Mercurial > repos > iuc > scanpy_inspect
diff inspect.xml @ 3:cc0deb593fc8 draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/scanpy/ commit 3b41d687ff30583540d055f6995de00530cca81d"
| author | iuc |
|---|---|
| date | Thu, 12 Dec 2019 09:27:38 -0500 |
| parents | 7d22964a8639 |
| children | 08192eebb47d |
line wrap: on
line diff
--- a/inspect.xml Thu Dec 05 07:13:18 2019 -0500 +++ b/inspect.xml Thu Dec 12 09:27:38 2019 -0500 @@ -135,7 +135,6 @@ sc.tl.rank_genes_groups( adata=adata, groupby='$method.groupby', - use_raw=$method.use_raw, #if str($method.groups) != '' #set $group=[x.strip() for x in str($method.groups).split(',')] groups=$group, @@ -199,7 +198,7 @@ tol=$method.tl_rank_genes_groups_method.tol, C=$method.tl_rank_genes_groups_method.c, #end if - only_positive=$method.only_positive) + use_raw=$method.use_raw) #else if $method.method == "tl.marker_gene_overlap" reference_markers = {} @@ -256,30 +255,30 @@ <expand macro="inputs_anndata"/> <conditional name="method"> <param argument="method" type="select" label="Method used for inspecting"> - <option value="pp.calculate_qc_metrics">Calculate quality control metrics, using `pp.calculate_qc_metrics`</option> - <option value="pp.neighbors">Compute a neighborhood graph of observations, using `pp.neighbors`</option> - <option value="tl.score_genes">Score a set of genes, using `tl.score_genes`</option> - <option value="tl.score_genes_cell_cycle">Score cell cycle genes, using `tl.score_genes_cell_cycle`</option> - <option value="tl.rank_genes_groups">Rank genes for characterizing groups, using `tl.rank_genes_groups`</option> - <!--<option value="tl.marker_gene_overlap">Calculate an overlap score between data-deriven marker genes and provided markers, using `tl.marker_gene_overlap`</option>--> - <option value="pp.log1p">Logarithmize the data matrix, using `pp.log1p`</option> - <option value="pp.scale">Scale data to unit variance and zero mean, using `pp.scale`</option> - <option value="pp.sqrt">Square root the data matrix, using `pp.sqrt`</option> + <option value="pp.calculate_qc_metrics">Calculate quality control metrics, using 'pp.calculate_qc_metrics'</option> + <option value="pp.neighbors">Compute a neighborhood graph of observations, using 'pp.neighbors'</option> + <option value="tl.score_genes">Score a set of genes, using 'tl.score_genes'</option> + <option value="tl.score_genes_cell_cycle">Score cell cycle genes, using 'tl.score_genes_cell_cycle'</option> + <option value="tl.rank_genes_groups">Rank genes for characterizing groups, using 'tl.rank_genes_groups'</option> + <!--<option value="tl.marker_gene_overlap">Calculate an overlap score between data-deriven marker genes and provided markers, using 'tl.marker_gene_overlap'</option>--> + <option value="pp.log1p">Logarithmize the data matrix, using 'pp.log1p'</option> + <option value="pp.scale">Scale data to unit variance and zero mean, using 'pp.scale'</option> + <option value="pp.sqrt">Square root the data matrix, using 'pp.sqrt'</option> </param> <when value="pp.calculate_qc_metrics"> <param argument="expr_type" type="text" value="counts" label="Name of kind of values in X"/> <param argument="var_type" type="text" value="genes" label="The kind of thing the variables are"/> - <param argument="qc_vars" type="text" value="" label="Keys for boolean columns of `.var` which identify variables you could want to control for" + <param argument="qc_vars" type="text" value="" label="Keys for boolean columns of '.var' which identify variables you could want to control for" help="Keys separated by a comma"/> <param argument="percent_top" type="text" value="" label="Proportions of top genes to cover" - help=" Values (integers) are considered 1-indexed, `50` finds cumulative proportion to the 50th most expressed genes. Values separated by a comma. + help=" Values (integers) are considered 1-indexed, '50' finds cumulative proportion to the 50th most expressed genes. Values separated by a