Mercurial > repos > iuc > semibin

changeset 1:6b517dc161e4 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/semibin commit 59a7b7a334fd2c3aca6163c2ff11d18ef654ab9d
author iuc
date Mon, 27 Mar 2023 08:25:14 +0000
parents 7b382efabb98
children 99ff9221182c
files macros.xml semibin.xml
diffstat 2 files changed, 150 insertions(+), 12 deletions(-) [+]
line wrap: on
line diff
--- a/macros.xml	Fri Oct 14 21:38:26 2022 +0000
+++ b/macros.xml	Mon Mar 27 08:25:14 2023 +0000
@@ -1,6 +1,6 @@
 <?xml version="1.0"?>
 <macros>
-    <token name="@TOOL_VERSION@">1.1.1</token>
+    <token name="@TOOL_VERSION@">1.5.1</token>
     <token name="@VERSION_SUFFIX@">0</token>
     <token name="@PROFILE@">21.01</token>
     <xml name="biotools">
@@ -282,7 +282,7 @@
         <data name="single_split_cov" format="csv" from_work_dir="output/*_data_split_cov.csv" label="${tool.name} on ${on_string}: Coverage (split data)">
             <filter>mode["select"]=="single" and extra_output and "coverage" in extra_output</filter>
         </data>
-        <collection name="co_cov" type="list" label="${tool.name} on ${on_string}: Coverage">
+        <collection name="co_cov" type="list" label="${tool.name} on ${on_string}: Coverage (co_cov)">
             <filter>mode["select"]=="co" and extra_output and "coverage" in extra_output</filter>
             <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_cov\.csv" format="csv" directory="output/" />
         </collection>
@@ -290,7 +290,7 @@
             <filter>mode["select"]=="co" and extra_output and "coverage" in extra_output</filter>
             <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_split_cov\.csv" format="csv" directory="output/" />
         </collection>
-        <collection name="multi_cov" type="list" label="${tool.name} on ${on_string}: Coverage">
+        <collection name="multi_cov" type="list" label="${tool.name} on ${on_string}: Coverage (multi_cov)">
             <filter>mode["select"]=="multi" and extra_output and "coverage" in extra_output</filter>
             <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_cov.csv" format="csv" directory="output/samples/" />
         </collection>
@@ -298,11 +298,11 @@
             <filter>mode["select"]=="multi" and extra_output and "coverage" in extra_output</filter>
             <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data_cov.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
         </collection>
-        <collection name="multi_split_cov" type="list" label="${tool.name} on ${on_string}: Coverage (split data) per sample">
+        <collection name="multi_split_cov" type="list" label="${tool.name} on ${on_string}: Coverage (split data) per sample (multi_split_cov)">
             <filter>mode["select"]=="multi" and extra_output and "coverage" in extra_output</filter>
             <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_split_cov.csv" format="csv" directory="output/samples/" />
         </collection>
-        <collection name="multi_split_cov_sample" type="list" label="${tool.name} on ${on_string}: Coverage (split data) per sample">
+        <collection name="multi_split_cov_sample" type="list" label="${tool.name} on ${on_string}: Coverage (split data) per sample (multi_split_cov_sample)">
             <filter>mode["select"]=="multi" and extra_output and "coverage" in extra_output</filter>
             <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data_split_cov.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
         </collection>
@@ -348,4 +348,4 @@
             <citation type="doi">10.1038/s41467-022-29843-y</citation>
         </citations>
     </xml>
-</macros>
\ No newline at end of file
+</macros>
--- a/semibin.xml	Fri Oct 14 21:38:26 2022 +0000
+++ b/semibin.xml	Mon Mar 27 08:25:14 2023 +0000
@@ -110,7 +110,7 @@
             <filter>mode["select"]!="multi"</filter>
             <discover_datasets pattern=".*?\.(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_bins" />
         </collection>
-        <collection name="multi_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins before reclustering">
+        <collection name="multi_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins before reclustering (multi_bins)">
             <filter>mode["select"]=="multi"</filter>
             <discover_datasets pattern=".*?\.(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/bins" />
         </collection>
@@ -158,13 +158,34 @@
             <section name="bin">
                 <param name="max_node" value="1"/>
                 <param name="max_edges" value="200"/>
-                <param name="minfasta_kbs" value="200"/>
+                <param name="minfasta_kbs" value="2"/>
                 <param name="no_recluster" value="false"/>
             </section>
             <param name="extra_output" value="data,coverage,contigs"/>
-            <output_collection name="output_recluster_bins" count="0"/>
-            <output_collection name="output_bins" count="3">
-                <element name="0" ftype="fasta">
+            <output_collection name="output_recluster_bins" count="39">
+            	<element name="0" ftype="fasta">
+                    <assert_contents>
+                        <has_text text=">g1k_0"/>
+                    </assert_contents>
+                </element>
+                <element name="1" ftype="fasta">
+                    <assert_contents>
+                        <has_text text=">g1k_1"/>
+                    </assert_contents>
+                </element>
+                <element name="2" ftype="fasta">
+                    <assert_contents>
+                        <has_text text=">g1k_2"/>
+                    </assert_contents>
+                </element>
+                <element name="39" ftype="fasta">
+                    <assert_contents>
+                        <has_text text=">g3k_9"/>
+                    </assert_contents>
+                </element>
+            </output_collection>
+            <output_collection name="output_bins" count="0">
+                <!--<element name="0" ftype="fasta">
                     <assert_contents>
                         <has_text text=">g1k_0"/>
                     </assert_contents>
@@ -178,7 +199,7 @@
                     <assert_contents>
