Mercurial > repos > iuc > semibin

diff semibin.xml @ 2:9de6b5e570df 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 a9fc83e0029266f910b549d5d1eef6a9bc3e3f7b
author iuc
date Tue, 25 Mar 2025 15:52:22 +0000
parents 2eeff5d4a5de
children 8673617e7e09
line wrap: on
line diff
--- a/semibin.xml	Mon Mar 27 08:22:16 2023 +0000
+++ b/semibin.xml	Tue Mar 25 15:52:22 2025 +0000
@@ -12,24 +12,25 @@
 #import re
 @BAM_FILES@
 @FASTA_FILES@
-
-SemiBin
+SemiBin2
 #if $mode.select == 'single' or $mode.select == 'co'
     single_easy_bin
     #if $mode.select == 'single' and str($mode.environment) != ''
     --environment '$mode.environment'
     #end if
-    #if $mode.ref.select == "cached"
+    #if $mode.ref.select == "cached":
     --reference-db-data-dir '$mode.ref.cached_db.fields.path'
-    #else
+    #end if
+    #if $mode.ref.select == "taxonomy"
     --taxonomy-annotation-table '$mode.ref.taxonomy_annotation_table'
     #end if
 #else
     multi_easy_bin
     --separator '$separator'
-    #if $mode.ref.select == "cached"
+    #if $mode.ref.select == "cached":
     --reference-db-data-dir '$mode.ref.cached_db.fields.path'
-    #else
+    #end if
+    #if $mode.ref.select == "taxonomy"
     --taxonomy-annotation-table 
         #for $e in $mode.ref.taxonomy_annotation_table
             '$e' 
@@ -44,7 +45,7 @@
     --orf-finder '$orf_finder'
     --random-seed $random_seed
 
-#if str($annot.ml_threshold) != ''
+#if $annot.ml_threshold:
     --ml-threshold $annot.ml_threshold
 #end if
     --epoches $training.epoches
@@ -52,7 +53,10 @@
     --max-node $bin.max_node
     --max-edges $bin.max_edges
     --minfasta-kbs $bin.minfasta_kbs
-    $bin.no_recluster
+#if ($mode.select == 'single' or $mode.select == 'co') and $extra_output and "pre_reclustering_bins" in $extra_output
+    --write-pre-reclustering-bins
+#end if
+    --compression none
     --threads \${GALAXY_SLOTS:-1}
     --processes \${GALAXY_SLOTS:-1}
 && 
@@ -93,26 +97,30 @@
             <expand macro="max-node"/>
             <expand macro="max-edges"/>
             <expand macro="minfasta-kbs"/>
-            <expand macro="no-recluster"/>
         </section>
         <param name="extra_output" type="select" multiple="true" optional="true" label="Extra outputs" help="In addition to the training data">
             <option value="data">Training data</option>
             <option value="coverage">Coverage files</option>
             <option value="contigs">Contigs (if multiple sample)</option>
+            <option value="pre_reclustering_bins">Pre-reclustering bins (only single sample and co-assembly)</option>
         </param>
     </inputs>
     <outputs>
-        <collection name="output_recluster_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins after reclustering">
-            <filter>not bin["no_recluster"]</filter>
-            <discover_datasets pattern=".*?\.(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_recluster_bins" />
+        <collection name="output_pre_recluster_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins before reclustering">
+            <filter>mode["select"]!="multi" and extra_output and "pre_reclustering_bins" in extra_output</filter>
+            <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_prerecluster_bins"/>
         </collection>
-        <collection name="output_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins before reclustering">
-            <filter>mode["select"]!="multi"</filter>
-            <discover_datasets pattern=".*?\.(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_bins" />
+        <collection name="output_after_recluster_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins after reclustering">
+            <filter>mode["select"]!="multi" and extra_output and "pre_reclustering_bins" in extra_output</filter>
+            <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_recluster_bins"/>
+        </collection>
+        <collection name="output_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins">
+            <filter>mode["select"]!="multi" and not "pre_reclustering_bins" in extra_output</filter>
+            <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_bins"/>
         </collection>
         <collection name="multi_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins before reclustering (multi_bins)">
             <filter>mode["select"]=="multi"</filter>
-            <discover_datasets pattern=".*?\.(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/bins" />
+            <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/bins"/>
         </collection>
         <data name="single_data" format="csv" from_work_dir="output/data.csv" label="${tool.name} on ${on_string}: Training data">
             <filter>(mode["select"]=="single" or mode["select"]=="co") and extra_output and "data" in extra_output</filter>
@@ -131,7 +139,7 @@
         <expand macro="generate_sequence_features_extra_outputs"/>
     </outputs>
     <tests>
-        <test expect_num_outputs="6">
+        <test expect_num_outputs="5">
             <conditional name="mode">
                 <param name="select" value="single"/>
                 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
@@ -147,10 +155,7 @@
                 <param name="min_len" value="0" />
             </conditional>
             <param name="orf_finder" value="prodigal"/>
-            <param name="random-seed" value="0"/>
-            <section name="annot">
-                <param name="ml_threshold" value=""/>
-            </section>
