Mercurial > repos > iuc > snapatac2_clustering
changeset 6:d258720d9a42 draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/snapatac2 commit e0f59fae19e57f54ae0c351a16dd1805d12aba1d
| author | iuc |
|---|---|
| date | Tue, 25 Nov 2025 16:40:54 +0000 |
| parents | d3ea0ba3d066 |
| children | |
| files | dimension_reduction_clustering.xml macros.xml test-data/all_fasta.loc test-data/chr21.gff3.gz test-data/chr21_small.fasta.gz test-data/cisBP_human.meme.gz test-data/gene_sets.loc test-data/meme.loc tool-data/all_fasta.loc.sample tool-data/gene_sets.loc.sample tool-data/meme.loc.sample tool_data_table_conf.xml.sample tool_data_table_conf.xml.test |
| diffstat | 13 files changed, 551 insertions(+), 276 deletions(-) [+] |
line wrap: on
line diff
--- a/dimension_reduction_clustering.xml Thu Nov 07 13:07:58 2024 +0000 +++ b/dimension_reduction_clustering.xml Tue Nov 25 16:40:54 2025 +0000 @@ -9,21 +9,49 @@ </requirements> <command detect_errors="exit_code"><![CDATA[ export NUMBA_CACHE_DIR="\${TEMP:-/tmp}"; -@PREP_ADATA@ +#if $method.method == 'tl.multi_spectral' + #for $i in range(len($method.adata)) + cp $method.adata[$i] 'adata_${i}.h5ad' && + #end for +#else + @CMD_PREP_ADATA@ +#end if @CMD@ ]]></command> <configfiles> <configfile name="script_file"><![CDATA[ -@CMD_imports@ -@CMD_read_inputs@ +@CONF_IMPORTS@ +#if $method.method == 'tl.multi_spectral' +## read all files ending with .h5ad in the working directory +import glob +files = sorted(glob.glob('adata_*.h5ad')) + +adata_list = [] +for fn in files: + ad = snap.read(fn, backed=None) + adata_list.append(ad) +#else +@CONF_READ_INPUTS@ +#end if #if $method.method == 'tl.spectral' #if $method.features with open('$method.features') as f: features_mask = [x.lower().capitalize() == "True" for x in f.read().splitlines()] #end if -sa.tl.spectral( + +## somewhere in the SnapATAC2 code, a pandas Series is being passed where a numpy array is expected. +## This is a workaround to add the nonzero method back to pandas Series. +## Add the nonzero method back to pandas Series +import pandas as pd +def series_nonzero(self): + return (self != 0).values.nonzero() + +pd.Series.nonzero = series_nonzero + + +snap.tl.spectral( adata, n_comps = $method.n_comps, #if $method.features @@ -39,8 +67,31 @@ inplace = True ) +#else if $method.method == 'tl.multi_spectral' + #if $method.features +with open('$method.features') as f: + features_mask = [x.lower().capitalize() == "True" for x in f.read().splitlines()] + #end if + +embedding = snap.tl.multi_spectral( + adatas = adata_list, + n_comps = $method.n_comps, + #if $method.features + features = features_mask, + #else + features = None, + #end if + weights = None, # Will enable if requested by users + random_state = $method.random_state, + weighted_by_sd = $method.weighted_by_sd, +) + +adata = adata_list[0].copy() +adata.uns['spectral_eigenvalue_joint'] = embedding[0] +adata.obsm['X_joint'] = embedding[1] + #else if $method.method == 'tl.umap' -sa.tl.umap( +snap.tl.umap( adata, n_comps = $method.n_comps, #if $method.use_dims != '' @@ -54,7 +105,7 @@ ) #else if $method.method == 'pp.knn' -sa.pp.knn( +snap.pp.knn( adata, n_neighbors = $method.n_neighbors, #if $method.use_dims != '' @@ -67,18 +118,43 @@ random_state = $method.random_state ) +#else if $method.method == 'tl.leiden' +snap.tl.leiden( + adata, + resolution = $method.resolution, + objective_function = '$method.objective_function', + min_cluster_size = $method.min_cluster_size, + n_iterations = $method.n_iterations, + random_state = $method.random_state, + key_added = '$method.key_added', + use_leidenalg = $method.use_leidenalg, + weighted = $method.weighted, + inplace = True +) + +#else if $method.method == 'tl.kmeans' +snap.tl.kmeans( + adata, + n_clusters = $method.n_clusters, + n_iterations = $method.n_iterations, + random_state = $method.random_state, + use_rep = '$method.use_rep', + key_added = '$method.key_added' +) + #else if $method.method == 'tl.dbscan' -sa.tl.dbscan( +snap.tl.dbscan( adata, eps = $method.eps, min_samples = $method.min_samples, leaf_size = $method.leaf_size, use_rep = '$method.use_rep', - key_added = '$method.key_added' + key_added = '$method.key_added', + n_jobs = int(os.getenv("GALAXY_SLOTS", 4)) ) #else if $method.method == 'tl.hdbscan' -sa.tl.hdbscan( +snap.tl.hdbscan( adata, min_cluster_size = $method.min_cluster_size, #if $method.min_samples @@ -92,43 +168,18 @@ key_added = '$method.key_added' ) -#else if $method.method == 'tl.leiden' -sa.tl.leiden( - adata, - resolution = $method.resolution, - objective_function = '$method.objective_function', - #if $method.objective_function == 'RBConfiguration' - use_leidenalg = True, - #end if - min_cluster_size = $method.min_cluster_size, - n_iterations = $method.n_iterations, - random_state = $method.random_state, - key_added = '$method.key_added', - weighted = $method.weighted, - inplace = True -) - -#else if $method.method == 'tl.kmeans' -sa.tl.kmeans( - adata, - n_clusters = $method.n_clusters, - n_iterations = $method.n_iterations, - random_state = $method.random_state, - use_rep = '$method.use_rep', - key_added = '$method.key_added' -) - -#else if $method.method == 'tl.aggregate_X' -sa.tl.aggregate_X( - adata, - #if $method.groupby != '' - groupby = '$method.groupby', - #end if - normalize = '$method.normalize' -) +## It is implemented in select_feature function, and it is problematic if the user don't select a groupby (will return an array). i think this can be skipped unless needed +## #else if $method.method == 'tl.aggregate_X' +## snap.tl.aggregate_X( +## adata, +## #if $method.groupby != '' +## groupby = '$method.groupby', +## #end if +## normalize = '$method.normalize' +## ) #else if $method.method == 'tl.aggregate_cells' -sa.tl.aggregate_cells( +snap.tl.aggregate_cells( adata, use_rep = '$method.use_rep', #if $method.target_num_cells @@ -141,26 +192,28 @@ ) #end if -@CMD_anndata_write_outputs@ +@CONF_ANNDATA_WRITE_OUTPUTS@ ]]></configfile> </configfiles> <inputs> <conditional name="method"> <param name="method" type="select" label="Dimension reduction and Clustering"> <option value="tl.spectral">Perform dimension reduction using Laplacian Eigenmap, using 'tl.spectral'</option> + <option value="tl.multi_spectral">similar to 'tl.multi_spectral' but it can work on multiple modalities.</option> <option value="tl.umap">Compute Umap, using 'tl.umap'</option> <option value="pp.knn">Compute a neighborhood graph of observations, using 'pp.knn'</option> <option value="tl.leiden">Cluster cells into subgroups, using 'tl.leiden'</option> <option value="tl.kmeans">Cluster cells into subgroups using the K-means algorithm, using 'tl.kmeans'</option> <option value="tl.dbscan">Cluster cells into subgroups using the DBSCAN algorithm, using 'tl.dbscan'</option> <option value="tl.hdbscan">Cluster cells into subgroups using the HDBSCAN algorithm, using 'tl.hdbscan'</option> - <option value="tl.aggregate_X">Aggregate values in adata.X in a row-wise fashion, using 'tl.aggregate_X'</option> + <!