comparison inspect.xml @ 12:03ed427eb5e7 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/scanpy/ commit c21958f44b81d740191999fb6015d5ae69538ee0

11:aa01179b0d1d

<tool id="scanpy_inspect" name="Inspect and manipulate" version="@galaxy_version@" profile="@profile@">
    <description> with scanpy</description>
    <expand macro="bio_tools"/>
    <macros>
        <import>macros.xml</import>
        <xml name="score_genes_params">
            <param argument="n_bins" type="integer" value="25" label="Number of expression level bins for sampling" help=""/>
            <param argument="random_state" type="integer" value="0" label="Random seed for sampling" help=""/>

        <xml name="random_state">
            <param argument="random_state" type="integer" value="" optional="true"
                label="The seed of the pseudo random number generator to use when shuffling the data" help=""/>
        </xml>
    </macros>
    <expand macro="requirements"/>
    <expand macro="version_command"/>
    <command detect_errors="exit_code"><![CDATA[
@CMD@
      ]]></command>

#if $method.method == "pp.calculate_qc_metrics"
sc.pp.calculate_qc_metrics(
    adata=adata,
    expr_type='$method.expr_type',
    var_type='$method.var_type',
    #if str($method.qc_vars) != ''
        #set $qc_vars = [str(x.strip()) for x in str($method.qc_vars).split(',')]
    qc_vars=$qc_vars,
    #end if
    #if str($method.percent_top) != ''
        #set $percent_top = [int(x.strip()) for x in str($method.percent_top).split(',')]
        percent_top=$method.percent_top,
    #end if
    inplace=True)

#else if $method.method == "tl.score_genes"
sc.tl.score_genes(

    adata=adata,
    n_neighbors=$method.n_neighbors,
    #if str($method.n_pcs) != ''
    n_pcs=$method.n_pcs,
    #end if
    #if str($method.use_rep) != ''
    use_rep='$method.use_rep',
    #end if
    knn=$method.knn,
    random_state=$method.random_state,
    method='$method.pp_neighbors_method',

#else if $method.method == 'tl.rank_genes_groups'
sc.tl.rank_genes_groups(
    adata=adata,
    groupby='$method.groupby',
    #if str($method.groups) != ''
    #set $group=[x.strip() for x in str($method.groups).split(',')]
    groups=$group,
    #end if
    #if $method.ref.rest == 'rest'
    reference='$method.ref.rest',

            #end if
    fit_intercept=$method.tl_rank_genes_groups_method.solver.intercept_scaling.fit_intercept,
            #if $method.tl_rank_genes_groups_method.solver.intercept_scaling.fit_intercept == 'True'
    intercept_scaling=$method.tl_rank_genes_groups_method.solver.intercept_scaling.intercept_scaling,
            #end if
            #if $method.tl_rank_genes_groups_method.solver.random_state
    random_state=$method.tl_rank_genes_groups_method.solver.random_state,
            #end if
        #else if $method.tl_rank_genes_groups_method.solver.solver == 'sag'
    penalty='l2',
    fit_intercept=$method.tl_rank_genes_groups_method.solver.fit_intercept,
            #if $method.tl_rank_genes_groups_method.solver.random_state
    random_state=$method.tl_rank_genes_groups_method.solver.random_state,
            #end if
    max_iter=$method.tl_rank_genes_groups_method.solver.max_iter,
    multi_class='$method.tl_rank_genes_groups_method.solver.multi_class',
        #else if $method.tl_rank_genes_groups_method.solver.solver == 'saga'

#end for

sc.tl.marker_gene_overlap(
    adata,
    reference_markers,
    #if str($method.key) != ''
    key='$method.key',
    #end if
    method='$method.overlap.method',
    #if $method.overlap.method == 'overlap_count' and str($method.overlap.normalize) != 'None'
    normalize='$method.overlap.normalize',

    top_n_markers=$method.top_n_markers,
    #end if
    #if str($method.adj_pval_threshold) != ''
    adj_pval_threshold=$method.adj_pval_threshold,
    #end if
    #if str($method.key_added) != ''
    key_added='$method.key_added',
    #end if
    inplace=True)

#else if $method.method == "pp.log1p"

