view scanpy-run-pca.xml @ 8:1618435e2a33 draft

planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/tree/develop/tools/tertiary-analysis/scanpy commit cbe12e02ee9ff5692be7547bdbe28fd1cd013a92

<?xml version="1.0" encoding="utf-8"?>
<tool id="scanpy_run_pca" name="Scanpy RunPCA" version="@TOOL_VERSION@+galaxy9" profile="@PROFILE@">
  <description>for dimensionality reduction</description>
  <macros>
    <import>scanpy_macros2.xml</import>
  </macros>
  <expand macro="requirements"/>
  <command detect_errors="exit_code"><![CDATA[
ln -s '${input_obj_file}' input.h5 &&
PYTHONIOENCODING=utf-8 scanpy-run-pca
    --n-comps '${n_pcs}'
#if $run_mode.chunked
    --chunked
    --chunk-size '${run_mode.chunk_size}'
#else
    ${run_mode.zero_center}
    #if $run_mode.svd_solver
        --svd-solver '${run_mode.svd_solver}'
    #end if
    #if $run_mode.random_seed is not None
        --random-state '${run_mode.random_seed}'
    #end if
#end if
#if $extra_outputs and "embeddings" in str($extra_outputs).split(','):
    --export-embedding embeddings.tsv
#end if
    @INPUT_OPTS@
    @OUTPUT_OPTS@
]]></command>

  <inputs>
    <expand macro="input_object_params"/>
    <expand macro="output_object_params"/>
    <param name="n_pcs" argument="--n-comps" type="integer" min="2" value="50" label="Number of PCs to produce"/>
    <conditional name="run_mode">
      <param name="chunked" argument="--chunked" type="boolean" checked="false" label="Perform incremental PCA by chunks"/>
      <when value="true">
        <param name="chunk_size" argument="--chunk-size" type="integer" value="0" label="Chunk size"/>
      </when>
      <when value="false">
        <param name="zero_center" argument="--zero-center" type="boolean" truevalue="" falsevalue="--no-zero-center" checked="true"
               label="Zero center data before scaling"/>
        <param name="svd_solver" argument="--svd-solver" type="select" optional="true" label="SVD solver">
          <option value="arpack">ARPACK</option>
          <option value="randomized">Randomised</option>
        </param>
        <param name="random_seed" argument="--random-state" type="integer" value="0" label="random seed for numpy random number generator"/>
      </when>
    </conditional>

    <param name="extra_outputs" type="select" multiple="true" display="checkboxes" optional="true" label="Export extra output">
      <option value="embeddings">PCA embeddings</option>
    </param>

  </inputs>

  <outputs>
    <expand macro="output_data_obj" description="PCA object"/>
    <data name="output_embed" format="tsv" from_work_dir="embeddings.tsv" label="${tool.name} on ${on_string}: PCA embeddings">
      <filter>extra_outputs and 'embeddings' in extra_outputs.split(',')</filter>
    </data>
  </outputs>

  <tests>
    <test>
      <param name="input_obj_file" value="scale_data.h5"/>
      <param name="input_format" value="anndata"/>
      <param name="output_format" value="anndata"/>
      <param name="extra_outputs" value="embeddings"/>
      <param name="n_pcs" value="50"/>
      <param name="zero_center" value="true"/>
      <param name="svd_solver" value="arpack"/>
      <param name="random_seed" value="0"/>
      <param name="chunked" value="false"/>
      <output name="output_h5" file="run_pca.h5" ftype="h5" compare="sim_size"/>
      <output name="output_embed" file="run_pca.embeddings.csv" ftype="csv" compare="sim_size">
        <assert_contents>
          <has_n_columns n="50" sep=","/>
        </assert_contents>
      </output>
    </test>
  </tests>

  <help><![CDATA[
================================================================================
Dimensionality reduction by PCA (principal component analysis) (`scanpy.pp.pca`)
================================================================================

It uses the implementation of *scikit-learn*.

@HELP@

@VERSION_HISTORY@
]]></help>
  <expand macro="citations"/>
</tool>