                         <has_text text=">g3k_0"/>
                     </assert_contents>
-                </element>
+                </element>-->
             </output_collection>
             <output name="single_data" ftype="csv">
                 <assert_contents>
@@ -292,6 +313,84 @@
                 </element>
             </output_collection>
         </test>
+        <test expect_num_outputs="4">
+            <conditional name="mode">
+                <param name="select" value="co"/>
+                <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
+                <param name="input_bam" ftype="bam" value="input_coassembly_sorted1.bam,input_coassembly_sorted2.bam,input_coassembly_sorted3.bam,input_coassembly_sorted4.bam,input_coassembly_sorted5.bam"/>
+                <conditional name="ref">
+                    <param name="select" value="taxonomy"/>
+                    <param name="taxonomy_annotation_table" value="taxonomy.tsv"/>
+                </conditional>
+            </conditional>
+            <conditional name="min_len">
+                <param name="method" value="ratio"/>
+                <param name="ratio" value="0.05"/>
+            </conditional>
+            <param name="orf_finder" value="fraggenescan"/>
+            <param name="random-seed" value="0"/>
+            <section name="annot">
+                <param name="ml_threshold" value=""/>
+            </section>
+            <section name="training">
+                <param name="epoches" value="20"/>
+                <param name="batch_size" value="2048"/>
+            </section>
+            <section name="bin">
+                <param name="max_node" value="1"/>
+                <param name="max_edges" value="200"/>
+                <param name="minfasta_kbs" value="200"/>
+                <param name="no_recluster" value="false"/>
+            </section>
+            <param name="extra_output" value="coverage"/>
+            <output_collection name="output_recluster_bins" count="1">
+                <element name="30" ftype="fasta">
+                    <assert_contents>
+                        <has_text text=">g3k_0"/>
+                    </assert_contents>
+                </element>
+            </output_collection>
+            <output_collection name="co_cov" count="5">
+                <element name="0" ftype="csv">
+                    <assert_contents>
+                        <has_text text="g1k_0"/>
+                        <has_text text="g2k_7"/>
+                    </assert_contents>
+                </element>
+                <element name="1" ftype="csv">
+                    <assert_contents>
+                        <has_text text="g1k_0"/>
+                        <has_text text="g2k_7"/>
+                    </assert_contents>
+                </element>
+                <element name="4" ftype="csv">
+                    <assert_contents>
+                        <has_text text="g1k_0"/>
+                        <has_text text="g2k_7"/>
+                    </assert_contents>
+                </element>
+            </output_collection>
+            <output_collection name="co_split_cov" count="5">
+                <element name="0" ftype="csv">
+                    <assert_contents>
+                        <has_text text="g1k_0_1"/>
+                        <has_text text="g2k_7_2"/>
+                    </assert_contents>
+                </element>
+                <element name="1" ftype="csv">
+                    <assert_contents>
+                        <has_text text="g1k_0_1"/>
+                        <has_text text="g2k_7_2"/>
+                    </assert_contents>
+                </element>
+                <element name="2" ftype="csv">
+                    <assert_contents>
+                        <has_text text="g1k_0_1"/>
+                        <has_text text="g2k_7_2"/>
+                    </assert_contents>
+                </element>
+            </output_collection>
+        </test>
         <test expect_num_outputs="1">
             <conditional name="mode">
                 <param name="select" value="single"/>
@@ -330,6 +429,44 @@
                 </element>
             </output_collection>
         </test>
+        <test expect_num_outputs="2">
+            <conditional name="mode">
+                <param name="select" value="single"/>
+                <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
+                <param name="input_bam" ftype="bam" value="input_single.bam"/>
+                <conditional name="ref">
+                    <param name="db_selector" value="cached"/>
+                    <param name="cached_db" value="test-db"/>
+                </conditional>
+            </conditional>
+            <conditional name="min_len">
+                <param name="method" value="ratio"/>
+                <param name="ratio" value="0.05"/>
+            </conditional>
+            <param name="orf_finder" value="fraggenescan"/>
+            <param name="random-seed" value="0"/>
+            <section name="annot">
+                <param name="ml_threshold" value=""/>
+            </section>
+            <section name="training">
+                <param name="epoches" value="20"/>
+                <param name="batch_size" value="2048"/>
+            </section>
+            <section name="bin">
+                <param name="max_node" value="1"/>
+                <param name="max_edges" value="200"/>
+                <param name="minfasta_kbs" value="200"/>
+                <param name="no_recluster" value="false"/>
+            </section>
+            <param name="extra_output" value=""/>
+            <output_collection name="output_recluster_bins" count="1">
+                <element name="30" ftype="fasta">
+                    <assert_contents>
+                        <has_text text=">g3k_0"/>
+                    </assert_contents>
+                </element>
+            </output_collection>
+        </test>
         <test expect_num_outputs="8">
             <conditional name="mode">
                 <param name="select" value="multi"/>
@@ -420,6 +557,7 @@
                 </element>
             </output_collection>
         </test>
+        
     </tests>
     <help><![CDATA[
 @HELP_HEADER@