comparison scanpy-find-markers.xml @ 15:cc776860fae1 draft

"planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/tree/develop/tools/tertiary-analysis/scanpy commit fda35ff3ea8609c4bb5e1fd9e58ba70cd5b5a997-dirty"

14:fb9bd74c32b0

<?xml version="1.0" encoding="utf-8"?>
<tool id="scanpy_find_markers" name="Scanpy FindMarkers" version="@TOOL_VERSION@+galaxy0" profile="@PROFILE@">
  <description>to find differentially expressed genes between groups</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-find-markers
#if $output_markers
    --save output.csv
#end if
    --n-genes '${n_genes}'
    --groupby '${groupby}'
#if $settings.default == "false"
    --method '${settings.method}'
    ${settings.use_raw}
    ${settings.rankby_abs}
    #if $settings.groups

]]></command>

  <inputs>
    <expand macro="input_object_params"/>
    <expand macro="output_object_params"/>
    <param name="output_markers" type="boolean" checked="true" label="Output markers table in csv format"/>
    <param name="n_genes" argument="--n-genes" type="integer" value="50" label="Number of top genes to show per group/cluster"/>
    <param name="groupby" argument="--groupby" type="text" value="louvain" label="The sample grouping/clustering to use."/>
    <conditional name="settings">
      <param name="default" type="boolean" checked="true" label="Use programme defaults"/>
      <when value="true"/>
      <when value="false">
        <param name="method" argument="--method" type="select" label="Method for testing differentially expressed genes">
          <option value="t-test_overestim_var" selected="true">t-test with over-estimated variance</option>
          <option value="t-test">t-test</option>
          <option value="wilcoxon">wilcoxon test, currently broken don't use</option>
          <option value="logreg">logistic regression</option>

    </conditional>
  </inputs>

  <outputs>
    <expand macro="output_data_obj" description="Marker genes"/>
    <data name="output_csv" format="csv" from_work_dir="output.csv" label="${tool.name} on ${on_string}: Marker table">
      <filter>output_markers</filter>
    </data>
  </outputs>

  <tests>
    <test>
      <param name="input_obj_file" value="find_cluster.h5"/>
      <param name="input_format" value="anndata"/>
      <param name="output_format" value="anndata"/>
      <param name="output_csv" value="true"/>
      <param name="n_genes" value="50"/>
      <param name="output_markers" value="false"/>
      <param name="default" value="false"/>
      <param name="groupby" value="louvain"/>
      <param name="method" value="t-test_overestim_var"/>
      <param name="rankby_abs" value="false"/>
      <output name="output_h5" file="find_markers.h5" ftype="h5" compare="sim_size"/>
    </test>
  </tests>

  <help><![CDATA[
=============================================================

15:cc776860fae1

<?xml version="1.0" encoding="utf-8"?>
<tool id="scanpy_find_markers" name="Scanpy FindMarkers" version="@TOOL_VERSION@+galaxy1" profile="@PROFILE@">
  <description>to find differentially expressed genes between groups</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-find-markers
#if $output_markers
    --save diffexp.tsv
#end if
    --n-genes '${n_genes}'
#set groupby = $groupby.replace('INPUT_OBJ', $input_obj_file.__getattr__('name'))
    --groupby '${groupby}'
#if $settings.key_added
    #set key_added = $settings.key_added.replace('GROUPBY', $groupby.__str__)
    --key-added '${key_added}'
#end if
#if $settings.default == "false"
    --method '${settings.method}'
    ${settings.use_raw}
    ${settings.rankby_abs}
    #if $settings.groups

]]></command>

  <inputs>
    <expand macro="input_object_params"/>
    <expand macro="output_object_params"/>
    <param name="output_markers" type="boolean" checked="true" label="Output markers table in tsv format"/>
    <param name="n_genes" argument="--n-genes" type="integer" value="50" label="Number of top genes to show per group/cluster"/>
    <param name="groupby" argument="--groupby" type="text" value="louvain" label="The sample grouping/clustering to use."/>
    <conditional name="settings">
      <param name="default" type="boolean" checked="true" label="Use programme defaults"/>
      <when value="true"/>
      <when value="false">
        <param name="key_added" argument="--key-added" type="text" optional="true"
               label="The key in adata.uns information is saved to. If included, the keyword 'GROUPBY' will be substituted with the value of the groupby setting."/>
        <param name="method" argument="--method" type="select" label="Method for testing differentially expressed genes">
          <option value="t-test_overestim_var" selected="true">t-test with over-estimated variance</option>
          <option value="t-test">t-test</option>
          <option value="wilcoxon">wilcoxon test, currently broken don't use</option>
          <option value="logreg">logistic regression</option>

    </conditional>
  </inputs>

  <outputs>
    <expand macro="output_data_obj" description="Marker genes"/>
    <data name="output_tsv" format="tabular" from_work_dir="diffexp.tsv" label="${tool.name} on ${on_string}: Marker table">
      <filter>output_markers</filter>
    </data>
  </outputs>

  <tests>
    <test>
      <param name="input_obj_file" value="louvain_1.0"/>
      <param name="input_format" value="anndata"/>
      <param name="output_format" value="anndata"/>
      <param name="output_tsv" value="true"/>
      <param name="n_genes" value="50"/>
      <param name="output_markers" value="true"/>
      <param name="default" value="false"/>
      <param name="groupby" value="INPUT_OBJ"/>
      <param name="key_added" value="GROUPBY_marker"/>
      <param name="method" value="t-test_overestim_var"/>
      <param name="rankby_abs" value="false"/>
      <output name="output_h5" file="find_markers.h5" ftype="h5" compare="sim_size"/>
      <output name="output_tsv" file="diffexp.tsv" ftype="tabular" compare="sim_size"/>
    </test>
  </tests>

  <help><![CDATA[
=============================================================