comparison scanpy-filter-genes.xml @ 3:77fbe74247c2 draft

planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/tree/develop/tools/tertiary-analysis/scanpy commit ccd9b839849600b1aa3b6cf54f667575a5f2da9d

2:a797a810d7e9

  <expand macro="requirements"/>
  <command detect_errors="exit_code"><![CDATA[
ln -s '${input_obj_file}' input.h5 &&
PYTHONIOENCODING=utf-8 scanpy-filter-genes
#if $parameters
    #set pars = ' '.join(['--param {name} {min} {max}'.format(**$p) for $p in $parameters])
    ${pars}
#end if
#if $categories
    #set cats = ' '.join(['--category {name} {values}'.format(**$c) for $c in $categories])
    ${cats}
#end if
#if $subsets
    #set subs = ' '.join(['--subsets {name} {subset}'.format(**$s) for $s in $subsets])
    ${subs}
#end if
    @INPUT_OPTS@
    @OUTPUT_OPTS@
]]></command>

  <inputs>
    <expand macro="input_object_params"/>
    <expand macro="output_object_params"/>

    <repeat name="parameters" title="Parameters used to filter cells" min="1">
      <param name="name" type="text" value="n_cells" label="Name of parameter to filter on" help="for example n_genes or n_counts">
        <option value="n_cells">n_cells</option>
        <option value="gene:n_counts">n_counts</option>
      </param>
      <param name="min" type="float" min="0" value="0" label="Min value"/>
      <param name="max" type="float" min="0" value="1e9" label="Max value"/>
    </repeat>

    <repeat name="categories" title="Categories used to filter genes" min="0">
      <param name="name" type="text" value="" label="Name of the categorical variable to filter on"/>
      <param name="values" type="text" value="" label="Comma-separated values"/>
    </repeat>

    <repeat name="subsets" title="Subsets used to filter genes" min="0">
      <param name="name" type="text" value="" label="Name of the categorical variable to filter on"/>
      <param name="subset" type="data" format="tabular" label="List of values"/>
    </repeat>
    <expand macro="export_mtx_params"/>
  </inputs>

  <outputs>

        <param name="name" value="n_cells"/>
        <param name="min" value="3"/>
        <param name="max" value="1e9"/>
      </repeat>
      <repeat name="parameters">
        <param name="name" value="gene:n_counts"/>
        <param name="min" value="0"/>
        <param name="max" value="1e9"/>
      </repeat>
      <output name="output_h5" file="filter_genes.h5" ftype="h5" compare="sim_size"/>
    </test>
  </tests>

  <help><![CDATA[
===================================================================
Filter genes based on number of cells or counts (`pp.filter_genes`)
===================================================================

Keep genes that have at least `min_counts` counts or are expressed in at
least `min_cells` cells or have at most `max_counts` counts or are expressed
in at most `max_cells` cells.

Only provide one of the optional parameters `min_counts`, `min_cells`,
`max_counts`, `max_cells` per call.


@HELP@

@VERSION_HISTORY@

3:77fbe74247c2

  <expand macro="requirements"/>
  <command detect_errors="exit_code"><![CDATA[
ln -s '${input_obj_file}' input.h5 &&
PYTHONIOENCODING=utf-8 scanpy-filter-genes
#if $parameters
    #set pars = ' '.join(['--param g:{name} {min} {max}'.format(**$p) for $p in $parameters])
    ${pars}
#end if
#if $categories
    #set cats = ' '.join(['--category g:{name} {values}'.format(**$c) for $c in $categories])
    ${cats}
#end if
#if $subsets
    #set subs = ' '.join(['--subset g:{name} {subset}'.format(**$s) for $s in $subsets])
    ${subs}
#end if
    @INPUT_OPTS@
    @OUTPUT_OPTS@
]]></command>

  <inputs>
    <expand macro="input_object_params"/>
    <expand macro="output_object_params"/>

    <repeat name="parameters" title="Parameters used to filter genes" min="1">
      <param name="name" type="text" value="n_cells" label="Name of parameter to filter on" help="for example n_genes or n_counts">
        <option value="n_cells">n_cells</option>
        <option value="n_counts">n_counts</option>
      </param>
      <param name="min" type="float" min="0" value="0" label="Min value"/>
      <param name="max" type="float" min="0" value="1e9" label="Max value"/>
    </repeat>

    <repeat name="categories" title="Categories used to filter genes" min="0">
      <param name="name" type="text" value="" label="Name of the categorical variable to filter on"/>
      <param name="values" type="text" value="" label="Comma-separated values to keep"/>
    </repeat>

    <repeat name="subsets" title="Subsets used to filter genes" min="0">
      <param name="name" type="text" value="" label="Name of the categorical variable to filter on"/>
      <param name="subset" type="data" format="tabular" label="List of values to keep" help="A one-column headerless text file is required"/>
    </repeat>
    <expand macro="export_mtx_params"/>
  </inputs>

  <outputs>

        <param name="name" value="n_cells"/>
        <param name="min" value="3"/>
        <param name="max" value="1e9"/>
      </repeat>
      <repeat name="parameters">
        <param name="name" value="n_counts"/>
        <param name="min" value="0"/>
        <param name="max" value="1e9"/>
      </repeat>
      <output name="output_h5" file="filter_genes.h5" ftype="h5" compare="sim_size"/>
    </test>
  </tests>

  <help><![CDATA[
=====================================================================
Filter genes based on arbitrary attributes (`scanpy.pp.filter_genes`)
=====================================================================

Keep genes that have at least `min_counts` counts or are expressed in at
least `min_cells` cells or have at most `max_counts` counts or are expressed
in at most `max_cells` cells. Other gene attributes can be used for filtering
too if available.


@HELP@

@VERSION_HISTORY@