comparison minimap2.xml @ 5:17e61517c166 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/minimap2 commit 31d0c015b36d7aa93f586c566ceeac56324863ad

4:6f50f36e4481

<?xml version="1.0"?>
<tool id="minimap2" name="Map with minimap2" version="2.5+gx1" profile="17.01">
    <description>A fast pairwise aligner for genomic and spliced nucleotide sequences</description>
    <requirements>
        <requirement type="package" version="2.5">minimap2</requirement>
        <requirement type="package" version="1.6">samtools</requirement>
    </requirements>
    <version_command>minimap2 --version</version_command>
    <command>
<![CDATA[
    #if $reference_source.reference_source_selector == 'history':

        ln -f -s '$reference_source.ref_file.fields.path' reference.fa &&
    #end if
    minimap2
    -x $analysis_type_selector
    ## indexing options
    #if $indexing_options.k:
        -k $indexing_options.k
    #end if
    #if $indexing_options.w:
        -w $indexing_options.w

        -I $indexing_options.I
    #end if
    ## Mapping options
    #if $mapping_options.f:
        -f $mapping_options.f
    #end if
    #if $mapping_options.g:
        -g $mapping_options.g
    #end if
    #if $mapping_options.G:

    #else if $io_options.output_format == 'CRAM':
        -a
        | samtools sort
        -@\${GALAXY_SLOTS:-2}
        -O $io_options.output_format
        --reference reference.fa
        --output-fmt-option no_ref
        -o '$alignment_output'
    #end if
    > '$alignment_output'

            <when value="history">
                <param name="ref_file" type="data" format="fasta,fastq" label="Use the following dataset as the reference sequence" help="You can upload a FASTA or FASTQ sequence to the history and use it as reference" />
            </when>
        </conditional>
        <section name="indexing_options" title="Indexing options">
            <!-- Homopolymer setting seems to not properly overwrite sr preset
            <param argument="-H" name="H" type="boolean" optional="true" truevalue="-H" falsevalue="" label="Use homopolymer-compressed k-mer ?"/>
            -->
            <param argument="-k" type="integer" min="4" max="28" optional="true"  label="k-mer size" help=""/>
            <param argument="-w" type="integer" min="1" optional="true"  label="minimizer window size" help=""/>
            <param argument="-I" type="integer" min="1" optional="true"  label="split index for every N input gigabases" help=""/>
        </section>
        <!-- start unchanged copy from bwa-mem -->

                <param name="fastq_input1" type="data" format="fastqsanger,fastqsanger.gz,fasta" label="Select fastq dataset" help="Specify dataset with interleaved reads"/>
            </when>
        </conditional>
        <!-- end unchanged copy from bwa-mem -->
        <param name="analysis_type_selector" type="select" label="Select analysis mode (sets default)">
            <option value="map-pb">-Hk19 (PacBio vs reference mapping)</option>
            <option value="map-ont">-k15 (Oxford Nanopore vs reference mapping)</option>
            <option value="asm5">-k19 -w19 -A1 -B19 -O39,81 -E3,1 -s200 -z200 (asm to ref mapping; break at 5% div.)</option>
            <option value="asm10">-k19 -w19 -A1 -B9 -O16,41 -E2,1 -s200 -z200 (asm to ref mapping; break at 10% div.)</option>
            <option value="ava-pb">-Hk19 -w5 -Xp0 -m100 -g10000 --max-chain-skip 25 (PacBio read overlap)</option>
            <option value="ava-ont">-k15 -w5 -Xp0 -m100 -g10000 --max-chain-skip 25 (ONT read overlap)</option>
            <option value="splice">long-read spliced alignment</option>
            <option value="sr">short single-end reads without splicing</option>
        </param>
        <section name="mapping_options" title="Set advanced mapping options" help="Sets -f, -g, -G, -F, -r, -n, -m, -X, -p and -N options." expanded="False">
            <param argument="-f" type="float" value="" optional="true" label="filter out top FLOAT fraction of repetitive minimizers" help="default=0.0002"/>
            <param argument="-g" type="integer" value="" optional="true" label="stop chain enlongation if there are no minimizers in INT-bp" help="default=5000"/>
            <param argument="-G" type="integer" value="" optional="true" label="max intron length in thousand (effective with -xsplice; changing -r)" help="default=200"/>
            <param argument="-F" type="integer" value="" optional="true" label="max fragment length (effective with -xsr or in the fragment mode)" help="default=800" />
            <param argument="-r" type="integer" value="" optional="true" label="bandwidth used in chaining and DP-based alignment" help="default=500" />
            <param argument="-n" type="integer" value="" optional="true" label="minimal number of minimizers on a chain" help="default=3"/>

