comparison minimap2.xml @ 7:831dcb48efa1 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/minimap2 commit 7cb87c310b34cb2af2547ad8a14679107fd86d5d

6:4d84d86b368e

<?xml version="1.0"?>
<tool id="minimap2" name="Map with minimap2" version="2.3" profile="17.01">
    <description>- A fast pairwise aligner for genomic and spliced nucleotide sequences</description>
    <requirements>
        <requirement type="package" version="2.3">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' reference.fa &&
    #else:
        ln -f -s '$reference_source.ref_file.fields.path' reference.fa &&
    #end if

    #end if
    #if $alignment_options.B:
        -B $alignment_options.B
    #end if
    #if $alignment_options.O:
        -O $alignment_options.O
    #end if
    #if $alignment_options.E:
        -E $alignment_options.E
    #end if
    #if $alignment_options.z:
        $alignment_options.z
    #end if
    #if $alignment_options.s:

    #if $fastq_input.fastq_input_selector in ['single', 'paired_iv']:
        '$fastq_input.fastq_input1'
    #else if $fastq_input.fastq_input_selector == 'paired':
         '$fastq_input.fastq_input1' '$fastq_input.fastq_input2'
    #else if $fastq_input.fastq_input_selector == 'paired_collection':
        '$fastq_input.fastq_input1.forward' '$fastq_input.fastq_input2.reverse'
    #end if
    | samtools sort
    -@\${GALAXY_SLOTS:-2}
    -O BAM
    #if $io_options.output_format == 'CRAM':
        -l 0| samtools view -T reference.fa -C
    #end if
    > '$alignment_output'
]]>
    </command>
    <inputs>
        <conditional name="reference_source">
            <param name="reference_source_selector" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options. See `Indexes` section of help below">

            <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="-m" type="integer" value="" optional="true" label="minimal chaining score (matching bases minus log gap penalty)" help="default=40"/>
            <param argument="-X" type="boolean" truevalue="-X" falsevalue="" optional="true" label="skip self and dual mappings (for the all-vs-all mode)"/>
            <param argument="-p" type="float" value="" max="1" optional="true" label="min secondary-to-primary score ratio" help="default=0.8"/>
            <param argument="-N" type="integer" min="0" optional="true" label="retain at most INT secondary alignments" help="default=5"/>
        </section>
        <section name="alignment_options" title="Set advanced alignment options" help="Sets -Q, -L, -R, -c, --cs, and -K options." expanded="False">
            <param argument="-A" type="integer" optional="true" label="Score for a sequence match" help="default=2"/>
            <param argument="-B" type="integer" optional="true" label="Penalty for a mismatch" help="-B; default=4" />
            <param argument="-O" type="text" optional="true" label="Gap open penalties for deletions and insertions" help="-O; default=4,24">
                <sanitizer invalid_char="">
                    <valid initial="string.digits"><add value=","/> </valid>
                </sanitizer>
            </param>
            <param argument="-E" type="text" optional="true" label="Gap extension penalties; a gap of size k cost &#39;-O + -E*k&#39;. If two numbers are specified, the first is the penalty of extending a deletion and the second for extending an insertion" help="-E; default=2,1">
                <sanitizer invalid_char="">
                    <valid initial="string.digits"><add value=","/> </valid>
                </sanitizer>
            </param>
            <param argument="-z" type="integer" optional="true" label="Z-drop score" help="default=400"/>
            <param argument="-s" type="integer" optional="true" label="minimal peak DP alignment score" help="default=80"/>
            <param argument="-u" type="select" optional="true" label="how to find GT-AG">
                <option value="n">don't match GT-AG</option>
                <option value="f">transcript strand</option>
                <option value="b">both strands</option>
            </param>
        </section>
        <section name="io_options" title="Set advanced output options" help="Sets -T, -h, -a, -C, -V, -Y, and -M options." expanded="False">
            <param name="output_format" type="select" label="Produce BAM or CRAM file?">
                <option value="BAM">BAM</option>
                <option value="CRAM">CRAM</option>
            </param>
            <param argument="-Q" type="boolean" truevalue="-Q" falsevalue="" optional="true" label="don't output base quality"/>

