comparison cloudmap.xml @ 23:5db0545b9004 draft

update to v0.1.7.3

22:24154c580718

<tool id="nacreousmap" name="NacreousMap" version="0.1.7.2">
  <description>Map causative mutations by multi-variant linkage analysis.</description>
  <expand macro="requirements_rplot"/>
  <version_command>python3 -m MiModD version -q</version_command>
  <command>
    python3 -m MiModD map ${opt.mode} "${opt.source.ifile}"
    #if $str($opt.source.sample):
      -m "${opt.source.sample}"
    #end if

    <import>toolshed_macros.xml</import>
    <macro name="svd_unconditional">
      <expand macro="hidden_vaf_algo_params" />
      <expand macro="seqdict_param" />
      <expand macro="bins" />
      <param name="norm" type="boolean" label="normalize variant counts to bin-width" truevalue="" falsevalue="--no-normalize" checked="true" help="without normalization the tool will just report the number of nucleotides per bin; with normalization the results for different bin-widths will be comparable." />
      <conditional name="plotopts">
        <param name="plots" type="select" label="graphical output settings">
          <option value="">Do not generate graphs.</option>
          <option value="-p">Give me graphics.</option>
        </param>
        <when value="-p">
          <expand macro="scatter_default" />
          <param name="hylim" type="text" label="upper limit for the histogram y-axis (leave blank for automatic scaling)" />
          <param name="xlim" type="select" label="x-axis scaling">
            <option value="">preserve relative contig sizes</option>
            <option value="--fit-width">scale each contig to fit the plot width</option>
          </param>
          <expand macro="hist_colors" />
        </when>
      </conditional>
    </macro>
    <macro name="vaf_unconditional">
      <expand macro="bins" />
      <param name="norm" type="boolean" label="normalize variant counts to bin-width" truevalue="" falsevalue="--no-normalize" checked="true" />
      <conditional name="plotopts">
        <param name="plots" type="select" label="graphical output settings">
          <option value="">Do not generate graphs.</option>
          <option value="--no-scatter -p">Generate only histograms</option>
          <option value="--no-hist -p">Generate only scatter plots</option>
          <option value="-p">Give me everything (scatter plots and histograms)</option>
        </param>
        <when value="--no-scatter -p">
          <expand macro="scatter_default" />
          <param name="hylim" type="text" label="upper limit for the histogram y-axis (leave blank for automatic scaling)" />
          <param name="xlim" type="select" label="x-axis scaling">
            <option value="">preserve relative contig sizes</option>
            <option value="--fit-width">scale each contig to fit the plot width</option>
          </param>
          <expand macro="hist_colors" />
        </when>
        <when value="--no-hist -p">
          <expand macro="hist_default" />
          <param name="sylim" type="text" label="upper limit for the scatter plot y-axis (default: 1)" />
          <param name="xlim" type="select" label="x-axis scaling">
            <option value="">preserve relative contig sizes</option>
            <option value="--fit-width">scale each contig to fit the plot width</option>
          </param>
          <param name="span" type="text" label="span value to be used in calculating the Loess regression line through the scatter data (default=0.1, specify 0 to prevent calculation)" help="smaller values give a more responsive curve that often picks up local evidence for tight linkage better, but too small values lead to plotting failures (in that case just rerun the tool with a larger value)." />
          <expand macro="scatter_colors" />
        </when>
        <when value="-p">
          <expand macro="plot_all" />
        </when>

      <param name="related_parent_sample" type="hidden" value="" />
      <param name="unrelated_parent_sample" type="hidden" value="" />
      <param name="infer_missing" type="hidden" value="" />
    </macro>
    <macro name="bins">
      <repeat name="bin_sizes" title="bin sizes to analyze variants in (defaults to: 1Mb and 500Kb)" default="0" min="0" help="Values can be entered in bases (e.g., 1000000), kilobases (e.g., 500Kb) or megabases (e.g., 1Mb), but must be integral, i.e. no decimal numbers are allowed.">
        <param name="bin_size" type="text" />
      </repeat>
    </macro>
    <macro name="scatter_default">
      <param name="sylim" type="hidden" value="" />