            <param argument="--cs" type="select" optional="true" label="Output cs tag?" help="The cs tag is a more compact standalone representation of the MD tag, see help below.">
                <option value="none">no</option>
                <option value="short">short</option>
                <option value="long">long</option>
            </param>
            <param argument="-Y" type="boolean" truevalue="-Y" falsevalue="" label="use soft clipping for supplementary alignments ?"/>
        </section>
    </inputs>
    <outputs>
        <data format="bam" name="alignment_output" label="${tool.name} on ${on_string} (mapped reads in ${io_options.output_format} format)">

5:17e61517c166

<?xml version="1.0"?>
<tool id="minimap2" name="Map with minimap2" version="@TOOL_VERSION@" profile="17.01">
    <description>A fast pairwise aligner for genomic and spliced nucleotide sequences</description>
    <macros>
        <token name="@TOOL_VERSION@">2.12</token>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">minimap2</requirement>
        <requirement type="package" version="1.9">samtools</requirement>
    </requirements>
    <version_command>minimap2 --version</version_command>
    <command>
<![CDATA[
    #if $reference_source.reference_source_selector == 'history':

        ln -f -s '$reference_source.ref_file.fields.path' reference.fa &&
    #end if
    minimap2
    -x $analysis_type_selector
    ## indexing options
    $indexing_options.H
    #if $indexing_options.k:
        -k $indexing_options.k
    #end if
    #if $indexing_options.w:
        -w $indexing_options.w

        -I $indexing_options.I
    #end if
    ## Mapping options
    #if $mapping_options.f:
        -f $mapping_options.f
    #end if
    #if $mapping_options.min_occ_floor:
        --min-occ-floor $min_occ_floor
    #end if
    #if $mapping_options.g:
        -g $mapping_options.g
    #end if
    #if $mapping_options.G:

    #else if $io_options.output_format == 'CRAM':
        -a
        | samtools sort
        -@\${GALAXY_SLOTS:-2}
        -O $io_options.output_format
        $io_options.eqx
        --reference reference.fa
        --output-fmt-option no_ref
        -o '$alignment_output'
    #end if
    > '$alignment_output'

            <when value="history">
                <param name="ref_file" type="data" format="fasta,fastq" label="Use the following dataset as the reference sequence" help="You can upload a FASTA or FASTQ sequence to the history and use it as reference" />
            </when>
        </conditional>
        <section name="indexing_options" title="Indexing options">
            <param argument="-H" name="H" type="boolean" optional="true" truevalue="-H" falsevalue="" label="Use homopolymer-compressed k-mer ?"/>
            <param argument="-k" type="integer" min="4" max="28" optional="true"  label="k-mer size" help=""/>
            <param argument="-w" type="integer" min="1" optional="true"  label="minimizer window size" help=""/>
            <param argument="-I" type="integer" min="1" optional="true"  label="split index for every N input gigabases" help=""/>
        </section>
        <!-- start unchanged copy from bwa-mem -->