-- It is implemented in select_feature function in preprocessing.xml tool (implemented in upstream code, not in the xml). It is problematic if the user don't select a groupby (will return an array). i think this can be skipped unless needed --> + <!-- <option value="tl.aggregate_X">Aggregate values in adata.X in a row-wise fashion, using 'tl.aggregate_X'</option> --> <option value="tl.aggregate_cells">Aggregate cells into pseudo-cells, using 'tl.aggregate_cells'</option> </param> <when value="tl.spectral"> - <expand macro="inputs_anndata"/> + <expand macro="param_inputs_anndata"/> <expand macro="param_n_comps"/> - <param argument="features" type="data" format="txt" optional="true" label="Text file indicating features to keep. Each line contains only word (True/False)." help="True means that the feature is kept. False means the feature is removed"/> + <param argument="features" type="data" format="txt,tabular" optional="true" label="Text file indicating features to keep. Each line contains only word (True/False)." help="True means that the feature is kept. False means the feature is removed"/> <expand macro="param_random_state"/> <param argument="sample_size" type="float" min="0" max="1" optional="true" label="Approximate the embedding using the Nystrom algorithm by selecting a subset of cells" help="Using this only when the number of cells is too large, e.g. > 10,000,000, or the `distance_metric` is “jaccard”"/> <param argument="chunk_size" type="integer" value="20000" label="chunk size"/> @@ -170,9 +223,18 @@ </param> <param argument="weighted_by_sd" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Whether to weight the result eigenvectors by the square root of eigenvalues"/> </when> + <when value="tl.multi_spectral"> + <expand macro="param_inputs_anndata" multiple="true" label="list of Anndatas to use for multi_spectral" help="Please note that the embedding will be saved in the first Anndata"/> + <!-- Will enable if requested by users --> + <!-- <param name="weights" type="data" format="tabular" optional="true" label="Weights" help="Text file indicating weights for each modality. Each line contains only floats.If not provided, all modalities are weighted equally" /> --> + <expand macro="param_n_comps"/> + <param argument="features" type="data" format="txt,tabular" optional="true" label="Text file indicating features to keep. Each line contains only word (True/False)." help="True means that the feature is kept. False means the feature is removed"/> + <expand macro="param_random_state"/> + <param argument="weighted_by_sd" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Whether to weight the result eigenvectors by the square root of eigenvalues"/> + </when> <when value="tl.umap"> - <expand macro="inputs_anndata"/> - <param argument="n_comps" type="integer" value="2" label="Number of dimensions of embedding"/> + <expand macro="param_inputs_anndata"/> + <expand macro="param_n_comps" value="2" label="Number of components" help=""/> <param argument="use_dims" type="text" optional="true" label="Use these dimensions in `use_rep`" help="comma separated list of dimensions"> <expand macro="sanitize_query"/> </param> @@ -181,21 +243,21 @@ <expand macro="param_random_state"/> </when> <when value="pp.knn"> - <expand macro="inputs_anndata"/> + <expand macro="param_inputs_anndata"/> <param argument="n_neighbors" type="integer" value="50" label="The number of nearest neighbors to be searched"/> <param argument="use_dims" type="text" value="" optional="true" label="The dimensions used for computation"> <expand macro="sanitize_query"/> </param> - <param argument="use_rep" type="text" value="X_spectral" label="The key for the matrix"/> + <expand macro="param_use_rep" label="The key for the matrix"/> <param argument="algorithm" type="select" label="Choose method"> <option value="kdtree" selected="true">'kdtree': use the kdtree algorithm to find the nearest neighbors</option> <option value="hora">'hora': use the HNSW algorithm to find the approximate nearest neighbors</option> <option value="pynndescent">'pynndescent': use the pynndescent algorithm to find the approximate nearest neighbors</option> </param> - <param argument="random_state" type="integer" value="0" label="Random seed for approximate nearest neighbor search"/> + <expand macro="param_random_state" label="Random seed for approximate nearest neighbor search" help="Note that this is only used when method='pynndescent'. Currently hora does not support random seed, so the result of hora is not reproducible."/> </when> <when value="tl.leiden"> - <expand macro="inputs_anndata"/> + <expand macro="param_inputs_anndata"/> <param argument="resolution" type="float" value="1" label="Parameter value controlling the coarseness of the clustering" help="Higher values lead to more clusters"/> <param argument="objective_function" type="select" label="Whether to use the Constant Potts Model (CPM) or modularity"> <option value="CPM">CPM</option> @@ -206,10 +268,11 @@ <expand macro="param_n_iterations"/> <expand macro="param_random_state"/> <expand macro="param_key_added" key_added="leiden"/> + <param argument="use_leidenalg" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Whether to use the leidenalg package for Leiden clustering"/> <param argument="weighted" type="boolean" truevalue="True" falsevalue="False" label="Whether to use the edge weights in the graph"/> </when> <when value="tl.kmeans"> - <expand macro="inputs_anndata"/> + <expand macro="param_inputs_anndata"/> <param argument="n_clusters" type="integer" value="5" label="Number of clusters to return"/> <expand macro="param_n_iterations"/> <expand macro="param_random_state"/> @@ -217,7 +280,7 @@ <expand macro="param_key_added" key_added="kmeans"/> </when> <when value="tl.dbscan"> - <expand macro="inputs_anndata"/> + <expand macro="param_inputs_anndata"/> <param argument="eps" type="float" value="0.5" label=" The maximum distance between two samples for one to be considered as in the neighborhood of the other" help="This is not a maximum bound on the distances of points within a cluster. This is the most important DBSCAN parameter to choose appropriately for your data set and distance function."/> <param argument="min_samples" type="integer" value="5" label="The number of samples (or total weight) in a neighborhood for a point to be considered as a core point."/> <param argument="leaf_size" type="integer" value="30" label="Leaf size passed to BallTree or cKDTree" help="This can affect the speed of the construction and query, as well as the memory required to store the tree."/> @@ -225,9 +288,9 @@ <expand macro="param_key_added" key_added="dbscan"/> </when> <when value="tl.hdbscan"> - <expand macro="inputs_anndata"/> + <expand macro="param_inputs_anndata"/> <param argument="min_cluster_size" type="integer" value="5" label="The minimum size of clusters"/> - <param argument="min_samples" type="integer" value="" optional="true" label="The number of samples in a neighbourhood for a point to be considered a core point"/> + <param argument="min_samples" type="integer" value="" optional="true" label="The number of samples in a neighborhood for a point to be considered a core point"/> <param argument="cluster_selection_epsilon" type="float" value="0.0" label="A distance threshold. Clusters below this value will be merged"/> <param argument="alpha" type="float" value="1.0" label="A distance scaling parameter as used in robust single linkage"/> <param argument="cluster_selection_method" type="select" label="The method used to select clusters from the condensed tree"> @@ -238,16 +301,16 @@ <expand macro="param_use_rep"/> <expand macro="param_key_added" key_added="hdbscan"/> </when> - <when value="tl.aggregate_X"> - <expand macro="inputs_anndata"/> + <!