Repository 'nextdenovo'
hg clone https://toolshed.g2.bx.psu.edu/repos/bgruening/nextdenovo

Changeset 0:733eab97b979 (2023-02-09)
Commit message:
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/nextdenovo commit 5890a5b5b51cfe2dc4a1bbe1866ce508a9f9ce9f
added:
macros.xml
nextdenovo.xml
test-data/nanopore.fasta.gz
b
diff -r 000000000000 -r 733eab97b979 macros.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml Thu Feb 09 21:24:58 2023 +0000
b
@@ -0,0 +1,27 @@
+<macros>
+    <token name="@TOOL_VERSION@">2.5.0</token>
+    <token name="@VERSION_SUFFIX@">0</token>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="@TOOL_VERSION@">nextdenovo</requirement>
+        </requirements>
+    </xml>
+    <xml name="biotools">
+        <xrefs>
+            <xref type="bio.tools">nextdenovo</xref>
+        </xrefs>
+    </xml>
+    <xml name="citations">
+        <citations>
+            <citation type="bibtex">
+                @misc{githubNextDenovo,
+                author = {Jiang, Hu},
+                year = {2022},
+                title = {NextDenovo},
+                publisher = {GitHub},
+                journal = {GitHub repository},
+                url = {https://github.com/Nextomics/NextDenovo}}
+            </citation>
+        </citations>
+    </xml>
+</macros>
b
diff -r 000000000000 -r 733eab97b979 nextdenovo.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/nextdenovo.xml Thu Feb 09 21:24:58 2023 +0000
[
b'@@ -0,0 +1,220 @@\n+<tool id="nextdenovo" name="NextDenovo" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">\n+    <description>string graph-based de novo assembler for long reads</description>\n+    <macros>\n+        <import>macros.xml</import>\n+    </macros>\n+    <expand macro="biotools"/>\n+    <expand macro="requirements" />\n+    <version_command>nextDenovo --version</version_command>\n+    <command detect_errors="exit_code"><![CDATA[\n+        mkdir -p \'./read_files\' &&\n+        #for $index,$sample in enumerate($input_reads)\n+            #set $ext = $sample.ext\n+            ln -s \'${sample}\' \'./read_files/sample_${index}.${ext}\' &&\n+        #end for\n+        ls \'./read_files\' -1 | sed -e \'s|^|read_files/|\' > \'./input.fofn\' &&\n+        cat \'${configfile}\' | sed -e "s/cores/\\${GALAXY_SLOTS:-4}/g" | sed -e "s|memory|\\$((\\${GALAXY_MEMORY_MB:-8192}/1024))|g" > \'./configfile\' &&\n+        nextDenovo \'./configfile\'\n+    ]]></command>\n+    <configfiles>\n+        <configfile name="configfile"><![CDATA[\n+            [General]\n+            job_type = local\n+            job_prefix = nextDenovo\n+            task = $task\n+            rewrite = yes\n+            deltmp = yes\n+            parallel_jobs = cores\n+            input_type = $input_type\n+            read_type = $read_type\n+            input_fofn = input.fofn\n+\n+            [correct_option]\n+            read_cutoff = $read_cutoff\n+            #if $genome_seed.selector == \'genome\'\n+                genome_size = $genome_seed.genome_size # estimated genome size\n+                seed_depth = $genome_seed.seed_depth\n+            #else\n+                seed_cutoff = $genome_seed.seed_cutoff\n+            #end if\n+            blocksize = $blocksize\n+            sort_options = -m memoryg -t cores -k $ovl_parameters.max_depth_overlap -l $ovl_parameters.max_over_hang_length\n+            minimap2_options_raw = -t cores --minlen $minimap_parameters.minlen --minmatch $minimap_parameters.minmatch --minide $minimap_parameters.minide --kn $minimap_parameters.kn --wn $minimap_parameters.wn --cn $minimap_parameters.cn --maxhan1 $minimap_parameters.maxhan1 --maxhan2 $minimap_parameters.maxhan2\n+            pa_correction = cores\n+            correction_options = -p cores\n+\n+            [assemble_option]\n+            minimap2_options_cns = -t cores\n+            nextgraph_options = -a $np.a $np.c $np.G $np.G $np.k $np.A -E $np.E -q $np.q -i $np.i -I $np.I -R $np.R -S $np.S -r $np.r -M $np.M -T $np.T -N $np.N -u $np.u -w $np.w -D $np.D -P $np.P -m $np.m -n $np.n -B $np.B -C $np.C -z $np.z -l $np.l -L $np.L -t $np.t -F $np.F\n+        ]]></configfile>\n+    </configfiles>\n+    <inputs>\n+        <param name="input_reads" type="data" format="fasta,fasta.gz,fastq,fastq.gz,fastqsanger,fastqsanger.gz" multiple="true" label="Sequence reads"/>\n+        <param name="task" type="select" label="Task">\n+            <option value="all">All</option>\n+            <option value="correct">Correct: only do the correction step</option>\n+            <option value="assemble">Assemble: only do the assembly step (only work if input type = corrected or read type = HiFi)</option>\n+        </param>\n+        <param name="input_type" type="select" label="Input type" help="You can use raw or corrected reads.">\n+            <option value="raw">Raw</option>\n+            <option