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

Changeset 11:b40b77418372 (2025-03-12)
Previous changeset 10:5be72b7648fa (2025-03-03) Next changeset 12:388dbecbf03b (2025-05-12)
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/spades commit f1fde73752b1554bb17b027795b6b8fa9bfbe2c4
modified:
macros.xml
plasmidspades.xml
test-data/ecoli_1K.fastq.gz
b
diff -r 5be72b7648fa -r b40b77418372 macros.xml
--- a/macros.xml Mon Mar 03 11:07:21 2025 +0000
+++ b/macros.xml Wed Mar 12 21:47:26 2025 +0000
[
b'@@ -1,10 +1,9 @@\n <macros>\n-    <token name="@TOOL_VERSION@">3.15.5</token>\n-    <token name="@VERSION_SUFFIX@">3</token>\n+    <token name="@TOOL_VERSION@">4.1.0</token>\n+    <token name="@VERSION_SUFFIX@">0</token>\n     <xml name="requirements">\n         <requirements>\n             <requirement type="package" version="@TOOL_VERSION@">spades</requirement>\n-            <requirement type="package" version="3.0">zip</requirement>\n             <yield/>\n         </requirements>\n     </xml>\n@@ -24,9 +23,10 @@\n     <xml name="version_command">\n         <version_command><![CDATA[spades.py --version 2>&1 | awk -F \'v\' \'{print $2}\']]></version_command>\n     </xml>\n-    <token name="@INTYPES@">\n-        \n-    </token>\n+    <token name="@FASTA_INTYPES@">fasta,fasta.gz</token>\n+    <token name="@FASTQ_INTYPES@">fastqillumina,fastqillumina.gz,fastqsanger,fastqsanger.gz</token>\n+    <token name="@INTYPES@">@FASTQ_INTYPES@,@FASTA_INTYPES@</token>\n+\n     <xml name="citations">\n         <citations>\n             <citation type="doi">10.1093/bioinformatics/btv688</citation>\n@@ -50,46 +50,33 @@\n <!-- PREPARE INPUT FILES-->\n \n <token name="@PREPROCESS_INPUT_FILES_MAIN@"><![CDATA[\n+#import re\n+#def fix_ext($ext):\n+    #set ext = $ext.replace(\'fastqsanger\', \'fastq\')\n+    #set ext = $ext.replace(\'fastqillumina\', \'fastq\')\n+    #return $ext\n+#end def\n+\n #if $singlePaired.sPaired == "single" or $singlePaired.sPaired == "paired_interlaced"\n     mkdir -p reads1 &&\n     #set file_paths1 = []\n     #for $input_file in $singlePaired.input1\n-        #set $ext = $input_file.ext.replace(\'fastqsanger\', \'fastq\')\n-        #set $fname = $input_file.element_identifier.replace(" ","_") + \'.\' + $ext\n-        #set $file_path = \'reads1/\' + $fname\n+        #set ext = $fix_ext($input_file.ext)\n+        #set fname = re.sub(\'[^\\w\\-_.]\', \'_\', $input_file.element_identifier) + \'.\' + $ext\n+        #set file_path = \'reads1/\' + $fname\n         ln -s \'$input_file\' \'$file_path\' &&\n         $file_paths1.append($file_path)\n     #end for\n-#else if $singlePaired.sPaired == "paired"\n-    mkdir -p paired_reads1 &&\n-    #set fw_reads1 = []\n-    #for $input_file in $singlePaired.input1\n-        #set $ext = $input_file.ext.replace(\'fastqsanger\', \'fastq\')\n-        #set $fname = $input_file.element_identifier.replace(" ","_") + \'.\' + $ext\n-        #set $file_path = \'paired_reads1/\' + str($fname)\n-        ln -s \'$input_file\' \'$file_path\' &&\n-        $fw_reads1.append($file_path)\n-    #end for\n-    #set rv_reads1 = []\n-    #for $input_file in $singlePaired.input2\n-        #set $ext = $input_file.ext.replace(\'fastqsanger\', \'fastq\')\n-        #set $fname = $input_file.element_identifier.replace(" ","_") + \'.\' + $ext\n-        #set $file_path = \'paired_reads1/\' + str($fname)\n-        ln -s \'$input_file\' \'$file_path\' &&\n-        $rv_reads1.append($file_path)\n-    #end for\n-    #silent $fw_reads1.sort()\n-    #silent $rv_reads1.sort()\n #else\n     mkdir -p paired_reads1 &&\n     #set fw_reads1 = []\n     #set rv_reads1 = []\n     #for $i, $input_file in enumerate($singlePaired.input)\n-        #set $ext = $input_file.forward.ext.replace(\'fastqsanger\', \'fastq\')\n-        #set $file_path = \'paired_reads1/fw\' + str($i) + \'.\' + $ext\n+        #set ext = $fix_ext($input_file.forward.ext)\n+        #set file_path = \'paired_reads1/\' + re.sub(\'[^\\w\\-_.]\', \'_\', $input_file.element_identifier) + \'1.\' + $ext\n         ln -s \'$input_file.forward\' \'$file_path\' &&\n         $fw_reads1.append($file_path)\n-        #set $file_path = \'paired_reads1/rv\' + str($i) + \'.\' + $ext\n+        #set file_path = \'paired_reads1/\' + re.sub(\'[^\\w\\-_.]