+            <param name="random_seed" value="0"/>
             <section name="training">
                 <param name="epoches" value="20"/>
                 <param name="batch_size" value="2048"/>
@@ -158,49 +163,61 @@
             <section name="bin">
                 <param name="max_node" value="1"/>
                 <param name="max_edges" value="200"/>
-                <param name="minfasta_kbs" value="2"/>
-                <param name="no_recluster" value="false"/>
+                <param name="minfasta_kbs" value="200"/>
             </section>
             <param name="extra_output" value="data,coverage,contigs"/>
-            <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>
-                </element>
-                <element name="1" ftype="fasta">
-                    <assert_contents>
-                        <has_text text=">g2k_0"/>
-                    </assert_contents>
-                </element>
-                <element name="2" ftype="fasta">
-                    <assert_contents>
-                        <has_text text=">g3k_0"/>
-                    </assert_contents>
-                </element>-->
-            </output_collection>
+            <output_collection name="output_bins" count="0"/>
+            <output name="single_data" ftype="csv">
+                <assert_contents>
+                    <has_text text="g1k_0"/>
+                    <has_text text="g4k_7"/>
+                </assert_contents>
+            </output>
+            <output name="single_data_split" ftype="csv">
+                <assert_contents>
+                    <has_text text="g1k_0_1"/>
+                    <has_text text="g1k_6_2"/>
+                </assert_contents>
+            </output>
+            <output name="single_cov" ftype="csv">
+                <assert_contents>
+                    <has_text text="g1k_0"/>
+                    <has_text text="0.027"/>
+                </assert_contents>
+            </output>
+            <output name="single_split_cov" ftype="csv">
+                <assert_contents>
+                    <has_size value="1" delta="1"/>
+                </assert_contents>
+            </output>
+        </test>
+        <test expect_num_outputs="5">
+            <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="select" value="ml"/>
+                </conditional>
+                <param name="environment" value="human_gut"/>
+            </conditional>
+            <conditional name="min_len">
+                <param name="method" value="min-len"/>
+                <param name="min_len" value="0" />
+            </conditional>
+            <param name="orf_finder" value="prodigal"/>
+            <param name="random_seed" value="0"/>
+            <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"/>
+            </section>
+            <param name="extra_output" value="data,coverage,contigs"/>
+            <output_collection name="output_bins" count="0"/>
             <output name="single_data" ftype="csv">
                 <assert_contents>
                     <has_text text="g1k_0"/>
@@ -231,19 +248,15 @@
                 <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"/>
+                    <param name="select" value="ml"/>
                 </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>
+            <param name="orf_finder" value="fast-naive"/>
+            <param name="random_seed" value="0"/>
             <section name="training">
                 <param name="epoches" value="20"/>
                 <param name="batch_size" value="2048"/>
@@ -252,26 +265,9 @@
                 <param name="max_node" value="1"/>
                 <param name="max_edges" value="200"/>
                 <param name="minfasta_kbs" value="200"/>
-                <param name="no_recluster" value="true"/>
             </section>
             <param name="extra_output" value="coverage"/>
-            <output_collection name="output_bins" count="3">
-                <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=">g2k_0"/>
-                    </assert_contents>
-                </element>
-                <element name="2" ftype="fasta">
-                    <assert_contents>
-                        <has_text text=">g3k_0"/>
-                    </assert_contents>
-                </element>
-            </output_collection>
+            <output_collection name="output_bins" count="0"/>
             <output_collection name="co_cov" count="5">
                 <element name="0" ftype="csv">
                     <assert_contents>
@@ -313,7 +309,75 @@
                 </element>
             </output_collection>
         </test>
-        <test expect_num_outputs="4">
+        <test expect_num_outputs="3">
+            <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="fast-naive"/>
+            <param name="random_seed" value="0"/>
+            <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"/>
+            </section>
+            <param name="extra_output" value="coverage"/>
+            <output_collection name="output_bins" count="0"/>
+            <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="3">
             <conditional name="mode">
                 <param name="select" value="co"/>
                 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
@@ -328,10 +392,7 @@
                 <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>
+            <param name="random_seed" value="0"/>
             <section name="training">
                 <param name="epoches" value="20"/>
                 <param name="batch_size" value="2048"/>