value="corrected">Corrected</option>\n+        </param>\n+        <param name="read_type" type="select" label="Read type">\n+            <option value="clr">CLR: continuous long read</option>\n+            <option value="hifi">HiFi: PacBio highly accurate long reads</option>\n+            <option value="ont">ONT: Nanopore 1D reads</option>\n+        </param>\n+        <param name="read_cutoff" type="integer" min="0" value="1000" optional="true" label="Read cutoff" help="filter reads with length smaller than read_cutoff"/>\n+        <conditional name="genome_seed">\n+            <param name="selector" type="select" label="Provide estimated genome size or seed c'..b'min="0" value="5" label="Maximal length of a short loop"/>\n+            <param argument="-t" type="integer" min="0" value="500" label="Maximal over hang length of dovetails"/>\n+            <param argument="-F" type="integer" min="0" value="1000" label="Fuzz length for trans-reduction"/>\n+        </section>\n+    </inputs>\n+    <outputs>\n+        <data name="stats" format="txt" from_work_dir="03.ctg_graph/nd.asm.fasta.stat" label="${tool.name} on ${on_string}: stats">\n+            <filter>task != \'correct\'</filter>\n+        </data>\n+        <data name="asmp" format="txt" from_work_dir="03.ctg_graph/nd.asm.p.fasta" label="${tool.name} on ${on_string}: nd.asm.p.fasta">\n+            <filter>task != \'correct\'</filter>\n+        </data>\n+        <data name="asm" format="txt" from_work_dir="03.ctg_graph/nd.asm.fasta.stat" label="${tool.name} on ${on_string}: nd.asm.p.fasta">\n+            <filter>task != \'correct\'</filter>\n+        </data>\n+        <data name="asm" format="txt" from_work_dir="02.cns_align/01.seed_cns.sh.work/seed_cns3" label="${tool.name} on ${on_string}: corrected">\n+            <filter>task != \'assemble\'</filter>\n+        </data>\n+        <data name="config" format="txt" from_work_dir="configfile" label="${tool.name} on ${on_string}: configuration file"/>\n+    </outputs>\n+    <tests>\n+        <!-- Default parameters: correct mode -->\n+        <test expect_num_outputs="2">\n+            <param name="input_reads" value="nanopore.fasta.gz"/>\n+            <param name="task" value="correct"/>\n+            <param name="input_type" value="raw"/>\n+            <param name="read_type" value="ont"/>\n+            <conditional name="genome_seed">\n+                <param name="selector" value="genome"/>\n+                <param name="genome_size" value="2k"/>\n+                <param name="seed_depth" value="45"/>\n+            </conditional>\n+            <output name="config">\n+                <assert_contents>\n+                    <has_text text="genome_size = 2k"/>\n+                    <has_n_lines n="26"/>\n+                </assert_contents>\n+            </output>\n+        </test>\n+        <test expect_failure="true">\n+            <param name="input_reads" value="nanopore.fasta.gz"/>\n+            <param name="task" value="all"/>\n+            <param name="input_type" value="raw"/>\n+            <param name="read_type" value="nanopore"/>\n+            <conditional name="genome_seed">\n+                <param name="selector" value="genome"/>\n+                <param name="genome_size" value="2k"/>\n+                <param name="seed_depth" value="45"/>\n+            </conditional>\n+            <assert_stderr>\n+                <has_text text="The read/seed length is too short, and the assembly result is unexpected and please check the assembly quality carefully." />\n+            </assert_stderr>\n+        </test>\n+        <test expect_failure="true">\n+            <param name="input_reads" value="nanopore.fasta.gz"/>\n+            <param name="task" value="assemble"/>\n+            <param name="input_type" value="raw"/>\n+            <param name="read_type" value="nanopore"/>\n+            <conditional name="genome_seed">\n+                <param name="selector" value="genome"/>\n+                <param name="genome_size" value="2k"/>\n+                <param name="seed_depth" value="45"/>\n+            </conditional>\n+            <assert_stderr>\n+                <has_text text="The read/seed length is too short, and the assembly result is unexpected and please check the assembly quality carefully." />\n+            </assert_stderr>\n+        </test>\n+    </tests>\n+    <help><![CDATA[\n+        NextDenovo is a string graph-based de novo assembler for long reads (CLR, HiFi and ONT). It uses \n+        a "correct-then-assemble" strategy similar to canu (no correction step for PacBio HiFi reads), but \n+        requires significantly less computing resources and storages.\n+    ]]></help>\n+    <expand macro="citations" />\n+</tool>\n\\ No newline at end of file\n'
b
diff -r 000000000000 -r 733eab97b979 test-data/nanopore.fasta.gz
b
Binary file test-data/nanopore.fasta.gz has changed