comma. If empty don't calculate"/> </when> <when value="pp.neighbors"> - <param argument="n_neighbors" type="integer" min="0" value="15" label="The size of local neighborhood (in terms of number of neighboring data points) used for manifold approximation" help="Larger values result in more global views of the manifold, while smaller values result in more local data being preserved. In general values should be in the range 2 to 100. If `knn` is `True`, number of nearest neighbors to be searched. If `knn` is `False`, a Gaussian kernel width is set to the distance of the `n_neighbors` neighbor."/> + <param argument="n_neighbors" type="integer" min="0" value="15" label="The size of local neighborhood (in terms of number of neighboring data points) used for manifold approximation" help="Larger values result in more global views of the manifold, while smaller values result in more local data being preserved. In general values should be in the range 2 to 100. If 'knn' is 'True', number of nearest neighbors to be searched. If 'knn' is 'False', a Gaussian kernel width is set to the distance of the 'n_neighbors' neighbor."/> <param argument="n_pcs" type="integer" min="0" value="" optional="true" label="Number of PCs to use" help=""/> <param argument="use_rep" type="text" value="" optional="true" label="Indicated representation to use" help="If not set, the representation is chosen automatically: for n_vars below 50, X is used, otherwise X_pca (uns) is used. If X_pca is not present, it's computed with default parameter"/> - <param argument="knn" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Use a hard threshold to restrict the number of neighbors to n_neighbors?" help="If true, it considers a knn graph. Otherwise, it uses a Gaussian Kernel to assign low weights to neighbors more distant than the `n_neighbors` nearest neighbor."/> + <param argument="knn" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Use a hard threshold to restrict the number of neighbors to n_neighbors?" help="If true, it considers a knn graph. Otherwise, it uses a Gaussian Kernel to assign low weights to neighbors more distant than the 'n_neighbors' nearest neighbor."/> <param argument="random_state" type="integer" value="0" label="Numpy random seed" help=""/> <param name="pp_neighbors_method" argument="method" type="select" label="Method for computing connectivities" help=""> <option value="umap">umap (McInnes et al, 2018)</option> @@ -292,11 +291,11 @@ <when value="tl.score_genes"> <param argument="gene_list" type="text" value="" label="The list of gene names used for score calculation" help="Genes separated by a comma"/> <param argument="ctrl_size" type="integer" value="50" label="Number of reference genes to be sampled" - help="If `len(gene_list)` is not too low, you can set `ctrl_size=len(gene_list)`."/> + help="If 'len(gene_list)' is not too low, you can set 'ctrl_size=len(gene_list)'."/> <param argument="gene_pool" type="text" value="" optional="true" label="Genes for sampling the reference set" help="Default is all genes. Genes separated by a comma"/> <expand macro="score_genes_params"/> - <param argument="score_name" type="text" value="score" label="Name of the field to be added in `.obs`" help=""/> + <param argument="score_name" type="text" value="score" label="Name of the field to be added in '.obs'" help=""/> </when> <when value="tl.score_genes_cell_cycle"> <conditional name='s_genes'> @@ -426,13 +425,11 @@ help="It must be a positive float. Like in support vector machines, smaller values specify stronger regularization."/> </when> </conditional> - <param argument="only_positive" type="boolean" truevalue="True" falsevalue="False" checked="true" - label="Only consider positive differences?" help=""/> </when> <!