view flye.xml @ 0:d9f4c141d88a draft

planemo upload for repository commit 2f6d48e1d2161d03411d9fbb4fc3d16f0fa3d2e1
author bgruening
date Tue, 25 Sep 2018 05:24:27 -0400
children cd256484eb1a
line wrap: on
line source

<tool id="flye" name="Assembly" version="2.3.5">
    <description>of long and error-prone reads</description>
    <expand macro="requirements" />
    <version_command>flye --version</version_command>
    <command detect_errors="exit_code">

    #for $counter, $input in enumerate($inputs):
        ln -s '$input' ./input_${counter}.${input.ext} &&
    #end for
    #for $counter, $input in enumerate($inputs):
    #end for

    -o out_dir 
    -g '$g'
    -t \${GALAXY_SLOTS:-4}
    -i $i
    #if $m:
        -m '$m'
    #end if    
        <param name="inputs" type="data" format="fasta,fasta.gz,fastq,fastq.gz" multiple="true" label="Input reads" />
        <param name="mode" type="select" label="Mode">
            <option value="--nano-raw">Nanopore raw</option>
            <option value="--nano-corr">Nanopore corrected</option>
            <option value="--pacbio-raw">PacBio raw</option>
            <option value="--pacbio-corr">PacBio corrected</option>
            <option value="--subassemblies">high-quality contig-like input</option>
        <param argument="-g" type="text" label="estimated genome size (for example, 5m or 2.6g)">
            <validator type="regex" message="Genome size must be a float  or integer, optionally followed by the a unit prefix (kmg)">^([0-9]*[.])?[0-9]+[kmg]?$</validator> 
        <param argument="-i" type="integer" value="1" label="number of polishing iterations" />
        <param argument="-m" type="integer" optional="true" label="minimum overlap between reads (default: auto)" />
        <data name="contigs" format="fasta" from_work_dir="out_dir/contigs.fasta" label="${} on ${on_string} (contigs)"/>
        <data name="scaffolds" format="fasta" from_work_dir="out_dir/scaffolds.fasta" label="${} on ${on_string} (scaffolds)"/>
        <data name="assembly_info" format="tabular" from_work_dir="out_dir/assembly_info.txt" label="${} on ${on_string} (assembly_info)"/>
        <data name="assembly_graph" format="graph_dot" from_work_dir="out_dir/" label="${} on ${on_string} (assembly_graph)"/>
        <data name="flye_log" format="txt" from_work_dir="out_dir/flye.log" label="${} on ${on_string} (log)"/>
            <param name="inputs" ftype="fasta" value="E.coli_PacBio_40x_first_200_reads.fasta"/>
            <param name="mode" value="--pacbio-raw"/>
            <param name="g" value="1m"/>
            <output name="contigs" file="result1_contigs.fasta" ftype="fasta"/>
            <output name="scaffolds" file="result1_scaffolds.fasta" ftype="fasta"/>
            <output name="assembly_info" file="result1_assembly_info.txt" ftype="tabular"/>
            <output name="assembly_graph" file="" ftype="graph_dot" compare="sim_size"/>    
            <param name="inputs" ftype="fasta" value="Loman_E.coli_MAP006-1_2D_50x_first_500_reads.fasta"/>
            <param name="mode" value="--nano-raw"/>
            <param name="g" value="100000"/>
            <output name="contigs" file="result2_contigs.fasta" ftype="fasta"/>
            <output name="scaffolds" file="result2_scaffolds.fasta" ftype="fasta"/>
            <output name="assembly_info" file="result2_assembly_info.txt" ftype="tabular"/>
            <output name="assembly_graph" file="" ftype="graph_dot" compare="sim_size"/>    
            <param name="inputs" ftype="fasta" value="E.coli_PacBio_40x_first_200_reads.fasta"/>
            <param name="mode" value="--pacbio-raw"/>
            <param name="g" value="1.1m"/>
            <param name="i" value="2"/>
            <output name="contigs" file="result3_contigs.fasta" ftype="fasta"/>
            <output name="scaffolds" file="result3_scaffolds.fasta" ftype="fasta"/>

Input reads could be in FASTA or FASTQ format, uncompressed
or compressed with gz. Currenlty, raw and corrected reads
from PacBio and ONT are supported. The expected error rates are
<30% for raw and <2% for corrected reads. Additionally,
--subassemblies option performs a consensus assembly of multiple
sets of high-quality contigs. You may specify multiple
files with reads (separated by spaces). Mixing different read
types is not yet supported.

You must provide an estimate of the genome size as input,
which is used for solid k-mers selection. The estimate could
be rough (e.g. withing 0.5x-2x range) and does not affect
the other assembly stages. Standard size modificators are
supported (e.g. 5m or 2.6g).

    <expand macro="citations" />