    <macro name="hist_default">
      <param name="hylim" type="hidden" value="" />
      <param name="hcols" type="hidden" value="" />
    </macro>
    <macro name="hist_colors">
      <repeat name="hcols" title="histogram colors" default="0" min="0" help="For each bin size chosen above a histogram will be generated with its color selected from the list provided here (defaults to alternating darkgrey, red).">
        <param name="hcolor" type="color" value="darkgrey">
          <sanitizer><valid><add value="#" /></valid></sanitizer>
        </param>
      </repeat>
    </macro>
    <macro name="scatter_colors">
      <param name="pcol" type="color" value="#454545" label="color to be used for the scatter plot data points (default: gray27)">
        <sanitizer><valid><add value="#" /></valid></sanitizer>
      </param>
      <param name="lcol" type="color" value="red" label="color to be used for the regression line (default: red)">
        <sanitizer><valid><add value="#" /></valid></sanitizer>
      </param>
    </macro>
    <macro name="plot_all">
      <param name="hylim" type="text" label="upper limit for the histogram y-axis (leave blank for automatic scaling)" />
      <param name="sylim" type="text" label="upper limit for the scatter plot y-axis (default: 1)" />
      <param name="xlim" type="select" label="x-axis scaling">
        <option value="">preserve relative contig sizes</option>
        <option value="--fit-width">scale each contig to fit the plot width</option>
      </param>
      <param name="span" type="text" label="span value to be used in calculating the Loess regression line through the scatter data (default=0.1, specify 0 to prevent calculation)" help="smaller values give a more responsive curve that often picks up local evidence for tight linkage better, but too small values lead to plotting failures (in that case just rerun the tool with a larger value)." />
      <expand macro="hist_colors" />
      <expand macro="scatter_colors" />
    </macro>
    <macro name="seqdict_param">
      <conditional name="seqdict_required">
        <param name="required" type="select" label="does this input file require a CloudMap-style sequence dictionary?" help="A sequence dictionary file is required ONLY if the input file does not provide information about the sizes of the chromosomes defined in it. It is NEVER needed for MiModD-generated input files.">
          <option value="no">No</option>
          <option value="yes">Yes</option>
        </param>
        <when value="yes">
          <param name="seqdict" type="data" format="tabular" label="CloudMap-style sequence dictionary file" />
        </when>
      </conditional>
    </macro>
  </macros>
  
  <inputs>
    <conditional name="opt">
      <param name="mode" type="select" label="type of mapping analysis to perform" help="Select Simple Variant Density (SVD) Mapping to map mutations based on linked inheritance in near isogenic populations, Variant Allele Frequency (VAF) Mapping for bulk segregant analysis. Select Reprocess for rapidly replotting the result of a previous VAF analysis.">
        <option value="SVD">Simple Variant Density Mapping</option>
        <option value="VAF">Variant Allele Frequency Mapping</option>
      </param>
      <when value="SVD">
        <conditional name="source">
          <param name="inputtype" type="select" label="data source to use">
            <option value="vcf">VCF file of variants (for de-novo mapping)</option>
            <option value="rep">per-variant report file (for remapping a previous analysis)</option>
          </param>
          <when value="vcf">
            <param name="ifile" type="data" format="vcf" label="input file with variants to analyze" />
            <expand macro="svd_unconditional" />
            <param name="tabfile" type="select" label="additional per-variant output file" help="You can either choose to produce a tabular per-variant report, which is useful for fast replotting with different plot settings or a vcf-like CloudMap-compatibility file that can be used as input for the CloudMap EMS Variant Density Mapping tool as an alternative plotting tool.">
              <option value="">Do not generate per-variant output</option>
              <option value="-t">Tabular per-variant report</option>
              <option value="--cloudmap -t">CloudMap compatibility file</option>
            </param>
          </when>
          <when value="rep">
            <param name="ifile" type="data" format="tabular" label="input file with variants to analyze" />
            <param name="tabfile" type="hidden" value="" />
            <expand macro="svd_unconditional" />
          </when>
        </conditional>
      </when>
      <when value="VAF">
        <conditional name="source">
          <param name="inputtype" type="select" label="data source to use">
            <option value="vcf">VCF file of variants (for de-novo mapping)</option>
            <option value="rep">per-variant report file (for remapping a previous analysis)</option>
          </param>
          <when value="vcf">
            <param name="ifile" type="data" format="vcf" label="input file with variants to analyze" />
            <expand macro="seqdict_param" />
            <param name="sample" type="text" label="mapping sample name" help="the sample to perform mutation mapping for" />
            <param name="related_parent_sample" type="text" label="name of the related parent sample" help="the sample that provides variants present in your original mutant strain or in an ancestor (like the pre-mutagenesis strain); leave blank if not available" />
            <param name="unrelated_parent_sample" type="text" label="name of the unrelated parent sample" help="the sample that provides variants present in the unrelated mapping strain (or in an ancestor of it) used in the mapping cross; leave blank if not available" />
            <param name="infer_missing" type="boolean" checked="false" truevalue="--infer-missing" falsevalue="" label="Infer alleles for missing parent" help="if variant data for either the related or the unrelated parent strain is not available, the tool can try to infer the alleles present in that parent from the allele spectrum found in the mapping sample. Use with caution on carefully filtered variant lists only!" />
            <expand macro="vaf_unconditional" />
            <param name="tabfile" type="select" label="additional per-variant output file" help="You can either choose to produce a tabular per-variant report, which is useful for fast replotting with different plot settings or a vcf-like CloudMap-compatibility file that can be used as input for the CloudMap Hawaiian Variant Mapping tool as an alternative plotting tool.">
              <option value="">Do not generate per-variant output</option>
              <option value="-t">Tabular per-variant report</option>
              <option value="--cloudmap -t">CloudMap compatibility file</option>
            </param>
          </when>
          <when value="rep">
            <param name="ifile" type="data" format="tabular" label="input file with variants to analyze" />
            <expand macro="seqdict_param" />
            <param name="tabfile" type="hidden" value="" />
            <expand macro="hidden_vaf_algo_params" />
            <expand macro="vaf_unconditional" />
          </when>