--<when value="tl.marker_gene_overlap"> <repeat name="reference_markers" title="Marker genes"> <param name="key" type="text" value="" label="Cell identity name" help=""/> - <param name="values" type="text" value="" label="List of genes" help="Comma-separated names from `var`"/> + <param name="values" type="text" value="" label="List of genes" help="Comma-separated names from 'var'"/> </repeat> <param argument="key" type="text" value="rank_genes_groups" label="Key in adata.uns where the rank_genes_groups output is stored"/> <conditional name="overlap"> @@ -598,7 +595,6 @@ <param name="method" value="t-test_overestim_var"/> <param name="corr_method" value="benjamini-hochberg"/> </conditional> - <param name="only_positive" value="true"/> </conditional> <assert_stdout> <has_text_matching expression="sc.tl.rank_genes_groups"/> @@ -608,7 +604,6 @@ <has_text_matching expression="n_genes=100"/> <has_text_matching expression="method='t-test_overestim_var'"/> <has_text_matching expression="corr_method='benjamini-hochberg'"/> - <has_text_matching expression="only_positive=True"/> </assert_stdout> <output name="anndata_out" file="tl.rank_genes_groups.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/> </test> @@ -634,7 +629,6 @@ <param name="tol" value="1e-4"/> <param name="c" value="1.0"/> </conditional> - <param name="only_positive" value="true"/> </conditional> <assert_stdout> <has_text_matching expression="sc.tl.rank_genes_groups"/> @@ -650,7 +644,6 @@ <has_text_matching expression="multi_class='auto'"/> <has_text_matching expression="tol=0.0001"/> <has_text_matching expression="C=1.0"/> - <has_text_matching expression="only_positive=True"/> </assert_stdout> <output name="anndata_out" file="tl.rank_genes_groups.newton-cg.pbmc68k_reduced.h5ad" ftype="h5ad" compare="sim_size"> <assert_contents> @@ -686,7 +679,6 @@ <param name="tol" value="1e-4"/> <param name="c" value="1.0"/> </conditional> - <param name="only_positive" value="true"/> </conditional> <assert_stdout> <has_text_matching expression="sc.tl.rank_genes_groups"/> @@ -702,7 +694,6 @@ <has_text_matching expression="intercept_scaling=1.0"/> <has_text_matching expression="tol=0.0001"/> <has_text_matching expression="C=1.0"/> - <has_text_matching expression="only_positive=True"/> </assert_stdout> <output name="anndata_out" file="tl.rank_genes_groups.liblinear.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"> <assert_contents> @@ -797,18 +788,18 @@ Calculates a number of qc metrics for an AnnData object, largely based on calculateQCMetrics from scater. Currently is most efficient on a sparse CSR or dense matrix. -It updates the observation level metrics: +It updates the observation level metrics with - total_{var_type}_by_{expr_type} (e.g. "total_genes_by_counts", number of genes with positive counts in a cell) - total_{expr_type} (e.g. "total_counts", total number of counts for a cell) -- pct_{expr_type}_in_top_{n}_{var_type} (e.g. "pct_counts_in_top_50_genes", cumulative percentage of counts for 50 most expressed genes in a cell) -- total_{expr_type}_{qc_var} (e.g. "total_counts_mito", total number of counts for variabes in qc_vars ) -- pct_{expr_type}_{qc_var} (e.g. "pct_counts_mito", proportion of total counts for a cell which are mitochondrial) +- pct_{expr_type}_in_top_{n}_{var_type} - for n in percent_top (e.g. "pct_counts_in_top_50_genes", cumulative percentage of counts for 50 most expressed genes in a cell) +- total_{expr_type}_{qc_var} - for qc_var in qc_vars (e.g. "total_counts_mito", total number of counts for variabes in qc_vars) +- pct_{expr_type}_{qc_var} - for qc_var in qc_vars (e.g. "pct_counts_mito", proportion of total counts for a cell which are mitochondrial) And also the variable level metrics: - total_{expr_type} (e.g. "total_counts", sum of counts for a gene) -- mean_{expr_type} (e.g. "mean counts", mean expression over all cells. +- mean_{expr_type} (e.g. "mean counts", mean expression over all cells) - n_cells_by_{expr_type} (e.g. "n_cells_by_counts", number of cells this expression is measured in) - pct_dropout_by_{expr_type} (e.g. "pct_dropout_by_counts", percentage of cells this feature does not appear in)