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

Changeset 3:b5a7583b8db0 (2025-03-25)
Previous changeset 2:99ff9221182c (2023-11-10) Next changeset 4:bcb50c148f4b (2025-08-01)
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/semibin commit a9fc83e0029266f910b549d5d1eef6a9bc3e3f7b
modified:
macros.xml
semibin.xml
b
diff -r 99ff9221182c -r b5a7583b8db0 macros.xml
--- a/macros.xml Fri Nov 10 20:50:01 2023 +0000
+++ b/macros.xml Tue Mar 25 15:55:28 2025 +0000
b
@@ -1,7 +1,7 @@
 <?xml version="1.0"?>
 <macros>
     <token name="@TOOL_VERSION@">2.0.2</token>
-    <token name="@VERSION_SUFFIX@">0</token>
+    <token name="@VERSION_SUFFIX@">1</token>
     <token name="@PROFILE@">21.01</token>
     <xml name="biotools">
         <xrefs>
@@ -140,9 +140,16 @@
     #end for
 #end if
     ]]></token>
+    <xml name="ref_select_cannot">
+        <param name="select" type="select" label="Reference database">
+            <option value="cached">Cached database</option>
+            <option value="taxonomy">Pre-computed taxonomy</option>
+        </param>
+    </xml>
     <xml name="ref_select">
         <param name="select" type="select" label="Reference database">
-            <option value="cached" selected="true">Cached database</option>
+            <option value="ml" selected="true">Use SemiBin ML function</option>
+            <option value="cached">Cached database</option>
             <option value="taxonomy">Pre-computed taxonomy</option>
         </param>
     </xml>
@@ -153,6 +160,28 @@
             </options>
         </param>
     </xml>
+    <xml name="ref-single-cannot">
+        <conditional name="ref">
+            <expand macro="ref_select_cannot"/>
+            <when value="cached">
+                <expand macro="cached_db"/>
+            </when>
+            <when value="taxonomy">
+                <param argument="--taxonomy-annotation-table" type="data" format="tabular" label="Pre-computed mmseqs2 format taxonomy TSV file"/>
+            </when>
+        </conditional>
+    </xml>
+    <xml name="ref-multi-cannot">
+        <conditional name="ref">
+            <expand macro="ref_select_cannot"/>
+            <when value="cached">
+                <expand macro="cached_db"/>
+            </when>
+            <when value="taxonomy">
+                <param argument="--taxonomy-annotation-table" type="data" format="tabular" multiple="true" label="Pre-computed mmseqs2 format taxonomy TSV file" help="One per bin file"/>
+            </when>
+        </conditional>
+    </xml>
     <xml name="ref-single">
         <conditional name="ref">
             <expand macro="ref_select"/>
@@ -162,6 +191,7 @@
             <when value="taxonomy">
                 <param argument="--taxonomy-annotation-table" type="data" format="tabular" label="Pre-computed mmseqs2 format taxonomy TSV file"/>
             </when>
+            <when value="ml"/>
         </conditional>
     </xml>
     <xml name="ref-multi">
@@ -173,6 +203,7 @@
             <when value="taxonomy">
                 <param argument="--taxonomy-annotation-table" type="data" format="tabular" multiple="true" label="Pre-computed mmseqs2 format taxonomy TSV file" help="One per bin file"/>
             </when>
+            <when value="ml"/>
         </conditional>
     </xml>
     <xml name="ref_single">
@@ -184,6 +215,7 @@
             <when value="taxonomy">
                 <param argument="--taxonomy-annotation-table" type="data" format="tabular" label="Pre-computed mmseqs2 format taxonomy TSV file"/>
             </when>
+            <when value="ml"/>
         </conditional>
     </xml>
     <xml name="min_len">
b
diff -r 99ff9221182c -r b5a7583b8db0 semibin.xml
--- a/semibin.xml Fri Nov 10 20:50:01 2023 +0000
+++ b/semibin.xml Tue Mar 25 15:55:28 2025 +0000
b