      </when>
    </conditional>
  </inputs>

  <outputs>
    <data name="ofile" format="tabular" label="MiModD ${opt.mode} Mapping - binned variant counts for ${on_string}" />
    <data name="tfile" format="tabular" label="MiModD ${opt.mode} Mapping - per-variant report for ${on_string}">
      <filter>(opt['source']['tabfile'])</filter>
    </data>
    <data name="pfile" format="pdf" label="MiModD ${opt.mode} Mapping - linkage plots for ${on_string}">
      <filter>(opt['source']['plotopts']['plots'])</filter>
    </data>
  </outputs>

  <help>

23:5db0545b9004

<tool id="nacreousmap" name="NacreousMap" version="0.1.7.3">
  <description>Map causative mutations by multi-variant linkage analysis.</description>
  <expand macro="requirements_rplot" />  <version_command>python3 -m MiModD version -q</version_command>
  <command>
    python3 -m MiModD map ${opt.mode} "${opt.source.ifile}"
    #if $str($opt.source.sample):
      -m "${opt.source.sample}"
    #end if

    <import>toolshed_macros.xml</import>
    <macro name="svd_unconditional">
      <expand macro="hidden_vaf_algo_params" />
      <expand macro="seqdict_param" />
      <expand macro="bins" />
      <param checked="true" falsevalue="--no-normalize" help="without normalization the tool will just report the number of nucleotides per bin; with normalization the results for different bin-widths will be comparable." label="normalize variant counts to bin-width" name="norm" truevalue="" type="boolean" />
      <conditional name="plotopts">
        <param label="graphical output settings" name="plots" type="select">
          <option value="">Do not generate graphs.</option>
          <option value="-p">Give me graphics.</option>
        </param>
        <when value="-p">
          <expand macro="scatter_default" />
          <param label="upper limit for the histogram y-axis (leave blank for automatic scaling)" name="hylim" type="text" />
          <param label="x-axis scaling" name="xlim" type="select">
            <option value="">preserve relative contig sizes</option>
            <option value="--fit-width">scale each contig to fit the plot width</option>
          </param>
          <expand macro="hist_colors" />
        </when>
      </conditional>
    </macro>
    <macro name="vaf_unconditional">
      <expand macro="bins" />
      <param checked="true" falsevalue="--no-normalize" label="normalize variant counts to bin-width" name="norm" truevalue="" type="boolean" />
      <conditional name="plotopts">
        <param label="graphical output settings" name="plots" type="select">
          <option value="">Do not generate graphs.</option>
          <option value="--no-scatter -p">Generate only histograms</option>
          <option value="--no-hist -p">Generate only scatter plots</option>
          <option value="-p">Give me everything (scatter plots and histograms)</option>
        </param>
        <when value="--no-scatter -p">
          <expand macro="scatter_default" />
          <param label="upper limit for the histogram y-axis (leave blank for automatic scaling)" name="hylim" type="text" />
          <param label="x-axis scaling" name="xlim" type="select">
            <option value="">preserve relative contig sizes</option>
            <option value="--fit-width">scale each contig to fit the plot width</option>
          </param>
          <expand macro="hist_colors" />
        </when>
        <when value="--no-hist -p">
          <expand macro="hist_default" />
          <param label="upper limit for the scatter plot y-axis (default: 1)" name="sylim" type="text" />
          <param label="x-axis scaling" name="xlim" type="select">
            <option value="">preserve relative contig sizes</option>
            <option value="--fit-width">scale each contig to fit the plot width</option>
          </param>
          <param help="smaller values give a more responsive curve that often picks up local evidence for tight linkage better, but too small values lead to plotting failures (in that case just rerun the tool with a larger value)." label="span value to be used in calculating the Loess regression line through the scatter data (default=0.1, specify 0 to prevent calculation)" name="span" type="text" />
          <expand macro="scatter_colors" />
        </when>
        <when value="-p">
          <expand macro="plot_all" />
        </when>