\', \'_\', $input_file.element_identifier) + \'2.\' + $ext\n         ln -s \'$input_file.reverse\' \'$file_path\' &&\n         $rv_reads1.append($file_path)\n     #end for\n@@ -101,42 +88,22 @@\n     mkdir -p reads2 &&\n     #set file_paths2 = []\n     #for $input_file in $additional_reads.singlePaired.input1\n-        #set $ext = $input_file.ext.replace(\'fastqsanger\', \'fastq\')\n-        #set $fname = $input_file.ele'..b' will use Oxford Nanopore reads for gap closure and repeat resolution"/>\n+        <param argument="--pacbio" type="data" format="@FASTQ_INTYPES@" multiple="true" optional="true" label="PacBio CLR reads" help="It is not recommended to run SPAdes on PacBio reads with low coverage (less than 5). In addition, SPAdes develpers suggest not to run SPAdes on PacBio reads for large genomes. SPAdes will use PacBio CLR reads for gap closure and repeat resolution"/>\n     </xml>\n     <xml name="flrna">\n-        <param argument="--fl-rna" name="flrna" type="data" format="fastq,fastq.gz,fasta,fasta.gz,fastqsanger,fastqsanger.gz" multiple="true" optional="true" label="PacBio/Nanopore/contigs that capture full-length transcripts" help="In addition to long reads, you may also provide a separate file with reads capturing the entire transcript sequences using this option. Full-length transcripts in such reads can be typically detected using the adapters. Note, that FL reads should be trimmed so that the adapters are excluded."/>\n+        <param argument="--fl-rna" name="flrna" type="data" format="@INTYPES@" multiple="true" optional="true" label="PacBio/Nanopore/contigs that capture full-length transcripts" help="In addition to long reads, you may also provide a separate file with reads capturing the entire transcript sequences using this option. Full-length transcripts in such reads can be typically detected using the adapters. Note, that FL reads should be trimmed so that the adapters are excluded."/>\n     </xml>\n \n     <xml name="phred">\n@@ -565,14 +496,14 @@\n         </param>\n     </xml>\n     <xml name="reads" token_paramname="reads" token_help="" token_label="">\n-        <param name="@PARAMNAME@" type="data" format="fastq,fastq.gz" label="@LABEL@ reads" help="@HELP@"/>\n+        <param name="@PARAMNAME@" type="data" format="@FASTQ_INTYPES@" label="@LABEL@ reads" help="@HELP@"/>\n     </xml>\n     <xml name="sanger">\n-        <param argument="--sanger" type="data" format="fastq,fastq.gz" multiple="true" optional="true" label="Sanger reads"/>\n+        <param argument="--sanger" type="data" format="@FASTQ_INTYPES@" multiple="true" optional="true" label="Sanger reads"/>\n     </xml>\n     <xml name="contigs">\n-        <param argument="--trusted-contigs" type="data" format="fasta,fasta.gz" multiple="true" optional="true" label="Trusted contigs" help="Reliable contigs of the same genome, which are likely to have no misassemblies and small rate of other errors (e.g. mismatches and indels). This option is not intended for contigs of the related species."/>\n-        <param argument="--untrusted-contigs" type="data" format="fasta,fasta.gz" multiple="true" optional="true" label="Untrusted contigs" help="Contigs of the same genome, quality of which is average or unknown. Contigs of poor quality can be used but may introduce errors in the assembly. This option is also not intended for contigs of the related species."/>\n+        <param argument="--trusted-contigs" type="data" format="@FASTA_INTYPES@" multiple="true" optional="true" label="Trusted contigs" help="Reliable contigs of the same genome, which are likely to have no misassemblies and small rate of other errors (e.g. mismatches and indels). This option is not intended for contigs of the related species."/>\n+        <param argument="--untrusted-contigs" type="data" format="@FASTA_INTYPES@" multiple="true" optional="true" label="Untrusted contigs" help="Contigs of the same genome, quality of which is average or unknown. Contigs of poor quality can be used but may introduce errors in the assembly. This option is also not intended for contigs of the related species."/>\n     </xml>\n     <xml name="assembly_graph">\n         <param argument="--assembly-graph" type="data" format="gfa1" multiple="true" optional="true" label="Assembly graphs" help=" The primary purpose of this option to run these pipelines on already constructed and simplified assembly graph this way skipping a large part of SPAdes pipeline."/>\n'
