Mercurial > repos > iuc > semibin_bin

changeset 2:dbf5571a8140 draft default tip

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 13abac83068b126399ec415141007a48c2efaa84
author iuc
date Fri, 10 Nov 2023 20:49:03 +0000
parents 4d561bdc2c31
children
files bin.xml macros.xml
diffstat 2 files changed, 52 insertions(+), 44 deletions(-) [+]
line wrap: on
line diff
--- a/bin.xml	Mon Mar 27 08:24:46 2023 +0000
+++ b/bin.xml	Fri Nov 10 20:49:03 2023 +0000
@@ -11,7 +11,7 @@
     <command detect_errors="exit_code"><![CDATA[
 #import re
 @FASTA_FILES@
-SemiBin bin
+SemiBin2 bin
     --input-fasta 'contigs.fasta'
     --data '$data'
 #if $mod.select == 'history'
@@ -22,10 +22,13 @@
     --output 'output'
     --threads \${GALAXY_SLOTS:-1}
     --minfasta-kbs $minfasta_kbs
-    $no_recluster
+#if $mode.select == 'single' or $mode_fasta.mode_select == 'co'
+    $write_pre_reclustering_bins
+#end if
     --max-node $max_node
     --max-edges $max_edges
     --random-seed $random_seed
+    --compression none
     @MIN_LEN@
     --orf-finder '$orf_finder'
     ]]></command>
@@ -50,20 +53,20 @@
         <expand macro="max-node"/>
         <expand macro="max-edges"/>
         <expand macro="minfasta-kbs"/>
-        <expand macro="no-recluster"/>
+        <expand macro="write_pre_reclustering_bins"/>
     </inputs>
     <outputs>
-        <collection name="output_recluster_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins after reclustering">
-            <filter>not no_recluster</filter>
-            <discover_datasets pattern=".*?\.(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_recluster_bins" />
+        <collection name="output_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins after reclustering">
+            <filter>not write_pre_reclustering_bins</filter>
+            <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_bins" />
         </collection>
-        <collection name="output_prerecluster_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins before reclustering">
-            <filter>not no_recluster</filter>
-            <discover_datasets pattern=".*?\.(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_prerecluster_bins" />
+        <collection name="output_recluster_bins" type="list" label="${tool.name} on ${on_string}: Reclustered bins?">
+            <filter>write_pre_reclustering_bins</filter>
+            <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_recluster_bins" />
         </collection>
-        <collection name="output_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins without reeclustering">
-            <filter>no_recluster</filter>
-            <discover_datasets pattern=".*?\.(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_bins" />
+        <collection name="output_prerecluster_bins" type="list" label="${tool.name} on ${on_string}: Pre reclustered bins">
+            <filter>write_pre_reclustering_bins</filter>
+            <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_prerecluster_bins" />
         </collection>
     </outputs>
     <tests>
@@ -86,22 +89,21 @@
             <param name="max_node" value="1"/>
             <param name="max_edges" value="200"/>
             <param name="minfasta_kbs" value="200"/>
-            <param name="no_recluster" value="false"/>
-            <output_collection name="output_recluster_bins" count="0"/>
+            <param name="write_pre_reclustering_bins" value="true"/>
             <output_collection name="output_prerecluster_bins" count="3">
-                <element name="0" ftype="fasta">
+                <element name="SemiBin_0" ftype="fasta">
                     <assert_contents>
                         <has_text text=">g1k_0"/>
                         <has_text text=">g4k_9"/>
                     </assert_contents>
                 </element>
-                <element name="1" ftype="fasta">
+                <element name="SemiBin_1" ftype="fasta">
                     <assert_contents>
                         <has_text text=">g2k_0"/>
                         <has_text text=">g2k_9"/>
                     </assert_contents>
                 </element>
-                <element name="2" ftype="fasta">
+                <element name="SemiBin_2" ftype="fasta">
                     <assert_contents>
                         <has_text text=">g3k_0"/>
                         <has_text text=">g3k_9"/>
@@ -128,27 +130,30 @@
             <param name="max_node" value="1"/>
             <param name="max_edges" value="200"/>
