<?xml version="1.0" encoding="utf-8"?>
<tool id="scanpy_integrate_mnn" name="Scanpy MNN" version="@TOOL_VERSION@+galaxy93" profile="@PROFILE@">
  <description>correct batch effects by matching mutual nearest neighbors</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 mnn 
  --batch-key '${batch_key}'
  #if $batch_layer
    --batch-layer '${batch_layer}'
  #end if
  #if $key_added
    --key-added '${key_added}'
  #end if
  #if $var_subset
    #set var_subsets = ' '.join(["--var-subset '{name}' '{values}'".format(**$v) for $v in $var_subset])
    ${var_subsets}
  #if $settings.default == "false"
    #if $settings.n_neighbors
        --n-neighbors '${settings.n_neighbors}'
    #end if
    #if $settings.sigma
        --sigma '${settings.sigma}'
    #end if
    #if not $settings.cos_norm_in
        ${settings.cos_norm_in}
    #end if
    #if $settings.svd_dim
        --svd-dim '${settings.svd_dim}'
    #end if
    #if not $settings.var_adj
        ${settings.var_adj}
    #end if
    #if $settings.compute_angle
        ${settings.compute_angle}
    #end if
    #if $settings.svd_mode
        --svd-mode '${settings.svd_mode}'
    #end if
  #end if
  @SAVE_MATRIX_OPTS@
#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"/>
    <expand macro="save_matrix_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="batch_layer" type="text" argument="--batch-layer" label="Layer to batch correct. By default corrects the contents of .X.">
      <sanitizer>
        <valid initial="string.printable"/>
      </sanitizer>
    </param>
    <param name="key_added" argument="--key-added" type="text" optional="true" label="Key under which to add the computed results." help="By default a new layer will be created called 'mnn', 'mnn_{layer}' or 'mnn_{layer}_{key_added}' where those parameters were specified. A value of 'X' causes batch-corrected values to overwrite the original content of .X."/>
    <repeat name="var_subset" title="The subset of vars (list of str) to be used when performing MNN correction" min="0">
      <param name="name" type="text" value="" label="Name of the categorical variable to filter on" help="e.g. 'highly_variable'"/>
      <param name="values" type="text" value="" label="Category or comma-separated list of categories" help="e.g. 'True'"/>
    </repeat>
    <conditional name="settings">
      <param name="default" type="boolean" checked="true" label="Use programme defaults"/>
      <when value="true"/>
      <when value="false">
        <param name="n_neighbors" argument="--n-neighbors" type="integer" value="20" label="Number of mutual nearest neighbors."/>
        <param name="sigma" argument="--sigma" type="float" value="1.0" label="Sigma" help="The bandwidth of the Gaussian smoothing kernel used to compute the correction vectors." />
        <param name="cos_norm_in" argument="--no-cos-norm-in" type="boolean" truevalue="" falsevalue="--no-cos-norm-in" checked="True"
            label="Perform cosine normalization prior to computing corrected expression values?" />
        <param name="svd_dim" argument="--svd-dim" type="integer" optional="true" label="Number of dimensions to use for summarizing biological substructure within each batch." help="If not set, biological components will not be removed from the correction vectors."/>
        <param name="var_adj" argument="--no-var-adj" type="boolean" truevalue="" falsevalue="--no-var-adj" checked="True"
            label="Adjust variance of the correction vectors?" help="Note this step takes most computing time." />
        <param name="compute_angle" argument="--compute-angle" type="boolean" truevalue="--compute-angle" falsevalue="" checked="False"
            label="Compute the angle between each cell’s correction vector and the biological subspace of the reference batch?" />
        <param name="svd_mode" argument="--svd-mode" type="select" label="SVD mode" help="'svd' computes SVD using a non-randomized SVD-via-ID algorithm, while 'rsvd' uses a randomized version. 'irlb' performs truncated SVD by implicitly restarted Lanczos bidiagonalization (forked from https://github.com/airysen/irlbpy)." >
          <option value="rsvd" selected="true">rsvd</option>
          <option value="svd">svd</option>
          <option value="irlb">irlb</option>
        </param>
      </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="mnn.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="mnn_copy.h5" ftype="h5" compare="sim_size"/>
    </test>
  </tests>-->

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

    **What it does**

    Corrects for batch effects by fitting linear models, gains statistical power via an EB framework where information is borrowed across genes.

    @HELP@

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