-- <when value="tl.aggregate_X"> + <expand macro="param_inputs_anndata"/> <expand macro="param_groupby"/> <param argument="normalize" type="select" optional="true" label="normalization method"> <option value="RPM">RPM</option> <option value="RPKM">RPKM</option> </param> - </when> + </when> --> <when value="tl.aggregate_cells"> - <expand macro="inputs_anndata"/> + <expand macro="param_inputs_anndata"/> <expand macro="param_use_rep"/> <param argument="target_num_cells" type="integer" value="" optional="true" label="target_num_cells" help="If None, `target_num_cells = num_cells / min_cluster_size`"/> <param argument="min_cluster_size" type="integer" value="50" label="The minimum size of clusters"/> @@ -255,23 +318,20 @@ <expand macro="param_key_added" key_added="pseudo_cell"/> </when> </conditional> - <expand macro="inputs_common_advanced"/> + <expand macro="param_common_advanced"/> </inputs> <outputs> - <data name="anndata_out" format="h5ad" from_work_dir="anndata.h5ad" label="${tool.name} (${method.method}) on ${on_string}: Annotated data matrix"/> + <data name="anndata_out" format="h5ad" from_work_dir="anndata.h5ad.gz" label="${tool.name} (${method.method}) on ${on_string}: Annotated data matrix"/> <data name="hidden_output" format="txt" label="Log file"> <filter>advanced_common['show_log']</filter> </data> - <data name="diff_peaks" format="tabular" from_work_dir="differential_peaks.tsv" label="${tool.name} on ${on_string}: Differential peaks"> - <filter>method['method'] and 'tl.diff_test' in method['method']</filter> - </data> </outputs> <tests> <test expect_num_outputs="2"> <!-- tl.spectral --> <conditional name="method"> <param name="method" value="tl.spectral"/> - <param name="adata" location="https://zenodo.org/records/11260316/files/pp.select_features.pbmc_500_chr21.h5ad"/> + <param name="adata" location="https://zenodo.org/records/17512085/files/pp.select_features.pbmc_500_chr21.h5ad"/> <param name="n_comps" value="30"/> <param name="random_state" value="0"/> <param name="chunk_size" value="20000"/> @@ -283,7 +343,7 @@ </section> <output name="hidden_output"> <assert_contents> - <has_text_matching expression="sa.tl.spectral"/> + <has_text_matching expression="snap.tl.spectral"/> <has_text_matching expression="random_state = 0"/> <has_text_matching expression="n_comps = 30"/> <has_text_matching expression="chunk_size = 20000"/> @@ -291,13 +351,46 @@ <has_text_matching expression="weighted_by_sd = True"/> </assert_contents> </output> - <output name="anndata_out" ftype="h5ad" compare="sim_size" delta_frac="0.1" location="https://zenodo.org/records/11260316/files/tl.spectral.pbmc_500_chr21.h5ad"/> + <output name="anndata_out" ftype="h5ad"> + <assert_contents> + <has_h5_keys keys="uns/spectral_eigenvalue"/> + <has_h5_keys keys="obsm/X_spectral"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="2"> + <!-- tl.multi_spectral --> + <conditional name="method"> + <param name="method" value="tl.multi_spectral"/> + <param name="adata" location="https://zenodo.org/records/17512085/files/snap_datasets_pbmc10k_multiome_RNA.h5ad.gz,https://zenodo.org/records/17512085/files/snap_datasets_pbmc10k_multiome_ATAC.h5ad.gz"/> + <param name="n_comps" value="30"/> + <param name="random_state" value="0"/> + <param name="weighted_by_sd" value="True"/> + </conditional> + <section name="advanced_common"> + <param name="show_log" value="true"/> + </section> + <output name="hidden_output"> + <assert_contents> + <has_text_matching expression="snap.tl.multi_spectral"/> + <has_text_matching expression="random_state = 0"/> + <has_text_matching expression="n_comps = 30"/> + <has_text_matching expression="weighted_by_sd = True"/> + <has_text_matching expression="features = None"/> + </assert_contents> + </output> + <output name="anndata_out" ftype="h5ad"> + <assert_contents> + <has_h5_keys keys="uns/spectral_eigenvalue_joint"/> + <has_h5_keys keys="obsm/X_joint"/> + </assert_contents> + </output> </test> <test expect_num_outputs="2"> <!-- tl.umap --> <conditional name="method"> <param name="method" value="tl.umap"/> - <param name="adata" location="https://zenodo.org/records/11260316/files/tl.spectral.pbmc_500_chr21.h5ad"/> + <param name="adata" location="https://zenodo.org/records/17512085/files/tl.spectral.pbmc_500_chr21.h5ad"/> <param name="n_comps" value="2"/> <param name="use_rep" value="X_spectral"/> <param name="key_added" value="umap"/> @@ -308,24 +401,27 @@ </section> <output name="hidden_output"> <assert_contents> - <has_text_matching expression="sa.tl.umap"/> + <has_text_matching expression="snap.tl.umap"/> <has_text_matching expression="n_comps = 2"/> <has_text_matching expression="use_rep = 'X_spectral'"/> <has_text_matching expression="key_added = 'umap'"/> <has_text_matching expression="random_state = 0"/> </assert_contents> </output> - <output name="anndata_out" ftype="h5ad" compare="sim_size" delta_frac="0.1" location="https://zenodo.org/records/11260316/files/tl.umap.pbmc_500_chr21.h5ad"/> + <output name="anndata_out" ftype="h5ad"> + <assert_contents> + <has_h5_keys keys="obsm/X_umap"/> + </assert_contents> + </output> </test> <test expect_num_outputs="2"> <!-- pp.knn --> <conditional name="method"> <param name="method" value="pp.knn"/> - <param name="adata" location="https://zenodo.org/records/11260316/files/tl.umap.pbmc_500_chr21.h5ad"/> + <param name="adata" location="https://zenodo.org/records/17512085/files/tl.umap.pbmc_500_chr21.h5ad"/> <param name="n_neighbors" value="50"/> <param name="use_rep" value="X_spectral"/> - <param name="method_" value="kdtree"/> - <param name="inplace" value="True"/> + <param name="algorithm" value="kdtree"/> <param name="random_state" value="0"/> </conditional> <section name="advanced_common"> @@ -333,7 +429,7 @@ </section> <output name="hidden_output"> <assert_contents> - <has_text_matching expression="sa.pp.knn"/> + <has_text_matching expression="snap.pp.knn"/> <has_text_matching expression="n_neighbors = 50"/> <has_text_matching expression="use_rep = 'X_spectral'"/> <has_text_matching expression="method = 'kdtree'"/> @@ -341,13 +437,17 @@ <has_text_matching expression="random_state = 0"/> </assert_contents> </output> - <output name="anndata_out" ftype="h5ad" compare="sim_size" delta_frac="0.1" location="https://zenodo.org/records/11260316/files/pp.knn.pbmc_500_chr21.h5ad"/> + <output name="anndata_out" ftype="h5ad"> + <assert_contents> + <has_h5_keys keys="obsp/distances"/> + </assert_contents> + </output> </test> <test expect_num_outputs="2"> <!