annotate preprocess_muon.xml @ 3:bd31b5d2130a draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/muon/ commit 62edff3d7020d653c5f14c9b8afef809eb0fcc8a

<tool id="preprocess_muon" name="muon filter and  normalize" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <expand macro="version_command"/>
    <command detect_errors="exit_code"><![CDATA[
@COPY_MUDATA@
@CMD@
    ]]></command>
    <configfiles>
        <configfile name="script_file"><![CDATA[
@CMD_imports@
@CMD_read_inputs@

#if $method.method == 'pp.intersect_obs'
mu.pp.intersect_obs(
    mdata
)
## Update the features. Only union features of the modalities are considered
mdata.update_var()


#else if $method.method == 'pp.l2norm'
mu.pp.l2norm(
    mdata,
    #if $method.mod
    mod='$method.mod',
    #end if
    #if $method.rep
    rep='$method.rep',
    #end if
    n_pcs=$method.n_pcs,
    copy=False
)

#else if $method.method == 'pp.neighbors'
mu.pp.neighbors(
    mdata,
    #if str($method.n_neighbors)
    n_neighbors=$method.n_neighbors,
    #end if
    n_bandwidth_neighbors=$method.n_bandwidth_neighbors,
    n_multineighbors=$method.n_multineighbors,
    @CMD_neighbor_keys@
    metric='$method.metric',
    #if $method.key_added
    key_added='$method.key_added',
    #end if
    weight_key='$method.weight_key',
    add_weights_to_modalities=$method.add_weights_to_modalities,
    eps=$method.eps,
    random_state=$method.random_state,
    copy=False
)

#else if $method.method == 'pp.sample_obs'
mu.pp.sample_obs(
    mdata,
    frac=$method.frac,
    #if $method.groupby
    groupby='$method.groupby',
    #end if
    #if str($method.min_n)
    min_n=$method.min_n
    #end if
)
#end if