#else if $method.method == "pp.scale"
sc.pp.scale(
    adata,
    zero_center=$method.zero_center,
    #if $method.max_value
    max_value=$method.max_value,
    #end if
    copy=False)

#else if $method.method == "pp.sqrt"

                    </when>
                </conditional>
                <param argument="n_genes" type="integer" min="0" value="100" label="The number of genes that appear in the returned tables" help=""/>
                <conditional name="tl_rank_genes_groups_method">
                    <param argument="method" type="select" label="Method">
                        <option value="t-test">t-test</option>
                        <option value="wilcoxon">Wilcoxon-Rank-Sum</option>
                        <option value="t-test_overestim_var" selected="true">t-test with overestimate of variance of each group</option>
                        <option value="logreg">Logistic regression</option>
                    </param>
                    <when value="t-test">
                        <expand macro="corr_method"/>
                    </when>

                        <param argument="c" type="float" value="1.0" label="Inverse of regularization strength"
                            help="It must be a positive float. Like in support vector machines, smaller values specify stronger regularization."/>
                    </when>
                </conditional>
            </when>
            <!--<when value="tl.marker_gene_overlap">
                <repeat name="reference_markers" title="Marker genes">
                    <param name="key" type="text" value="" label="Cell identity name" help=""/>
                    <param name="values" type="text" value="" label="List of genes" help="Comma-separated names from 'var'"/>
                </repeat>
                <param argument="key" type="text" value="rank_genes_groups" label="Key in adata.uns where the rank_genes_groups output is stored"/>

                    <when value="overlap_coef"/>
                    <when value="jaccard"/>
                </conditional>
                <param argument="top_n_markers" type="integer" optional="true" label="Number of top data-derived marker genes to use" help="By default all calculated marker genes are used. If adj_pval_threshold is set along with top_n_markers, then adj_pval_threshold is ignored."/>
                <param argument="adj_pval_threshold" type="float" optional="true" label="Significance threshold on the adjusted p-values to select marker genes" help=" This can only be used when adjusted p-values are calculated by 'tl.rank_genes_groups'. If adj_pval_threshold is set along with top_n_markers, then adj_pval_threshold is ignored."/>
                <param argument="key_added" type="text" value="" optional="true" label="Key that will contain the marker overlap scores in 'uns'"/>
            </when>-->
            <when value="pp.log1p"/>
            <when value="pp.scale">
                <param argument="zero_center" type="boolean" truevalue="True" falsevalue="False" checked="true"
                    label="Zero center?" help="If not, it omits zero-centering variables, which allows to handle sparse input efficiently."/>

    </inputs>
    <outputs>
        <expand macro="anndata_outputs"/>
    </outputs>
    <tests>
        <test>
            <!-- test 0 -->
            <param name="adata" value="sparce_csr_matrix.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.calculate_qc_metrics"/>
                <param name="expr_type" value="counts"/>
                <param name="var_type" value="genes"/>

                    <has_text_matching expression="qc_vars=\['mito', 'negative'\]" />
                </assert_contents>
            </output>
            <output name="anndata_out" file="pp.calculate_qc_metrics.sparce_csr_matrix.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test>
            <!-- test 1 -->
            <param name="adata" value="pp.recipe_weinreb17.paul15_subsample.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.neighbors"/>
                <param name="n_neighbors" value="15"/>
                <param name="knn" value="True"/>

                <assert_contents>
                    <has_h5_keys keys="X, obs, obsm, uns, var" />
                </assert_contents>
            </output>
        </test>
        <test>
            <!-- test 2 -->
            <param name="adata" value="pp.recipe_weinreb17.paul15_subsample.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.neighbors"/>
                <param name="n_neighbors" value="15"/>
                <param name="knn" value="True"/>

                    <has_text_matching expression="metric='braycurtis'"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test>
            <!-- test 3 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.score_genes"/>
                <param name="gene_list" value="Gata2, Fog1"/>
                <param name="ctrl_size" value="2"/>

                    <has_text_matching expression="copy=False" />
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.score_genes.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test>
            <!-- test 4 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.score_genes_cell_cycle"/>
                <conditional name='s_genes'>
                    <param name="format" value="text"/>