-- tl.leiden --> <conditional name="method"> <param name="method" value="tl.leiden"/> - <param name="adata" location="https://zenodo.org/records/11260316/files/pp.knn.pbmc_500_chr21.h5ad"/> + <param name="adata" location="https://zenodo.org/records/17512085/files/pp.knn.pbmc_500_chr21.h5ad"/> <param name="resolution" value="2"/> <param name="objective_function" value="modularity"/> <param name="min_cluster_size" value="3"/> @@ -361,7 +461,7 @@ </section> <output name="hidden_output"> <assert_contents> - <has_text_matching expression="sa.tl.leiden"/> + <has_text_matching expression="snap.tl.leiden"/> <has_text_matching expression="resolution = 2"/> <has_text_matching expression="objective_function = 'modularity'"/> <has_text_matching expression="min_cluster_size = 3"/> @@ -371,13 +471,17 @@ <has_text_matching expression="weighted = False"/> </assert_contents> </output> - <output name="anndata_out" ftype="h5ad" compare="sim_size" delta_frac="0.1" location="https://zenodo.org/records/11260316/files/tl.leiden.modularity.pbmc_500_chr21.h5ad"/> + <output name="anndata_out" ftype="h5ad"> + <assert_contents> + <has_h5_keys keys="obs/leiden"/> + </assert_contents> + </output> </test> <test expect_num_outputs="2"> <!-- tl.leiden --> <conditional name="method"> <param name="method" value="tl.leiden"/> - <param name="adata" location="https://zenodo.org/records/11260316/files/pp.knn.pbmc_500_chr21.h5ad"/> + <param name="adata" location="https://zenodo.org/records/17512085/files/pp.knn.pbmc_500_chr21.h5ad"/> <param name="resolution" value="2"/> <param name="objective_function" value="RBConfiguration"/> <param name="min_cluster_size" value="3"/> @@ -391,7 +495,7 @@ </section> <output name="hidden_output"> <assert_contents> - <has_text_matching expression="sa.tl.leiden"/> + <has_text_matching expression="snap.tl.leiden"/> <has_text_matching expression="resolution = 2"/> <has_text_matching expression="objective_function = 'RBConfiguration'"/> <has_text_matching expression="min_cluster_size = 3"/> @@ -401,13 +505,17 @@ <has_text_matching expression="weighted = False"/> </assert_contents> </output> - <output name="anndata_out" ftype="h5ad" compare="sim_size" delta_frac="0.1" location="https://zenodo.org/records/11260316/files/tl.leiden.RBConfiguration.pbmc_500_chr21.h5ad"/> + <output name="anndata_out" ftype="h5ad"> + <assert_contents> + <has_h5_keys keys="obs/leiden"/> + </assert_contents> + </output> </test> <test expect_num_outputs="2"> <!-- tl.kmeans --> <conditional name="method"> <param name="method" value="tl.kmeans"/> - <param name="adata" location="https://zenodo.org/records/11260316/files/tl.spectral.pbmc_500_chr21.h5ad"/> + <param name="adata" location="https://zenodo.org/records/17512085/files/tl.spectral.pbmc_500_chr21.h5ad"/> <param name="n_iterations" value="-1"/> <param name="random_state" value="0"/> <param name="use_rep" value="X_spectral"/> @@ -418,20 +526,24 @@ </section> <output name="hidden_output"> <assert_contents> - <has_text_matching expression="sa.tl.kmeans"/> + <has_text_matching expression="snap.tl.kmeans"/> <has_text_matching expression="n_iterations = -1"/> <has_text_matching expression="random_state = 0"/> <has_text_matching expression="use_rep = 'X_spectral'"/> <has_text_matching expression="key_added = 'kmeans'"/> </assert_contents> </output> - <output name="anndata_out" ftype="h5ad" compare="sim_size" delta_frac="0.1" location="https://zenodo.org/records/11260316/files/tl.kmeans.pbmc_500_chr21.h5ad"/> + <output name="anndata_out" ftype="h5ad"> + <assert_contents> + <has_h5_keys keys="obs/kmeans"/> + </assert_contents> + </output> </test> <test expect_num_outputs="2"> <!-- tl.dbscan --> <conditional name="method"> <param name="method" value="tl.dbscan"/> - <param name="adata" location="https://zenodo.org/records/11260316/files/tl.spectral.pbmc_500_chr21.h5ad"/> + <param name="adata" location="https://zenodo.org/records/17512085/files/tl.spectral.pbmc_500_chr21.h5ad"/> <param name="eps" value="0.5"/> <param name="min_samples" value="3"/> <param name="leaf_size" value="5"/> @@ -443,7 +555,7 @@ </section> <output name="hidden_output"> <assert_contents> - <has_text_matching expression="sa.tl.dbscan"/> + <has_text_matching expression="snap.tl.dbscan"/> <has_text_matching expression="eps = 0.5"/> <has_text_matching expression="min_samples = 3"/> <has_text_matching expression="leaf_size = 5"/> @@ -451,13 +563,17 @@ <has_text_matching expression="key_added = 'dbscan'"/> </assert_contents> </output> - <output name="anndata_out" ftype="h5ad" compare="sim_size" delta_frac="0.1" location="https://zenodo.org/records/11260316/files/tl.dbscan.pbmc_500_chr21.h5ad"/> + <output name="anndata_out" ftype="h5ad"> + <assert_contents> + <has_h5_keys keys="obs/dbscan"/> + </assert_contents> + </output> </test> <test expect_num_outputs="2"> <!-- tl.hdbscan --> <conditional name="method"> <param name="method" value="tl.hdbscan"/> - <param name="adata" location="https://zenodo.org/records/11260316/files/tl.spectral.pbmc_500_chr21.h5ad"/> + <param name="adata" location="https://zenodo.org/records/17512085/files/tl.spectral.pbmc_500_chr21.h5ad"/> <param name="min_cluster_size" value="3"/> <param name="min_samples" value="3"/> <param name="cluster_selection_method" value="eom"/> @@ -470,7 +586,7 @@ </section> <output name="hidden_output"> <assert_contents> - <has_text_matching expression="sa.tl.hdbscan"/> + <has_text_matching expression="snap.tl.hdbscan"/> <has_text_matching expression="min_cluster_size = 3"/> <has_text_matching expression="min_samples = 3"/> <has_text_matching expression="cluster_selection_method = 'eom'"/> @@ -479,13 +595,17 @@ <has_text_matching expression="key_added = 'hdbscan'"/> </assert_contents> </output> - <output name="anndata_out" ftype="h5ad" compare="sim_size" delta_frac="0.1" location="https://zenodo.org/records/11260316/files/tl.hdbscan.pbmc_500_chr21.h5ad"/> + <output name="anndata_out" ftype="h5ad"> + <assert_contents> + <has_h5_keys keys="obs/hdbscan"/> + </assert_contents> + </output> </test> - <test expect_num_outputs="2"> - <!-- tl.aggregate_X --> + <!-- <test expect_num_outputs="2"> + tl.aggregate_X <conditional name="method"> <param name="method" value="tl.aggregate_X"/> - <param name="adata" location="https://zenodo.org/records/11260316/files/tl.spectral.pbmc_500_chr21.h5ad"/> + <param name="adata" location="https://zenodo.org/records/17512085/files/tl.spectral.pbmc_500_chr21.h5ad"/> <param name="normalize" value="RPKM"/> </conditional> <section name="advanced_common"> @@ -493,17 +613,21 @@ </section> <output name="hidden_output"> <assert_contents> - <has_text_matching expression="sa.tl.aggregate_X"/> + <has_text_matching expression="snap.tl.aggregate_X"/> <has_text_matching expression="normalize = 'RPKM'"/> </assert_contents> </output> - <output name="anndata_out" ftype="h5ad" compare="sim_size" delta_frac="0.1" location="https://zenodo.org/records/11260316/files/tl.aggregate_X.pbmc_500_chr21.h5ad"/> - </test> + <output name="anndata_out" ftype="h5ad"> + <assert_contents> + <has_h5_keys keys="obs/n_fragment"/> + </assert_contents> + </output> + </test> --> <test expect_num_outputs="2"> <!