Mercurial > repos > iuc > semibin_train

changeset 6:3215ab8a94de 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/main/tools/semibin commit 2c08a2e49a2844efe92340c5a9e9c8323e4a33d6
author iuc
date Tue, 28 Oct 2025 08:20:57 +0000
parents 14046254799c
children
files macros.xml test-data/input_multi_sorted10_naming.bam test-data/input_multi_sorted1_naming.bam test-data/input_multi_sorted2_naming.bam test-data/input_multi_sorted3_naming.bam test-data/input_multi_sorted4_naming.bam test-data/input_multi_sorted5_naming.bam test-data/input_multi_sorted6_naming.bam test-data/input_multi_sorted7_naming.bam test-data/input_multi_sorted8_naming.bam test-data/input_multi_sorted9_naming.bam test-data/input_single.fasta.bz2 test-data/input_single.fasta.gz train.xml
diffstat 14 files changed, 80 insertions(+), 51 deletions(-) [+]
line wrap: on
line diff
--- a/macros.xml	Sun Aug 10 11:40:20 2025 +0000
+++ b/macros.xml	Tue Oct 28 08:20:57 2025 +0000
@@ -1,7 +1,7 @@
 <?xml version="1.0"?>
 <macros>
     <token name="@TOOL_VERSION@">2.1.0</token>
-    <token name="@VERSION_SUFFIX@">0</token>
+    <token name="@VERSION_SUFFIX@">1</token>
     <token name="@PROFILE@">21.01</token>
     <xml name="biotools">
         <xrefs>
@@ -79,7 +79,7 @@
         </param>
     </xml>
     <xml name="input-fasta-single">
-        <param argument="--input-fasta" type="data" format="fasta,fasta.gz" label="Contig sequences"/>
+        <param argument="--input-fasta" type="data" format="fasta,fasta.gz,fasta.bz2" label="Contig sequences"/>
     </xml>
     <xml name="input-fasta-multi">
         <conditional name="multi_fasta">
@@ -88,11 +88,11 @@
                 <option value="multi">1 contig file per sample</option>
             </param>
             <when value="concatenated">
-                <param argument="--input-fasta" type="data" format="fasta,fasta.gz" label="Combined contig sequences"/>
+                <param argument="--input-fasta" type="data" format="fasta,fasta.gz,fasta.bz2" label="Combined contig sequences"/>
                 <expand macro="separator"/>
             </when>
             <when value="multi">
-                <param argument="--input-fasta" type="data" multiple="true" format="fasta,fasta.gz" label="Contig sequences"/>
+                <param argument="--input-fasta" type="data" multiple="true" format="fasta,fasta.gz,fasta.bz2" label="Contig sequences"/>
                 <expand macro="concat_min_len"/>
             </when>
         </conditional>
@@ -101,39 +101,27 @@
         <param name="min_len" type="integer" min="0" value="0" label="Minimal length for contigs to be kept"/>
     </xml>
     <token name="@SINGLE_FASTA_FILES@"><![CDATA[
-#if $input_fasta.ext.endswith(".gz")
-gunzip -c '$input_fasta' > 'contigs.fasta' &&
-#else
-ln -s '$input_fasta' 'contigs.fasta' &&
-#end if
+ln -s '$input_fasta' 'contigs.$input_fasta.ext' &&
     ]]></token>
     <token name="@FASTA_FILES@"><![CDATA[
 #if $mode.select == 'single' or $mode.select == 'co'
-    #if $mode.input_fasta.ext.endswith(".gz")
-gunzip -c '$mode.input_fasta' > 'contigs.fasta' &&
-    #else
-ln -s '$mode.input_fasta' 'contigs.fasta' &&
-    #end if
+ln -s '$input_fasta' 'contigs.$input_fasta.ext' &&
 #else
     #if $mode.multi_fasta.select == 'concatenated'
-        #if $mode.multi_fasta.input_fasta.ext.endswith(".gz")
-gunzip -c '$mode.multi_fasta.input_fasta' > 'contigs.fasta' &&
-        #else
-ln -s '$mode.multi_fasta.input_fasta' 'contigs.fasta' &&
-        #end if
+ln -s '$input_fasta' 'contigs.$input_fasta.ext' &&
 #set $separator = $mode.multi_fasta.separator
     #else
         #for $e in $mode.multi_fasta.input_fasta
-            #set $identifier = re.sub('[^\s\w\-\\.]', '_', str($e.element_identifier))
-            #if $e.ext.endswith(".gz")
-gunzip -c '$e' > '${identifier}.fasta' &&
-            #else
-ln -s '$e' '${identifier}.fasta' &&
-            #end if
+            #set $identifier = re.sub('[^\s\w\-]', '_', str($e.element_identifier))
