Repository 'mash_sketch'
hg clone https://toolshed.g2.bx.psu.edu/repos/iuc/mash_sketch

Changeset 2:91ee99b4f05a (2021-04-24)
Previous changeset 1:77289957d47b (2020-02-26) Next changeset 3:43f9ca23c132 (2021-04-24)
Commit message:
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/mash commit 57309b08e7a08b6f72982f0d78cb5574616c7b67"
modified:
macros.xml
mash_sketch.xml
added:
test-data/test_01_mash_sketch.msh
test-data/test_02_mash_sketch.msh
test-data/test_03_mash_sketch.msh
test-data/test_04_mash_sketch.msh
test-data/test_05_mash_sketch.msh
test-data/test_06_mash_sketch.msh
test-data/test_07_mash_sketch.msh
removed:
test-data/ERR024951_seqtk_sample_1000_1.sketch.msh
test-data/test_assembly.sketch.msh
b
diff -r 77289957d47b -r 91ee99b4f05a macros.xml
--- a/macros.xml Wed Feb 26 15:48:46 2020 -0500
+++ b/macros.xml Sat Apr 24 11:29:14 2021 +0000
b
@@ -1,23 +1,19 @@
 <macros>
-    <token name="@TOOL_VERSION@">2.1</token>
+    <token name="@TOOL_VERSION@">2.3</token>
     <token name="@INTYPES@">
         fasta,fasta.gz,fastq,fastq.gz,fastqsanger,fastqsanger.gz
     </token>
-    
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="@TOOL_VERSION@">mash</requirement>
+        </requirements>
+    </xml>
     <xml name="citations">
         <citations>
             <citation type="doi">10.1186/s13059-016-0997-x</citation>
         </citations>
     </xml>
-
-    <xml name="requirements">
-        <requirements>
-            <requirement type="package" version="@TOOL_VERSION@">mash</requirement>
-        </requirements>
-    </xml>
-
     <xml name="version_command">
         <version_command>mash --version</version_command>
     </xml>
-
 </macros>
b
diff -r 77289957d47b -r 91ee99b4f05a mash_sketch.xml
--- a/mash_sketch.xml Wed Feb 26 15:48:46 2020 -0500
+++ b/mash_sketch.xml Sat Apr 24 11:29:14 2021 +0000
[
b'@@ -11,22 +11,29 @@\n         mash sketch\n             -s \'${sketch_size}\'\n             -k \'${kmer_size}\'\n+            -w \'${prob_threshold}\'\n             #if str ( $reads_assembly.reads_assembly_selector ) == "reads"\n-              -m \'${reads_assembly.minimum_kmer_copies}\'\n-              -r\n-              #if str( $reads_assembly.reads_input.reads_input_selector ) == "paired"\n-                \'$reads_assembly.reads_input.reads_1\' \'$reads_assembly.reads_input.reads_2\'\n-              #end if\n-              #if str( $reads_assembly.reads_input.reads_input_selector ) == "paired_collection"\n-                \'$reads_assembly.reads_input.reads.forward\' \'$reads_assembly.reads_input.reads.reverse\'\n-              #end if\n-              #if str( $reads_assembly.reads_input.reads_input_selector ) == "single"\n-                \'$reads_assembly.reads_input.reads\'\n-              #end if\n+                -m \'${reads_assembly.minimum_kmer_copies}\'\n+                -r\n+                #if $reads_assembly.target_coverage\n+                    -c \'${reads_assembly.target_coverage}\'\n+                #end if\n+                #if $reads_assembly.genome_size\n+                    -g \'${reads_assembly.genome_size}\'\n+                #end if\n+                #if str( $reads_assembly.reads_input.reads_input_selector ) == "paired"\n+                    \'$reads_assembly.reads_input.reads_1\' \'$reads_assembly.reads_input.reads_2\'\n+                #end if\n+                #if str( $reads_assembly.reads_input.reads_input_selector ) == "paired_collection"\n+                    \'$reads_assembly.reads_input.reads.forward\' \'$reads_assembly.reads_input.reads.reverse\'\n+                #end if\n+                #if str( $reads_assembly.reads_input.reads_input_selector ) == "single"\n+                    \'$reads_assembly.reads_input.reads\'\n+                #end if\n             #elif str ( $reads_assembly.reads_assembly_selector ) == "assembly"\n-              -p \\${GALAXY_SLOTS:-1}\n-              \'${assembly}\'\n-              ${reads_assembly.individual_sequences}\n+                -p \\${GALAXY_SLOTS:-1}\n+                \'${assembly}\'\n+                ${reads_assembly.individual_sequences}\n             #end if\n             -o \'sketch\'\n     ]]></command>\n@@ -55,29 +62,104 @@\n                     </when>\n                 </conditional>\n                 <param type="integer" name="minimum_kmer_copies" argument="-m" value="1" min="1" max="1000" label="Minimum copies of each k-mer required to pass noise filter"/>\n+                <param type="integer" name="target_coverage" argument="-c" value="" min="0" max="500" optional="true" label="Target coverage" help="If specified, sketching will conclude if this coverage is reached before the end of the input file (estimated by average k-mer multiplicity)"/>\n+                <param type="integer" name="genome_size" argument="-g" value="" min="1000" max="10  0000000000" optional="true" label="Genome size" help="If specified, will be used for p-value calculation instead of an estimated size from k-mer content"/>\n             </when>\n             <when value="assembly">\n                 <param name="assembly" type="data" format="fasta,fasta.gz" label="Assembly"/>\n-                <param type="boolean" name="individual_sequences" truevalue="-i" falsevalue="" label="Sketch individual Sequences"/>\n+                <param type="boolean" name="individual_sequences" truevalue="-i" falsevalue="" label="Sketch individual Sequences" help="Sketch individual sequences, rather than whole files, e.g. for multi-fastas of single-chromosome genomes or pair-wise gene comparisons"/>\n             </when>\n         </conditional>\n-        <param type="integer" name="sketch_size" argument="-s" value="1000" min="10" max="1000000" label="Sketch size" />\n+        <param type="integer" name="sketch_size" argument="-s" value="1000" min="10" max="1000000" label="Sketch size" help="Each sketch will have at most this many non-redundant min-hashes"/>\n         <param type='..b'       <conditional name="reads_assembly">\n+                <param name="reads_assembly_selector" value="reads"/>\n+                <conditional name="reads_input">\n+                    <param name="reads_input_selector" value="single"/>\n+                    <param name="reads" value="ERR024951_seqtk_sample_1000_1.fastq"/>\n+                    <param name="minimum_kmer_copies" value="10"/>\n+                </conditional>\n+            </conditional>\n+            <output name="sketch" file="test_02_mash_sketch.msh" compare="sim_size" />\n+        </test>\n+        <test>\n+            <conditional name="reads_assembly">\n+                <param name="reads_assembly_selector" value="reads"/>\n+                <conditional name="reads_input">\n+                    <param name="reads_input_selector" value="single"/>\n+                    <param name="reads" value="ERR024951_seqtk_sample_1000_1.fastq"/>\n+                    <param name="target_coverage" value="1"/>\n+                </conditional>\n+            </conditional>\n+            <output name="sketch" file="test_03_mash_sketch.msh" compare="sim_size" />\n         </test>\n         <test>\n-            <param name="reads_assembly_selector" value="assembly" />\n-            <param name="assembly" value="test_assembly.fasta"/>\n-            <output name="sketch" file="test_assembly.sketch.msh" compare="sim_size" />\n+            <conditional name="reads_assembly">\n+                <param name="reads_assembly_selector" value="reads"/>\n+                <conditional