-- tl.aggregate_cells --> <conditional name="method"> <param name="method" value="tl.aggregate_cells"/> - <param name="adata" location="https://zenodo.org/records/11260316/files/tl.spectral.pbmc_500_chr21.h5ad"/> + <param name="adata" location="https://zenodo.org/records/17512085/files/tl.spectral.pbmc_500_chr21.h5ad"/> <param name="use_rep" value="X_spectral"/> <param name="target_num_cells" value="5"/> <param name="min_cluster_size" value="3"/> @@ -515,7 +639,7 @@ </section> <output name="hidden_output"> <assert_contents> - <has_text_matching expression="sa.tl.aggregate_cells"/> + <has_text_matching expression="snap.tl.aggregate_cells"/> <has_text_matching expression="use_rep = 'X_spectral'"/> <has_text_matching expression="target_num_cells = 5"/> <has_text_matching expression="min_cluster_size = 3"/> @@ -523,7 +647,11 @@ <has_text_matching expression="key_added = 'pseudo_cell'"/> </assert_contents> </output> - <output name="anndata_out" ftype="h5ad" compare="sim_size" delta_frac="0.1" location="https://zenodo.org/records/11260316/files/tl.aggregate_cells.pbmc_500_chr21.h5ad"/> + <output name="anndata_out" ftype="h5ad"> + <assert_contents> + <has_h5_keys keys="obs/pseudo_cell"/> + </assert_contents> + </output> </test> </tests> <help><![CDATA[ @@ -535,7 +663,15 @@ Convert the cell-by-feature count matrix into lower dimensional representations using the spectrum of the normalized graph Laplacian defined by pairwise similarity between cells. This function utilizes the matrix-free spectral embedding algorithm to compute the embedding when `distance_metric` is “cosine”, which scales linearly with the number of cells. For other types of similarity metrics, the time and space complexity scale quadratically with the number of cells. More details on the `SnapATAC2 documentation -<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.tl.spectral.html>`__ +<https://scverse.org/SnapATAC2/api/_autosummary/snapatac2.tl.spectral.html>`__ + +Compute Laplacian Eigenmaps simultaneously on multiple modalities, with linear space and time complexity, using `tl.multi_spectral` +=================================================================================================================================== + +This is similar to `spectral`, but it can work on multiple modalities. + +More details on the `SnapATAC2 documentation +<https://scverse.org/SnapATAC2/api/_autosummary/snapatac2.tl.multi_spectral.html>`__ Compute Umap, using `tl.umap` ============================= @@ -543,7 +679,7 @@ Compute Umap More details on the `SnapATAC2 documentation -<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.tl.umap.html>`__ +<https://scverse.org/SnapATAC2/api/_autosummary/snapatac2.tl.umap.html>`__ Compute a neighborhood graph of observations, using `pp.knn` ============================================================ @@ -553,7 +689,7 @@ Computes a neighborhood graph of observations stored in adata using the method specified by method. The distance metric used is Euclidean. More details on the `SnapATAC2 documentation -<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.pp.knn.html>`__ +<https://scverse.org/SnapATAC2/api/_autosummary/snapatac2.pp.knn.html>`__ Cluster cells into subgroups, using `tl.leiden` =============================================== @@ -563,7 +699,7 @@ Cluster cells using the Leiden algorithm, an improved version of the Louvain algorithm. It has been proposed for single-cell analysis by. This requires having ran `knn`. More details on the `SnapATAC2 documentation -<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.tl.leiden.html>`__ +<https://scverse.org/SnapATAC2/api/_autosummary/snapatac2.tl.leiden.html>`__ Cluster cells into subgroups using the K-means algorithm, using `tl.kmeans` =========================================================================== @@ -571,7 +707,7 @@ Cluster cells into subgroups using the K-means algorithm, a classical algorithm in data mining. More details on the `SnapATAC2 documentation -<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.tl.kmeans.html>`__ +<https://scverse.org/SnapATAC2/api/_autosummary/snapatac2.tl.kmeans.html>`__ Cluster cells into subgroups using the DBSCAN algorithm, using `tl.dbscan` ========================================================================== @@ -579,7 +715,7 @@ Cluster cells into subgroups using the DBSCAN algorithm. More details on the `SnapATAC2 documentation -<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.tl.dbscan.html>`__ +<https://scverse.org/SnapATAC2/api/_autosummary/snapatac2.tl.dbscan.html>`__ Cluster cells into subgroups using the HDBSCAN algorithm, using `tl.hdbscan` ============================================================================ @@ -587,17 +723,17 @@ Cluster cells into subgroups using the HDBSCAN algorithm. More details on the `SnapATAC2 documentation -<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.tl.hdbscan.html>`__ +<https://scverse.org/SnapATAC2/api/_autosummary/snapatac2.tl.hdbscan.html>`__ -Aggregate values in adata.X in a row-wise fashion, using `tl.aggregate_X` -========================================================================= +.. Aggregate values in adata.X in a row-wise fashion, using `tl.aggregate_X` +.. ========================================================================= -Aggregate values in adata.X in a row-wise fashion. +.. Aggregate values in adata.X in a row-wise fashion. -Aggregate values in adata.X in a row-wise fashion. This is used to compute RPKM or RPM values stratified by user-provided groupings. +.. Aggregate values in adata.X in a row-wise fashion. This is used to compute RPKM or RPM values stratified by user-provided groupings. -More details on the `SnapATAC2 documentation -<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.tl.aggregate_X.html>`__ +.. More details on the `SnapATAC2 documentation +.. <https://scverse.org/SnapATAC2/api/_autosummary/snapatac2.tl.aggregate_X.html>`__ Aggregate cells into pseudo-cells, using `tl.aggregate_cells` ============================================================= @@ -607,7 +743,7 @@ Aggregate cells into pseudo-cells by iterative clustering. More details on the `SnapATAC2 documentation -<https://kzhang.org/SnapATAC2/api/_autosummary/snapatac2.tl.aggregate_cells.html>`__ +<https://scverse.org/SnapATAC2/api/_autosummary/snapatac2.tl.aggregate_cells.html>`__ ]]></help> <expand macro="citations"/> </tool>
