comparison minimap2.xml @ 8:53c0b7a1a0c3 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/minimap2 commit 4f9072805884196ffdc9ad1df93ecce08b7f08ba"

7:b3eab4b67562

<?xml version="1.0"?>
<tool id="minimap2" name="Map with minimap2" version="@TOOL_VERSION@+galaxy0" profile="17.01">
    <description>A fast pairwise aligner for genomic and spliced nucleotide sequences</description>
    <macros>
        <token name="@TOOL_VERSION@">2.17</token>
    </macros>
    <requirements>

        -u $alignment_options.u
    #end if
    ## Output options
    $io_options.Q
    $io_options.L
    #if $io_options.cs:
        --cs $io_options.cs
    #end if
    $io_options.Y
    #if $io_options.K:

                <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>
            <option value="self-homology">Construct a self-homology map - use same genome as query and reference (-DP -k19 -w19 -m200)</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 name="output_format" type="select" label="Select an output format">
                <option value="BAM">BAM</option>
                <option value="CRAM">CRAM</option>
                <option value="paf">paf</option>
            </param>
            <param argument="-Q" type="boolean" truevalue="-Q" falsevalue="" optional="true" label="don't output base quality"/>
            <param argument="-L" type="boolean" truevalue="-L" falsevalue="" optional="true" label="write CIGAR with >65535 ops to the CG tag" help="Useful for very long reads in SAM/BAM format"/>
            <param argument="-K" type="integer" optional="true" label="minibatch size for mapping (in megabyte)" help="default=500M"/>
            <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>

8:53c0b7a1a0c3

<?xml version="1.0"?>
<tool id="minimap2" name="Map with minimap2" version="@TOOL_VERSION@+galaxy1" profile="17.01">
    <description>A fast pairwise aligner for genomic and spliced nucleotide sequences</description>
    <macros>
        <token name="@TOOL_VERSION@">2.17</token>
    </macros>
    <requirements>

        -u $alignment_options.u
    #end if
    ## Output options
    $io_options.Q
    $io_options.L
    $io_options.c
    #if $io_options.cs:
        --cs $io_options.cs
    #end if
    $io_options.Y
    #if $io_options.K:

                <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) (map-pb)</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. (map-ont)</option>
            <option value="ava-pb">PacBio all-vs-all overlap mapping (-Hk19 -Xw5 -m100 -g10000 --max-chain-skip 25) (ava-pb)</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. (ava-ont)</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%. (asm5)</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. (asm10)</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. (asm20)</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. (splice)</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) (sr)</option>
            <option value="self-homology">Construct a self-homology map - use same genome as query and reference (-DP -k19 -w19 -m200) (self-homology)</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 name="output_format" type="select" label="Select an output format">
                <option value="BAM">BAM</option>
                <option value="CRAM">CRAM</option>
                <option value="paf">paf</option>
            </param>
            <param argument="-Q" type="boolean" truevalue="-Q" falsevalue="" label="don't output base quality"/>
            <param argument="-L" type="boolean" truevalue="-L" falsevalue="" label="write CIGAR with >65535 ops to the CG tag" help="Useful for very long reads in SAM/BAM format"/>
            <param argument="-K" type="integer" optional="true" label="minibatch size for mapping (in megabyte)" help="default=500M"/>
            <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="-c" type="boolean" truevalue="-c" falsevalue="" label="Generate CIGAR"
                help="In PAF, the CIGAR is written to the ‘cg’ custom tag." />

            <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>