annotate macros.xml @ 2:f923c54a17ee draft default tip

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/freec commit 30718e775cd7cd2a7746608a0c99e86521cf8d7b"

<macros>
    <token name="@VERSION_SUFFIX@">2</token>
    <token name="@TOOL_VERSION@">11.6</token>
    <xml name="requirements">
        <requirements>
            <requirement type="package" version="5.0.1">gawk</requirement>
            <requirement type="package" version="@TOOL_VERSION@">control-freec</requirement>
        </requirements>
    </xml>
    <xml name="reference_interface">
        <conditional name="reference_source">
            <param name="ref_selector" type="select" label="Choose the source for the reference genome">
                <option value="cached">Locally cached</option>
                <option value="history">History</option>
            </param>
            <when value="cached">
                <param argument="--ref" type="select" label="Reference genome">
                    <options from_data_table="fasta_indexes">
                        <!-- <filter type="data_meta" column="dbkey" key="dbkey" ref="input_sample_file" /> -->
                        <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file" />
                    </options>
                </param>
            </when>
            <when value="history">
                <param argument="--ref" type="data" format="fasta" label="Reference" help="Reference sequence" />
            </when>
        </conditional>
    </xml>
    <xml name="xrefs">
        <xrefs>
            <xref type="bio.tools">freec</xref>
        </xrefs>
    </xml>
    <xml name="WGS">
        <param name="degree" type="select" label="Degree of polynomial" help="">
            <option value="34" selected="True">GC-content based normalization, WGS (3&amp;4)</option>
            <option value="1">control-read-count-based normalization, WES (1)</option>
        </param>
        <param name="forceGCcontentNormalization" type="select" label="Read Count (RC) correction for GC-content bias and low mappability" help="Set to 1 or 2 to correct the Read Count (RC) for GC-content bias and low mappability even when you have a control sample. - Default (WGS): 0 - Default (WES): 1">
            <option value="0" selected="True">simply model "sample RC ~ Control RC" (0)</option>
            <option value="1">normalize the sample and the control RC using GC-content and then calculate the ratio "Sample RC/contol RC" (1)</option>
            <option value="2">model "sample RC ~ Control RC" bias, and then normalize for GC-content (2)</option>
        </param>
        <param name="minCNAlength" type="select" label="Minimal number of consecutive windows to call a CNA" help="">
            <option value="1" selected="True">WGS (1)</option>
            <option value="3">WES (3)</option>
        </param>
        <param name="minimalSubclonePresence" type="integer" label="Detects subclones present in x% of cell population" value="20" help="Default: 100 (meaning &quot;do not look for subclones&quot;) Suggested: 20 for WGS and 30 for WES." />
        <param name="readCountThreshold" type="integer" label="Threshold on the minimal number of reads per window" value="10" help="Threshold on the minimal number of reads per window in the control sample. Useful for exome-seq or targeted sequencing data. Default: 10 recommended value >=50 for for exome data." />
        <section name="window_section" title="Select window size" expanded="true">
            <param name="window" type="integer" value="50000" label="Explicit window size" help="Higher priority than coefficientOfVariation. Ex: for whole genome sequencing: &quot;50000&quot;; for whole exome sequencing: &quot;0&quot;" />
            <param name="step" type="integer" value="10000" label="Step" help="Used only when &quot;window&quot; is specified. Do not use for exome sequencing (instead set &quot;0&quot;). Ex: 10000" />
        </section>
        <param name="printNA" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE" label="Print NA to avoid &quot;-1&quot;" help="Set &quot;No&quot; to avoid printing &quot;-1&quot; to the _ratio.txt files. Useful for exome-seq or targeted sequencing data." />
        <param name="noisyData" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="Noisy Data" help="Set &quot;Yes&quot; for target resequencing data (e.g., exome-seq) to avoid false positive predictions due to non-uniform capture" />
    </xml>
    <xml name="WES">
        <param name="degree" type="select" label="Degree of polynomial" help="">
            <option value="34">GC-content based normalization, WGS (3&amp;4)</option>
            <option value="1" selected="True">control-read-count-based normalization, WES (1)</option>
        </param>
        <param name="forceGCcontentNormalization" type="select" label="Read Count (RC) correction for GC-content bias and low mappability" help="Set to 1 or 2 to correct the Read Count (RC) for GC-content bias and low mappability even when you have a control sample. - Default (WGS): 0 - Default (WES): 1">
            <option value="0">simply model "sample RC ~ Control RC" (0)</option>
            <option value="1" selected="True">normalize the sample and the control RC using GC-content and then calculate the ratio "Sample RC/contol RC" (1)</option>
            <option value="2">model "sample RC ~ Control RC" bias, and then normalize for GC-content (2)</option>
        </param>
        <param name="minCNAlength" type="select" label="Minimal number of consecutive windows to call a CNA" help="">
            <option value="1">WGS (1)</option>
            <option value="3" selected="True">WES (3)</option>
        </param>