--- a/macros.xml Thu Nov 07 13:07:58 2024 +0000 +++ b/macros.xml Tue Nov 25 16:40:54 2025 +0000 @@ -1,7 +1,7 @@ <macros> - <token name="@TOOL_VERSION@">2.6.4</token> - <token name="@VERSION_SUFFIX@">1</token> - <token name="@PROFILE@">23.0</token> + <token name="@TOOL_VERSION@">2.8.0</token> + <token name="@VERSION_SUFFIX@">0</token> + <token name="@PROFILE@">24.0</token> <xml name="xrefs"> <xrefs> <xref type="bio.tools">snapatac</xref> @@ -9,168 +9,74 @@ </xml> <xml name="requirements"> <requirement type="package" version="@TOOL_VERSION@">snapatac2</requirement> - <requirement type="package" version="5.22.0">plotly</requirement> - <requirement type="package" version="0.2.1">python-kaleido</requirement> - <requirement type="package" version="1.1.0">polars</requirement> - <requirement type="package" version="16.1.0">pyarrow</requirement> - <requirement type="package" version="0.11.6">python-igraph</requirement> - <requirement type="package" version="0.8.37">hdbscan</requirement> - <requirement type="package" version="0.0.10">harmonypy</requirement> - <requirement type="package" version="1.7.4">scanorama</requirement> - <requirement type="package" version="3.0.1">macs3</requirement> - <requirement type="package" version="0.70.16">multiprocess</requirement> - <requirement type="package" version="0.10.2">leidenalg</requirement> + <requirement type="package" version="0.8.37">hdbscan</requirement> + <requirement type="package" version="0.10.2">leidenalg</requirement> + <requirement type="package" version="0.5.7">umap-learn</requirement> + <requirement type="package" version="3.0.4">xgboost</requirement> + <requirement type="package" version="0.2.1">python-kaleido</requirement> + <requirement type="package" version="1.31.0">polars</requirement> + <requirement type="package" version="5.24.1">plotly</requirement> + <requirement type="package" version="0.2.1">python-kaleido</requirement> + <requirement type="package" version="0.0.10">harmonypy</requirement> + <requirement type="package" version="1.7.4">scanorama</requirement> <yield /> </xml> - <token name="@PREP_ADATA@"><![CDATA[ + <!-- command section --> + <token name="@CMD_PREP_ADATA@"><![CDATA[ + ## ln -s does not work here cp '$method.adata' 'anndata.h5ad' && - ]]> - </token> - + ]]></token> <token name="@CMD@"><![CDATA[ cat '$script_file' > '$hidden_output' && python '$script_file' >> '$hidden_output' && touch 'anndata_info.txt' && - cat 'anndata_info.txt' @CMD_prettify_stdout@ - ]]> - </token> - - <token name="@CMD_prettify_stdout@"><![CDATA[ | sed -r '1 s|AnnData object with (.+) = (.*)\s*|\1: \2|g' | sed "s|'||g" | sed -r 's|^\s*(.*):\s(.*)|[\1]\n- \2|g' | sed 's|, |\n- |g' + cat 'anndata_info.txt' @CMD_PRETTIFY_STDOUT@ + ]]></token> + <token name="@CMD_PRETTIFY_STDOUT@"><![CDATA[ + | sed -r '1 s|AnnData 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="@CMD_GET_GFF@"><![CDATA[ + #if $method.gff_file_condi.gffSource == 'cached': + ln -s '$method.gff_file_condi.gff_pre_installed.fields.path' gff && + #else: + ln -s '$method.gff_file_condi.gff_history' gff && + #end if + ]]></token> + <token name="@CMD_GET_FASTA@"><![CDATA[ + #if $method.fasta_file_condi.fastaSource == 'indexed': + zcat '$method.fasta_file_condi.fasta_pre_installed.fields.path' > fasta.fa && + echo "Using built-in FASTA: '$method.fasta_file_condi.fasta_pre_installed.fields.name'" >&2 && + #else: + #if $method.fasta_file_condi.fasta_history.ext.endswith('.gz') + zcat '$method.fasta_file_condi.fasta_history' > fasta.fa && + #else: + ln -s '$method.fasta_file_condi.fasta_history' fasta.fa && + #end if + #end if ]]></token> - <token name="@CMD_imports@"><![CDATA[ -import snapatac2 as sa + <!-- Config section --> + <token name="@CONF_IMPORTS@"><![CDATA[ +import snapatac2 as snap import os - ]]> - </token> - <xml name="sanitize_query" token_validinitial="string.printable"> - <sanitizer> - <valid initial="@VALIDINITIAL@"> - <remove value="'" /> - </valid> - </sanitizer> - </xml> - - <xml name="inputs_anndata"> - <param name="adata" type="data" format="h5ad" label="Annotated data matrix"/> - </xml> - - <token name="@CMD_read_inputs@"><![CDATA[ - -adata = sa.read('anndata.h5ad', backed = None) -]]> - </token> - - <xml name="dimentions_plot"> - <param argument="width" type="integer" value="500" label="Width of the plot"/> - <param argument="height" type="integer" value="400" label="Height of the plot"/> - </xml> - - <xml name="param_groupby"> - <param argument="groupby" type="text" label="The key of the observation grouping to consider"> - <expand macro="sanitize_query" /> - </param> - </xml> - - <xml name="out_file"> - <param name="out_file" type="select" optional="true" label="Type of output plot"> - <option value="png" selected="true">PNG</option> - <option value="svg">SVG</option> - <option value="pdf">PDF</option> - </param> - </xml> - <token name="@CMD_anndata_write_outputs@"><![CDATA[ -adata.write('anndata.h5ad') + ]]></token> + <token name="@CONF_READ_INPUTS@"><![CDATA[ +adata = snap.read('anndata.h5ad', backed = None) + ]]></token> + <token name="@CONF_ANNDATA_WRITE_OUTPUTS@"><![CDATA[ +adata.write_h5ad('anndata.h5ad.gz', compression='gzip') with open('anndata_info.txt','w', encoding='utf-8') as ainfo: print(adata, file=ainfo) -]]> - </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="params_render_plot"> - <param argument="width" type="integer" value="600" label="Width of the plot"/> - <param argument="height" type="integer" value="400" label="Height of the plot"/> - <expand macro="out_file"/> - </xml> - <xml name="param_shift"> - <param argument="shift_left" type="integer" value="4" label="Insertion site correction for the left end" help="Note this has no effect on single-end reads"/> - <param argument="shift_right" type="integer" value="-5" label="Insertion site correction for the right end" help="Note this has no effect on single-end reads"/> - </xml> - <xml name="param_chunk_size" tokens="size"> - <param argument="chunk_size" type="integer" value="@SIZE@" label="chunk size"/> - </xml> - <xml name="min_max_frag_size"> - <param argument="min_frag_size" type="integer" optional="true" value="" label="Minimum fragment size to include"/> - <param argument="max_frag_size" type="integer" optional="true" value="" label="Maximum fragment size to include"/> - </xml> - <xml name="params_data_integration"> - <param argument="use_rep" type="text" value="X_spectral" label="The key for the matrix"/> - <param argument="use_dims" type="text" optional="true" value="" label="The dimensions used for computation"> - <expand macro="sanitize_query"/> - </param> - <param argument="groupby" type="text" optional="true" value="" label="The key of the observation grouping to consider"> - <expand macro="sanitize_query" /> - </param> - <param argument="key_added" type="text" optional="true" value="" label="If specified, add the result to adata.obsm with this key"/> - </xml> - <xml name="param_n_comps"> - <param argument="n_comps" type="integer" value="30" label="Number of dimensions to keep" help="The result is insensitive to this parameter when `weighted_by_sd` is set, as long as it is large enough, e.g. 30."