                    <has_text_matching expression="use_raw=False"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.score_genes_cell_cycle.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test>
            <!-- test 5 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.rank_genes_groups"/>
                <param name="groupby" value="cell_type"/>
                <param name="use_raw" value="True"/>
                <conditional name="ref">
                    <param name="rest" value="rest"/>
                </conditional>
                <param name="n_genes" value="100"/>
                <conditional name="tl_rank_genes_groups_method">

            </section>
            <output name="hidden_output">
                <assert_contents>
                    <has_text_matching expression="sc.tl.rank_genes_groups"/>
                    <has_text_matching expression="groupby='cell_type'"/>
                    <has_text_matching expression="use_raw=True"/>
                    <has_text_matching expression="reference='rest'"/>
                    <has_text_matching expression="n_genes=100"/>
                    <has_text_matching expression="method='t-test_overestim_var'"/>
                    <has_text_matching expression="corr_method='benjamini-hochberg'"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.rank_genes_groups.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test>
            <!-- test 6 -->
            <param name="adata" value="pbmc68k_reduced.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.rank_genes_groups"/>
                <param name="groupby" value="louvain"/>
                <param name="use_raw" value="True"/>

                <assert_contents>
                    <has_h5_keys keys="X, obs, obsm, raw/X, raw/var, uns, var" />
                </assert_contents>
            </output>
        </test>
        <test>
            <!-- test 7 -->
            <param name="adata" value="pbmc68k_reduced.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.rank_genes_groups"/>
                <param name="groupby" value="louvain"/>
                <param name="use_raw" value="True"/>

                <assert_contents>
                    <has_h5_keys keys="X, obs, obsm, raw/X, raw/var, uns, var" />
                </assert_contents>
            </output>
        </test>
        <!--<test>
            < test 9 >
            <param name="adata" value="tl.rank_genes_groups.louvain.neighbors.pca.pbmc68k_reduced.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.marker_gene_overlap"/>
                <repeat name="reference_markers">
                    <param name="key" value="CD4 T cells"/>
                    <param name="value" value="IL7R"/>

                <repeat name="reference_markers">
                    <param name="key" value="B cells"/>
                    <param name="value" value="MS4A1"/>
                </repeat>
                <conditional name="overlap">
                    <param argument="method" value="overlap_count"/>
                    <param argument="normalize" value="None"/>
                </conditional>
            </conditional>
            <assert_stdout>
                <has_text_matching expression="tl.marker_gene_overlap"/>
                <has_text_matching expression="key='rank_genes_groups'"/>
                <has_text_matching expression="method='overlap_count'"/>
            </assert_stdout>
            <output name="anndata_out" file="pp.log1p.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>-->
        <test>
            <!-- test 8 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.log1p"/>
            </conditional>
            <section name="advanced_common">
                <param name="show_log" value="true" />
            </section>
            <output name="hidden_output">
                <assert_contents>
                    <has_text_matching expression="sc.pp.log1p"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="pp.log1p.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test>
            <!-- test 9 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.scale"/>
                <param name="zero_center" value="true"/>
            </conditional>

                    <has_text_matching expression="zero_center=True"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="pp.scale.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test>
            <!-- test 10 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.scale"/>
                <param name="zero_center" value="true"/>
                <param name="max_value" value="10"/>

                    <has_text_matching expression="max_value=10.0"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="pp.scale_max_value.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test>
            <!-- test 11 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.sqrt"/>
            </conditional>
            <section name="advanced_common">

                <assert_contents>
                    <has_text_matching expression="sc.pp.sqrt"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="pp.sqrt.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
    </tests>
    <help><![CDATA[
Calculate quality control metrics., using `pp.calculate_qc_metrics`
===================================================================

- mean_{expr_type} (e.g. "mean counts", mean expression over all cells)
- n_cells_by_{expr_type} (e.g. "n_cells_by_counts", number of cells this expression is measured in)
- pct_dropout_by_{expr_type} (e.g. "pct_dropout_by_counts", percentage of cells this feature does not appear in)

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

Compute a neighborhood graph of observations, using `pp.neighbors`
==================================================================

The neighbor search efficiency of this heavily relies on UMAP (McInnes et al, 2018),

- Distances for each pair of neighbors (distances)

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

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

Score a set of genes, using `tl.score_genes`
============================================

The score is the average expression of a set of genes subtracted with the

This reproduces the approach in Seurat (Satija et al, 2015) and has been implemented
for Scanpy by Davide Cittaro.

