comparison cluster_reduce_dimension.xml @ 11:edec35114f72 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/scanpy/ commit aba2a85f5da6e1094f382d1f0d94c4b8f2544a7d

10:aaa5da8e73a9

<tool id="scanpy_cluster_reduce_dimension" name="Cluster, infer trajectories and embed" version="@galaxy_version@" profile="@profile@">
    <description>with scanpy</description>
    <expand macro="bio_tools"/>
    <macros>
        <import>macros.xml</import>
        <xml name="pca_inputs">
            <param argument="n_comps" type="integer" min="0" value="50" label="Number of principal components to compute" help="If the value is larger than the number of observations the number of observations is used instead"/>
            <param argument="dtype" type="text" value="float32" label="Numpy data type string to which to convert the result" help="">

                </when>
                <when value="False">
                    <param argument="zero_center" type="boolean" truevalue="True" falsevalue="False" checked="true"
                        label="Compute standard PCA from covariance matrix?"
                        help="If not, it omits zero-centering variables (uses *TruncatedSVD* from scikit-learn), which allows to handle sparse input efficiently."/>
                    <expand macro="svd_solver"/> 
                    <param argument="random_state" type="integer" value="0" label="Initial states for the optimization" help=""/>
                </when>
            </conditional>
            <param argument="use_highly_variable" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Use highly variable genes only?" help="They should be use if they have been determined beforehand."/>
        </xml>

    random_state=$method.pca.random_state,
#end if
    use_highly_variable=$method.use_highly_variable
]]></token>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="0.7.0">louvain</requirement>
    </expand>
    <expand macro="version_command"/>
    <command detect_errors="exit_code"><![CDATA[
@CMD@
      ]]></command>

    n_dcs=$method.n_dcs,
    n_branchings=$method.n_branchings,
    min_group_size=$method.min_group_size,
    allow_kendall_tau_shift=$method.allow_kendall_tau_shift,
    copy=False)
#end if

@CMD_anndata_write_outputs@
]]></configfile>
    </configfiles>

                <option value="tl.tsne">t-distributed stochastic neighborhood embedding (tSNE), using 'tl.tsne'</option>
                <option value="tl.umap">Embed the neighborhood graph using UMAP, using 'tl.umap'</option>
                <option value="tl.draw_graph">Force-directed graph drawing, using 'tl.draw_graph'</option>
                <option value="tl.dpt">Infer progression of cells through geodesic distance along the graph, using 'tl.dpt'</option>
                <option value="tl.paga">Generate cellular maps of differentiation manifolds with complex topologies, using 'tl.paga'</option>
            </param>
            <when value="tl.louvain">
                <conditional name="flavor">
                    <param argument="flavor" type="select" label="Flavor for the clustering" help="">
                        <option value="vtraag">vtraag (much more powerful)</option>

                <param argument="model" type="select" label="PAGA connectivity model" help="">
                    <option value="v1.2">v1.2</option>
                    <option value="v1.0">v1.0</option>
                </param>
            </when>
        </conditional>            
        <expand macro="inputs_common_advanced"/>
    </inputs>
    <outputs>
        <expand macro="anndata_outputs"/>
    </outputs>
    <tests>
        <test>
            <!-- test 0 -->
            <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.louvain"/>
                <conditional name="flavor">
                    <param name="flavor" value="vtraag"/>

                    <has_text_matching expression="use_weights=False"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.louvain.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test>
            <!-- test 1 -->
            <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.leiden"/>
                <param name="random_state" value="1"/>
                <param name="random_state" value="10"/>

                    <has_text_matching expression="n_iterations=-1"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.leiden.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test>
            <!-- test 1 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.pca"/>
                <param name="n_comps" value="50"/>
                <param name="dtype" value="float32"/>

