Mercurial > repos > iuc > mudata_import_export
changeset 0:089a6101d5d9 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/muon/ commit bcf2ec32c3d13b29da55e0e638da7ddd7162c436
| author | iuc |
|---|---|
| date | Wed, 05 Feb 2025 10:53:15 +0000 |
| parents | |
| children | 47645ab08727 |
| files | macros.xml mudata_import_export.xml |
| diffstat | 2 files changed, 408 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Wed Feb 05 10:53:15 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="'" /> + </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/mudata_import_export.xml Wed Feb 05 10:53:15 2025 +0000 @@ -0,0 +1,144 @@ +<tool id="mudata_import_export" name="MuData import and export" 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[ +@CMD@ + ]]></command> + <configfiles> + <configfile name="script_file"><![CDATA[ +@CMD_imports@ +#if $operation.mode == 'import' +import anndata as ad + +mdata = mu.MuData({ + #for $modality in $operation.modalities + '$modality.name': ad.read_h5ad('$modality.anndata'), + #end for + }) + #if $make_unique +mdata.var_names_make_unique() + #end if +mdata.write_h5mu('mudata.h5mu') + +#else if $operation.mode == 'export' +mdata = mu.read_h5mu('$operation.mudata_in') +for mod in mdata.mod: + mdata[mod].write_h5ad(mod + '.h5ad') + +#end if + +]]></configfile> + </configfiles> + <inputs> + <conditional name="operation"> + <param name="mode" type="select" label="Mode of operation"> + <option value="import" selected="true">Import multiple Anndata objects into a MuData object</option> + <option value="export">Export Anndata objects from a MuData objects</option> + </param> + <when value="import"> + <repeat name="modalities" title="Modalities" min="2" default="2"> + <param name="name" type="text" label="Modality name" value="" + help="Name to give for the modality in the MuData object"> + <expand macro="sanitize_string" /> + </param> + <param name="anndata" type="data" format="h5ad" label="Anndata object for the modality"/> + </repeat> + <param name="make_unique" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Make variable names unique?"/> + </when> + <when value="export"> + <param name="mudata_in" type="data" format="h5ad" label="Multimodal MuData object"/> + </when> + </conditional> + <expand macro="inputs_common_advanced" /> + </inputs> + <outputs> + <data name="mudata_out" format="h5ad" from_work_dir="mudata.h5mu" label="MuData object built from ${on_string}"> + <filter>operation['mode'] == 'import' </filter> + </data> + <collection name="collection_anndata" type="list" label="Anndata objects extracted from ${on_string}"> + <discover_datasets pattern="(?P<designation>.*).h5ad" format="h5ad"/> + <filter>operation['mode'] == 'export' </filter> + </collection> + <expand macro="outputs_common_advanced"/> + </outputs> + <tests> + <test expect_num_outputs="2"> + <!--Import test for RNA and ATAC modalities--> + <conditional name="operation"> + <param name="mode" value="import"/> + <repeat name="modalities"> + <param name="name" value="RNA"/> + <param name="anndata" location="https://zenodo.org/records/12570984/files/rna.h5ad"/> + </repeat> + <repeat name="modalities"> + <param name="name" value="ATAC"/> + <param name="anndata" location="https://zenodo.org/records/12570984/files/atac.h5ad"/> + </repeat> + <param name="make_unique" value="True"/> + </conditional> + <section name="advanced_common"> + <param name="show_log" value="true" /> + </section> + <output name="hidden_output"> + <assert_contents> + <has_text_matching expression="mu.MuData"/> + <has_text_matching expression="'RNA': ad.read"/> + <has_text_matching expression="'ATAC': ad.read"/> + <has_text_matching expression="var_names_make_unique()"/> + </assert_contents> + </output> + <output name="mudata_out" ftype="h5ad"> + <assert_contents> + <has_h5_keys keys="mod/RNA"/> + <has_h5_keys keys="mod/ATAC"/> + <has_h5_keys keys="var/feature_types"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="2"> + <!--Export test for RNA and ATAC modalities--> + <conditional name="operation"> + <param name="mode" value="export"/> + <param name="mudata_in" location="https://zenodo.org/records/12570984/files/rna_atac.h5mu"/> + </conditional> + <section name="advanced_common"> + <param name="show_log" value="true" /> + </section> + <output name="hidden_output"> + <assert_contents> + <has_text_matching expression="mu.read_h5mu"/> + <has_text_matching expression="write_h5ad"/> + </assert_contents> + </output> + <output_collection name="collection_anndata" type="list" count="2"> + <element name="ATAC" ftype="h5ad"> + <assert_contents> + <has_h5_keys keys="var/gene_ids"/> + <has_h5_keys keys="uns/neighbors"/> + <has_h5_keys keys="obsp/connectivities"/> + </assert_contents> + </element> + <element name="RNA" ftype="h5ad"> + <assert_contents> + <has_h5_keys keys="var/gene_ids"/> + <has_h5_keys keys="uns/neighbors"/> + <has_h5_keys keys="obsp/connectivities"/> + </assert_contents> + </element> + </output_collection> + </test> + </tests> + <help><![CDATA[ + **What it does** + Create MuData from AnnData is a tool that allows creating a muon.MuData object out of two or more AnnData objects + for multimodal analysis. The multimodal data is created by combining AnnData objects as + h5ad files into a MuData object as a h5mu file using muon. + Furthermore, it runs pp.intersect_obs to keep only entries present in both modalities (AnnData objects) in the + final MuData file. + ]]></help> + <expand macro="citations"/> +</tool> \ No newline at end of file