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

Score cell cycle genes, using `tl.score_genes_cell_cycle`
=========================================================

Given two lists of genes associated to S phase and G2M phase, calculates
scores and assigns a cell cycle phase (G1, S or G2M). See
`score_genes` for more explanation.

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

Rank genes for characterizing groups, using `tl.rank_genes_groups`
==================================================================

The returned AnnData object contains:

- Ajusted p-values

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

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


Calculate an overlap score between data-deriven marker genes and provided markers (`tl.marker_gene_overlap`)
============================================================================================================

Logarithmize the data matrix (`pp.log1p`)
=========================================

More details on the `scanpy documentation
<https://icb-scanpy.readthedocs-hosted.com/en/@version@/api/scanpy.pp.log1p.html>`__

Scale data to unit variance and zero mean (`pp.scale`)
======================================================

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

Computes the square root the data matrix (`pp.sqrt`)
====================================================

`X = sqrt(X)`

12:03ed427eb5e7

<tool id="scanpy_inspect" name="Inspect and manipulate" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@profile@">
    <description> with scanpy</description>
    <macros>
        <import>macros.xml</import>
        <xml name="score_genes_params">
            <param argument="n_bins" type="integer" value="25" label="Number of expression level bins for sampling" help=""/>
            <param argument="random_state" type="integer" value="0" label="Random seed for sampling" help=""/>

        <xml name="random_state">
            <param argument="random_state" type="integer" value="" optional="true"
                label="The seed of the pseudo random number generator to use when shuffling the data" help=""/>
        </xml>
    </macros>
    <expand macro="bio_tools"/>
    <expand macro="requirements"/>
    <expand macro="version_command"/>
    <command detect_errors="exit_code"><![CDATA[
@CMD@
      ]]></command>

#if $method.method == "pp.calculate_qc_metrics"
sc.pp.calculate_qc_metrics(
    adata=adata,
    expr_type='$method.expr_type',
    var_type='$method.var_type',
    #if $method.qc_vars
        #set $qc_vars = [str(x.strip()) for x in str($method.qc_vars).split(',')]
    qc_vars=$qc_vars,
    #end if
    #if $method.percent_top
        #set $percent_top = [int(x.strip()) for x in str($method.percent_top).split(',')]
        percent_top=$percent_top,
    #end if
    inplace=True)

#else if $method.method == "tl.score_genes"
sc.tl.score_genes(

    adata=adata,
    n_neighbors=$method.n_neighbors,
    #if str($method.n_pcs) != ''
    n_pcs=$method.n_pcs,
    #end if
    #if $method.use_rep
    use_rep='$method.use_rep',
    #end if
    knn=$method.knn,
    random_state=$method.random_state,
    method='$method.pp_neighbors_method',

#else if $method.method == 'tl.rank_genes_groups'
sc.tl.rank_genes_groups(
    adata=adata,
    groupby='$method.groupby',
    #if $method.groups
    #set $group=[x.strip() for x in str($method.groups).split(',')]
    groups=$group,
    #end if
    #if $method.ref.rest == 'rest'
    reference='$method.ref.rest',

            #end if
    fit_intercept=$method.tl_rank_genes_groups_method.solver.intercept_scaling.fit_intercept,
            #if $method.tl_rank_genes_groups_method.solver.intercept_scaling.fit_intercept == 'True'
    intercept_scaling=$method.tl_rank_genes_groups_method.solver.intercept_scaling.intercept_scaling,
            #end if
            #if str($method.tl_rank_genes_groups_method.solver.random_state) != ''
    random_state=$method.tl_rank_genes_groups_method.solver.random_state,
            #end if
        #else if $method.tl_rank_genes_groups_method.solver.solver == 'sag'
    penalty='l2',
    fit_intercept=$method.tl_rank_genes_groups_method.solver.fit_intercept,
            #if str($method.tl_rank_genes_groups_method.solver.random_state) != ''
    random_state=$method.tl_rank_genes_groups_method.solver.random_state,
            #end if
    max_iter=$method.tl_rank_genes_groups_method.solver.max_iter,
    multi_class='$method.tl_rank_genes_groups_method.solver.multi_class',
        #else if $method.tl_rank_genes_groups_method.solver.solver == 'saga'