                    <has_text_matching expression="use_highly_variable=False"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="pp.pca.krumsiek11.h5ad" ftype="h5ad" compare="sim_size" delta="100000" delta_frac="0.15"/>
        </test>
        <!--<test>
            < test 3 >
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.pca"/>
                <param name="n_comps" value="20"/>
                <param name="dtype" value="float32"/>

                    <param name="chunked" value="True"/>
                    <param name="chunk_size" value="50"/>
                </conditional>
                <param name="use_highly_variable" value="false"/>
            </conditional>
            <assert_stdout>
                <has_text_matching expression="sc.pp.pca"/>
                <has_text_matching expression="data=adata"/>
                <has_text_matching expression="n_comps=20"/>
                <has_text_matching expression="dtype='float32'"/>
                <has_text_matching expression="copy=False"/>
                <has_text_matching expression="chunked=True"/>
                <has_text_matching expression="chunk_size=50"/>
                <has_text_matching expression="use_highly_variable=False"/>
            </assert_stdout>
            <output name="anndata_out" file="pp.pca.krumsiek11_chunk.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        -->
        <test>
            <!-- test 2 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.pca"/>
                <param name="n_comps" value="50"/>
                <param name="dtype" value="float32"/>

                    <has_text_matching expression="use_highly_variable=False"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.pca.krumsiek11.h5ad" ftype="h5ad" compare="sim_size" delta="100000" delta_frac="0.15"/>
        </test>
        <test>
            <!-- test 3 -->
            <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.diffmap"/>
                <param name="n_comps" value="15"/>
            </conditional>

                    <has_text_matching expression="sc.tl.diffmap"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test>
            <!-- test 4 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.tsne"/>
                <param name="n_pcs" value="10"/>
                <param name="perplexity" value="30"/>

                    <has_text_matching expression="use_fast_tsne=True"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.tsne.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test>
            <!-- test 5 -->
            <param name="adata" value="pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.umap"/>
                <param name="min_dist" value="0.5"/>
                <param name="spread" value="1.0"/>

                <assert_contents>
                    <has_h5_keys keys="X, obs, obsm, uns, var" />
                </assert_contents>
            </output>
        </test>
        <test>
            <!-- test 6 -->
            <param name="adata" value="pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad"/>
            <conditional name="method">
                <param name="method" value="tl.draw_graph"/>
                <param name="layout" value="fa"/>
                <param name="random_state" value="0"/>

                    <has_text_matching expression="random_state=0"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.draw_graph.pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test>
            <!-- test 7 -->
            <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad"/>
            <conditional name="method">
                <param name="method" value="tl.paga"/>
                <param name="groups" value="paul15_clusters"/>
                <param name="use_rna_velocity" value="False"/>

                    <has_text_matching expression="model='v1.2'"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.paga.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test>
            <!-- test 8 -->
            <param name="adata" value="tl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.dpt"/>
                <param name="n_dcs" value="15"/>
                <param name="n_branchings" value="1"/>

                    <has_text_matching expression="allow_kendall_tau_shift=True"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
    </tests>
    <help><![CDATA[
Cluster cells into subgroups (`tl.louvain`)
===========================================

analysis by Levine et al, 2015.

This requires to run `pp.neighbors`, first.

More details on the `tl.louvain scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.louvain.html>`_

Cluster cells into subgroups (`tl.leiden`)
==========================================

Cluster cells using the Leiden algorithm (Traag et al, 2018), an improved version of the Louvain algorithm (Blondel et al, 2008).

The Louvain algorithm has been proposed for single-cell analysis by Levine et al, 2015.

More details on the `tl.leiden scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.leiden.html>`_

Computes PCA (principal component analysis) coordinates, loadings and variance decomposition, using `pp.pca`
============================================================================================================

@CMD_pca_outputs@

More details on the `pp.pca scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.pp.pca.html>`__

Computes PCA (principal component analysis) coordinates, loadings and variance decomposition, using `tl.pca`
============================================================================================================

@CMD_pca_outputs@

More details on the `tl.pca scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.pca.html>`__

Diffusion Maps, using `tl.diffmap`
==================================

Diffusion maps (Coifman et al  2005) has been proposed for visualizing single-cell

using a Gaussian kernel, use `method=='gauss'` in
`pp.neighbors`. To use an exponential kernel, use the default
`method=='umap'`. Differences between these options shouldn't usually be
dramatic.