b
diff -r 5be72b7648fa -r b40b77418372 plasmidspades.xml
--- a/plasmidspades.xml Mon Mar 03 11:07:21 2025 +0000
+++ b/plasmidspades.xml Wed Mar 12 21:47:26 2025 +0000
[
b'@@ -44,12 +44,11 @@\n     @PHREDOFFSET@\n     ## postprocessing\n     @STATS@\n-    @CORRECTED@\n     ]]></command>\n     <inputs>\n         <expand macro="operation_mode"/>\n-        <expand macro="input_files_all" format="fastq, fastq.gz,fastqsanger.gz,fasta,fasta.gz" label="FASTA/FASTQ file(s)"/>\n-        <expand macro="input_additional_files_all" format="fastq,fastq.gz,fastqsanger.gz,fasta,fasta.gz" label="FASTA/FASTQ file(s)"/>\n+        <expand macro="input_files_all" format="@INTYPES@" label="FASTA/FASTQ file(s)"/>\n+        <expand macro="input_additional_files_all" format="@INTYPES@" label="FASTA/FASTQ file(s)"/>\n         <section name="arf" title="Additional read files">\n             <expand macro="nanopore_pacbio"/>\n             <expand macro="sanger"/>\n@@ -93,20 +92,31 @@\n         <!-- #1 single, separate, fastq.gz, default parameters -->\n          <test expect_num_outputs="4">\n             <conditional name="singlePaired">\n-                <param name="sPaired" value="paired"/>\n-                <param name="input1" value="pl1.fq.gz"/>\n-                <param name="input2" value="pl2.fq.gz"/>\n+                <param name="sPaired" value="paired_collection"/>\n+                <param name="input">\n+                    <collection type="list:paired">\n+                        <element name="ecoli_1K">\n+                            <collection type="paired">\n+                                <element name="forward" value="pl1.fq.gz" ftype="fastqsanger.gz"/>\n+                                <element name="reverse" value="pl2.fq.gz" ftype="fastqsanger.gz"/>\n+                            </collection>\n+                        </element>\n+                    </collection>\n+                </param>\n             </conditional>\n             <output name="out_ag">\n                 <assert_contents>\n                     <has_n_lines n="326"/>\n-                    <has_text_matching expression=">EDGE\\_18\\_length\\_9689\\_cov\\_4\\.668331"/>\n+                    <has_text_matching expression=">EDGE\\_[0-9]+\\_length\\_[0-9]+\\_cov\\_[0-9]+\\.[0-9]+"/>\n                 </assert_contents>\n             </output>\n             <output name="out_ags">\n                 <assert_contents>\n-                    <has_n_lines n="3"/>\n+                    <has_n_lines n="4"/>\n+                    <has_text_matching expression="H.+"/>\n                     <has_text_matching expression="S.+"/>\n+                    <has_text_matching expression="L.+"/>\n+                    <has_text_matching expression="P.+"/>\n                 </assert_contents>\n             </output>\n             <output name="out_cn">\n@@ -125,12 +135,20 @@\n         <!-- #2 single, separate, fastq, all outputs and custom parameters -->\n         <test expect_num_outputs="10">\n             <conditional name="singlePaired">\n-                <param name="sPaired" value="paired"/>\n-                <param name="input1" value="pl1.fq.gz"/>\n-                <param name="input2" value="pl2.fq.gz"/>\n+                <param name="sPaired" value="paired_collection"/>\n+                <param name="input">\n+                    <collection type="list:paired">\n+                        <element name="pl">\n+                            <collection type="paired">\n+                                <element name="forward" value="pl1.fq.gz" ftype="fastqsanger.gz"/>\n+                                <element name="reverse" value="pl2.fq.gz" ftype="fastqsanger.gz"/>\n+                            </collection>\n+                        </element>\n+                    </collection>\n+                </param>\n             </conditional>\n             <conditional name="cov_cond">\n-                <param name="cov_sel" value="auto"/>\n+                <param name="cov_cutoff" value="auto"/>\n             </conditional>\n             <param name="phred_offset" value="33"/>\n             <param name="optional_output" value="ag,ags,cn,cp,cr,cs,l,sc,sp,ss"/>\n@@ -142,8 +160,11 @@\n             </output>\n             <output name="out_ags">\n     '..b'             <element name="reverse" value="pl2.fq.gz" ftype="fastqsanger.gz"/>\n+                            </collection>\n+                        </element>\n+                    </collection>\n+                </param>\n             </conditional>\n             <param name="optional_output" value="cr,l"/>\n             <output_collection name="out_cr" type="list" count="3">\n-                <element name="pl1.fq.gz.fastq.00.0_0">\n+                <element name="pl1.fastq00.0_0">\n                     <assert_contents>\n                         <has_size value="72173" delta="1000"/>\n                     </assert_contents>\n                 </element>\n-                <element name="pl2.fq.gz.fastq.00.0_0">\n+                <element name="pl2.fastq00.0_0">\n                     <assert_contents>\n                         <has_size value="72173" delta="1000"/>\n                     </assert_contents>\n                 </element>\n-                <element name="pl_unpaired.00.0_0">\n+                <element name="pl_unpaired00.0_0">\n                     <assert_contents>\n                         <has_size value="392" delta="100"/>\n                     </assert_contents>\n@@ -304,16 +357,24 @@\n             </output_collection>\n             <output name="out_l">\n                 <assert_contents>\n-                    <has_text_matching expression="Thank you for using SPAdes!"/>\n+                    <has_text_matching expression="Thank you for using plasmidSPAdes!"/>\n                 </assert_contents>\n             </output>\n         </test>\n         <!-- #7 hybrid assembly: nanpopore, pacbio, sanger, untrustedcontigs -->\n         <test expect_num_outputs="2">\n             <conditional name="singlePaired">\n-                <param name="sPaired" value="paired"/>\n-                <param name="input1" value="pl1.fq.gz"/>\n-                <param name="input2" value="pl2.fq.gz"/>\n+                <param name="sPaired" value="paired_collection"/>\n+                <param name="input">\n+                    <collection type="list:paired">\n+                        <element name="pl">\n+                            <collection type="paired">\n+                                <element name="forward" value="pl1.fq.gz" ftype="fastqsanger.gz"/>\n+                                <element name="reverse" value="pl2.fq.gz" ftype="fastqsanger.gz"/>\n+                            </collection>\n+                        </element>\n+                    </collection>\n+                </param>\n             </conditional>\n             <section name="arf">\n                 <param name="nanopore" value="ecoli_1K.fastq.gz"/>\n@@ -330,17 +391,17 @@\n             <param name="mode_sel" value="--careful"/>\n             <param name="optional_output" value="cr,l"/>\n             <output_collection name="out_cr" type="list" count="3">\n-                <element name="pl1.fq.gz.fastq.00.0_0">\n+                <element name="pl1.fastq00.0_0">\n                     <assert_contents>\n                         <has_size value="72173" delta="1000"/>\n                     </assert_contents>\n                 </element>\n-                <element name="pl2.fq.gz.fastq.00.0_0">\n+                <element name="pl2.fastq00.0_0">\n                     <assert_contents>\n                         <has_size value="72173" delta="1000"/>\n                     </assert_contents>\n                 </element>\n-                <element name="pl_unpaired.00.0_0">\n+                <element name="pl_unpaired00.0_0">\n                     <assert_contents>\n                         <has_size value="392" delta="100"/>\n                     </assert_contents>\n@@ -348,7 +409,7 @@\n             </output_collection>\n             <output name="out_l">\n                 <assert_contents>\n-                    <has_text_matching expression="Thank you for using SPAdes!"/>\n+                    <has_text_matching expression="Thank you for using plasmidSPAdes!"/>\n                 </assert_contents>\n             </output>\n         </test>\n'
b
diff -r 5be72b7648fa -r b40b77418372 test-data/ecoli_1K.fastq.gz
b
Binary file test-data/ecoli_1K.fastq.gz has changed