#end for

sc.tl.marker_gene_overlap(
    adata,
    reference_markers,
    #if $method.key
    key='$method.key',
    #end if
    method='$method.overlap.method',
    #if $method.overlap.method == 'overlap_count' and str($method.overlap.normalize) != 'None'
    normalize='$method.overlap.normalize',

    top_n_markers=$method.top_n_markers,
    #end if
    #if str($method.adj_pval_threshold) != ''
    adj_pval_threshold=$method.adj_pval_threshold,
    #end if
    #if $method.key_added
    key_added='$method.key_added',
    #end if
    inplace=True)

#else if $method.method == "pp.log1p"

#else if $method.method == "pp.scale"
sc.pp.scale(
    adata,
    zero_center=$method.zero_center,
    #if str($method.max_value) != ''
    max_value=$method.max_value,
    #end if
    copy=False)

#else if $method.method == "pp.sqrt"

                    </when>
                </conditional>
                <param argument="n_genes" type="integer" min="0" value="100" label="The number of genes that appear in the returned tables" help=""/>
                <conditional name="tl_rank_genes_groups_method">
                    <param argument="method" type="select" label="Method">
                        <option value="t-test" selected="true">t-test</option>
                        <option value="wilcoxon">Wilcoxon-Rank-Sum</option>
                        <option value="t-test_overestim_var">t-test with overestimate of variance of each group</option>
                        <option value="logreg">Logistic regression</option>
                    </param>
                    <when value="t-test">
                        <expand macro="corr_method"/>
                    </when>

                        <param argument="c" type="float" value="1.0" label="Inverse of regularization strength"
                            help="It must be a positive float. Like in support vector machines, smaller values specify stronger regularization."/>
                    </when>
                </conditional>
            </when>
            <!-- With inplace=True, NotImplementedError: Writing Pandas dataframes to h5ad is currently under development. Please use `inplace=False`. -->
            <!-- <when value="tl.marker_gene_overlap">
                <repeat name="reference_markers" title="Marker genes">
                    <param name="key" type="text" value="" label="Cell identity name" help=""/>
                    <param name="values" type="text" value="" label="List of genes" help="Comma-separated names from 'var'"/>
                </repeat>
                <param argument="key" type="text" value="rank_genes_groups" label="Key in adata.uns where the rank_genes_groups output is stored"/>

                    <when value="overlap_coef"/>
                    <when value="jaccard"/>
                </conditional>
                <param argument="top_n_markers" type="integer" optional="true" label="Number of top data-derived marker genes to use" help="By default all calculated marker genes are used. If adj_pval_threshold is set along with top_n_markers, then adj_pval_threshold is ignored."/>
                <param argument="adj_pval_threshold" type="float" optional="true" label="Significance threshold on the adjusted p-values to select marker genes" help=" This can only be used when adjusted p-values are calculated by 'tl.rank_genes_groups'. If adj_pval_threshold is set along with top_n_markers, then adj_pval_threshold is ignored."/>
                <param argument="key_added" type="text" value="marker_gene_overlap" optional="true" label="Key that will contain the marker overlap scores in 'uns'"/>
            </when>-->
            <when value="pp.log1p"/>
            <when value="pp.scale">
                <param argument="zero_center" type="boolean" truevalue="True" falsevalue="False" checked="true"
                    label="Zero center?" help="If not, it omits zero-centering variables, which allows to handle sparse input efficiently."/>

    </inputs>
    <outputs>
        <expand macro="anndata_outputs"/>
    </outputs>
    <tests>
        <test expect_num_outputs="2">
            <!-- test 1 -->
            <param name="adata" value="sparce_csr_matrix.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.calculate_qc_metrics"/>
                <param name="expr_type" value="counts"/>
                <param name="var_type" value="genes"/>

                    <has_text_matching expression="qc_vars=\['mito', 'negative'\]" />
                </assert_contents>
            </output>
            <output name="anndata_out" file="pp.calculate_qc_metrics.sparce_csr_matrix.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 2 -->
            <param name="adata" value="pp.recipe_weinreb17.paul15_subsample.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.neighbors"/>
                <param name="n_neighbors" value="15"/>
                <param name="knn" value="True"/>