+ln -s '$e' '${identifier}.$e.ext' &&
         #end for
 #set $separator = ':'
 SemiBin2 concatenate_fasta
-    --input-fasta *.fasta
+    --input-fasta
+    #for $e in $mode.multi_fasta.input_fasta
+        #set $identifier = re.sub('[^\s\w\-]', '_', str($e.element_identifier))
+        '${identifier}.$e.ext'
+    #end for
     --output 'output'
     --separator '$separator'
     --compression none
@@ -158,18 +146,18 @@
     </xml>
     <token name="@BAM_FILES@"><![CDATA[
 #if $mode.select == 'single'
-#set $identifier = re.sub('[^\s\w\-\\.]', '_', str($mode.input_bam.element_identifier))
+#set $identifier = re.sub('[^\s\w\-]', '_', str($mode.input_bam.element_identifier))
 ln -s '$mode.input_bam' '${identifier}.bam' &&
 #else
     #for $e in $mode.input_bam
-        #set $identifier = re.sub('[^\s\w\-\\.]', '_', str($e.element_identifier))
+        #set $identifier = re.sub('[^\s\w\-]', '_', str($e.element_identifier))
 ln -s '$e' '${identifier}.bam' &&
     #end for
 #end if
     ]]></token>
     <token name="@STROBEALIGN_FILES@"><![CDATA[
 #for $e in $mode.align_select.abundance
-    #set $identifier = re.sub('[^\s\w\-\\.]', '_', str($e.element_identifier))
+    #set $identifier = re.sub('[^\s\w\-]', '_', str($e.element_identifier))
     ln -s '$e' '${identifier}.txt' &&
 #end for
     ]]></token>
@@ -513,4 +501,4 @@
             <citation type="doi">10.1038/s41467-022-29843-y</citation>
         </citations>
     </xml>
-</macros>
+</macros>
\ No newline at end of file
Binary file test-data/input_multi_sorted10_naming.bam has changed
Binary file test-data/input_multi_sorted1_naming.bam has changed
Binary file test-data/input_multi_sorted2_naming.bam has changed
Binary file test-data/input_multi_sorted3_naming.bam has changed
Binary file test-data/input_multi_sorted4_naming.bam has changed
Binary file test-data/input_multi_sorted5_naming.bam has changed
Binary file test-data/input_multi_sorted6_naming.bam has changed
Binary file test-data/input_multi_sorted7_naming.bam has changed
Binary file test-data/input_multi_sorted8_naming.bam has changed
Binary file test-data/input_multi_sorted9_naming.bam has changed
Binary file test-data/input_single.fasta.bz2 has changed
Binary file test-data/input_single.fasta.gz has changed
--- a/train.xml	Sun Aug 10 11:40:20 2025 +0000
+++ b/train.xml	Tue Oct 28 08:20:57 2025 +0000
@@ -11,40 +11,37 @@
     <command detect_errors="exit_code"><![CDATA[
 #import re
 #if $mode.select == 'single'
-    #if $mode.input_fasta.ext.endswith(".gz")
-gunzip -c '$mode.input_fasta' > 'contigs.fasta' &&
-    #else
-ln -s '$mode.input_fasta' 'contigs.fasta' &&
-    #end if
+ln -s '$mode.input_fasta' 'contigs.$input_fasta.ext' &&
 #else
     #for $e in $mode.input_fasta
-        #set $identifier = re.sub('[^\s\w\-\\.]', '_', str($e.element_identifier))
-        #if $e.ext.endswith(".gz")
-gunzip -c '$e' > '${identifier}.fasta' &&
-        #else
-ln -s '$e' '${identifier}.fasta' &&
-        #end if
+        #set $identifier = re.sub('[^\s\w\-]', '_', str($e.element_identifier))
+ln -s '$e' '${identifier}.$e.ext' &&
     #end for
 #end if
 SemiBin2 train_semi
 #if $mode.select == 'single'
-    --input-fasta 'contigs.fasta'
+    --input-fasta 'contigs.$input_fasta.ext'
     --data '$mode.data'
     --data-split '$mode.data_split'
     --cannot-link '$mode.cannot_link'
 #else
     --train-from-many
+    --input-fasta
     #for $e in $mode.input_fasta
-    --input-fasta '${e.element_identifier}.fasta'
-    #end for
-    #for $e in $mode.data
-    --data '$e'
+        #set $identifier = re.sub('[^\s\w\-]', '_', str($e.element_identifier))
+        '${identifier}.$e.ext'
     #end for
-    #for $e in $mode.data_split
-    --data-split '$e'
+    --data
+    #for $e in $mode.data
+        '$e'
     #end for
+    --data-split 
+    #for $e in $mode.data_split
+        '$e'
+    #end for
+    --cannot-link
     #for $e in $mode.cannot_link
-    --cannot-link '$e'
+        '$e'
     #end for
 #end if
     --output 'output'
