25B04/2020|20-03-24	Spain/BRIS-1853249/2020|20-04-02_B
+NPL/61-TW/2020|MT072688.1|20-01-13	Spain/BRIS-1853249/2020|20-04-02_C
+Wales/LIVE-A6831/2020|20-03-16	Spain/BRIS-1853249/2020|20-04-02_D