             <param name="minfasta_kbs" value="200"/>
-            <param name="no_recluster" value="true"/>
-            <output_collection name="output_bins" count="3">
-                <element name="0" ftype="fasta">
-                    <assert_contents>
-                        <has_text text=">g1k_0"/>
-                        <has_text text=">g4k_9"/>
-                    </assert_contents>
-                </element>
-                <element name="1" ftype="fasta">
-                    <assert_contents>
-                        <has_text text=">g2k_0"/>
-                        <has_text text=">g2k_9"/>
-                    </assert_contents>
-                </element>
-                <element name="2" ftype="fasta">
-                    <assert_contents>
-                        <has_text text=">g3k_0"/>
-                        <has_text text=">g3k_9"/>
-                    </assert_contents>
-                </element>
-            </output_collection>
+            <param name="write_pre_reclustering_bins" value="false"/>
+            <output_collection name="output_bins" count="0"/>
+        </test>
+        <test expect_num_outputs="2">
+            <conditional name="mode">
+                <param name="select" value="single"/>
+                <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
+            </conditional>
+            <param name="data" ftype="csv" value="data.csv"/>
+            <conditional name="mod">
+                <param name="select" value="history"/>
+                <param name="model" ftype="h5" value="model.h5"/>
+            </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"/>
+            <param name="max_node" value="1"/>
+            <param name="max_edges" value="200"/>
+            <param name="minfasta_kbs" value="200"/>
+            <param name="write_pre_reclustering_bins" value="true"/>
+            <output_collection name="output_prerecluster_bins" count="3"/>
         </test>
     </tests>
     <help><![CDATA[
--- a/macros.xml	Mon Mar 27 08:24:46 2023 +0000
+++ b/macros.xml	Fri Nov 10 20:49:03 2023 +0000
@@ -1,6 +1,6 @@
 <?xml version="1.0"?>
 <macros>
-    <token name="@TOOL_VERSION@">1.5.1</token>
+    <token name="@TOOL_VERSION@">2.0.2</token>
     <token name="@VERSION_SUFFIX@">0</token>
     <token name="@PROFILE@">21.01</token>
     <xml name="biotools">
@@ -15,7 +15,7 @@
         </requirements>
     </xml>
     <xml name="version">
-        <version_command>SemiBin -v</version_command>
+        <version_command>SemiBin2 -v</version_command>
     </xml>
     <xml name="mode_fasta_bam">
         <conditional name="mode">
@@ -109,10 +109,11 @@
             #end if
         #end for
 #set $separator = ':'
-SemiBin concatenate_fasta
+SemiBin2 concatenate_fasta
     --input-fasta *.fasta
     --output 'output'
     --separator '$separator'
+    --compression none
     -m $mode.multi_fasta.min_len
 &&
 ln -s 'output/concatenated.fa' 'contigs.fasta' &&
@@ -222,7 +223,8 @@
     </xml>
     <xml name="orf-finder">
         <param argument="--orf-finder" type="select" label="ORF finder used to estimate the number of bins">
-            <option value="prodigal" selected="true">Prodigal</option>
+            <option value="fast-naive" selected="true">Fast-Naive</option>
+            <option value="prodigal">Prodigal</option>
             <option value="fraggenescan">Fraggenescan</option>
         </param>
     </xml>
@@ -251,8 +253,8 @@
     <xml name="minfasta-kbs">
         <param argument="--minfasta-kbs" type="integer" min="0" value="200" label="Miminimum bin size in Kbps"/>
     </xml>
-    <xml name="no-recluster">
-        <param argument="--no-recluster" type="boolean" truevalue="--no-recluster" falsevalue="" checked="false" label="Do not recluster bins?"/>
+    <xml name="write_pre_reclustering_bins">
+        <param argument="--write-pre-reclustering-bins" type="boolean" truevalue="--write-pre-reclustering-bins" falsevalue="" checked="false" label="Return also the pre reclustered bins?"/>
     </xml>
     <xml name="data">
         <param argument="--data" type="data" format="csv" label="Train data"/>
@@ -310,6 +312,7 @@
             <filter>mode["select"]=="multi" and extra_output and "contigs" in extra_output</filter>
             <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/samples/" />
         </collection>
+        
     </xml>
     <xml name="train_output">
         <data name="model" format="h5" from_work_dir="output/model.h5" label="${tool.name} on ${on_string}: Semi-supervised deep learning model" />