The diffusion map representation of data are added to the return AnnData in the multi-dimensional 
observations annotation (obsm). It is the right eigen basis of the transition matrix with eigenvectors 
as colum. It can be accessed using the inspect tool for AnnData

More details on the `tl.diffmap scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.diffmap.html>`__

t-distributed stochastic neighborhood embedding (tSNE), using `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). 

It returns `X_tsne`, tSNE coordinates of data.

More details on the `tl.tsne scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.tsne.html>`__

Embed the neighborhood graph using UMAP, using `tl.umap`
========================================================

UMAP (Uniform Manifold Approximation and Projection) is a manifold learning

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>`__.

The UMAP coordinates of data are added to the return AnnData in the multi-dimensional 
observations annotation (obsm). This data is accessible using the inspect tool for AnnData

More details on the `tl.umap scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.umap.html>`__

Force-directed graph drawing, using `tl.draw_graph`
===================================================

Force-directed graph drawing describes a class of long-established algorithms for visualizing graphs. 
It has been suggested for visualizing single-cell data by Islam et al, 11. 
Many other layouts as implemented in igraph are available. Similar approaches have been used by 
Zunder et al, 2015 or Weinreb et al, 2016.

This is an alternative to tSNE that often preserves the topology of the data better. 
This requires to run `pp.neighbors`, first.

The default layout (ForceAtlas2) uses the package fa2.

The coordinates of graph layout are added to the return AnnData in the multi-dimensional 
observations annotation (obsm). This data is accessible using the inspect tool for AnnData.

More details on the `tl.draw_graph scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.draw_graph.html>`__

Infer progression of cells through geodesic distance along the graph (`tl.dpt`)
===============================================================================

Reconstruct the progression of a biological process from snapshot

version, which is able to deal with disconnected graphs (Wolf et al, 2017) and can
be run in a `hierarchical` mode by setting the parameter
`n_branchings>1`. We recommend, however, to only use
`tl.dpt` for computing pseudotime (`n_branchings=0`) and
to detect branchings via `paga`. For pseudotime, you need
to annotate your data with a root cell. 

This requires to run `pp.neighbors`, first. In order to
reproduce the original implementation of DPT, use `method=='gauss'` in
this. Using the default `method=='umap'` only leads to minor quantitative
differences, though.

- dpt_groups : Array of dim (number of samples) that stores the subgroup id ('0','1', ...) for each cell. The groups  typically correspond to 'progenitor cells', 'undecided cells' or 'branches' of a process.

The tool is similar to the R package `destiny` of Angerer et al (2016).

More details on the `tl.dpt scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.dpt.html>`_


Generate cellular maps of differentiation manifolds with complex topologies (`tl.paga`)
=======================================================================================

- Adjacency matrix of the tree-like subgraph that best explains the topology (connectivities_tree)

These datasets are stored in the unstructured annotation (uns) and can be accessed using the inspect tool for AnnData objects

More details on the `tl.paga scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.tl.paga.html>`_
    ]]></help>
    <expand macro="citations"/>
</tool>

11:edec35114f72

<tool id="scanpy_cluster_reduce_dimension" name="Cluster, infer trajectories and embed" version="@galaxy_version@" profile="@profile@">
    <description>with scanpy</description>
    <macros>
        <import>macros.xml</import>
        <xml name="pca_inputs">
            <param argument="n_comps" type="integer" min="0" value="50" label="Number of principal components to compute" help="If the value is larger than the number of observations the number of observations is used instead"/>
            <param argument="dtype" type="text" value="float32" label="Numpy data type string to which to convert the result" help="">