/> - </xml> - <xml name="param_random_state"> - <param argument="random_state" type="integer" value="0" label="Seed of the random state generator"/> - </xml> - <xml name="param_key_added" tokens="key_added"> - <param argument="key_added" type="text" value="@KEY_ADDED@" label="`adata.obs` key under which t add cluster labels"/> - </xml> - <xml name="param_use_rep"> - <param argument="use_rep" type="text" value="X_spectral" label="Use the indicated representation in `.obsm`"/> - </xml> - <xml name="genome_fasta"> - <param argument="genome_fasta" type="text" label="A fasta file containing the genome sequences or a Genome object"/> - </xml> - <xml name="background"> - <param argument="background" type="text" optional="true" value="" label="A list of regions to be used as the background"> - <expand macro="sanitize_query"/> - </param> - </xml> - <xml name="mat"> - <param argument="peak_mat" type="data" format="h5ad" optional="true" label="AnnData or AnnDataSet object storing the cell by peak count matrix"/> - <param argument="gene_mat" type="data" format="h5ad" optional="true" label="AnnData or AnnDataSet object storing the cell by gene count matrix"/> - </xml> - <xml name="param_network"> - <param argument="network" type="text" label="network"/> - </xml> - <xml name="param_n_iterations"> - <param argument="n_iterations" type="integer" value="-1" label="How many iterations of the Leiden clustering algorithm to perform" - help="Positive values above 2 define the total number of iterations to perform, -1 has the algorithm run until it reaches its optimal clustering."/> - </xml> - - <xml name="citations"> - <citations> - <citation type="doi">10.1038/s41592-023-02139-9</citation> - </citations> - </xml> - <xml name="render_plot_test"> - <param name="width" value="650"/> - <param name="height" value="450"/> - </xml> - <xml name="render_plot_matching_text"> - <has_text_matching expression="width = 650"/> - <has_text_matching expression="height = 450"/> - </xml> - <xml name="param_counting_strategy"> - <param argument="counting_strategy" type="select" label="The strategy to compute feature counts"> - <option value="fragment">"fragment": based on the number of fragments that overlap with a region of interest</option> - <option value="insertion" selected="true">"insertion": based on the number of insertions that overlap with a region of interest</option> - <option value="paired-insertion">"paired-insertion": similar to "insertion", but it only counts the insertions once if the pair of insertions of a fragment are both within the same region of interest</option> - </param> - </xml> - - <token name="@CMD_params_data_integration@"><![CDATA[ + ]]></token> + <token name="@CONF_PARAMS_RENDER_PLOT@"><![CDATA[ + width = $method.width, + height = $method.height, + show = False, + interactive = False, + out_file = 'plot.$method.out_file', + ]]></token> + <token name="@CONF_PARAMS_DATA_INTEGRATION@"><![CDATA[ use_rep = '$method.use_rep', #if $method.use_dims != '' #set $dims = ([x.strip() for x in str($method.use_dims).split(',')]) @@ -183,13 +89,168 @@ #if $method.key_added != '' key_added = '$method.key_added', #end if - ]]> - </token> + ]]></token> + <token name="@CONF_IMPORT_MEME@"><![CDATA[ +motifs = read_motifs("input.meme") +for motif in motifs: + motif.name = motif.id.split('+')[0] + +unique_motifs = {} +for motif in motifs: + name = motif.name + if ( + name not in unique_motifs or + unique_motifs[name].info_content() < motif.info_content() + ): + unique_motifs[name] = motif +motifs = list(unique_motifs.values()) + + +#else: +motifs = read_motifs("input.meme") +for motif in motifs: + motif.name = motif.id.split('_')[0] + motif.family = motif.id.split('+')[-1] + ]]></token> + + <!-- input section --> + <xml name="sanitize_query" token_validinitial="string.printable"> + <sanitizer> + <valid initial="@VALIDINITIAL@"> + <remove value="'" /> + <yield/> + </valid> + </sanitizer> + </xml> - <token name="@CMD_params_render_plot@"><![CDATA[ - width = $method.width, - height = $method.height, - out_file = 'plot.$method.out_file', - ]]> - </token> + <xml name="param_inputs_anndata" token_multiple="false" token_label="Annotated data matrix"> + <param name="adata" type="data" multiple="@MULTIPLE@" format="h5ad" label="@LABEL@"/> + </xml> + <xml name="param_groupby"> + <param argument="groupby" type="text" label="The key of the observation grouping to consider"> + <expand macro="sanitize_query" /> + </param> + </xml> + <xml name="param_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="param_render_plot"> + <param argument="width" type="integer" value="600" label="Width of the plot"/> + <param argument="height" type="integer" value="400" label="Height of the plot"/> + <param name="out_file" type="select" optional="true" label="Type of output plot"> + <option value="png" selected="true">PNG</option> + <option value="svg">SVG</option> + <option value="pdf">PDF</option> + <option value="html">HTML</option> + </param> + </xml> + <xml name="param_shift" tokens="varname" token_value="0" token_label="Insertion site correction for the left end"> + <param argument="@VARNAME@" type="integer" value="@VALUE@" label="@LABEL@" help="Note this has no effect on single-end reads"/> + </xml> + <xml name="param_chunk_size" tokens="size"> + <param argument="chunk_size" type="integer" value="@SIZE@" label="chunk size"/> + </xml> + <xml name="param_min_max_frag_size"> + <param argument="min_frag_size" type="integer" optional="true" value="" label="Minimum fragment size to include"/> + <param argument="max_frag_size" type="integer" optional="true" value="" label="Maximum fragment size to include"/> + </xml> + <xml name="param_data_integration"> + <param argument="use_rep" type="text" value="X_spectral" label="The key for the matrix"/> + <param argument="use_dims" type="text" optional="true" value="" label="The dimensions used for computation"> + <expand macro="sanitize_query"/> + </param> + <param argument="groupby" type="text" optional="true" value="" label="The key of the observation grouping to consider"> + <expand macro="sanitize_query" /> + </param> + <param argument="key_added" type="text" optional="true" value="" label="If specified, add the result to adata.obsm with this key"/> + </xml> + <xml name="param_random_state" token_label="Seed of the random state generator" token_help=""> + <param argument="random_state" type="integer" value="0" label="@LABEL@" help="@HELP@"/> + </xml> + <xml name="param_key_added" tokens="key_added"> + <param argument="key_added" type="text" value="@KEY_ADDED@" label="`adata.obs` key under which t add cluster labels"/> + </xml> + <xml name="param_use_rep" token_label="Use the indicated representation in `.obsm`"> + <param argument="use_rep" type="text" value="X_spectral" label="@LABEL@"/> + </xml> + <xml name="param_n_iterations"> + <param argument="n_iterations" type="integer" value="-1" label="How many iterations of the Leiden clustering algorithm to perform" + help="Positive values above 2 define the total number of iterations to perform, -1 has the algorithm run until it reaches its optimal clustering."/> + </xml> + <xml name="param_counting_strategy"> + <param argument="counting_strategy" type="select" label="The strategy to compute feature counts"> + <option value="fragment">"fragment": based on the number of fragments that overlap with a region of interest</option> + <option value="insertion">"insertion": based on the number of insertions that overlap with a region of interest</option> + <option value="paired-insertion" selected="true">"paired-insertion": similar to "insertion", but it only counts the insertions once if the pair of insertions of a fragment are both within the same region of interest</option> + </param> + </xml> + <xml name="param_chrom_sizes"> + <param argument="chrom_sizes" type="data" format="tabular" label="Chromosome sizes" help="First column the chromosome name and second column the size"/> + </xml> + <xml name="param_genome_fasta"> + <conditional name="fasta_file_condi"> + <param name="fastaSource" type="select" label="Select a built-in FASTA or one from your history" help="Choose history if you don't see the correct FASTA."