@CMD_mudata_write_outputs@
]]></configfile>
    </configfiles>
    <inputs>
        <expand macro="inputs_mudata"/>
        <conditional name="method">
            <param name="method" type="select" label="Method used for plotting">
                    <option value="pp.intersect_obs">Subset: Subset observations present only in all modalities, using 'muon.pp.intersect_obs'</option>
                    <option value="pp.l2norm">Normalize: Normalize observations to unit L2 norm, using 'muon.pp.l2norm'</option>
                    <option value="pp.neighbors">Search: Multimodal nearest neighbor search, using 'muon.pp.neighbors'</option>
                    <option value="pp.sample_obs">Return an object with some of the observations (subsampling). 'muon.pp.sample_obs'</option>
            </param>
            <when value="pp.intersect_obs"/>
            <when value="pp.l2norm">
                <param argument="mod" type="text" optional="true" label="Names of the modalities to normalize" help="Leave empty to use all modalities">
                    <expand macro="sanitize_string" />
                </param>
                <param argument="rep" type="text" optional="true" label="The representation to normalize." help="X or any key for .obsm is valid, for all modalities">
                    <expand macro="sanitize_query" />
                </param>
                <param argument="n_pcs" type="integer" min="0" value="0" label="The number of principal components to use." help="This affects the result only if a PCA representation is being normalized"/>
            </when>
            <when value="pp.neighbors">
                <param argument="n_neighbors" type="integer" optional="true" label="Number of nearest neighbors to find"
                    help="If not set, arithmetic mean of per-modality neighbors will be used"/>
                <param argument="n_bandwidth_neighbors" type="integer" value="20" label="Number of nearest neighbors to use for bandwidth selection"/>
                <param argument="n_multineighbors" type="integer" value="200" label="Number of nearest neighbors in each modality to consider as candidates for multimodal nearest neighbors"
                    help="Only points in the union of per-modality nearest neighbors are candidates for multimodal nearest neighbors.
                    This will use the same metric that was used for the nearest neighbor search in the respective modality."/>
                <expand macro="param_neighbor_keys"/>
                <param argument="metric" type="select" label="Distance measure to use" help="This will only be used in the final step to search for nearest neighbors in the set of candidates.">
                    <option value="euclidean" selected="true">euclidean</option>
                    <option value="braycurtis">braycurtis</option>
                    <option value="canberra">canberra</option>
                    <option value="chebyshev">chebyshev</option>
                    <option value="cityblock">cityblock</option>
                    <option value="correlation">correlation</option>
                    <option value="cosine">cosine</option>
                    <option value="dice">dice</option>
                    <option value="hamming">hamming</option>
                    <option value="jaccard">jaccard</option>
                    <option value="jensenshannon">jensenshannon</option>
                    <option value="kulsinski">kulsinski</option>
                    <option value="mahalanobis">mahalanobis</option>
                    <option value="matching">matching</option>
                    <option value="minkowski">minkowski</option>
                    <option value="rogerstanimoto">rogerstanimoto</option>
                    <option value="russellrao">russellrao</option>
                    <option value="seuclidean">seuclidean</option>
                    <option value="sokalmichener">sokalmichener</option>
                    <option value="sokalsneath">sokalsneath</option>
                    <option value="sqeuclidean">sqeuclidean</option>
                    <option value="wminkowski">wminkowski</option>
                    <option value="yule">yule</option>
                </param>
                <expand macro="param_key_added_common"/>
                <param argument="weight_key" type="text" value="mod_weight" label="Weight key to add to each modality’s .obs or to mdata.obs">
                    <expand macro="sanitize_query" />
                </param>
                <param argument="add_weights_to_modalities" type="boolean" truevalue="True" falsevalue="False" checked="false" label="If to add weights to individual modalities" help="By default, the weights will be added to mdata.obs"/>
                <expand macro="param_eps" eps_value="0.0001"/>
                <expand macro="param_random_state" seed="42"/>
            </when>
            <when value="pp.sample_obs">
                <param argument="frac" type="float" min="0" max="1" value="0.1" label="A fraction of observations to return"/>
                <param argument="groupby" type="text" optional="true" label="Categorical column in .obs that is used for prior grouping before sampling observations">
                    <expand macro="sanitize_query"/>
                </param>
                <param argument="min_n" type="integer" min="0" optional="true" label="Return min_n observations if fraction frac of observations is below min_n"
                    help="When groupby is not None, min_n is applied per group."/>
            </when>
        </conditional>
        <expand macro="inputs_common_advanced" />
    </inputs>
    <outputs>
        <expand macro="muon_outputs"/>
    </outputs>
    <tests>
        <test expect_num_outputs="2">
            <!-- test1: intersect_obs -->
            <param name="mdata" ftype="h5ad" location="https://zenodo.org/records/12570984/files/pbmc3k_chr21.h5mu"/>
            <param name="method" value="pp.intersect_obs"/>
            <section name="advanced_common">
                <param name="show_log" value="true" />
            </section>
            <output name="hidden_output">
                <assert_contents>
                    <has_text_matching expression="mu.pp.intersect_obs"/>
                </assert_contents>
            </output>
            <assert_stdout>
                <has_text_matching expression="179 × 490"/>
                <has_text_matching expression="179 x 178"/>
                <has_text_matching expression="179 x 312"/>
            </assert_stdout>
            <output name="mudata_out" ftype="h5ad">
                <assert_contents>
                    <has_h5_keys keys="mod/rna"/>
                    <has_h5_keys keys="mod/atac"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="2">
            <!-- test2: l2norm -->
            <param name="mdata" ftype="h5ad" location="https://zenodo.org/records/12570984/files/pbmc3k_chr21.h5mu"/>
            <param name="method" value="pp.l2norm"/>
            <param name="n_pcs" value="5"/>
            <section name="advanced_common">
                <param name="show_log" value="true" />
            </section>
            <output name="hidden_output">
                <assert_contents>
                    <has_text_matching expression="mu.pp.l2norm"/>
                    <has_text_matching expression="copy=False"/>
                    <has_text_matching expression="n_pcs=5"/>
                </assert_contents>
            </output>
            <assert_stdout>
                <has_text_matching expression="179 × 490"/>
                <has_text_matching expression="179 x 178"/>
                <has_text_matching expression="179 x 312"/>
            </assert_stdout>
            <output name="mudata_out" ftype="h5ad">
                <assert_contents>
                    <has_h5_keys keys="mod/rna"/>
                    <has_h5_keys keys="mod/atac"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="2">
            <!-- test3: neighbors -->
            <param name="mdata" ftype="h5ad" location="https://zenodo.org/records/12570984/files/pbmc3k_chr21_pp.neighbors_in.h5mu"/>
            <param name="method" value="pp.neighbors"/>
            <param name="n_neighbors" value="2"/>
            <param name="n_bandwidth_neighbors" value="3"/>
            <param name="n_multineighbors" value="5"/>
            <conditional name="n_keys">
                <param name="type" value="separate"/>
                <repeat name="modalities">
                    <param name="mod_name" value="rna"/>
                    <param name="neighbor_keys" value="neighbors"/>
                </repeat>
                <repeat name="modalities">
                    <param name="mod_name" value="atac"/>
                    <param name="neighbor_keys" value="neighbors"/>
                </repeat>
            </conditional>
            <section name="advanced_common">
                <param name="show_log" value="true" />
            </section>
            <output name="hidden_output">
                <assert_contents>
                    <has_text_matching expression="mu.pp.neighbors"/>
                    <has_text_matching expression="copy=False"/>
                    <has_text_matching expression="n_neighbors=2"/>
                    <has_text_matching expression="n_bandwidth_neighbors=3"/>
                    <has_text_matching expression="n_multineighbors=5"/>
                    <has_text_matching expression="metric='euclidean'"/>
                    <has_text_matching expression="weight_key='mod_weight'"/>
                    <has_text_matching expression="add_weights_to_modalities=False"/>
                    <has_text_matching expression="eps=0.0001"/>
                    <has_text_matching expression="random_state=42"/>
                </assert_contents>
            </output>
            <assert_stdout>
                <has_text_matching expression="2711 × 1781"/>
                <has_text_matching expression="2711 x 555"/>
                <has_text_matching expression="2711 x 1226"/>
            </assert_stdout>
            <output name="mudata_out" ftype="h5ad">
                <assert_contents>
                    <has_h5_keys keys="mod/rna"/>
                    <has_h5_keys keys="mod/atac"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="2">
            <!-- test4: sample_obs -->
            <param name="mdata" ftype="h5ad" location="https://zenodo.org/records/12570984/files/pbmc3k_chr21.h5mu"/>
            <param name="method" value="pp.sample_obs"/>
            <param name="frac" value="0.5"/>
            <param name="min_n" value="10"/>
            <section name="advanced_common">
                <param name="show_log" value="true" />
            </section>
            <output name="hidden_output">
                <assert_contents>
                    <has_text_matching expression="mu.pp.sample_obs"/>
                    <has_text_matching expression="frac=0.5"/>
                    <has_text_matching expression="min_n=10"/>
                </assert_contents>
            </output>
            <assert_stdout>
                <has_text_matching expression="179 × 490"/>
                <has_text_matching expression="179 x 178"/>
                <has_text_matching expression="179 x 312"/>
            </assert_stdout>
            <output name="mudata_out" ftype="h5ad">
                <assert_contents>
                    <has_h5_keys keys="mod/rna"/>
                    <has_h5_keys keys="mod/atac"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
Filter: Filter observations (samples or cells) in-place using any column in .obs or in .X ('muon.pp.filter_obs')
================================================================================================================