      <param name="related_parent_sample" type="hidden" value="" />
      <param name="unrelated_parent_sample" type="hidden" value="" />
      <param name="infer_missing" type="hidden" value="" />
    </macro>
    <macro name="bins">
      <repeat default="0" help="Values can be entered in bases (e.g., 1000000), kilobases (e.g., 500Kb) or megabases (e.g., 1Mb), but must be integral, i.e. no decimal numbers are allowed." min="0" name="bin_sizes" title="bin sizes to analyze variants in (defaults to: 1Mb and 500Kb)">
        <param name="bin_size" type="text" />
      </repeat>
    </macro>
    <macro name="scatter_default">
      <param name="sylim" type="hidden" value="" />

    <macro name="hist_default">
      <param name="hylim" type="hidden" value="" />
      <param name="hcols" type="hidden" value="" />
    </macro>
    <macro name="hist_colors">
      <repeat default="0" help="For each bin size chosen above a histogram will be generated with its color selected from the list provided here (defaults to alternating darkgrey, red)." min="0" name="hcols" title="histogram colors">
        <param name="hcolor" type="color" value="darkgrey">
          <sanitizer><valid><add value="#" /></valid></sanitizer>
        </param>
      </repeat>
    </macro>
    <macro name="scatter_colors">
      <param label="color to be used for the scatter plot data points (default: gray27)" name="pcol" type="color" value="#454545">
        <sanitizer><valid><add value="#" /></valid></sanitizer>
      </param>
      <param label="color to be used for the regression line (default: red)" name="lcol" type="color" value="red">
        <sanitizer><valid><add value="#" /></valid></sanitizer>
      </param>
    </macro>
    <macro name="plot_all">
      <param label="upper limit for the histogram y-axis (leave blank for automatic scaling)" name="hylim" type="text" />
      <param label="upper limit for the scatter plot y-axis (default: 1)" name="sylim" type="text" />
      <param label="x-axis scaling" name="xlim" type="select">
        <option value="">preserve relative contig sizes</option>
        <option value="--fit-width">scale each contig to fit the plot width</option>
      </param>
      <param help="smaller values give a more responsive curve that often picks up local evidence for tight linkage better, but too small values lead to plotting failures (in that case just rerun the tool with a larger value)." label="span value to be used in calculating the Loess regression line through the scatter data (default=0.1, specify 0 to prevent calculation)" name="span" type="text" />
      <expand macro="hist_colors" />
      <expand macro="scatter_colors" />
    </macro>
    <macro name="seqdict_param">
      <conditional name="seqdict_required">
        <param help="A sequence dictionary file is required ONLY if the input file does not provide information about the sizes of the chromosomes defined in it. It is NEVER needed for MiModD-generated input files." label="does this input file require a CloudMap-style sequence dictionary?" name="required" type="select">
          <option value="no">No</option>
          <option value="yes">Yes</option>
        </param>
        <when value="yes">
          <param format="tabular" label="CloudMap-style sequence dictionary file" name="seqdict" type="data" />
        </when>
      </conditional>
    </macro>
  </macros>
  
