comparison ivar_trim.xml @ 15:a2b94388d00d draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ivar/ commit 3839802e0a790cb519cffdc2d8a6b92d73e4c9ef

14:bcaa0d571ce2

        #if $amplicons.filter_by == 'yes' or $amplicons.filter_by == 'yes_compute'
            -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>

        </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" max="255" value="20" label="Minimum quality threshold for sliding window to pass"/>
        <param name="window_width" argument="-s" type="integer" min="0" max="255" 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" ftype="bam">
                <assert_contents>
                    <has_size value="4023965" delta="1000"/>
                </assert_contents>
            </output>
            <assert_stdout>
                <has_text text="Found 68 primers in BED file"/>
                <has_text text="Using Region: PRV"/>
                <has_text text="Found 40964 mapped reads"/>
                <has_text text="reads were quality trimmed below the minimum length of 30 bp and were not written to file"/>
                <has_text text="reads that started outside of primer regions were not written to file"/>
            </assert_stdout>
        </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>
        <test>
            <conditional name="primer">
                <param name="source" value="cached" />

            </conditional>
            <conditional name="amplicons">
                <param name="filter_by" value="yes_compute" />
            </conditional>
            <param name="input_bam" value="sars-cov-2/sars_cov2_untrimmed.bam" ftype="bam" />
            <assert_command>
                <has_text text="write_amplicon_info_file" />
            </assert_command>
            <output name="output_bam" file="sars-cov-2/sars_cov2_trimmed.bam" compare="sim_size" delta="100000"/>
        </test>

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>

15:a2b94388d00d

        #if $amplicons.filter_by == 'yes' or $amplicons.filter_by == 'yes_compute'
            -f amplicon_info.tsv
        #end if
        -x $primer_pos_wiggle
        $inc_primers
        #if $trimmed_length.filter == 'off':
            -m 0
        #elif $trimmed_length.filter == 'auto':
            -m -1
        #else:
            -m $trimmed_length.min_len
        #end if
        -q $min_qual
        -s $window_width
        ## since v1.4 ivar trim *almost* supports piping its output, but
        ## unfortunately still writes *some* regular messages to stdout,
        ## so we need to stick writing to an intermediate file for now and
        ## want to unify the output stream
        -p trimmed 1>&2 &&
        samtools sort -@ \${GALAXY_SLOTS:-1} -T "\${TMPDIR:-.}" -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>

        </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_qual" argument="-q" type="integer" min="0" max="255" value="20" label="Minimum quality threshold for sliding window to pass"/>
        <param name="window_width" argument="-s" type="integer" min="0" max="255" value="4" label="Width of sliding window"/>
        <conditional name="trimmed_length">
            <param name="filter" type="select" label="Require a minimum length for reads to retain them after any trimming?" help="The default automatic setting will determine the threshold as 50% of the mean length of the first 1000 raw input reads, which may or may not be adequate for your data. You can always make the outcome of filtering more predictable by specifying the threshold explicitly. You can also opt to retain reads independently of their trimmed length, but typically this only makes sense if you are performing additional read filtering with additional tools in your analysis pipeline.">
                <option value="off">No, keep reads independently of their trimmed length (-m 0)</option>
                <option value="auto" selected="true">Yes, and determine required length threshold automatically from input (-m -1)</option>
                <option value="custom">Yes, and provide a custom threshold</option>
            </param>
            <when value="off" />
            <when value="auto" />
            <when value="custom">
                <param name="min_len" argument="-m" type="integer" min="1" value="30" label="Minimum trimmed length threshold" help="Reads with a trimmed length shorter than this value will be discarded."/>
            </when>
        </conditional>
    </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" />
            <conditional name="trimmed_length">
                <param name="filter" value="custom" />
                <param name="min_len" value="30" />
            </conditional>
            <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" />
            <conditional name="trimmed_length">
                <param name="filter" value="custom" />
                <param name="min_len" value="30" />
            </conditional>
            <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" />
            <conditional name="trimmed_length">
                <param name="filter" value="custom" />
                <param name="min_len" value="30" />
            </conditional>
            <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" />
            <conditional name="trimmed_length">
                <param name="filter" value="auto" />
            </conditional>
            <output name="output_bam" ftype="bam">
                <assert_contents>
                    <has_size value="3373924" delta="1000"/>
                </assert_contents>
            </output>
            <assert_stderr>
                <has_text text="Found 68 primers in BED file"/>
                <has_text text="reads were quality trimmed below the minimum length of 125 bp and were not written to file"/>
                <has_text text="reads that started outside of primer regions were not written to file"/>
            </assert_stderr>
        </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" />
            <conditional name="trimmed_length">
                <param name="filter" value="custom" />
                <param name="min_len" value="30" />
            </conditional>
            <output name="output_bam" file="sars-cov-2/sars_cov2_trimmed.bam" compare="sim_size" delta="100000"/>
        </test>
        <test>
            <conditional name="primer">
                <param name="source" value="cached" />

            </conditional>
            <conditional name="amplicons">
                <param name="filter_by" value="yes_compute" />
            </conditional>
            <param name="input_bam" value="sars-cov-2/sars_cov2_untrimmed.bam" ftype="bam" />
            <conditional name="trimmed_length">
                <param name="filter" value="custom" />
                <param name="min_len" value="30" />
            </conditional>
            <assert_command>
                <has_text text="write_amplicon_info_file" />
            </assert_command>
            <output name="output_bam" file="sars-cov-2/sars_cov2_trimmed.bam" compare="sim_size" delta="100000"/>
        </test>

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 and final length filtering**

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.

Finally, the trimmed length threshold gets applied if specified, and fully
trimmed surviving reads are written to the BAM output.

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