changeset 0:36f2cd69d20e draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/muon/ commit bcf2ec32c3d13b29da55e0e638da7ddd7162c436
author iuc
date Wed, 05 Feb 2025 10:53:37 +0000
parents
children 49bee59efec0
files macros.xml plot_muon.xml
diffstat 2 files changed, 535 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml	Wed Feb 05 10:53:37 2025 +0000
@@ -0,0 +1,264 @@
+<macros>
+    <token name="@TOOL_VERSION@">0.1.6</token>
+    <token name="@VERSION_SUFFIX@">0</token>
+    <token name="@PROFILE@">23.0</token>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="@TOOL_VERSION@">muon</requirement>
+            <requirement type="package" version="0.10.2">leidenalg</requirement>
+            <requirement type="package" version="0.8.2">louvain</requirement>
+            <requirement type="package" version="0.7.2">mofapy2</requirement>
+        </requirements>
+    </xml>
+    <xml name="bio_tools">
+        <xrefs>
+            <xref type="bio.tools">muon</xref>
+        </xrefs>
+    </xml>
+    <xml name="creators">
+        <creator>
+            <organization name="European Galaxy Team" url="https://galaxyproject.org/eu/" />
+        </creator>
+    </xml>
+    <xml name="citations">
+        <citations>
+            <citation type="doi">10.1186/s13059-021-02577-8</citation>
+        </citations>
+    </xml>
+    <xml name="sanitize_query">
+        <sanitizer>
+            <valid initial="string.printable">
+                <remove value="&apos;" />
+            </valid>
+       </sanitizer>
+    </xml>
+    <xml name="sanitize_string">
+        <sanitizer>
+            <valid initial="string.letters,string.digits"><add value="_" /></valid>
+        </sanitizer>
+    </xml>
+    <xml name="version_command">
+        <version_command><![CDATA[python -c "import muon as mu;print('Muon version: %s' % mu.__version__)"]]></version_command>
+    </xml>
+
+    <token name="@CMD_imports@"><![CDATA[
+import mudata as md
+import muon as mu
+import scanpy as sc
+import os
+            ]]>
+    </token>
+    <xml name="inputs_mudata">
+        <param name="mdata" type="data" format="h5ad" label="MuData input file"/>
+    </xml>
+    <token name="@CMD_read_inputs@"><![CDATA[
+mdata = md.read('mudata.h5mu')
+        ]]>
+    </token>
+    <token name="@CMD_prettify_stdout@"><![CDATA[ | sed -r '1 s|MuData object with (.+) = (.*)\s*|\1: \2|g' | sed "s|'||g"  | sed -r 's|^\s*(.*):\s(.*)|[\1]\n-    \2|g' | sed 's|, |\n-    |g'
+    ]]></token>
+    <token name="@COPY_MUDATA@"><![CDATA[
+cp '$mdata' 'mudata.h5mu' &&
+    ]]>
+    </token>
+
+    <token name="@CMD@"><![CDATA[
+cat '$script_file' > '$hidden_output' &&
+python '$script_file' >> '$hidden_output' &&
+touch 'mudata_info.txt' &&
+cat 'mudata_info.txt' @CMD_prettify_stdout@
+    ]]>
+    </token>
+
+    <token name="@CMD_params_clustering@"><![CDATA[
+    #if $method.res.type == 'same'
+        #if str($method.res.resolution)
+    resolution=$method.res.resolution,
+        #end if
+    #else if $method.res.type == 'separate'
+    resolution={
+        #for $modality in $method.res.modalities
+        '$modality.mod_name': $modality.resolution,
+        #end for
+    },
+    #end if
+    #if $method.weights.type == 'same'
+        #if str($method.weights.mod_weights)
+    mod_weights=$method.weights.mod_weights,
+        #end if
+    #else if $method.weights.type == 'separate'
+    mod_weights={
+        #for $modality in $method.weights.modalities
+        '$modality.mod_name': $modality.mod_weights,
+        #end for
+    },
+    #end if
+    random_state=$method.random_state,
+    key_added='$method.key_added',
+    #if $method.neighbors_key
+    neighbors_key='$method.neighbors_key',
+    #end if
+    directed=$method.directed
+    ]]></token>
+
+    <token name="@CMD_neighbor_keys@"><![CDATA[
+    #if $method.n_keys.type == 'same'
+    neighbor_keys='$method.n_keys.neighbor_keys',
+    #else if $method.n_keys.type == 'separate'
+    neighbor_keys={
+        #for $modality in $method.n_keys.modalities
