comparison scanpy-filter-cells.xml @ 1:dcfb23758646 draft

"planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/tree/develop/tools/tertiary-analysis/scanpy commit 4846776f55931e176f7e77af7c185ec6fec7d142"

0:9f0ca1641ab2

<?xml version="1.0" encoding="utf-8"?>
<tool id="scanpy_filter_cells" name="Scanpy FilterCells" version="@TOOL_VERSION@+galaxy0">
  <description>based on counts and numbers of genes expressed</description>
  <macros>
    <import>scanpy_macros.xml</import>
  </macros>
  <expand macro="requirements"/>
  <command detect_errors="exit_code"><![CDATA[
ln -s '${input_obj_file}' input.h5 &&
PYTHONIOENCODING=utf-8 scanpy-filter-cells.py
    -i input.h5
    -f '${input_format}'
    -o output.h5
    -F '${output_format}'
    #if $parameters
        #set pars = ','.join([str($p['name']) for $p in $parameters])
        -p '${pars}'
        #set mins = ','.join([str($p['min']) for $p in $parameters])
        -l '${mins}'
        #set maxs = ','.join([str($p['max']) for $p in $parameters])
        -j '${maxs}'
    #end if
    #if $subset
        -s '${subset}'
    #end if
    ]]></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_genes" label="Name of parameter to filter on" help="for example n_genes or n_counts">
        <option value="n_genes">n_genes</option>
        <option value="n_counts">n_counts</option>
      </param>
      <param name="min" type="float" value="0" min="0" label="Min value"/>
      <param name="max" type="float" value="1e9" label="Max value"/>
    </repeat>
    <param name="subset" argument="--subset-list" type="data" format="tsv" optional="true" label="List of barcodes"/>
  </inputs>

  <outputs>
    <data name="output_h5" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: Filtered cells"/>
  </outputs>

  <tests>
    <test>
      <param name="input_obj_file" value="read_10x.h5"/>

        <param name="name" value="n_genes"/>
        <param name="min" value="200"/>
        <param name="max" value="2500"/>
      </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_cells.h5" ftype="h5" compare="sim_size"/>
    </test>
  </tests>

  <help><![CDATA[
========================================================================================
Filter cells outliers based on counts and numbers of genes expressed (`pp.filter_cells`)
========================================================================================

For instance, only keep cells with at least `min_counts` counts or
`min_genes` genes expressed. This is to filter measurement outliers, i.e.,
"unreliable" observations.

@HELP@

@VERSION_HISTORY@
]]></help>

1:dcfb23758646

<?xml version="1.0" encoding="utf-8"?>
<tool id="scanpy_filter_cells" name="Scanpy FilterCells" version="@TOOL_VERSION@+galaxy0">
  <description>based on counts and numbers of genes expressed</description>
  <macros>
    <import>scanpy_macros2.xml</import>
  </macros>
  <expand macro="requirements"/>
  <command detect_errors="exit_code"><![CDATA[
ln -s '${input_obj_file}' input.h5 &&
PYTHONIOENCODING=utf-8 scanpy-filter-cells
#if $gene_name
    --gene-name '${gene_name}'
#end if
#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 $c in $subsets])
    ${subs}
#end if
    @INPUT_OPTS@
    @OUTPUT_OPTS@
    ]]></command>

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

    <param name="gene_name" type="text" value="index" label="Name of the column in `anndata.var` that contains gene name"
           help="This is used for flagging mitochondria genes (starting with 'MT-')"/>

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

    <repeat name="categories" title="Categories used to filter cells" 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 cells" 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>
    <data name="output_h5" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: Filtered cells"/>
    <expand macro="export_mtx_outputs"/>
  </outputs>

  <tests>
    <test>
      <param name="input_obj_file" value="read_10x.h5"/>

        <param name="name" value="n_genes"/>
        <param name="min" value="200"/>
        <param name="max" value="2500"/>
      </repeat>
      <repeat name="parameters">
        <param name="name" value="cell:n_counts"/>
        <param name="min" value="0"/>
        <param name="max" value="1e9"/>
      </repeat>
      <output name="output_h5" file="output.h5" ftype="h5" compare="sim_size"/>
    </test>
  </tests>

  <help><![CDATA[
===================================================================
Filter cells based on various QC metrics (`scanpy.pp.filter_cells`)
===================================================================

For instance, only keep cells with at least `min_counts` and at most
`max_counts` UMI and/or at least `min_genes` expressed genes and/or at most
`max_mito_percent` mitocondria expression. This is to filter measurement
outliers, i.e., "unreliable" observations.

@HELP@

@VERSION_HISTORY@
]]></help>