Mercurial > repos > bgruening > minipolish
diff minipolish.xml @ 0:1f9f2edc8cf4 draft default tip
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/minipolish commit 2772d922443f5838d84646282be6fbfad2df1c77
author | bgruening |
---|---|
date | Wed, 19 Oct 2022 14:58:27 +0000 |
parents | |
children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/minipolish.xml Wed Oct 19 14:58:27 2022 +0000 @@ -0,0 +1,87 @@ +<tool id="minipolish" name="minipolish" version="@TOOL_VERSION@+galaxy@SUFFIX_VERSION@" profile="20.01"> + <description>polishing miniasm assemblies</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements" /> + <expand macro="biotools"/> + <version_command>gfastats --version</version_command> + <command detect_errors="exit_code"><![CDATA[ + #if $reads.ext.startswith("fasta") + #set ext="fasta" + #else + #set ext="fastq" + #end if + #if $reads.ext.endswith(".gz") + #set ext=ext+".gz" + #end if + ln -s '$reads' reads.$ext && + minipolish + -t \${GALAXY_SLOTS:-4} + --rounds $rounds + $pacbio + $skip_initial + reads.$ext + '${assembly}' > $polished_gfa + ]]></command> + <inputs> + <param name="reads" type="data" format="fasta,fastq,fastq.gz,fastqsanger.gz" label="Long reads for polishing"/> + <param name="assembly" type="data" format="gfa1" label="Miniasm assembly to be polished"/> + <param argument="--rounds" type="integer" min="0" value="2" label="Rounds" help="Number of full Racon polishing rounds. Default: 2" /> + <param argument="--pacbio" type="boolean" truevalue="--pacbio" falsevalue="" checked="false" label="PacBio reads" help="Use this flag for PacBio reads to make Minipolish use the map-pb + Minimap2 preset. Default: assumes Nanopore reads and uses the map-ont preset" /> + <param argument="--skip_initial" type="boolean" truevalue="--skip_initial" falsevalue="" checked="false" label="Skip the initial polishing round" help="Appropriate if the input GFA does + not have 'a' lines. Default: do the initial polishing round" /> + </inputs> + <outputs> + <data name="polished_gfa" format="gfa1" label="${tool.name} on ${on_string}: polished GFA"/> + </outputs> + <tests> + <!-- Test default parameters --> + <test expect_num_outputs="1"> + <param name="reads" value="reads.fastq"/> + <param name="assembly" value="miniasm.gfa"/> + <param name="rounds" value="2"/> + <output name="polished_gfa" file="test_01.gfa" ftype="gfa1"/> + + </test> + <!-- Test optional parameters --> + <test expect_num_outputs="1"> + <param name="reads" value="reads.fastq.gz"/> + <param name="assembly" value="miniasm.gfa"/> + <param name="rounds" value="3"/> + <param name="pacbio" value="true"/> + <param name="skip_initial" value="true"/> + <output name="polished_gfa" file="test_02.gfa" ftype="gfa1"/> + </test> + </tests> + <help><![CDATA[ + +.. class:: infomark + +**Purpose** + +Miniasm is a great long-read assembly tool: straight-forward, effective and very fast. However, it does not include a polishing step, so its assemblies have a high error rate – they are essentially made of stitched-together pieces of long reads. + +Racon is a great polishing tool that can be used to clean up assembly errors. It's also very fast and well suited for long-read data. However, it operates on FASTA files, not the GFA graphs that miniasm makes. + +That's where Minipolish comes in. With a single command, it will use Racon to polish up a miniasm assembly, while keeping the assembly in graph form. + +It also takes care of some of the other nuances of polishing a miniasm assembly: + +- Adding read depth information to contigs +- Fixing sequence truncation that can occur in Racon +- Adding circularising links to circular contigs if not already present (so they display better in Bandage) +- 'Rotating' circular contigs between polishing rounds to ensure clean circularisation + +.. class:: infomark + +**CIGARs** + +It is important to note here something that Minipolish does not do: change/fix the CIGAR strings indicating contig overlap. While circular contigs will be connected with an overlap-free link (i.e. a CIGAR of 0M), links between linear contigs will have overlap. + +So take CIGAR overlaps between polished contigs with a grain of salt. They will still indicate the approximate amount of overlap, not the exact amount. + + ]]></help> + <expand macro="citations" /> +</tool>