view ivar_trim.xml @ 5:cf65217ad61c draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ivar/ commit a5ff06c631a2a5a0d5d44edd6cb58a599d50918b"

<tool id="ivar_trim" name="ivar trim" version="@VERSION@+galaxy0">
    <description>Trim reads in aligned BAM</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="3.8.1">python</requirement>
    </expand>
    <expand macro="version_command" />
    <command detect_errors="exit_code"><![CDATA[
        #if $primer.source == 'history'
            cp '$primer.input_bed' bed.bed &&
        #else
            cp '$primer.cached_bed.fields.path' bed.bed &&
        #end if
        python '$__tool_directory__/sanitize_bed.py' bed.bed &&
        #if $amplicons.filter_by == 'yes'
            python '$__tool_directory__/prepare_amplicon_info.py' bed.bed '$amplicons.amplicon_info' amplicon_info.tsv &&
        #end if
        ln -s '$input_bam' sorted.bam &&
        ln -s '${input_bam.metadata.bam_index}' sorted.bam.bai &&

        ivar trim
        -i sorted.bam
        -b bed.bed
        #if $amplicons.filter_by == 'yes'
            -f amplicon_info.tsv
        #end if
        -x $primer_pos_wiggle
        $inc_primers
        -m $min_len
        -q $min_qual
        -s $window_width
        -p trimmed &&
        samtools sort -@ \${GALAXY_SLOTS:-1} -o trimmed.sorted.bam trimmed.bam
    ]]>    </command>
    <inputs>
        <param name="input_bam" argument="-i" type="data" format="bam" label="Bam file" help="Aligned reads, to trim primers and quality"/>
        <conditional name="primer">
            <param label="Source of primer information" name="source" type="select">
                <option value="history" selected="true">History</option>
                <option value="cached">Built-in</option>
            </param>
            <when value="history">
                <param name="input_bed" argument="-b" type="data" format="bed" label="BED file with primer sequences and positions"/>
            </when>
            <when value="cached">
                <param name="cached_bed" type="select" label="Primer scheme name" help="Select primer scheme bed file from a list">
                    <options from_data_table="primer_scheme_bedfiles">
                        <filter type="sort_by" column="1" />
                    <validator type="no_options" message="No primer schemes are available" />
                    </options>
                </param>
            </when>
        </conditional>
        <conditional name="amplicons">
            <param name="filter_by" type="select"
            label="Filter reads based on amplicon info"
            help="When you select Yes you will need to provide an additional amplicon info dataset. Reads that are not fully contained in any amplicon will be dropped before primer trimming. This option is currently marked as [Experimental] in ivar, but nevertheless recommended here.">
                <option value="">No, allow reads to extend beyond amplicon boundaries</option>
                <option value="yes">Yes, drop reads that extend beyond amplicon boundaries</option>
            </param>
            <when value="yes">
                <param name="amplicon_info" argument="-f" type="data" format="tabular" />
            </when>
            <when value="" />
        </conditional>
        <param name="primer_pos_wiggle" argument="-x" type="integer" min="0" value="0"
        label="Wiggling room for read ends relative to primer binding sites"
        help="Reads that occur at the specified offset positions relative to primer positions (as annotated in the primer information dataset) will also be trimmed (default: 0)" />
        <param name="inc_primers" argument="-e" type="boolean" truevalue="-e" falsevalue="" checked="false" label="Include reads not ending in any primer binding sites?"/>
        <param name="min_len" argument="-m" type="integer" min="0" value="30" label="Minimum length of read to retain after trimming"/>
        <param name="min_qual" argument="-q" type="integer" min="0" value="20" label="Minimum quality threshold for sliding window to pass"/>
        <param name="window_width" argument="-s" type="integer" min="0" value="4" label="Width of sliding window"/>
    </inputs>
    <outputs>
        <data name="output_bam" format="bam" label="${tool.name} on ${on_string} Trimmed bam" from_work_dir="trimmed.sorted.bam"/>
    </outputs>
    <tests>
        <!-- #1: SARS-Cov data-->
        <test>
            <param name="input_bam" value="covid19/PC00101P_sub.sorted.bam" />
            <param name="input_bed" value="covid19/ARTIC-V1.bed" />
            <param name="inc_primers" value="true" />
            <output name="output_bam" file="covid19/PC00101P_sub.sorted.bam" compare="sim_size" delta="300000"/>
        </test>
        <test>
            <!-- Test with primer bed file that needs to be sanitized -->
            <param name="input_bam" value="covid19/PC00101P_sub.sorted.bam" />
            <param name="input_bed" value="covid19/ARTIC-V1-bad.bed" />
            <param name="inc_primers" value="true" />
            <output name="output_bam" file="covid19/PC00101P_sub.sorted.bam" compare="sim_size" delta="300000"/>
        </test>
        <!-- #1: Zika data-->
        <test>
            <conditional name="primer">
                <param name="source" value="history" />
                <param name="input_bed" value="zika/db/zika_primers.bed" />
            </conditional>
            <param name="input_bam" value="zika/Z52_a.sorted.bam" />
            <output name="output_bam" file="zika/Z52_a.trimmed.sorted.bam" compare="sim_size" delta="100000"/>
        </test>
        <test>
            <conditional name="primer">
                <param name="source" value="history" />
                <param name="input_bed" value="zika/db/zika_primers.bed" />
            </conditional>
            <param name="input_bam" value="zika/Z52_b.sorted.bam" />
            <output name="output_bam" file="zika/Z52_b.trimmed.sorted.bam" compare="sim_size" delta="100000"/>
        </test>
        <test>
            <conditional name="primer">
                <param name="source" value="cached" />
                <param name="cached_bed" value="SARS-CoV-2-ARTICv1" />
            </conditional>
            <param name="input_bam" value="sars-cov-2/sars_cov2_untrimmed.bam" ftype="bam" />
            <output name="output_bam" file="sars-cov-2/sars_cov2_trimmed.bam" compare="sim_size" delta="100000"/>
        </test>
    </tests>
    <help><![CDATA[
iVar uses primer positions supplied in a BED file to soft clip primer
sequences from an aligned and sorted BAM file. Following this, the reads are
trimmed further based on a quality threshold.

**Primer and Amplicon info**

The tool requires information about primers and their binding sites in 6-column
BED format. The information from this file is used to decide whether any mapped
read in the BAM input ends with a primer sequence and should, thus, be
soft-clipped.

Optionally, the tool can also discard reads that do not fully map to within any
amplicon. Such reads are likely to be wet-lab or mapping artefacts and removing
them can increase variant calling precision. To calculate the extent of
expected amplicons the tool requires an additional amplicon info dataset that
lists the names of primers that together form any given amplicon. Primer names
(exactly matching those in the primer info dataset) need to be TAB-separated
with one line per amplicon.
If the primer scheme has more than two primers contributing to a given amplicon
(in schemes using alternate primers), you can (in this Galaxy tool only)
specify all of them on one line and the tool will calculate the maximum extent
of the amplicon.

**Quality trimming details**

To do the quality trimming, iVar uses a sliding window approach. The window
slides from the 5' end to the 3' end and if at any point the average base
quality in the window falls below the threshold, the remaining read is soft
clipped. If after trimming, the length of the read is greater than the minimum
length specified, the read is written to the new trimmed BAM file.

Documentation can be found at `<https://andersen-lab.github.io/ivar/html/manualpage.html>`_.
    ]]></help>
    <expand macro="citations" />
</tool>