name="reads_input">\n+                    <param name="reads_input_selector" value="single"/>\n+                    <param name="reads" value="ERR024951_seqtk_sample_1000_1.fastq"/>\n+                    <param name="genome_size" value="1000"/>\n+                </conditional>\n+            </conditional>\n+            <output name="sketch" file="test_04_mash_sketch.msh" compare="sim_size" />\n+        </test>\n+        <test>\n+            <conditional name="reads_assembly">\n+                <param name="reads_assembly_selector" value="reads"/>\n+                <conditional name="reads_input">\n+                    <param name="reads_input_selector" value="single"/>\n+                    <param name="reads" value="ERR024951_seqtk_sample_1000_1.fastq"/>\n+                </conditional>\n+            </conditional>\n+            <param name="sketch_size" value="500"/>\n+            <output name="sketch" file="test_05_mash_sketch.msh" compare="sim_size" />\n+        </test>\n+        <test>\n+            <conditional name="reads_assembly">\n+                <param name="reads_assembly_selector" value="reads"/>\n+                <conditional name="reads_input">\n+                    <param name="reads_input_selector" value="single"/>\n+                    <param name="reads" value="ERR024951_seqtk_sample_1000_1.fastq"/>\n+                </conditional>\n+            </conditional>\n+            <param name="kmer_size" value="17"/>\n+            <output name="sketch" file="test_06_mash_sketch.msh" compare="sim_size" />\n+        </test>\n+        <test>\n+            <conditional name="reads_assembly">\n+                <param name="reads_assembly_selector" value="reads"/>\n+                <conditional name="reads_input">\n+                    <param name="reads_input_selector" value="single"/>\n+                    <param name="reads" value="ERR024951_seqtk_sample_1000_1.fastq"/>\n+                </conditional>\n+            </conditional>\n+            <param name="prob_threshold" value="0.1"/>\n+            <output name="sketch" file="test_06_mash_sketch.msh" compare="sim_size" />\n+        </test>\n+        <test>\n+            <conditional name="reads_assembly">\n+                <param name="reads_assembly_selector" value="assembly"/>\n+                <param name="assembly" value="test_assembly.fasta"/>\n+            </conditional>\n+            <output name="sketch" file="test_07_mash_sketch.msh" compare="sim_size" />\n         </test>\n     </tests>\n     <help><![CDATA[\n'
b
diff -r 77289957d47b -r 91ee99b4f05a test-data/ERR024951_seqtk_sample_1000_1.sketch.msh
b
Binary file test-data/ERR024951_seqtk_sample_1000_1.sketch.msh has changed
b
diff -r 77289957d47b -r 91ee99b4f05a test-data/test_01_mash_sketch.msh
b
Binary file test-data/test_01_mash_sketch.msh has changed
b
diff -r 77289957d47b -r 91ee99b4f05a test-data/test_02_mash_sketch.msh
b
Binary file test-data/test_02_mash_sketch.msh has changed
b
diff -r 77289957d47b -r 91ee99b4f05a test-data/test_03_mash_sketch.msh
b
Binary file test-data/test_03_mash_sketch.msh has changed
b
diff -r 77289957d47b -r 91ee99b4f05a test-data/test_04_mash_sketch.msh
b
Binary file test-data/test_04_mash_sketch.msh has changed
b
diff -r 77289957d47b -r 91ee99b4f05a test-data/test_05_mash_sketch.msh
b
Binary file test-data/test_05_mash_sketch.msh has changed
b
diff -r 77289957d47b -r 91ee99b4f05a test-data/test_06_mash_sketch.msh
b
Binary file test-data/test_06_mash_sketch.msh has changed
b
diff -r 77289957d47b -r 91ee99b4f05a test-data/test_07_mash_sketch.msh
b
Binary file test-data/test_07_mash_sketch.msh has changed
b
diff -r 77289957d47b -r 91ee99b4f05a test-data/test_assembly.sketch.msh
b
Binary file test-data/test_assembly.sketch.msh has changed