        Filter observations (samples or cells) in-place using any column in .obs or in .X.

        More details on the `muon documentation
        <https://muon.readthedocs.io/en/latest/api/generated/muon.pp.filter_obs.html#muon.pp.filter_obs>`__

Filter: Filter variables (features) ('muon.pp.filter_var')
==========================================================

        Filter variables (features, e.g. genes) in-place using any column in .var or row in .X.

        More details on the `muon documentation
        <https://muon.readthedocs.io/en/latest/api/generated/muon.pp.filter_var.html#muon.pp.filter_var>`__

Subset: Subset observations (samples or cells) in-place taking observations present only in all modalities ('muon.pp.intersect_obs')
====================================================================================================================================

        Subset observations (samples or cells) in-place taking observations present only in all modalities.

        More details on the `muon documentation
        <https://muon.readthedocs.io/en/latest/api/generated/muon.pp.intersect_obs.html#muon.pp.intersect_obs>`__

Normalize: Normalize observations to unit L2 norm ('muon.pp.l2norm')
====================================================================

        Normalize observations to unit L2 norm.

        More details on the `muon documentation
        <https://muon.readthedocs.io/en/latest/api/generated/muon.pp.l2norm.html#muon.pp.l2norm>`__

Search: Multimodal nearest neighbor search ('muon.pp.neighbors')
================================================================

        Multimodal nearest neighbor search by implementing the multimodal nearest neighbor method of Hao et al. and Swanson et al.
        The neighbor search efficiency on this heavily relies on UMAP. In particular, you may want to decrease
        n_multineighbors for large data set to avoid excessive peak memory use. To achieve results as close as possible
        to the Seurat implementation, observations must be normalized to unit L2 norm prior to running per-modality
        nearest-neighbor search.

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

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