b'@@ -18,17 +18,19 @@\n     #if $mode.select == \'single\' and str($mode.environment) != \'\'\n     --environment \'$mode.environment\'\n     #end if\n-    #if $mode.ref.select == "cached"\n+    #if $mode.ref.select == "cached":\n     --reference-db-data-dir \'$mode.ref.cached_db.fields.path\'\n-    #else\n+    #end if\n+    #if $mode.ref.select == "taxonomy"\n     --taxonomy-annotation-table \'$mode.ref.taxonomy_annotation_table\'\n     #end if\n #else\n     multi_easy_bin\n     --separator \'$separator\'\n-    #if $mode.ref.select == "cached"\n+    #if $mode.ref.select == "cached":\n     --reference-db-data-dir \'$mode.ref.cached_db.fields.path\'\n-    #else\n+    #end if\n+    #if $mode.ref.select == "taxonomy"\n     --taxonomy-annotation-table \n         #for $e in $mode.ref.taxonomy_annotation_table\n             \'$e\' \n@@ -43,7 +45,7 @@\n     --orf-finder \'$orf_finder\'\n     --random-seed $random_seed\n \n-#if str($annot.ml_threshold) != \'\'\n+#if $annot.ml_threshold:\n     --ml-threshold $annot.ml_threshold\n #end if\n     --epoches $training.epoches\n@@ -51,7 +53,7 @@\n     --max-node $bin.max_node\n     --max-edges $bin.max_edges\n     --minfasta-kbs $bin.minfasta_kbs\n-#if ($mode.select == \'single\' or $mode.select == \'co\') and "pre_reclustering_bins" in $extra_output\n+#if ($mode.select == \'single\' or $mode.select == \'co\') and $extra_output and "pre_reclustering_bins" in $extra_output\n     --write-pre-reclustering-bins\n #end if\n     --compression none\n@@ -153,10 +155,58 @@\n                 <param name="min_len" value="0" />\n             </conditional>\n             <param name="orf_finder" value="prodigal"/>\n-            <param name="random-seed" value="0"/>\n-            <section name="annot">\n-                <param name="ml_threshold" value=""/>\n+            <param name="random_seed" value="0"/>\n+            <section name="training">\n+                <param name="epoches" value="20"/>\n+                <param name="batch_size" value="2048"/>\n+            </section>\n+            <section name="bin">\n+                <param name="max_node" value="1"/>\n+                <param name="max_edges" value="200"/>\n+                <param name="minfasta_kbs" value="200"/>\n             </section>\n+            <param name="extra_output" value="data,coverage,contigs"/>\n+            <output_collection name="output_bins" count="0"/>\n+            <output name="single_data" ftype="csv">\n+                <assert_contents>\n+                    <has_text text="g1k_0"/>\n+                    <has_text text="g4k_7"/>\n+                </assert_contents>\n+            </output>\n+            <output name="single_data_split" ftype="csv">\n+                <assert_contents>\n+                    <has_text text="g1k_0_1"/>\n+                    <has_text text="g1k_6_2"/>\n+                </assert_contents>\n+            </output>\n+            <output name="single_cov" ftype="csv">\n+                <assert_contents>\n+                    <has_text text="g1k_0"/>\n+                    <has_text text="0.027"/>\n+                </assert_contents>\n+            </output>\n+            <output name="single_split_cov" ftype="csv">\n+                <assert_contents>\n+                    <has_size value="1" delta="1"/>\n+                </assert_contents>\n+            </output>\n+        </test>\n+        <test expect_num_outputs="5">\n+            <conditional name="mode">\n+                <param name="select" value="single"/>\n+                <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>\n+                <param name="input_bam" ftype="bam" value="input_single.bam"/>\n+                <conditional name="ref">\n+                    <param name="select" value="ml"/>\n+                </conditional>\n+                <param name="environment" value="human_gut"/>\n+            </conditional>\n+            <conditional name="min_len">\n+                <param name="method" value="min-len"/>\n+                <param name="min_len" value="0" />\n+            </conditional>\n+            <param name="orf_finder" val'..b'v"/>\n                 </conditional>\n@@ -207,10 +324,7 @@\n                 <param name="ratio" value="0.05"/>\n             </conditional>\n             <param name="orf_finder" value="fast-naive"/>\n-            <param name="random-seed" value="0"/>\n-            <section name="annot">\n-                <param name="ml_threshold" value=""/>\n-            </section>\n+            <param name="random_seed" value="0"/>\n             <section name="training">\n                 <param name="epoches" value="20"/>\n                 <param name="batch_size" value="2048"/>\n@@ -278,10 +392,7 @@\n                 <param name="ratio" value="0.05"/>\n             </conditional>\n             <param name="orf_finder" value="fraggenescan"/>\n-            <param name="random-seed" value="0"/>\n-            <section name="annot">\n-                <param name="ml_threshold" value=""/>\n-            </section>\n+            <param name="random_seed" value="0"/>\n             <section name="training">\n                 <param name="epoches" value="20"/>\n                 <param name="batch_size" value="2048"/>\n@@ -340,7 +451,7 @@\n                 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>\n                 <param name="input_bam" ftype="bam" value="input_single.bam"/>\n                 <conditional name="ref">\n-                    <param name="db_selector" value="cached"/>\n+                    <param name="select" value="cached"/>\n                     <param name="cached_db" value="test-db"/>\n                 </conditional>\n             </conditional>\n@@ -349,10 +460,7 @@\n                 <param name="ratio" value="0.05"/>\n             </conditional>\n             <param name="orf_finder" value="fraggenescan"/>\n-            <param name="random-seed" value="0"/>\n-            <section name="annot">\n-                <param name="ml_threshold" value=""/>\n-            </section>\n+            <param name="random_seed" value="0"/>\n             <section name="training">\n                 <param name="epoches" value="20"/>\n                 <param name="batch_size" value="2048"/>\n@@ -362,7 +470,6 @@\n                 <param name="max_edges" value="200"/>\n                 <param name="minfasta_kbs" value="200"/>\n             </section>\n-            <param name="extra_output" value=""/>\n             <output_collection name="output_bins" count="1">\n                 <element name="SemiBin_30" ftype="fasta">\n                     <assert_contents>\n@@ -377,7 +484,7 @@\n                 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>\n                 <param name="input_bam" ftype="bam" value="input_single.bam"/>\n                 <conditional name="ref">\n-                    <param name="db_selector" value="cached"/>\n+                    <param name="select" value="cached"/>\n                     <param name="cached_db" value="test-db"/>\n                 </conditional>\n             </conditional>\n@@ -386,10 +493,7 @@\n                 <param name="ratio" value="0.05"/>\n             </conditional>\n             <param name="orf_finder" value="fraggenescan"/>\n-            <param name="random-seed" value="0"/>\n-            <section name="annot">\n-                <param name="ml_threshold" value=""/>\n-            </section>\n+            <param name="random_seed" value="0"/>\n             <section name="training">\n                 <param name="epoches" value="20"/>\n                 <param name="batch_size" value="2048"/>\n@@ -444,9 +548,6 @@\n             </conditional>\n             <param name="orf_finder" value="fraggenescan"/>\n             <param name="random_seed" value="0"/>\n-            <section name="annot">\n-                <param name="ml_threshold" value=""/>\n-            </section>\n             <section name="training">\n                 <param name="epoches" value="20"/>\n                 <param name="batch_size" value="2048"/>\n@@ -520,4 +621,4 @@\n \n     ]]></help>\n     <expand macro="citations"/>\n-</tool>\n+</tool>\n\\ No newline at end of file\n'