            </change_format>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="reference_source_selector" value="history" />
            <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
            <param name="fastq_input_selector" value="paired"/>
            <param name="fastq_input1" ftype="fastqsanger" value="bwa-mem-fastq1.fq"/>
            <param name="fastq_input2" ftype="fastqsanger" value="bwa-mem-fastq2.fq"/>
            <param name="analysis_type_selector" value="sr"/>
            <output name="alignment_output" ftype="bam" file="bwa-mem-test1.bam" lines_diff="2" />
        </test>
        <test>
            <param name="reference_source_selector" value="history" />
            <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
            <param name="fastq_input_selector" value="single"/>
            <param name="fastq_input1" ftype="fastqsanger" value="bwa-mem-fasta1.fa"/>
            <param name="analysis_type_selector" value="sr"/>
            <output name="alignment_output" ftype="bam" file="bwa-mem-test1-fasta.bam" lines_diff="2" />
        </test>
        <test>
            <param name="reference_source_selector" value="history" />
            <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
            <param name="fastq_input_selector" value="paired"/>
            <param name="fastq_input1" ftype="fastqsanger.gz" value="bwa-mem-fastq1.fq.gz"/>
            <param name="fastq_input2" ftype="fastqsanger" value="bwa-mem-fastq2.fq"/>
            <param name="analysis_type_selector" value="sr"/>
            <output name="alignment_output" ftype="bam" file="bwa-mem-test1.bam" lines_diff="2" />
        </test>
        <test>
            <param name="reference_source_selector" value="history" />
            <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
            <param name="fastq_input_selector" value="paired"/>
            <param name="fastq_input1" ftype="fastqsanger" value="bwa-mem-fastq1.fq"/>
            <param name="fastq_input2" ftype="fastqsanger" value="bwa-mem-fastq2.fq"/>
            <param name="analysis_type_selector" value="sr"/>
            <output name="alignment_output" ftype="bam" file="bwa-mem-test2.bam" lines_diff="2" />
        </test>
    </tests>
    <help>

Users’ Guide

-  Minimap2 may produce suboptimal alignments through long
   low-complexity regions where seed positions may be suboptimal. This
   should not be a big concern because even the optimal alignment may be
   wrong in such regions.

-  Minimap2 requires SSE2 instructions to compile. It is possible to add
   non-SSE2 support, but it would make minimap2 slower by several times.

In general, minimap2 is a young project with most code written since
June, 2017. It may have bugs and room for improvements. Bug reports and
suggestions are warmly welcomed.
    </help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btp324</citation>
        <citation type="doi">10.1093/bioinformatics/btp698</citation>
        <citation type="bibtex">@misc{1303.3997,

7:831dcb48efa1

<?xml version="1.0"?>
<tool id="minimap2" name="Map with minimap2" version="2.3" profile="17.01">
    <description>A fast pairwise aligner for genomic and spliced nucleotide sequences</description>
    <requirements>
        <requirement type="package" version="2.3">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' reference.fa &&
    #else:
        ln -f -s '$reference_source.ref_file.fields.path' reference.fa &&
    #end if

    #end if
    #if $alignment_options.B:
        -B $alignment_options.B
    #end if
    #if $alignment_options.O:
        #if $alignment_options.O2:
            -O $alignment_options.O,$alignment_options.O2
        #end if
            -O $alignment_options.O
        #end if
    #if $alignment_options.E:
        #if $alignment_options.E2:
            -E $alignment_options.E,$alignment_options.E2
        #else
            -E $alignment_options
        #end if
    #end if
    #if $alignment_options.z:
        $alignment_options.z
    #end if
    #if $alignment_options.s:

    #if $fastq_input.fastq_input_selector in ['single', 'paired_iv']:
        '$fastq_input.fastq_input1'
    #else if $fastq_input.fastq_input_selector == 'paired':
         '$fastq_input.fastq_input1' '$fastq_input.fastq_input2'
    #else if $fastq_input.fastq_input_selector == 'paired_collection':
        '$fastq_input.fastq_input1.forward' '$fastq_input.fastq_input1.reverse'
    #end if
    | samtools sort
    -@\${GALAXY_SLOTS:-2}
    -O $io_options.output_format
    #if $io_options.output_format == 'CRAM':
        --reference reference.fa
    #end if
    -o '$alignment_output'
]]>
    </command>
    <inputs>
        <conditional name="reference_source">
            <param name="reference_source_selector" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options. See `Indexes` section of help below">