                </when>
                <when value="False">
                    <param argument="zero_center" type="boolean" truevalue="True" falsevalue="False" checked="true"
                        label="Compute standard PCA from covariance matrix?"
                        help="If not, it omits zero-centering variables (uses *TruncatedSVD* from scikit-learn), which allows to handle sparse input efficiently."/>
                    <expand macro="svd_solver"/>
                    <param argument="random_state" type="integer" value="0" label="Initial states for the optimization" help=""/>
                </when>
            </conditional>
            <param argument="use_highly_variable" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Use highly variable genes only?" help="They should be use if they have been determined beforehand."/>
        </xml>

    random_state=$method.pca.random_state,
#end if
    use_highly_variable=$method.use_highly_variable
]]></token>
    </macros>
    <expand macro="bio_tools"/>
    <expand macro="requirements">
    </expand>
    <expand macro="version_command"/>
    <command detect_errors="exit_code"><![CDATA[
@CMD@
      ]]></command>

    n_dcs=$method.n_dcs,
    n_branchings=$method.n_branchings,
    min_group_size=$method.min_group_size,
    allow_kendall_tau_shift=$method.allow_kendall_tau_shift,
    copy=False)

#else if $method.method == "tl.embedding_density"
sc.tl.embedding_density(
    adata=adata,
    basis='$method.basis',
#if str($method.groupby) != ''
    groupby='$method.groupby',
#end if
#if str($method.key_added) != ''
    key_added='$method.key_added',
#end if
    )

#end if

@CMD_anndata_write_outputs@
]]></configfile>
    </configfiles>

                <option value="tl.tsne">t-distributed stochastic neighborhood embedding (tSNE), using 'tl.tsne'</option>
                <option value="tl.umap">Embed the neighborhood graph using UMAP, using 'tl.umap'</option>
                <option value="tl.draw_graph">Force-directed graph drawing, using 'tl.draw_graph'</option>
                <option value="tl.dpt">Infer progression of cells through geodesic distance along the graph, using 'tl.dpt'</option>
                <option value="tl.paga">Generate cellular maps of differentiation manifolds with complex topologies, using 'tl.paga'</option>
                <option value="tl.embedding_density">Calculate the density of cells in an embedding (per condition)</option>
            </param>
            <when value="tl.louvain">
                <conditional name="flavor">
                    <param argument="flavor" type="select" label="Flavor for the clustering" help="">
                        <option value="vtraag">vtraag (much more powerful)</option>

                <param argument="model" type="select" label="PAGA connectivity model" help="">
                    <option value="v1.2">v1.2</option>
                    <option value="v1.0">v1.0</option>
                </param>
            </when>
            <when value="tl.embedding_density">
                <param argument="basis" type="text" value="umap" label="The embedding over which the density will be calculated." help="This embedded representation should be found in adata.obsm['X_[basis]']">
                    <expand macro="sanitize_query" />
                </param>
                <param argument="groupby" type="text" optional="true" value="" label="Key for categorical observation/cell annotation for which densities are calculated per category." >
                    <expand macro="sanitize_query" />
                </param>
                <param argument="key_added" type="text" optional="true" value="" label="Name of the .obs covariate that will be added with the density estimates.">
                    <expand macro="sanitize_query" />
                </param>
            </when>
        </conditional>
        <expand macro="inputs_common_advanced"/>
    </inputs>
    <outputs>
        <expand macro="anndata_outputs"/>
    </outputs>
    <tests>
        <test expect_num_outputs="2">
            <!-- test 1 -->
            <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.louvain"/>
                <conditional name="flavor">
                    <param name="flavor" value="vtraag"/>

                    <has_text_matching expression="use_weights=False"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.louvain.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 2 -->
            <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.leiden"/>
                <param name="random_state" value="1"/>
                <param name="random_state" value="10"/>

