view scanpy-integrate-harmony.xml @ 11:ca0c7251e415 draft

"planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/tree/develop/tools/tertiary-analysis/scanpy commit 9ea121884e1aecd2ee66a0686057cb3ed904b9eb-dirty"

<?xml version="1.0" encoding="utf-8"?>
<tool id="scanpy_integrate_harmony" name="Scanpy Harmony" version="@TOOL_VERSION@+galaxy0" profile="@PROFILE@">
  <description>adjust principal components for variables that might introduce batch effect</description>
  <macros>
    <import>scanpy_macros2.xml</import>
  </macros>
  <expand macro="requirements"/>
  <command detect_errors="exit_code"><![CDATA[
#if $batch_key
  ln -s '${input_obj_file}' input.h5 &&
  PYTHONIOENCODING=utf-8 scanpy-integrate harmony
  --batch-key '${batch_key}'
  #if $basis
    --basis '${basis}'
  #end if
  --adjusted-basis '${adjusted_basis}'
  #if not $settings.default
      #if $settings.theta
      --theta '${settings.theta}'
      #end if 
      #if $settings.lambda
      --lambda '${settings.lambda}'
      #end if 
      #if $settings.sigma
      --sigma '${settings.sigma}'
      #end if 
      #if $settings.nclust
      --nclust '${settings.nclust}'
      #end if 
      #if $settings.tau
      --tau '${settings.tau}'
      #end if 
      #if $settings.block_size
      --block-size '${settings.block_size}'
      #end if 
      #if $settings.max_iter_cluster
      --max-iter-cluster '${settings.max_iter_cluster}'
      #end if 
      #if $settings.max_iter_harmony
      --max-iter-harmony '${settings.max_iter_harmony}'
      #end if 
      #if $settings.epsilon_cluster
      --epsilon-cluster '${settings.epsilon_cluster}'
      #end if 
      #if $settings.epsilon_harmony
      --epsilon-harmony '${settings.epsilon_harmony}'
      #end if 
      #if $settings.random_state
      --random-state '${settings.random_state}'
      #end if 
  #end if
  @INPUT_OPTS@
  @OUTPUT_OPTS@
#else
  echo "No batch variables passed, simply passing original input as output unchanged." && cp '${input_obj_file}' output.h5
#end if
]]></command>

  <inputs>
    <expand macro="input_object_params"/>
    <expand macro="output_object_params"/>
    <param name="batch_key" type="text" argument="--batch-key" label="The name of the column in adata.obs that differentiates among experiments/batches.">
      <sanitizer>
        <valid initial="string.printable"/>
      </sanitizer>
    </param>
    <param name="basis" argument="--basis" type="text" value='X_pca' label="The name of the field in adata.obsm where the PCA table is stored. Defaults to 'X_pca', which is the default for sc.tl.pca().">
      <sanitizer>
        <valid initial="string.printable"/>
      </sanitizer>
    </param>
    <param name="adjusted_basis" argument="--adjusted-basis" type="text" value='X_pca_harmony' label="he name of the field in adata.obsm where the adjusted PCA table will be stored after running this function.">
      <sanitizer>
        <valid initial="string.printable"/>
      </sanitizer>
    </param>
    <conditional name="settings">
      <param name="default" type="boolean" checked="true" label="Use programme defaults"/>
      <when value="true"/>
      <when value="false">
        <param name="theta" argument="--theta" type="float" value="2.0"
              label="Diversity clustering penalty parameter" help="theta=0 does not encourage any diversity. Larger values of theta result in more diverse clusters." />
        <param name="lambda" argument="--lambda" type="float" min="0" value="1.0"
              label="Ridge regression penalty parameter" help="Lambda must be strictly positive. Smaller values result in more aggressive correction." />
        <param name="sigma" argument="--sigma" type="float" value="0.1"
              label="Ridge regression penalty parameter" help="Width of soft kmeans clusters. Sigma scales the distance from a cell to cluster centroids. Larger values of sigma result in cells assigned to more clusters. Smaller values of sigma make soft kmeans cluster approach hard clustering." />
        <param name="nclust" argument="--nclust" type="integer" value="" optional="true"
              label="Number of clusters in model." help="nclust=1 equivalent to simple linear regression." />
        <param name="tau" argument="--tau" type="integer" value="0"
              label="Protection against overclustering small datasets with large ones." help="'tau is the expected number of cells per cluster." />
        <param name="block_size" argument="--block-size" type="float" value="0.05"
              label="What proportion of cells to update during clustering" min="0" max="1" help="Between 0 to 1, default 0.05. Larger values may be faster but less accurate." />
        <param name="max_iter_cluster" argument="--max-iter-cluster" type="integer" value="20"
              label="Maximum number of rounds to run clustering at each round of Harmony" />
        <param name="max_iter_harmony" argument="--max-iter-harmony" type="integer" value="10"
              label="Maximum number of rounds to run Harmony. One round of Harmony involves one clustering and one correction step." />
        <param name="epsilon_cluster" argument="--epsilon-cluster" type="float" value="0.00001"
              label="Convergence tolerance for clustering round of Harmony" help="Set to -Inf to never stop early." />
        <param name="epsilon_harmony" argument="--epsilon-harmony" type="float" value="0.00001"
              label="Convergence tolerance for Harmony." help="Set to -Inf to never stop early." />
        <param name="random_state" argument="--random-state" type="integer" value="0"
              label="Seed for random number generator." />
      </when>
    </conditional>    
  </inputs>

  <outputs>
    <expand macro="output_data_obj" description="Batch-corrected for ${batch_key}"/>
  </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="batch_key" value="louvain"/>
      <output name="output_h5" file="harmony.h5" ftype="h5" compare="sim_size"/>
    </test>
    <test>
      <param name="input_obj_file" value="find_cluster.h5"/>
      <param name="input_format" value="anndata"/>
      <param name="output_format" value="anndata"/>
      <output name="output_h5" file="harmony_copy.h5" ftype="h5" compare="sim_size"/>
    </test>
  </tests>

  <help><![CDATA[
    .. class:: infomark

    **What it does**

    Uses harmonypy [Korunsky19] to integrate different experiments at the principal components level. 

    @HELP@

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