@@ -66,13 +63,13 @@
                 <option value="several">From multiple samples (train model across several samples can get better pre-trained model for single-sample binning)</option>
             </param>
             <when value="single">
-                <param argument="--input-fasta" type="data" format="fasta,fasta.gz" label="Contig sequences"/>
+                <param argument="--input-fasta" type="data" format="fasta,fasta.gz,fasta.bz2" label="Contig sequences"/>
                 <param argument="--data" type="data"  format="csv" label="Train data"/>
                 <param argument="--data-split" type="data" format="csv" label="Split train data"/>
                 <param argument="--cannot-link" type="data" format="txt" label="Cannot-link constraints"/>
             </when>
             <when value="several">
-                <param argument="--input-fasta" type="data" multiple="true" format="fasta,fasta.gz" label="Contig sequences"/>
+                <param argument="--input-fasta" type="data" multiple="true" format="fasta,fasta.gz,fasta.bz2" label="Contig sequences"/>
                 <param argument="--data" type="data" format="csv" multiple="true" label="Train data"/>
                 <param argument="--data-split" type="data" format="csv" multiple="true" label="Split train data"/>
                 <param argument="--cannot-link" type="data" format="txt" multiple="true" label="Cannot-link constraints"/>
@@ -112,6 +109,50 @@
         </test>
         <test expect_num_outputs="1">
             <conditional name="mode">
+                <param name="select" value="single"/>
+                <param name="input_fasta" ftype="fasta.bz2" value="input_single.fasta.bz2"/>
+                <param name="data" ftype="csv" value="data.csv"/>
+                <param name="data_split" ftype="csv" value="data_split.csv"/>
+                <param name="cannot_link" ftype="txt" value="cannot.txt"/>
+            </conditional>
+            <conditional name="min_len">
+                <param name="method" value="min-len"/>
+                <param name="min_len" value="2500" />
+            </conditional>
+            <param name="orf_finder" value="prodigal"/>
+            <param name="random_seed" value="0"/>
+            <param name="epoches" value="1"/>
+            <param name="batch_size" value="2048"/>
+            <output name="model" ftype="h5">
+                <assert_contents>
+                    <has_size value="3119000" delta="2000" />
+                </assert_contents>
+            </output>
+        </test>
+        <test expect_num_outputs="1">
+            <conditional name="mode">
+                <param name="select" value="single"/>
+                <param name="input_fasta" ftype="fasta.gz" value="input_single.fasta.gz"/>
+                <param name="data" ftype="csv" value="data.csv"/>
+                <param name="data_split" ftype="csv" value="data_split.csv"/>
+                <param name="cannot_link" ftype="txt" value="cannot.txt"/>
+            </conditional>
+            <conditional name="min_len">
+                <param name="method" value="min-len"/>
+                <param name="min_len" value="2500" />
+            </conditional>
+            <param name="orf_finder" value="prodigal"/>
+            <param name="random_seed" value="0"/>
+            <param name="epoches" value="1"/>
+            <param name="batch_size" value="2048"/>
+            <output name="model" ftype="h5">
+                <assert_contents>
+                    <has_size value="3119000" delta="2000" />
+                </assert_contents>
+            </output>
+        </test>
+        <test expect_num_outputs="1">
+            <conditional name="mode">
                 <param name="select" value="several"/>
                 <param name="input_fasta" ftype="fasta" value="input_single.fasta,input_single_2.fasta,input_single_3.fasta"/>
                 <param name="data" ftype="csv" value="data.csv,data.csv,data.csv"/>