                <assert_contents>
                    <has_h5_keys keys="X, obs, obsm, uns, var" />
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="2">
            <!-- test 3 -->
            <param name="adata" value="pp.recipe_weinreb17.paul15_subsample.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.neighbors"/>
                <param name="n_neighbors" value="15"/>
                <param name="knn" value="True"/>

                    <has_text_matching expression="metric='braycurtis'"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 4 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.score_genes"/>
                <param name="gene_list" value="Gata2, Fog1"/>
                <param name="ctrl_size" value="2"/>

                    <has_text_matching expression="copy=False" />
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.score_genes.krumsiek11.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.score_genes_cell_cycle"/>
                <conditional name='s_genes'>
                    <param name="format" value="text"/>

                    <has_text_matching expression="use_raw=False"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.score_genes_cell_cycle.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 6 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.rank_genes_groups"/>
                <param name="groupby" value="cell_type"/>
                <param name="use_raw" value="False"/>
                <conditional name="ref">
                    <param name="rest" value="rest"/>
                </conditional>
                <param name="n_genes" value="100"/>
                <conditional name="tl_rank_genes_groups_method">

            </section>
            <output name="hidden_output">
                <assert_contents>
                    <has_text_matching expression="sc.tl.rank_genes_groups"/>
                    <has_text_matching expression="groupby='cell_type'"/>
                    <has_text_matching expression="use_raw=False"/>
                    <has_text_matching expression="reference='rest'"/>
                    <has_text_matching expression="n_genes=100"/>
                    <has_text_matching expression="method='t-test_overestim_var'"/>
                    <has_text_matching expression="corr_method='benjamini-hochberg'"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="tl.rank_genes_groups.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 7 -->
            <param name="adata" value="pbmc68k_reduced.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.rank_genes_groups"/>
                <param name="groupby" value="louvain"/>
                <param name="use_raw" value="True"/>

                <assert_contents>
                    <has_h5_keys keys="X, obs, obsm, raw/X, raw/var, uns, var" />
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="2">
            <!-- test 8 -->
            <param name="adata" value="pbmc68k_reduced.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.rank_genes_groups"/>
                <param name="groupby" value="louvain"/>
                <param name="use_raw" value="True"/>

                <assert_contents>
                    <has_h5_keys keys="X, obs, obsm, raw/X, raw/var, uns, var" />
                </assert_contents>
            </output>
        </test>
        <!-- test expect_num_outputs="2">
            < test 9  tl.marker_gene_overlap function was commented because inpace=True does not work>
            <param name="adata" value="tl.rank_genes_groups.newton-cg.pbmc68k_reduced.h5ad" />
            <conditional name="method">
                <param name="method" value="tl.marker_gene_overlap"/>
                <repeat name="reference_markers">
                    <param name="key" value="CD4 T cells"/>
                    <param name="value" value="IL7R"/>

                <repeat name="reference_markers">
                    <param name="key" value="B cells"/>
                    <param name="value" value="MS4A1"/>
                </repeat>
                <conditional name="overlap">
                    <param name="method" value="overlap_count"/>
                    <param name="normalize" value="None"/>
                </conditional>
            </conditional>
            <assert_stdout>
                <has_text_matching expression="tl.marker_gene_overlap"/>
                <has_text_matching expression="key='rank_genes_groups'"/>
                <has_text_matching expression="method='overlap_count'"/>
            </assert_stdout>
            <output name="anndata_out" file="tl.marker_gene_overlap.pbmc68k_reduced.h5ad" ftype="h5ad" compare="sim_size"/>
        </test> -->
        <test expect_num_outputs="2">
            <!-- test 10 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.log1p"/>
            </conditional>
            <section name="advanced_common">
                <param name="show_log" value="true" />
            </section>
            <output name="hidden_output">
                <assert_contents>
                    <has_text_matching expression="sc.pp.log1p"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="pp.log1p.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 11 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.scale"/>
                <param name="zero_center" value="true"/>
            </conditional>