> + <option value="indexed" selected="true">Use a built-in FASTA</option> + <option value="history">Use a FASTA from history</option> + </param> + <when value="indexed"> + <param name="fasta_pre_installed" type="select" label="Select a FASTA file" help="Select the FASTA file from a list of pre-installed genomes"> + <options from_data_table="all_fasta"> + <filter type="sort_by" column="2" /> + </options> + </param> + </when> + <when value="history"> + <param name="fasta_history" type="data" format="fasta,fasta.gz" label="FASTA file" /> + </when> + </conditional> + </xml> + <xml name="param_gene_anno"> + <conditional name="gff_file_condi"> + <param name="gffSource" type="select" label="Select a built-in GFF file or one from your history" help="Choose history if you don't see the correct GFF" > + <option value="cached" selected="true">Use a built-in GFF</option> + <option value="history">Use a GFF from history</option> + </param> + <when value="cached"> + <param name="gff_pre_installed" type="select" label="Select a GFF file" help="Select the GFF from a list of pre-installed files"> + <options from_data_table="gene_sets"> + <filter type="sort_by" column="1" /> + </options> + </param> + </when> + <when value="history"> + <param name="gff_history" type="data" format="gff3.gz" label="Select a GFF file" help="Make sure that the GFF corresponds to the same genome as the FASTA"/> + </when> + </conditional> + </xml> + <xml name="param_n_comps" token_value="30" token_label="Number of dimensions to keep" token_help="The result is insensitive to this parameter when `weighted_by_sd` is set, as long as it is large enough, e.g. 30."> + <param argument="n_comps" type="integer" value="@VALUE@" label="@LABEL@" help="@HELP@"/> + </xml> + <xml name="param_meme_table"> + <param name="motifs" type="select" label="Select list of transcription factor motifs"> + <options from_data_table="meme"> + <filter type="sort_by" column="2" /> + </options> + </param> + </xml> + + + <!-- test section --> + <xml name="test_param_render_plot"> + <param name="width" value="650"/> + <param name="height" value="450"/> + </xml> + <xml name="test_render_plot_matching_text"> + <has_text_matching expression="width = 650"/> + <has_text_matching expression="height = 450"/> + </xml> + + + <xml name="citations"> + <citations> + <citation type="doi">10.1038/s41592-023-02139-9</citation> + </citations> + </xml> </macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/all_fasta.loc Tue Nov 25 16:40:54 2025 +0000 @@ -0,0 +1,1 @@ +hg38 hg38 Human (hg38) ${__HERE__}/chr21_small.fasta.gz \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/gene_sets.loc Tue Nov 25 16:40:54 2025 +0000 @@ -0,0 +1,1 @@ +hg38 hg38 hg38GFF ${__HERE__}/chr21.gff3.gz \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/meme.loc Tue Nov 25 16:40:54 2025 +0000 @@ -0,0 +1,1 @@ +cisbp snap.datasets.cis_bp(unique=True) ${__HERE__}/cisBP_human.meme.gz \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/all_fasta.loc.sample Tue Nov 25 16:40:54 2025 +0000 @@ -0,0 +1,17 @@ +#This file lists the locations and dbkeys of all the genome and transcriptome fasta files +#under the "genome" directory (a directory that contains a directory +#for each build. This file has the format (white space characters are +#TAB characters): +# +#<unique_build_id> <dbkey> <display_name> <file_path> +# +#So, all_fasta.loc could look something like this: +# +#apiMel4.5 apiMel4.5 Honeybee (Apis mellifera): apiMel4.5 /path/to/genome/apiMel4.5/apiMel4.5.fa +#hg38canon hg38 Human (Homo sapiens): hg38 Canonical /path/to/genome/hg38/hg38canon.fa +#hg38full hg38 Human (Homo sapiens): hg38 Full /path/to/genome/hg38/hg38full.fa +#hg38full.90 hg38 Human (Homo sapiens): hg38 Full Trans v90 /path/to/genome/hg38/hg38fulltrans.fa + +#Your all_fasta.loc file should contain an entry for each individual +#fasta file. So there will be multiple fasta files for each build, +#such as with hg38 above. \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/gene_sets.loc.sample Tue Nov 25 16:40:54 2025 +0000 @@ -0,0 +1,14 @@ +# This is a sample file distributed with featureCounts that enables it and other# tools to use gene/exon annotations in the GFF/GTF format. +# +# The gene_sets.loc file syntax is: +#<unique_build_id> <dbkey> <display_name> <path> +# +# Please ensure that the above fields are tab separated. +# +# In case you have TWO or MORE providers PER dbkey, the one mentioned +# first in the file, should have the "default" priority. +# +#Example: +# +#Homo_sapiens.GRCh38.90 hg38 GRCh38 (hg38) annotation from Ensembl, release 90 /depot/data2/galaxy/hg38/gene_sets/Homo_sapiens.GRCh38.90.gtf +#Homo_sapiens.GRCh37.87 hg19 GRCh37 (hg19) annotation from Ensembl, release 87 /depot/data2/galaxy/hg19/gene_sets/Homo_sapiens.GRCh37.87.gtf \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/meme.loc.sample Tue Nov 25 16:40:54 2025 +0000 @@ -0,0 +1,13 @@ +# This is a sample file distributed with snapatac2 which enables the tool to perform motif enrichment analysis +# +# The meme.loc file syntax is: +#<unique_id> <display_name> <path> +# +# Please ensure that the above fields are tab separated. +# +# Currently the files should be downloaded manually +# +#Example: +# +#cisbp cis_bp(unique=True) /path/to/cisBP_human.meme.gz +#meuleman_2020 Meuleman_2020 /path/to/Meuleman_2020.meme.gz \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Tue Nov 25 16:40:54 2025 +0000 @@ -0,0 +1,17 @@ +<tables> + <!-- Locations of all fasta files under genome directory --> + <table name="all_fasta" comment_char="#" allow_duplicate_entries="False"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/all_fasta.loc" /> + </table> + <!-- Locations of all gff files with annotations of genome builds --> + <table name="gene_sets" comment_char="#" allow_duplicate_entries="False"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/gene_sets.loc" /> + </table> + <!-- Locations of all meme files --> + <table name="meme" comment_char="#" allow_duplicate_entries="False"> + <columns>value, name, path</columns> + <file path="tool-data/meme.loc" /> + </table> +</tables> \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.test Tue Nov 25 16:40:54 2025 +0000 @@ -0,0 +1,14 @@ +<tables> + <table name="all_fasta" comment_char="#"> + <columns>value, dbkey, name, path</columns> + <file path="${__HERE__}/test-data/all_fasta.loc" /> + </table> + <table name="gene_sets" comment_char="#"> + <columns>value, dbkey, name, path</columns> + <file path="${__HERE__}/test-data/gene_sets.loc" /> + </table> + <table name="meme" comment_char="#"> + <columns>value, name, path</columns> + <file path="${__HERE__}/test-data/meme.loc" /> + </table> +</tables> \ No newline at end of file