  <inputs>
    <conditional name="opt">
      <param help="Select Simple Variant Density (SVD) Mapping to map mutations based on linked inheritance in near isogenic populations, Variant Allele Frequency (VAF) Mapping for bulk segregant analysis. Select Reprocess for rapidly replotting the result of a previous VAF analysis." label="type of mapping analysis to perform" name="mode" type="select">
        <option value="SVD">Simple Variant Density Mapping</option>
        <option value="VAF">Variant Allele Frequency Mapping</option>
      </param>
      <when value="SVD">
        <conditional name="source">
          <param label="data source to use" name="inputtype" type="select">
            <option value="vcf">VCF file of variants (for de-novo mapping)</option>
            <option value="rep">per-variant report file (for remapping a previous analysis)</option>
          </param>
          <when value="vcf">
            <param format="vcf" label="input file with variants to analyze" name="ifile" type="data" />
            <expand macro="svd_unconditional" />
            <param help="You can either choose to produce a tabular per-variant report, which is useful for fast replotting with different plot settings or a vcf-like CloudMap-compatibility file that can be used as input for the CloudMap EMS Variant Density Mapping tool as an alternative plotting tool." label="additional per-variant output file" name="tabfile" type="select">
              <option value="">Do not generate per-variant output</option>
              <option value="-t">Tabular per-variant report</option>
              <option value="--cloudmap -t">CloudMap compatibility file</option>
            </param>
          </when>
          <when value="rep">
            <param format="tabular" label="input file with variants to analyze" name="ifile" type="data" />
            <param name="tabfile" type="hidden" value="" />
            <expand macro="svd_unconditional" />
          </when>
        </conditional>
      </when>
      <when value="VAF">
        <conditional name="source">
          <param label="data source to use" name="inputtype" type="select">
            <option value="vcf">VCF file of variants (for de-novo mapping)</option>
            <option value="rep">per-variant report file (for remapping a previous analysis)</option>
          </param>
          <when value="vcf">
            <param format="vcf" label="input file with variants to analyze" name="ifile" type="data" />
            <expand macro="seqdict_param" />
            <param help="the sample to perform mutation mapping for" label="mapping sample name" name="sample" type="text" />
            <param help="the sample that provides variants present in your original mutant strain or in an ancestor (like the pre-mutagenesis strain); leave blank if not available" label="name of the related parent sample" name="related_parent_sample" type="text" />
            <param help="the sample that provides variants present in the unrelated mapping strain (or in an ancestor of it) used in the mapping cross; leave blank if not available" label="name of the unrelated parent sample" name="unrelated_parent_sample" type="text" />
            <param checked="false" falsevalue="" help="if variant data for either the related or the unrelated parent strain is not available, the tool can try to infer the alleles present in that parent from the allele spectrum found in the mapping sample. Use with caution on carefully filtered variant lists only!" label="Infer alleles for missing parent" name="infer_missing" truevalue="--infer-missing" type="boolean" />
            <expand macro="vaf_unconditional" />
            <param help="You can either choose to produce a tabular per-variant report, which is useful for fast replotting with different plot settings or a vcf-like CloudMap-compatibility file that can be used as input for the CloudMap Hawaiian Variant Mapping tool as an alternative plotting tool." label="additional per-variant output file" name="tabfile" type="select">
              <option value="">Do not generate per-variant output</option>
              <option value="-t">Tabular per-variant report</option>
              <option value="--cloudmap -t">CloudMap compatibility file</option>
            </param>
          </when>
          <when value="rep">
            <param format="tabular" label="input file with variants to analyze" name="ifile" type="data" />
            <expand macro="seqdict_param" />
            <param name="tabfile" type="hidden" value="" />
            <expand macro="hidden_vaf_algo_params" />
            <expand macro="vaf_unconditional" />
          </when>

      </when>
    </conditional>
  </inputs>

  <outputs>
    <data format="tabular" label="MiModD ${opt.mode} Mapping - binned variant counts for ${on_string}" name="ofile" />
    <data format="tabular" label="MiModD ${opt.mode} Mapping - per-variant report for ${on_string}" name="tfile">
      <filter>(opt['source']['tabfile'])</filter>
    </data>
    <data format="pdf" label="MiModD ${opt.mode} Mapping - linkage plots for ${on_string}" name="pfile">
      <filter>(opt['source']['plotopts']['plots'])</filter>
    </data>
  </outputs>

  <help>