+        '$modality.mod_name': '$modality.neighbor_keys',
+        #end for
+    },
+    #end if
+    ]]></token>
+    <token name="@CMD_params_embedding@"><![CDATA[
+    #if $method.color
+    #set $color = ([x.strip() for x in str($method.color).split(',')])
+    color=$color,
+    #end if
+    use_raw=$method.use_raw,
+    #if $method.layer
+    layer='$method.layer',
+    #end if
+    ]]></token>
+
+    <xml name="inputs_common_advanced">
+        <section name="advanced_common" title="Advanced Options" expanded="false">
+            <param name="show_log" type="boolean" checked="false" label="Output Log?" />
+        </section>
+    </xml>
+    <xml name="outputs_common_advanced">
+        <data name="hidden_output" format="txt" label="Log file" >
+            <filter>advanced_common['show_log']</filter>
+        </data>
+    </xml>
+    <xml name="muon_outputs">
+        <data name="mudata_out" format="h5ad" from_work_dir="mudata.h5mu" label="${tool.name} (${method.method}) on ${on_string}: MuData"/>
+        <expand macro="outputs_common_advanced"/>
+    </xml>
+    <token name="@CMD_mudata_write_outputs@"><![CDATA[
+mdata.write('mudata.h5mu')
+with open('mudata_info.txt','w', encoding='utf-8') as ainfo:
+    print(mdata, file=ainfo)
+        ]]>
+    </token>
+
+    <xml name="param_neighbor_keys">
+        <conditional name="n_keys">
+            <param name="type" type="select" label="Same or separate neighborhood information for each modality?">
+                <option value="same">Same neighborhood key for all modalities</option>
+                <option value="separate">Separate neighborhood keys per modality</option>
+            </param>
+            <when value="same">
+                <param argument="neighbor_keys" type="text" value="neighbors" label="Keys in .uns where per-modality neighborhood information is stored"/>
+            </when>
+            <when value="separate">
+                <repeat name="modalities" title="Modalities" min="2" default="2">
+                    <param name="mod_name" type="text" label="Modality name" optional="true">
+                        <expand macro="sanitize_string" />
+                    </param>
+                    <param argument="neighbor_keys" type="text" value="neighbors" label="Keys in .uns where neighborhood information is stored"/>
+                </repeat>
+            </when>
+        </conditional>
+    </xml>
+    <xml name="param_resolution">
+        <conditional name="res">
+            <param name="type" type="select" label="Same or separate resolutions for each modality?">
+                <option value="same">Same resolution for all modalities</option>
+                <option value="separate">Separate resolutions per modality</option>
+            </param>
+            <when value="same">
+                <param argument="resolution" type="float" optional="true" label="Coarseness of the clustering" help="Higher values -> more clusters"/>
+            </when>
+            <when value="separate">
+                <repeat name="modalities" title="Modalities" min="2" default="2">
+                    <param name="mod_name" type="text" label="Modality name" optional="true">
+                        <expand macro="sanitize_string" />
+                    </param>
+                    <param name="resolution" type="float" label="Resolution for the above modality" help="Higher values -> more clusters"/>
+                </repeat>
+            </when>
+        </conditional>
+    </xml>
+    <xml name="param_weight">
+        <conditional name="weights">
+            <param name="type" type="select" label="Same or separate weights for each modality?">
+                <option value="same">Same weight for all modalities</option>
+                <option value="separate">Separate weight per modality</option>
+            </param>
+            <when value="same">
+                <param argument="mod_weights" type="float" optional="true" label="Weight each modality controlling its contribution" help="Higher values -> more important"/>
