<?xml version="1.0" encoding="utf-8"?>
<tool id="scanpy_run_umap" name="Scanpy RunUMAP" version="@TOOL_VERSION@+galaxy1">
  <description>visualise cell clusters using UMAP</description>
  <macros>
    <import>scanpy_macros.xml</import>
  </macros>
  <expand macro="requirements"/>
  <command detect_errors="exit_code"><![CDATA[
ln -s '${input_obj_file}' input.h5 &&
PYTHONIOENCODING=utf-8 scanpy-run-umap.py
    -i input.h5
    -f '${input_format}'
    -o output.h5
    -F '${output_format}'
    #if $embeddings
        --output-embeddings-file embeddings.csv
    #end if
    #if $settings.default == "false"
        -n '${settings.n_components}'
        --min-dist '${settings.min_dist}'
        --spread '${settings.spread}'
        --alpha '${settings.alpha}'
        --gamma '${settings.gamma}'
        --negative-sample-rate '${settings.negative_sample_rate}'
        #if $settings.init_pos
            --init-pos '${settings.init_pos}'
        #end if
        #if $settings.maxiter
            --maxiter '${settings.maxiter}'
        #end if
        #if $settings.a
            -a '${settings.a}'
        #end if
        #if $settings.b
            -b '${settings.b}'
        #end if
        #if $settings.random_seed is not None
            -s '${settings.random_seed}'
        #end if
   #end if

@PLOT_OPTS@
]]></command>

  <inputs>
    <expand macro="input_object_params"/>
    <expand macro="output_object_params"/>
    <param name="embeddings" type="boolean" checked="true" label="Output embeddings in csv format"/>
    <conditional name="settings">
      <param name="default" type="boolean" checked="true" label="Use programme defaults"/>
      <when value="true"/>
      <when value="false">
        <param name="n_components" argument="--n-components" type="integer" value="2" label="The number of dimensions of the embedding"/>
        <param name="min_dist" argument="--min-dist" type="float" value="0.5" label="The effective minimum distance between embedded points"/>
        <param name="spread" argument="--spread" type="float" value="1.0" label="The effective spread of embedded points"/>
        <param name="alpha" argument="--alpha" type="float" value="1.0" label="Initial learning rate"/>
        <param name="gamma" argument="--gamma" type="float" value="1.0" label="Weighting applied to negative samples"/>
        <param name="negative_sample_rate" argument="--negative-sample-rate" type="integer" value="5" label="The ratio of negative to positive edge in optimisation"/>
        <param name="init_pos" argument="--init-pos" type="text" label="Method to initialise embedding, any key for adata.obsm or choose from the preset methods">
          <option value="spectral" selected="true">spectral</option>
          <option value="paga">paga</option>
          <option value="random">random</option>
        </param>
        <param name="maxiter" argument="--maxiter" type="integer" optional="true" label="Number of iterations of optimisation"/>
        <param name="a" argument="-a" type="float" optional="true" label="More specific parameter controlling embedding, automatically determined from --min-dist and --spread if unset"/>
        <param name="b" argument="-b" type="float" optional="true" label="More specific parameter controlling embedding, automatically determined from --min-dist and --spread if unset"/>
        <param name="random_seed" argument="--random-seed" type="integer" value="0" label="Seed for numpy random number generator"/>
      </when>
    </conditional>
    <conditional name="do_plotting">
      <param name="plot" type="boolean" checked="false" label="Make UMAP plot"/>
      <when value="true">
        <expand macro="output_plot_params"/>
        <param name="color_by" argument="--color-by" type="text" value="louvain" label="Color by attributes, comma separated strings"/>
      </when>
      <when value="false"/>
    </conditional>
  </inputs>

  <outputs>
    <data name="output_h5" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: UMAP object"/>
    <data name="output_png" format="png" from_work_dir="output.png" label="${tool.name} on ${on_string}: UMAP plot">
      <filter>do_plotting['plot']</filter>
    </data>
    <data name="output_embed" format="csv" from_work_dir="embeddings.csv" label="${tool.name} on ${on_string}: UMAP embeddings">
      <filter>embeddings</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="default" value="false"/>
      <param name="embeddings" value="true"/>
      <param name="random_seed" value="0"/>
      <param name="plot" value="true"/>
      <param name="color_by" value="louvain"/>
      <output name="output_h5" file="run_umap.h5" ftype="h5" compare="sim_size"/>
      <output name="output_png" file="run_umap.png" ftype="png" compare="sim_size"/>
      <output name="output_embed" file="run_umap.embeddings.csv" ftype="csv" compare="sim_size">
        <assert_contents>
          <has_n_columns n="2" sep=","/>
        </assert_contents>
      </output>
    </test>
  </tests>

  <help><![CDATA[
========================================================
Embed the neighborhood graph using UMAP (`tl.umap`)
========================================================

UMAP (Uniform Manifold Approximation and Projection) is a manifold learning
technique suitable for visualizing high-dimensional data. Besides tending to
be faster than tSNE, it optimizes the embedding such that it best reflects
the topology of the data, which we represent throughout Scanpy using a
neighborhood graph. tSNE, by contrast, optimizes the distribution of
nearest-neighbor distances in the embedding such that these best match the
distribution of distances in the high-dimensional space.  We use the
implementation of `umap-learn <https://github.com/lmcinnes/umap>`__
(McInnes et al, 2018). For a few comparisons of UMAP with tSNE, see this `preprint
<https://doi.org/10.1101/298430>`__.

It yields `X_umap`, UMAP coordinates of data.

@HELP@

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