        <param name="minimalSubclonePresence" type="integer" label="Detects subclones present in x% of cell population" value="30" help="Default: 100 (meaning &quot;do not look for subclones&quot;) Suggested: 20 for WGS and 30 for WES." />
        <param name="readCountThreshold" type="integer" label="Threshold on the minimal number of reads per window" value="50" help="Threshold on the minimal number of reads per window in the control sample. Useful for exome-seq or targeted sequencing data. Default: 10 recommended value >=50 for for exome data." />
        <section name="window_section" title="Select window size" expanded="false">
             <param name="window" type="integer" value="0" label="Explicit window size" help="Higher priority than coefficientOfVariation. Ex: for whole genome sequencing: &quot;50000&quot;; for whole exome sequencing: &quot;0&quot;" />
             <param name="step" type="integer" value="0" label="Step" help="Used only when &quot;window&quot; is specified. Do not use for exome sequencing (instead set &quot;0&quot;). Ex: 10000" />
        </section>
        <param name="printNA" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="Print NA to avoid &quot;-1&quot;" help="Set &quot;No&quot; to avoid printing &quot;-1&quot; to the _ratio.txt files. Useful for exome-seq or targeted sequencing data." />
        <param name="noisyData" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE" label="Noisy Data" help="Set &quot;Yes&quot; for target resequencing data (e.g., exome-seq) to avoid false positive predictions due to non-uniform capture" />
    </xml>
    <xml name="other">
        <param name="degree" type="select" label="Degree of polynomial" help="">
            <option value="34" selected="True">GC-content based normalization, WGS (3&amp;4)</option>
            <option value="1">control-read-count-based normalization, WES (1)</option>
        </param>
        <param name="forceGCcontentNormalization" type="select" label="Read Count (RC) correction for GC-content bias and low mappability" help="Set to 1 or 2 to correct the Read Count (RC) for GC-content bias and low mappability even when you have a control sample. - Default (WGS): 0 - Default (WES): 1">
            <option value="0" selected="True">simply model "sample RC ~ Control RC" (0)</option>
            <option value="1">normalize the sample and the control RC using GC-content and then calculate the ratio "Sample RC/contol RC" (1)</option>
            <option value="2">model "sample RC ~ Control RC" bias, and then normalize for GC-content (2)</option>
        </param>
        <param name="minCNAlength" type="select" label="Minimal number of consecutive windows to call a CNA" help="">
            <option value="1" selected="True">WGS (1)</option>
            <option value="3">WES (3)</option>
        </param>
        <param name="minimalSubclonePresence" type="integer" label="Detects subclones present in x% of cell population" value="100" help="Default: 100 (meaning &quot;do not look for subclones&quot;) Suggested: 20 for WGS and 30 for WES." />
        <param name="readCountThreshold" type="integer" label="Threshold on the minimal number of reads per window" value="10" help="Threshold on the minimal number of reads per window in the control sample. Useful for exome-seq or targeted sequencing data. Default: 10 recommended value >=50 for for exome data." />
        <section name="window_section" title="Select window size" expanded="true">
            <param name="window" type="integer" value="50000" label="Explicit window size" help="Higher priority than coefficientOfVariation. Ex: for whole genome sequencing: &quot;50000&quot;; for whole exome sequencing: &quot;0&quot;" />
            <param name="step" type="integer" value="10000" label="Step" help="Used only when &quot;window&quot; is specified. Do not use for exome sequencing (instead set &quot;0&quot;). Ex: 10000" />
        </section>
        <param name="printNA" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE" label="Print NA to avoid &quot;-1&quot;" help="Set &quot;No&quot; to avoid printing &quot;-1&quot; to the _ratio.txt files. Useful for exome-seq or targeted sequencing data." />
        <param name="noisyData" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="Noisy Data" help="Set &quot;Yes&quot; for target resequencing data (e.g., exome-seq) to avoid false positive predictions due to non-uniform capture" />
    </xml>
    <xml name="shared">
        <!-- general parameters -->
            <param name="breakPointThreshold" type="float" label="Segmentation of normalized profiles (break point)" value="0.8" help="Positive value of threshold for segmentation of normalized profiles. Use something like 0.6 to get more segments (and thus more predicted CNVs)." />
            <param name="breakPointType" type="select" label="Desired behavior in the ambiguous regions">
                <option value="0" selected="true">the "unknown" region is attached to the "known" region on the right (0)</option>
                <option value="1">make a separate fragment of this "unknown" region and then attaches it to the left or to the right region choosing the longer one (1)</option>
                <option value="2">make a separate fragment of this "unknown" region and then attaches it to the left or to the right region but the "ploidy" copy number has a priority (2)</option>
                <option value="3">make a separate fragment of this "unknown" region and then attaches it to the left or to the right region choosing the longer one but this "known" region should make at least half-size of the "unknown" region (3)</option>
                <option value="4">make a separate fragment of this "unknown" region and do not assign any copy number to this region at all (4)</option>
            </param>
            <param name="coefficientOfVariation" type="float" label="Coefficient of variation to evaluate necessary window size" value="0.05" />