                    <has_text_matching expression="zero_center=True"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="pp.scale.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 12 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.scale"/>
                <param name="zero_center" value="true"/>
                <param name="max_value" value="10"/>

                    <has_text_matching expression="max_value=10.0"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="pp.scale_max_value.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 13 -->
            <param name="adata" value="krumsiek11.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.sqrt"/>
            </conditional>
            <section name="advanced_common">

                <assert_contents>
                    <has_text_matching expression="sc.pp.sqrt"/>
                </assert_contents>
            </output>
            <output name="anndata_out" file="pp.sqrt.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
        <test expect_num_outputs="2">
            <!-- test 13 -->
            <param name="adata" value="sparce_csr_matrix.h5ad" />
            <conditional name="method">
                <param name="method" value="pp.calculate_qc_metrics"/>
                <param name="expr_type" value="counts"/>
                <param name="var_type" value="genes"/>
                <param name="qc_vars" value="mito,negative"/>
                <param name="percent_top" value="50,100,200,300"/>
            </conditional>
            <section name="advanced_common">
                <param name="show_log" value="true" />
            </section>
            <output name="hidden_output">
                <assert_contents>
                    <has_text_matching expression="sc.pp.calculate_qc_metrics" />
                    <has_text_matching expression="expr_type='counts'" />
                    <has_text_matching expression="var_type='genes'" />
                    <has_text_matching expression="qc_vars=\['mito', 'negative'\]" />
                    <has_text_matching expression="percent_top=\[50, 100, 200, 300\]" />
                </assert_contents>
            </output>
            <output name="anndata_out" file="pp.calculate_qc_metrics.sparce_csr_matrix.h5ad" ftype="h5ad" compare="sim_size"/>
        </test>
    </tests>
    <help><![CDATA[
Calculate quality control metrics., using `pp.calculate_qc_metrics`
===================================================================

- mean_{expr_type} (e.g. "mean counts", mean expression over all cells)
- n_cells_by_{expr_type} (e.g. "n_cells_by_counts", number of cells this expression is measured in)
- pct_dropout_by_{expr_type} (e.g. "pct_dropout_by_counts", percentage of cells this feature does not appear in)

More details on the `scanpy documentation
<https://scanpy.readthedocs.io/en/stable/api/scanpy.pp.calculate_qc_metrics.html>`__

Compute a neighborhood graph of observations, using `pp.neighbors`
==================================================================

The neighbor search efficiency of this heavily relies on UMAP (McInnes et al, 2018),

- Distances for each pair of neighbors (distances)

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

More details on the `scanpy documentation
<https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pp.neighbors.html>`__

Score a set of genes, using `tl.score_genes`
============================================

The score is the average expression of a set of genes subtracted with the

This reproduces the approach in Seurat (Satija et al, 2015) and has been implemented
for Scanpy by Davide Cittaro.

More details on the `scanpy documentation
<https://scanpy.readthedocs.io/en/stable/api/scanpy.tl.score_genes.html>`__

Score cell cycle genes, using `tl.score_genes_cell_cycle`
=========================================================

Given two lists of genes associated to S phase and G2M phase, calculates
scores and assigns a cell cycle phase (G1, S or G2M). See
`score_genes` for more explanation.

More details on the `scanpy documentation
<https://scanpy.readthedocs.io/en/stable/api/scanpy.tl.score_genes_cell_cycle.html>`__

Rank genes for characterizing groups, using `tl.rank_genes_groups`
==================================================================

The returned AnnData object contains:

- Ajusted p-values

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

More details on the `scanpy documentation
<https://scanpy.readthedocs.io/en/stable/api/scanpy.tl.rank_genes_groups.html>`__


Calculate an overlap score between data-deriven marker genes and provided markers (`tl.marker_gene_overlap`)
============================================================================================================

Logarithmize the data matrix (`pp.log1p`)
=========================================

More details on the `scanpy documentation
<https://scanpy.readthedocs.io/en/stable/api/scanpy.pp.log1p.html>`__

Scale data to unit variance and zero mean (`pp.scale`)
======================================================

More details on the `scanpy documentation
<https://scanpy.readthedocs.io/en/stable/api/scanpy.pp.scale.html>`__

Computes the square root the data matrix (`pp.sqrt`)
====================================================

`X = sqrt(X)`