+            </when>
+            <when value="separate">
+                <repeat name="modalities" title="Modalities" min="2" default="2">
+                    <param name="mod_name" type="text" label="Modality name" optional="true">
+                        <expand macro="sanitize_string" />
+                    </param>
+                    <param name="mod_weights" type="float" label="Weight for the above modality" help="Higher values -> more important"/>
+                </repeat>
+            </when>
+        </conditional>
+    </xml>
+    <xml name="param_random_state" tokens="seed">
+        <param argument="random_state" type="integer" value="@SEED@" optional="true" label="Random seed for the optimization"/>
+    </xml>
+    <xml name="param_key_added" tokens="key_added">
+        <param argument="key_added" type="text" value="@KEY_ADDED@" label="mdata.obs key where cluster labels to be added">
+            <expand macro="sanitize_string" />
+        </param>
+    </xml>
+    <xml name="param_neighbors_key">
+        <param argument="neighbors_key" type="text" optional="true" label="Use neighbors connectivities as adjacency"
+        help="If not specified, look for .obsp['connectivities'] in each modality.
+        If specified, look for .obsp[.uns[neighbors_key]['connectivities_key']] in each modality for connectivities.">
+            <expand macro="sanitize_string" />
+        </param>
+    </xml>
+    <xml name="param_directed">
+        <param argument="directed" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Treat the graph as directed"/>
+    </xml>
+    <xml name="param_key_added_common">
+        <param argument="key_added" type="text" optional="true" label="Key to be added to store neighbors, distances and connectivities data"
+            help="If not specified, the multimodal neighbors data is stored in .uns['neighbors'], distances and connectivities are stored in .obsp['distances'] and .obsp['connectivities'], respectively.
+            If specified, the neighbors data is added to .uns[key_added], distances are stored in .obsp[key_added + '_distances'] and connectivities in .obsp[key_added + '_connectivities'].">
+            <expand macro="sanitize_string" />
+        </param>
+    </xml>
+    <xml name="param_eps" tokens="eps_value">
+        <param argument="eps" type="float" value="@EPS_VALUE@" label="Small number to avoid numerical errors"/>
+    </xml>
+    <xml name="param_use_raw" tokens="label,checked">
+        <param argument="use_raw" type="boolean" truevalue="True" falsevalue="False" checked="@CHECKED@" label="@LABEL@" />
+    </xml>
+    <xml name="param_keys">
+        <conditional name="key_variables">
+            <param name="type" type="select" label="Keys to plot">
+                <option value="var_names">All variables in '.var_names'</option>
+                <option value="obs">All fields in '.obs'</option>
+                <option value="custom">Subset of variables in 'adata.var_names' or fields of '.obs'</option>
+            </param>
+            <when value="var_names"/>
+            <when value="obs"/>
+            <when value="custom">
+                <param argument="keys" type="text" value="" label="Keys to plot" help="One or a list of comma-separated index or key from '.var_names' or fields of '.obs'">
+                    <expand macro="sanitize_query" />
+                </param>
+            </when>
+        </conditional>
+    </xml>
+    <xml name="param_color">
+        <param argument="color" type="text" optional="true" label="Keys for variables or annotations of observations (.obs columns)" help="Can be from any modality.">
+            <expand macro="sanitize_query" />
+        </param>
+    </xml>
+    <xml name="params_embedding">
+        <expand macro="param_color"/>
+        <expand macro="param_use_raw" label="Use raw slot of AnnData as input values" checked="true"/>
+        <param argument="layer" type="text" optional="true" label="Name of the layer in the modality where a feature (from color) is derived from"