                    <has_text_matching expression="n_iterations=-1"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.leiden.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 3 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.pca"/>
                <param name="n_comps" value="50"/>
                <param name="dtype" value="float32"/>

                    <has_text_matching expression="use_highly_variable=False"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="pp.pca.krumsiek11.h5ad" ftype="h5ad" compare="sim_size" delta="100000" delta_frac="0.15"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 4 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.pca"/>
                <param name="n_comps" value="20"/>
                <param name="dtype" value="float32"/>

                    <param name="chunked" value="True"/>
                    <param name="chunk_size" value="50"/>
                </conditional>
                <param name="use_highly_variable" value="false"/>
            </conditional>
            <section name="advanced_common">
                <param name="show_log" value="true" />
            </section>
            <output name="hidden_output">
                <assert_contents>
                    <has_text_matching expression="sc.pp.pca"/>
                    <has_text_matching expression="data=adata"/>
                    <has_text_matching expression="dtype='float32'"/>
                    <has_text_matching expression="copy=False"/>
                    <has_text_matching expression="chunked=True"/>
                    <has_text_matching expression="chunk_size=50"/>
                    <has_text_matching expression="use_highly_variable=False"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="pp.pca.krumsiek11_chunk.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 5 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.pca"/>
                <param name="n_comps" value="50"/>
                <param name="dtype" value="float32"/>

                    <has_text_matching expression="use_highly_variable=False"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.pca.krumsiek11.h5ad" ftype="h5ad" compare="sim_size" delta="100000" delta_frac="0.15"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 6 -->
            <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.diffmap"/>
                <param name="n_comps" value="15"/>
            </conditional>

                    <has_text_matching expression="sc.tl.diffmap"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 7 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.tsne"/>
                <param name="n_pcs" value="10"/>
                <param name="perplexity" value="30"/>

                    <has_text_matching expression="use_fast_tsne=True"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.tsne.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 8 -->
            <param name="adata" value="pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.umap"/>
                <param name="min_dist" value="0.5"/>
                <param name="spread" value="1.0"/>

                <assert_contents>
                    <has_h5_keys keys="X, obs, obsm, uns, var" />
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="2">
            <!-- test 9 -->
            <param name="adata" value="pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad"/>
            <conditional name="method">
                <param name="method" value="tl.draw_graph"/>
                <param name="layout" value="fa"/>
                <param name="random_state" value="0"/>

                    <has_text_matching expression="random_state=0"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.draw_graph.pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 10 -->
            <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad"/>
            <conditional name="method">
                <param name="method" value="tl.paga"/>
                <param name="groups" value="paul15_clusters"/>
                <param name="use_rna_velocity" value="False"/>

                    <has_text_matching expression="model='v1.2'"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.paga.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 11 -->
            <param name="adata" value="tl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.dpt"/>
                <param name="n_dcs" value="15"/>
                <param name="n_branchings" value="1"/>

                    <has_text_matching expression="allow_kendall_tau_shift=True"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 12 -->
            <param name="adata" value="tl.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.embedding_density"/>
                <param name="basis" value="umap"/>
                <param name="key_added" value="umap_density"/>
            </conditional>
            <section name="advanced_common">
                <param name="show_log" value="true" />
            </section>
            <output name="hidden_output">
                <assert_contents>
                    <has_text_matching expression="sc.tl.embedding_density"/>
                    <has_text_matching expression="basis='umap'"/>
                    <has_text_matching expression="key_added='umap_density'"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.embedding_density.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
    </tests>
    <help><![CDATA[
Cluster cells into subgroups (`tl.louvain`)
===========================================

analysis by Levine et al, 2015.

This requires to run `pp.neighbors`, first.

More details on the `tl.louvain scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.louvain.html>`_

Cluster cells into subgroups (`tl.leiden`)
==========================================

Cluster cells using the Leiden algorithm (Traag et al, 2018), an improved version of the Louvain algorithm (Blondel et al, 2008).

