comparison scanpy-run-tsne.xml @ 1:2e74fd7b5f45 draft

"planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/tree/develop/tools/tertiary-analysis/scanpy commit 4846776f55931e176f7e77af7c185ec6fec7d142"

0:f6f189ce4ebc

<?xml version="1.0" encoding="utf-8"?>
<tool id="scanpy_run_tsne" name="Scanpy RunTSNE" version="@TOOL_VERSION@+galaxy1">
  <description>visualise cell clusters using tSNE</description>
  <macros>
    <import>scanpy_macros.xml</import>
  </macros>
  <expand macro="requirements"/>
  <command detect_errors="exit_code"><![CDATA[
ln -s '${input_obj_file}' input.h5 &&
PYTHONIOENCODING=utf-8 scanpy-run-tsne.py
    -i input.h5
    -f '${input_format}'
    -o output.h5
    -F '${output_format}'
    #if $embeddings
        --output-embeddings-file embeddings.csv
    #end if
    #if $settings.default == "false"
        #if $settings.perplexity_file
          --perplexity \$( cat $settings.perplexity_file )
        #else
          --perplexity '${settings.perplexity}'
        #end if
        --early-exaggeration '${settings.early_exaggeration}'
        --learning-rate '${settings.learning_rate}'
        #if $settings.use_rep != "auto"
            -r '${settings.use_rep}'
        #end if
        #if $settings.n_pc
            -n '${settings.n_pc}'
        #end if
        #if not $settings.fast_tsne
            --no-fast-tsne
        #end if
        #if $settings.n_job
            --n-jobs '${settings.n_job}'
        #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="use_rep" argument="--use-rep" type="select" label="Use the indicated representation">
          <option value="X_pca">X_pca, use PCs</option>
          <option value="X">X, use normalised expression values</option>
          <option value="auto" selected="true">Automatically chosen based on problem size</option>
        </param>
        <param name="perplexity" argument="--perplexity" type="float" value="30" label="The perplexity is related to the number of nearest neighbours, select a value between 5 and 50"/>
        <param name="perplexity_file" argument="--perplexity" type="data" format="txt,tsv" label="The perplexity is related to the number of nearest neighbours" help="For use with the parameter iterator. Overrides the persplexity option above" optional="true"/>
        <param name="early_exaggeration" argument="--early-exaggeration" type="float" value="12" label="Controls the tightness within and between clusters"/>
        <param name="learning_rate" argument="--learning-rate" type="float" value="1000" label="Learning rate, should be between 100 and 1000"/>
        <param name="fast_tsne" type="boolean" checked="true" label="Use multicoreTSNE"/>

        <param name="n_pc" argument="--n-pcs" type="integer" optional="true" label="The number of PCs to use"/>
        <param name="random_seed" argument="--random-seed" type="integer" value="0" label="Seed for random number generator"/>
      </when>
    </conditional>

    <conditional name="do_plotting">
      <param name="plot" type="boolean" checked="false" label="Make tSNE 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 ${on_string}: tSNE object"/>
    <data name="output_png" format="png" from_work_dir="output.png" label="${tool.name} on ${on_string}: tSNE plot">
      <filter>do_plotting['plot']</filter>
    </data>
    <data name="output_embed" format="csv" from_work_dir="embeddings.csv" label="${tool.name} on ${on_string}: tSNE embeddings">
      <filter>embeddings</filter>
    </data>
  </outputs>

      <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_tsne.h5" ftype="h5" compare="sim_size"/>
      <output name="output_png" file="run_tsne.png" ftype="png" compare="sim_size"/>
      <output name="output_embed" file="run_tsne.embeddings.csv" ftype="csv" compare="sim_size">
        <assert_contents>
          <has_n_columns n="2" sep=","/>
        </assert_contents>
      </output>
    </test>
  </tests>

  <help><![CDATA[
==================================================================
t-distributed stochastic neighborhood embedding (tSNE) (`tl.tsne`)
==================================================================

t-distributed stochastic neighborhood embedding (tSNE) (Maaten et al, 2008) has been
proposed for visualizating single-cell data by (Amir et al, 2013). Here, by default,
we use the implementation of *scikit-learn* (Pedregosa et al, 2011).