+            help="If a valid layer is provided, this takes precedence over use_raw=True">
+            <expand macro="sanitize_query" />
+        </param>
+    </xml>
+</macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/plot_muon.xml	Wed Feb 05 10:53:37 2025 +0000
@@ -0,0 +1,271 @@
+<tool id="plot_muon" name="muon plot" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="bio_tools"/>
+    <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 $method.method == "pl.embedding"
+plot = mu.pl.embedding(
+    mdata,
+    basis='$method.basis',
+    @CMD_params_embedding@
+    return_fig=True
+)
+plot.savefig("plot.$plot_ext")
+
+#else if $method.method == "pl.histogram"
+plot = mu.pl.histogram(
+    mdata,
+    #if $method.key_variables.type == "var_names"
+        #set $key_list = mdata.var_names
+    #else if $method.key_variables.type == "obs"
+        #set $key_list = mdata.obs.select_dtypes(exclude=['category']).columns
+    #else if $method.key_variables.type == "custom"
+        #set $key_list=([x.strip() for x in str($method.key_variables.keys).split(',')])
+    #end if
+    keys=$key_list,
+    #if $method.groupby
+    groupby='$method.groupby',
+    #end if
+    save='plot.$plot_ext'
+)
+os.rename(os.path.join('figures', 'histogram_plot.$plot_ext'), 'plot.$plot_ext')
+
+#else if $method.method == "pl.mofa"
+plot = mu.pl.mofa(
+    mdata,
+    @CMD_params_embedding@
+    return_fig=True
+)
+plot.savefig("plot.$plot_ext")
+
+#else if $method.method == "pl.mofa_loadings"
+plot = mu.pl.mofa_loadings(
+    mdata,
+    #if $method.factors
+    factors='$method.factors',
+    #end if
+    include_lowest=$method.include_lowest,
+    #if str($method.n_points)
+    n_points=$method.n_points,
+    #end if
+    save='plot.$plot_ext'
+)
+os.rename(os.path.join('figures', 'mofa_loadings_plot.$plot_ext'), 'plot.$plot_ext')
+
+#else if $method.method == "pl.umap"
+plot = mu.pl.umap(
+    mdata,
+    @CMD_params_embedding@
+    return_fig=True
+)
+plot.savefig("plot.$plot_ext")
+
+#end if
+
+]]></configfile>
+    </configfiles>
+    <inputs>
+        <expand macro="inputs_mudata"/>
+        <conditional name="method">
+            <param name="method" type="select" label="Method used for plotting">
+                    <option value="pl.embedding">Scatter: Scatter plot along observations (.obs column), using 'muon.pl.embedding'</option>
+                    <option value="pl.histogram">Histogram: Plot Histogram of Fragment lengths within specified region, using 'muon.pl.histogram'</option>
+                    <option value="pl.mofa">Scatter: Scatter plot in MOFA factor coordinates, using 'muon.pl.mofa'</option>
+                    <option value="pl.mofa_loadings">Ranking: Rank genes according to contributions to MOFA factors, using 'muon.pl.mofa_loadings'</option>
+                    <option value="pl.umap">Scatter: UMAP scatter plot, using 'muon.pl.umap'</option>
+            </param>
+            <when value="pl.embedding">
+                <param argument="basis" type="text" value="X_mofa" label="Name of the obsm basis to use" help="can also be a basis inside any modality, e.g. 'rna:X_pca'">
+                    <expand macro="sanitize_query" />
+                </param>
+                <expand macro="params_embedding"/>
+            </when>
+            <when value="pl.histogram">
+                <expand macro="param_keys"/>
+                <param argument="groupby" type="text" optional="true" label="Column name(s) of .obs slot of the AnnData object according to which the plot is split">
+                    <expand macro="sanitize_query" />
+                </param>
+            </when>
+            <when value="pl.mofa">
+                <expand macro="params_embedding"/>
+            </when>
+            <when value="pl.mofa_loadings">
+                <param argument="factors" type="text" optional="true" label="Comma separated list of factors" help="For example, '1,2,3' means [1, 2, 3], first, second, third factors">
+                    <expand macro="sanitize_query" />