                <param name="fastq_input1" type="data" format="fastqsanger,fastqsanger.gz,fasta" label="Select fastq dataset" help="Specify dataset with interleaved reads"/>
            </when>
        </conditional>
        <!-- end unchanged copy from bwa-mem -->
        <param name="analysis_type_selector" type="select" label="Select analysis mode (sets default)">
            <option value="map-pb">PacBio/Oxford Nanopore read to reference mapping (-Hk19)</option>
            <option value="map-ont">Oxford Nanopore read to reference mapping. Slightly more sensitive for Oxford Nanopore to reference mapping (-k15). For PacBio reads, HPC minimizers consistently leads to faster performance and more sensitive results in comparison to normal minimizers. For Oxford Nanopore data, normal minimizers are better, though not much. The effectiveness of HPC is determined by the sequencing error mode.</option>
            <option value="ava-pb">PacBio all-vs-all overlap mapping (-Hk19 -Xw5 -m100 -g10000 --max-chain-skip 25)</option>
            <option value="ava-ont">Oxford Nanopore all-vs-all overlap mapping (-k15 -Xw5 -m100 -g10000 -r2000 --max-chain-skip 25). Similarly, the major difference from ava-pb is that this preset is not using HPC minimizers.</option>
            <option value="asm5">Long assembly to reference mapping (-k19 -w19 -A1 -B19 -O39,81 -E3,1 -s200 -z200 --min-occ-floor=100). Typically, the alignment will not extend to regions with 5% or higher sequence divergence. Only use this preset if the average divergence is far below 5%.</option>
            <option value="asm10">Long assembly to reference mapping (-k19 -w19 -A1 -B9 -O16,41 -E2,1 -s200 -z200 --min-occ-floor=100). Up to 10% sequence divergence.</option>
            <option value="asm20">Long assembly to reference mapping (-k19 -w10 -A1 -B6 -O6,26 -E2,1 -s200 -z200 --min-occ-floor=100). Up to 20% sequence divergence.</option>
            <option value="splice">Long-read spliced alignment (-k15 -w5 --splice -g2000 -G200k  -A1 -B2  -O2,32  -E1,0  -C9  -z200  -ub  --splice-flank=yes). In the splice mode, 1) long deletions are taken as  introns  and  represented as the `N' CIGAR operator 2) long insertions are disabled 3) deletion and insertion gap costs are different during chaining 4) the computation of the `ms' tag ignores introns to demote hits to pseudogenes.</option>
            <option value="sr">Short single-end reads without splicing (-k21 -w11 --sr --frag=yes -A2 -B8 -O12,32 -E2,1 -r50 -p.5 -N20 -f1000,5000 -n2 -m20 -s40 -g200 -2K50m --heap-sort=yes --secondary=no)</option>
        </param>
        <section name="mapping_options" title="Set advanced mapping options" help="Sets -f, -g, -G, -F, -r, -n, -m, -X, -p, -N and --min-occ-floor options." expanded="False">
            <param argument="-f" type="float" value="" optional="true" label="filter out top FLOAT fraction of repetitive minimizers" help="default=0.0002"/>
            <param argument="--min-occ-floor" name="min_occ_floor" type="integer" label="force minimap2 to always use k-mers occuring this many times or fewer" help="Maximum occurence is the number of repetitive minimizers determined by '-f' or this value, whichever is higher." optional="true" />
            <param argument="-g" type="integer" value="" optional="true" label="stop chain enlongation if there are no minimizers in INT-bp" help="default=5000"/>
            <param argument="-G" type="integer" value="" optional="true" label="max intron length in thousand (effective with -xsplice; changing -r)" help="default=200"/>
            <param argument="-F" type="integer" value="" optional="true" label="max fragment length (effective with -xsr or in the fragment mode)" help="default=800" />
            <param argument="-r" type="integer" value="" optional="true" label="bandwidth used in chaining and DP-based alignment" help="default=500" />
            <param argument="-n" type="integer" value="" optional="true" label="minimal number of minimizers on a chain" help="default=3"/>

            <param argument="--cs" type="select" optional="true" label="Output cs tag?" help="The cs tag is a more compact standalone representation of the MD tag, see help below.">
                <option value="none">no</option>
                <option value="short">short</option>
                <option value="long">long</option>
            </param>
            <param argument="--eqx" type="boolean" truevalue="--eqx" falsevalue="" label="write =/X CIGAR operators"/>
            <param argument="-Y" type="boolean" truevalue="-Y" falsevalue="" label="use soft clipping for supplementary alignments ?"/>
        </section>
    </inputs>
    <outputs>
        <data format="bam" name="alignment_output" label="${tool.name} on ${on_string} (mapped reads in ${io_options.output_format} format)">