1:2e74fd7b5f45

<?xml version="1.0" encoding="utf-8"?>
<tool id="scanpy_run_tsne" name="Scanpy RunTSNE" version="@TOOL_VERSION@+galaxy1">
  <description>visualise cell clusters using tSNE</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-tsne
#if $use_rep != "auto"
    --use-rep '${use_rep}'
#end if
#if $key_added
    --key-added '${key_added}'
#end if
#if $embeddings
    --export-embedding embeddings.csv
#end if
#if $settings.default == "false"
    #if $settings.perplexity_file
        --perplexity \$( cat $settings.perplexity_file )
    #else
        --perplexity '${settings.perplexity}'
    #end if
    --early-exaggeration '${settings.early_exaggeration}'
    --learning-rate '${settings.learning_rate}'
    #if $settings.n_pc
        --n-pcs ${settings.n_pc}
    #end if
    #if not $settings.fast_tsne
        --no-fast-tsne
    #end if
    #if $settings.n_job
        --n-jobs ${settings.n_job}
    #end if
    #if $settings.random_seed is not None
        --random-state ${settings.random_seed}
    #end if
#end if
    @INPUT_OPTS@
    @OUTPUT_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"/>

    <param name="use_rep" argument="--use-rep" type="select" label="Use the indicated representation">
      <option value="X_pca">X_pca, use PCs</option>
      <option value="X">X, use normalised expression values</option>
      <option value="auto" selected="true">Automatically chosen based on problem size</option>
    </param>
    <param name="key_added" argument="--key-added" type="text" optional="true"
           label="Additional suffix to the name of the slot to save the embedding"/>

    <conditional name="settings">
      <param name="default" type="boolean" checked="true" label="Use programme defaults"/>
      <when value="true"/>
      <when value="false">
        <param name="perplexity" argument="--perplexity" type="float" value="30" label="The perplexity is related to the number of nearest neighbours, select a value between 5 and 50"/>
        <param name="perplexity_file" argument="--perplexity" type="data" format="txt,tsv" label="The perplexity is related to the number of nearest neighbours" help="For use with the parameter iterator. Overrides the persplexity option above" optional="true"/>
        <param name="early_exaggeration" argument="--early-exaggeration" type="float" value="12" label="Controls the tightness within and between clusters"/>
        <param name="learning_rate" argument="--learning-rate" type="float" value="1000" label="Learning rate, should be between 100 and 1000"/>
        <param name="fast_tsne" type="boolean" checked="true" label="Use multicoreTSNE"/>

        <param name="n_pc" argument="--n-pcs" type="integer" optional="true" label="The number of PCs to use"/>
        <param name="random_seed" argument="--random-seed" type="integer" value="0" label="Seed for random number generator"/>
      </when>
    </conditional>

  </inputs>

  <outputs>
    <data name="output_h5" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: tSNE object"/>
    <data name="output_embed" format="csv" from_work_dir="embeddings.csv" label="${tool.name} on ${on_string}: tSNE embeddings">
      <filter>embeddings</filter>
    </data>
  </outputs>

      <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"/>
      <output name="output_h5" file="run_tsne.h5" ftype="h5" compare="sim_size"/>
      <output name="output_embed" file="run_tsne.embeddings.csv" ftype="csv" compare="sim_size">
        <assert_contents>
          <has_n_columns n="2" sep=","/>
        </assert_contents>
      </output>
    </test>
  </tests>

  <help><![CDATA[
=========================================================================
t-distributed stochastic neighborhood embedding (tSNE) (`scanpy.tl.tsne`)
=========================================================================

For making TSNE plots, please use `Scanpy PlotEmbed` with the output of this tool and enter "tsne" as the
name of the embedding to plot.

t-distributed stochastic neighborhood embedding (tSNE) (Maaten et al, 2008) has been
proposed for visualizating single-cell data by (Amir et al, 2013). Here, by default,
we use the implementation of *scikit-learn* (Pedregosa et al, 2011).