The Louvain algorithm has been proposed for single-cell analysis by Levine et al, 2015.

More details on the `tl.leiden scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.leiden.html>`_

Computes PCA (principal component analysis) coordinates, loadings and variance decomposition, using `pp.pca`
============================================================================================================

@CMD_pca_outputs@

More details on the `pp.pca scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.pp.pca.html>`__

Computes PCA (principal component analysis) coordinates, loadings and variance decomposition, using `tl.pca`
============================================================================================================

@CMD_pca_outputs@

More details on the `tl.pca scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.pca.html>`__

Diffusion Maps, using `tl.diffmap`
==================================

Diffusion maps (Coifman et al  2005) has been proposed for visualizing single-cell

using a Gaussian kernel, use `method=='gauss'` in
`pp.neighbors`. To use an exponential kernel, use the default
`method=='umap'`. Differences between these options shouldn't usually be
dramatic.

The diffusion map representation of data are added to the return AnnData in the multi-dimensional
observations annotation (obsm). It is the right eigen basis of the transition matrix with eigenvectors
as colum. It can be accessed using the inspect tool for AnnData

More details on the `tl.diffmap scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.diffmap.html>`__

t-distributed stochastic neighborhood embedding (tSNE), using `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).

It returns `X_tsne`, tSNE coordinates of data.

More details on the `tl.tsne scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.tsne.html>`__

Embed the neighborhood graph using UMAP, using `tl.umap`
========================================================

UMAP (Uniform Manifold Approximation and Projection) is a manifold learning

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>`__.

The UMAP coordinates of data are added to the return AnnData in the multi-dimensional
observations annotation (obsm). This data is accessible using the inspect tool for AnnData

More details on the `tl.umap scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.umap.html>`__

Force-directed graph drawing, using `tl.draw_graph`
===================================================

Force-directed graph drawing describes a class of long-established algorithms for visualizing graphs.
It has been suggested for visualizing single-cell data by Islam et al, 11.
Many other layouts as implemented in igraph are available. Similar approaches have been used by
Zunder et al, 2015 or Weinreb et al, 2016.

This is an alternative to tSNE that often preserves the topology of the data better.
This requires to run `pp.neighbors`, first.

The default layout (ForceAtlas2) uses the package fa2.

The coordinates of graph layout are added to the return AnnData in the multi-dimensional
observations annotation (obsm). This data is accessible using the inspect tool for AnnData.

More details on the `tl.draw_graph scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.draw_graph.html>`__

Infer progression of cells through geodesic distance along the graph (`tl.dpt`)
===============================================================================

Reconstruct the progression of a biological process from snapshot

version, which is able to deal with disconnected graphs (Wolf et al, 2017) and can
be run in a `hierarchical` mode by setting the parameter
`n_branchings>1`. We recommend, however, to only use
`tl.dpt` for computing pseudotime (`n_branchings=0`) and
to detect branchings via `paga`. For pseudotime, you need
to annotate your data with a root cell.

This requires to run `pp.neighbors`, first. In order to
reproduce the original implementation of DPT, use `method=='gauss'` in
this. Using the default `method=='umap'` only leads to minor quantitative
differences, though.

- dpt_groups : Array of dim (number of samples) that stores the subgroup id ('0','1', ...) for each cell. The groups  typically correspond to 'progenitor cells', 'undecided cells' or 'branches' of a process.

The tool is similar to the R package `destiny` of Angerer et al (2016).

More details on the `tl.dpt scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.dpt.html>`_


Generate cellular maps of differentiation manifolds with complex topologies (`tl.paga`)
=======================================================================================

- Adjacency matrix of the tree-like subgraph that best explains the topology (connectivities_tree)

These datasets are stored in the unstructured annotation (uns) and can be accessed using the inspect tool for AnnData objects

More details on the `tl.paga scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/stable/api/scanpy.tl.paga.html>`_
    ]]></help>
    <expand macro="citations"/>
</tool>