            <param name="contaminationAdjustment" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="Adjust sample contamination?" help="a priori known value of tumor sample contamination by normal cells. Set &quot;Yes&quot; to correct for contamination by normal cells. If &quot;contamination&quot; is not provided, it will automatically evaluate the level of contamination." />
            <param name="contamination" type="float" label="Sample contamination by normal cells" value="0" help="Ex: contamination=0.25" />
            <!-- GCcontentProfile -->
            <!-- gemMappabilityFile -->
            <param name="intercept" type="select" label="Intercept of polynomial" help="">
                <option value="0">with a control dataset (0)</option>
                <option value="1" selected="True">with GC-content (1)</option>
            </param>
            <param name="minMappabilityPerWindow" type="float" label="Minimal mappability per window" value="0.85" min="0" max="1" help="Only windows with fraction of mappable positions higher than or equal to this threshold will be considered (if &quot;gemMappabilityFile&quot; is not provided, one uses the percentage of non-N letters per window)" />
            <param name="minExpectedGC" type="float" label="Minimal expected value of the GC-content" value="0.35" min="0" max="1" help="Minimal expected value of the GC-content for the prior evaluation of &quot;Read Count ~ GC-content&quot; dependency. Change only if you run Control-FREEC on a bacterial genome." />
            <param name="maxExpectedGC" type="float" label="Maximal expected value of the GC-content" value="0.55" min="0" max="1" help="Maximal expected value of the GC-content for the prior evaluation of &quot;Read Count ~ GC-content&quot; dependency. Change only if you run Control-FREEC on a bacterial genome." />
            <param name="ploidy" type="text" value="2" label="Genome ploidy" help="In case of doubt, you can set different values and Control-FREEC will select the one that explains most observed CNAs. Ex: 2 or 2,3,4" />
            <param name="sex" type="select" label="Sample sex" help="&quot;XX&quot; will exclude chr Y from the analysis. &quot;XY&quot; will not annotate one copy of chr X and Y as a loss.">
                <option value="XY" selected="True">XY</option>
                <option value="XX">XX</option>
                <option value="no value">Do not expecify sex</option>
            </param>
            <param name="telocentromeric" type="integer" value="50000" label="Length of pre-telomeric and pre-centromeric regions" help="Control-FREEC will not output small CNAs and LOH found within these regions (they are likely to be false because of mappability/genome assembly issues). 50000 is OK for human/mouse genomes. Use smaller values for yeasts and flies. Do not set anything for exome-seq data." />
            <!-- uniqueMatch if true -> gemMappabilityFile is needed-->
        <!-- BAF parameters -->
            <!-- makePileup: path to a BED or VCF file with SNP positions -->
            <!-- fastaFile -->
            <!-- minimalCoveragePerPosition -->
            <!-- minimalQualityPerPosition -->
            <!-- shiftInQuality -->
            <!-- SNPfile -->
    </xml>
    <xml name="mateOrientation_selector">
        <param name="mateOrientation_selector" type="select" display="radio" label="Format of reads" help="If you specify orientation of your reads then only reads mapping in the corresponding orientation will be used for calculation of copy number profiles.">
            <option value="0" selected="True">single-end (0)</option>
            <option value="RF">Illumina mate-pair (RF)</option>
            <option value="FR">Illumina paired-end (FR)</option>
            <option value="FF">SOLiD mate-pair (FF)</option>
        </param>
    </xml>
    <xml name="input_control_sample">
        <param name="input_sample_file" type="data" format="bam" multiple="false" label="Sample file" help="Sample file in .BAM format." />
        <param name="input_control_file" type="data" format="bam" multiple="false" label="Control file" help="Control file in .BAM format." />
    </xml>
    <xml name="input_control_sample_wgs">
        <param name="input_sample_file" type="data" format="bam" multiple="false" label="Sample file" help="Sample file in .BAM format." />
        <param name="input_control_file" type="data" format="bam" multiple="false" optional="true" label="Control file" help="Control file in .BAM format." />
    </xml>
    <xml name="wes_input_files">
        <expand macro="input_control_sample" />
        <param name="input_capture_file" optional="true" type="data" format="bed" multiple="false" label="BED file with capture regions" help="Capture regions in .BED format." />
        <expand macro="mateOrientation_selector" />
    </xml>
    <xml name="wgs_input_files">
        <expand macro="input_control_sample_wgs" />
        <expand macro="mateOrientation_selector" />
    </xml>
    <xml name="output_section">
        <section name="output_section" title="Outputs" expanded="false">
            <param name="BedGraphOutput" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="BedGraph Output for UCSC genome browser" help="Set &quot;Yes&quot; if you want an additional output in BedGraph format for the UCSC genome browser." />
            <param name="makeGraph" type="boolean" checked="false" label="Visualize normalized copy number profile with predicted CNAs" help="Currently only human genomes are supported!" />
            <param name="circos_data" type="boolean" checked="false" label="2D data track file for Circos" help="Output: chrName startPos endPos log2Ratio" />
        </section>
    </xml>
</macros>