+                </param>
+                <param argument="include_lowest" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Whether to show the variables with both highest and lowest loadings"/>
+                <param argument="n_points" type="integer" optional="true" label="Number of variables to plot for each factor"/>
+            </when>
+            <when value="pl.umap">
+                <expand macro="params_embedding"/>
+            </when>
+        </conditional>
+        <param name="plot_ext" type="select" label="Type of output plot">
+            <option value="png" selected="true">PNG</option>
+            <option value="svg">SVG</option>
+            <option value="pdf">PDF</option>
+        </param>
+        <expand macro="inputs_common_advanced" />
+    </inputs>
+    <outputs>
+        <data name="out_png" format="png" from_work_dir="plot.png" label="PNG plot from ${tool.name} (${method.method}) on ${on_string}">
+            <filter>plot_ext == 'png'</filter>
+        </data>
+        <data name="out_pdf" format="pdf" from_work_dir="plot.pdf" label="PDF plot from ${tool.name} (${method.method}) on ${on_string}">
+            <filter>plot_ext == 'pdf'</filter>
+        </data>
+        <data name="out_svg" format="svg" from_work_dir="plot.svg" label="SVG plot from ${tool.name} (${method.method}) on ${on_string}">
+            <filter>plot_ext == 'svg'</filter>
+        </data>
+        <data name="hidden_output" format="txt" label="Log file" hidden="true" >
+            <filter>advanced_common['show_log']</filter>
+        </data>
+    </outputs>
+    <tests>
+        <test expect_num_outputs="2">
+            <!-- test1: pl.embedding -->
+            <param name="mdata" location="https://zenodo.org/records/12570984/files/tl.mofa.h5mu"/>
+            <param name="method" value="pl.embedding"/>
+            <param name="basis" value="X_mofa"/>
+            <param name="color" value="rna:leiden,atac:leiden"/>
+            <param name="use_raw" value="False"/>
+            <param name="plot_ext" value="pdf"/>
+            <section name="advanced_common">
+                <param name="show_log" value="true" />
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="mu.pl.embedding"/>
+                    <has_text_matching expression="basis='X_mofa'"/>
+                    <has_text_matching expression="color=\['rna:leiden', 'atac:leiden'\]"/>
+                    <has_text_matching expression="use_raw=False"/>
+                </assert_contents>
+            </output>
+            <output name="out_pdf" ftype="pdf" location="https://zenodo.org/records/12570984/files/pl.embedding.pdf" compare="sim_size" delta_frac="0.1"/>
+        </test>
+        <test expect_num_outputs="2">
+            <!-- test2 pl.histogram -->
+            <param name="mdata" location="https://zenodo.org/records/12570984/files/tl.mofa.h5mu"/>
+            <param name="method" value="pl.histogram"/>
+            <conditional name="key_variables">
+                <param name="type" value="custom"/>
+                <param name="keys" value="rna:n_genes_by_counts,rna:total_counts"/>
+            </conditional>
+            <param name="plot_ext" value="png"/>
+            <section name="advanced_common">
+                <param name="show_log" value="true" />
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="mu.pl.histogram"/>
+                    <has_text_matching expression="keys=\['rna:n_genes_by_counts', 'rna:total_counts'\]"/>
+                </assert_contents>
+            </output>
+            <output name="out_png" ftype="png" location="https://zenodo.org/records/12570984/files/pl.histogram.png" compare="image_diff"/>
+        </test>
+        <test expect_num_outputs="2">
+            <!-- test3: pl.mofa -->
+            <param name="mdata" location="https://zenodo.org/records/12570984/files/tl.mofa.h5mu"/>
+            <param name="method" value="pl.mofa"/>
+            <param name="use_raw" value="False"/>
+            <param name="plot_ext" value="svg"/>