            <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="-m" type="integer" value="" optional="true" label="minimal chaining score (matching bases minus log gap penalty)" help="default=40"/>
            <param argument="-X" type="boolean" truevalue="-X" falsevalue="" optional="true" label="skip self and dual mappings (for the all-vs-all mode)"/>
            <param argument="-p" type="float" value="" max="1" optional="true" label="min secondary-to-primary score ratio" help="default=0.8"/>
            <param argument="-N" type="integer" min="0" optional="true" label="retain at most INT secondary alignments" help="default=5"/>
        </section>
        <section name="alignment_options" title="Set advanced alignment options" help="Sets -A, -B, -O, -E, -z, -s and -u options." expanded="False">
            <param argument="-A" type="integer" optional="true" label="Score for a sequence match" help="default=2"/>
            <param argument="-B" type="integer" optional="true" label="Penalty for a mismatch" help="-B; default=4" />
            <param argument="-O" type="integer" min="0" optional="true" label="Gap open penalties for deletions" help="-O; default=4"/>
            <param name="-O2" type="integer" min="0" optional="true" label="Gap open penalties for insertions" help="-O; default=24"/>
            <param argument="-E" type="integer" min="0" optional="true" label="Gap extension penalties; a gap of size k cost &#39;-O + -E*k&#39;. If two numbers are specified, the first is the penalty of extending a deletion and the second for extending an insertion" help="-E; default=2"/>
            <param name="E2" type="integer" min="0" optional="true" label="Gap extension penalty for extending an insertion; if left empty uses the value specified for Gap extension penalties above" help="-E; default=1"/>
            <param argument="-z" type="integer" optional="true" label="Z-drop score" help="default=400"/>
            <param argument="-s" type="integer" optional="true" label="minimal peak DP alignment score" help="default=80"/>
            <param argument="-u" type="select" optional="true" label="how to find GT-AG">
                <option value="n">don't match GT-AG</option>
                <option value="f">transcript strand</option>
                <option value="b">both strands</option>
            </param>
        </section>
        <section name="io_options" title="Set advanced output options" help="Sets -Q, -L, -R, -c, --cs and -K options." expanded="False">
            <param name="output_format" type="select" label="Produce BAM or CRAM file?">
                <option value="BAM">BAM</option>
                <option value="CRAM">CRAM</option>
            </param>
            <param argument="-Q" type="boolean" truevalue="-Q" falsevalue="" optional="true" label="don't output base quality"/>

            </change_format>
        </data>
    </outputs>
    <tests>
        <test>
            <!-- test single input -->
            <param name="reference_source_selector" value="history" />
            <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
            <param name="fastq_input_selector" value="single"/>
            <param name="fastq_input1" ftype="fastqsanger" value="bwa-mem-fasta1.fa"/>
            <param name="analysis_type_selector" value="sr"/>
            <output name="alignment_output" ftype="bam" file="minimap2-test1-fasta.bam" lines_diff="2" />
        </test>
        <test>
            <!-- test cram output -->
            <param name="reference_source_selector" value="history" />
            <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
            <param name="fastq_input_selector" value="single"/>
            <param name="fastq_input1" ftype="fastqsanger" value="bwa-mem-fasta1.fa"/>
            <param name="analysis_type_selector" value="sr"/>
            <param name="output_format" value="CRAM"/>
            <output name="alignment_output" ftype="cram" file="minimap2-test1-fasta.cram" compare="sim_size" />
        </test>
        <test>
            <!-- test paired input -->
            <param name="reference_source_selector" value="history" />
            <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
            <param name="fastq_input_selector" value="paired"/>
            <param name="fastq_input1" ftype="fastqsanger" value="bwa-mem-fastq1.fq"/>
            <param name="fastq_input2" ftype="fastqsanger" value="bwa-mem-fastq2.fq"/>
            <param name="analysis_type_selector" value="sr"/>
            <output name="alignment_output" ftype="bam" file="minimap2-test1.bam" lines_diff="2" />
        </test>
        <test>
            <!-- test paired input with one pair compressed -->
            <param name="reference_source_selector" value="history" />
            <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
            <param name="fastq_input_selector" value="paired"/>
            <param name="fastq_input1" ftype="fastqsanger.gz" value="bwa-mem-fastq1.fq.gz"/>
            <param name="fastq_input2" ftype="fastqsanger" value="bwa-mem-fastq2.fq"/>
            <param name="analysis_type_selector" value="sr"/>
            <output name="alignment_output" ftype="bam" file="minimap2-test1.bam" lines_diff="2" />
        </test>
        <test>
            <!-- test collection input -->
            <param name="reference_source_selector" value="history" />
            <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
            <param name="fastq_input_selector" value="paired_collection"/>
            <param name="fastq_input1">
                <collection type="paired">
                    <element name="forward" value="bwa-mem-fastq1.fq" />
                    <element name="reverse" value="bwa-mem-fastq2.fq" />
                </collection>
            </param>
            <param name="analysis_type_selector" value="sr"/>
            <output name="alignment_output" ftype="bam" file="minimap2-test2.bam" lines_diff="2" />
        </test>
        <test>
            <!-- test data table reference -->
            <param name="reference_source_selector" value="cached" />
            <param name="ref_file" value="bwa-mem-mt-genome"/>
            <param name="fastq_input_selector" value="single"/>
            <param name="fastq_input1" ftype="fastqsanger" value="bwa-mem-fasta1.fa"/>
            <param name="analysis_type_selector" value="sr"/>
            <output name="alignment_output" ftype="bam" file="minimap2-test1-fasta.bam" lines_diff="2" />
        </test>
    </tests>
    <help>

Users’ Guide

-  Minimap2 may produce suboptimal alignments through long
   low-complexity regions where seed positions may be suboptimal. This
   should not be a big concern because even the optimal alignment may be
   wrong in such regions.
    </help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btp324</citation>
        <citation type="doi">10.1093/bioinformatics/btp698</citation>
        <citation type="bibtex">@misc{1303.3997,