@@ -340,16 +401,9 @@
                 <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="output_bins" count="0"/>
             <output_collection name="co_cov" count="5">
                 <element name="0" ftype="csv">
                     <assert_contents>
@@ -397,7 +451,7 @@
                 <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="select" value="cached"/>
                     <param name="cached_db" value="test-db"/>
                 </conditional>
             </conditional>
@@ -406,10 +460,7 @@
                 <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>
+            <param name="random_seed" value="0"/>
             <section name="training">
                 <param name="epoches" value="20"/>
                 <param name="batch_size" value="2048"/>
@@ -418,13 +469,11 @@
                 <param name="max_node" value="1"/>
                 <param name="max_edges" value="200"/>
                 <param name="minfasta_kbs" value="200"/>
-                <param name="no_recluster" value="true"/>
             </section>
-            <param name="extra_output" value=""/>
-            <output_collection name="output_bins" count="3">
-                <element name="0" ftype="fasta">
+            <output_collection name="output_bins" count="1">
+                <element name="SemiBin_30" ftype="fasta">
                     <assert_contents>
-                        <has_text text=">g1k_0"/>
+                        <has_text text=">g3k_0"/>
                     </assert_contents>
                 </element>
             </output_collection>
@@ -435,7 +484,7 @@
                 <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="select" value="cached"/>
                     <param name="cached_db" value="test-db"/>
                 </conditional>
             </conditional>
@@ -444,10 +493,7 @@
                 <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>
+            <param name="random_seed" value="0"/>
             <section name="training">
                 <param name="epoches" value="20"/>
                 <param name="batch_size" value="2048"/>
@@ -456,13 +502,29 @@
                 <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">
+            <param name="extra_output" value="pre_reclustering_bins"/>
+            <output_collection name="output_pre_recluster_bins" count="3">
+                <element name="SemiBin_0" ftype="fasta">
+                    <assert_contents>    
+                        <has_text text="g1k_0"/>
+                    </assert_contents>
+                </element>
+                <element name="SemiBin_1" ftype="fasta">
+                    <assert_contents>    
+                        <has_text text="g2k_0"/>
+                    </assert_contents>
+                </element>
+                <element name="SemiBin_2" ftype="fasta">
+                    <assert_contents>    
+                        <has_text text="g3k_0"/>
+                    </assert_contents>
+                </element>
+            </output_collection>
+            <output_collection name="output_after_recluster_bins" count="1">
+                <element name="SemiBin_30" ftype="fasta">
                     <assert_contents>
-                        <has_text text=">g3k_0"/>
+                        <has_text text="g3k_0"/>
                     </assert_contents>
                 </element>
             </output_collection>
@@ -486,9 +548,6 @@
             </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"/>
@@ -497,23 +556,9 @@
                 <param name="max_node" value="1"/>
                 <param name="max_edges" value="200"/>
                 <param name="minfasta_kbs" value="200"/>
-                <param name="no_recluster" value="true"/>
             </section>
             <param name="extra_output" value="data,coverage,contigs"/>
-            <output_collection name="multi_bins" count="2">
-                <element name="0" ftype="fasta">
-                    <assert_contents>
-                        <has_text text=">g1k_0"/>
-                    </assert_contents>
-                </element>
-            </output_collection>
-            <output_collection name="multi_contigs" count="10">
-                <element name="S8" ftype="fasta">
-                    <assert_contents>
-                        <has_text text=">g1k_0"/>
-                    </assert_contents>
-                </element>
-            </output_collection>
+            <output_collection name="multi_bins" count="0"/>
             <output_collection name="multi_data" count="10">
                 <element name="S8" ftype="csv">
                     <assert_contents>
@@ -521,6 +566,13 @@
                     </assert_contents>
                 </element>
             </output_collection>
+            <output_collection name="multi_data_split" count="10">
+                <element name="S8" ftype="csv">
+                    <assert_contents>
+                        <has_text text="g1k_0_1,"/>
+                    </assert_contents>
+                </element>
+            </output_collection>
             <output_collection name="multi_cov" count="10">
                 <element name="8" ftype="csv">
                     <assert_contents>
@@ -557,7 +609,6 @@
                 </element>
             </output_collection>
         </test>
-        
     </tests>
     <help><![CDATA[
 @HELP_HEADER@
@@ -570,4 +621,4 @@
 
     ]]></help>
     <expand macro="citations"/>
-</tool>
+</tool>
\ No newline at end of file