+            <section name="advanced_common">
+                <param name="show_log" value="true" />
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="mu.pl.mofa"/>
+                    <has_text_matching expression="use_raw=False"/>
+                </assert_contents>
+            </output>
+            <output name="out_svg" ftype="svg" location="https://zenodo.org/records/12570984/files/pl.mofa.svg" compare="sim_size" delta_frac="0.1"/>
+        </test>
+        <test expect_num_outputs="2">
+            <!-- test4: pl.mofa_loadings -->
+            <param name="mdata" location="https://zenodo.org/records/12570984/files/tl.mofa.h5mu"/>
+            <param name="method" value="pl.mofa_loadings"/>
+            <param name="factors" value="1,2,3"/>
+            <param name="include_lowest" value="True"/>
+            <section name="advanced_common">
+                <param name="show_log" value="true" />
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="mu.pl.mofa_loadings"/>
+                    <has_text_matching expression="factors='1,2,3'"/>
+                    <has_text_matching expression="include_lowest=True"/>
+                </assert_contents>
+            </output>
+            <output name="out_png" ftype="png" location="https://zenodo.org/records/12570984/files/pl.mofa_loadings.png" compare="image_diff"/>
+        </test>
+        <test expect_num_outputs="2">
+            <!-- test5: pl.umap -->
+            <param name="mdata" location="https://zenodo.org/records/12570984/files/tl.umap.h5mu"/>
+            <param name="method" value="pl.umap"/>
+            <param name="use_raw" value="False"/>
+            <section name="advanced_common">
+                <param name="show_log" value="true" />
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="mu.pl.umap"/>
+                    <has_text_matching expression="use_raw=False"/>
+                </assert_contents>
+            </output>
+            <output name="out_png" ftype="png" location="https://zenodo.org/records/12570984/files/pl.umap.png" compare="image_diff"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+Scatter: Scatter plot along observations (.obs column) ('muon.pl.embedding')
+============================================================================
+
+        Produce a scatter plot in the define basis (.obs), which can also be a basis inside any modality.
+
+        More details on the `muon documentation
+        <https://muon.readthedocs.io/en/latest/api/generated/muon.pl.embedding.html#muon.pl.embedding>`__
+
+Scatter: Scatter plot in MOFA factor coordinates ('muon.pl.mofa')
+=================================================================
+
+        Scatter plot in MOFA factors coordinates.
+
+        More details on the `muon documentation
+        <https://muon.readthedocs.io/en/latest/api/generated/muon.pl.mofa.html#muon.pl.mofa>`__
+
+Scatter: UMAP scatter plot ('muon.pl.umap')
+===========================================
+
+        UMAP Scatter plot.
+
+        More details on the `muon documentation
+        <https://muon.readthedocs.io/en/latest/api/generated/muon.pl.umap.html#muon.pl.umap>`__
+
+Histogram: Plot Histogram of Fragment lengths within specified region ('muon.pl.histogram')
+===========================================================================================
+
+        Plot Histogram of Fragment lengths within specified region.
+
+        More details on the `muon documentation
+        <https://muon.readthedocs.io/en/latest/api/generated/muon.pl.histogram.html#muon.pl.histogram>`__
+
+Ranking: Rank genes according to contributions to MOFA factors ('muon.pl.mofa_loadings')
+========================================================================================
+
+        Rank genes according to contributions to MOFA factors.
+
+        More details on the `muon documentation
+        <https://muon.readthedocs.io/en/latest/api/generated/muon.pl.mofa_loadings.html#muon.pl.mofa_loadings>`__
+    ]]></help>
+    <expand macro="citations"/>
+</tool>
\ No newline at end of file