comparison scanpy-find-variable-genes.xml @ 0:305d0cbe0ffd draft

planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/tree/develop/tools/tertiary-analysis/scanpy commit 9bf9a6e46a330890be932f60d1d996dd166426c4
author ebi-gxa
date Wed, 03 Apr 2019 11:12:05 -0400
parents
children b089f4a55e6b
comparison
equal deleted inserted replaced
-1:000000000000 0:305d0cbe0ffd
1 <?xml version="1.0" encoding="utf-8"?>
2 <tool id="scanpy_find_variable_genes" name="Scanpy FindVariableGenes" version="@TOOL_VERSION@+galaxy0">
3 <description>based on normalised dispersion of expression</description>
4 <macros>
5 <import>scanpy_macros.xml</import>
6 </macros>
7 <expand macro="requirements"/>
8 <command detect_errors="exit_code"><![CDATA[
9 ln -s '${input_obj_file}' input.h5 &&
10 PYTHONIOENCODING=utf-8 scanpy-find-variable-genes.py -i input.h5
11 -f '${input_format}'
12 -o output.h5
13 -F '${output_format}'
14 --flavor '${flavor}'
15 -b '${n_bin}'
16 #if $parameters
17 #set pars = ','.join([str($p['name']) for $p in $parameters])
18 -p '${pars}'
19 #set mins = ','.join([str($p['min']) for $p in $parameters])
20 -l '${mins}'
21 #set maxs = ','.join([str($p['max']) for $p in $parameters])
22 -j '${maxs}'
23 #end if
24 #if $n_top_gene
25 -n '${n_top_gene}'
26 #end if
27 ]]></command>
28
29 <inputs>
30 <expand macro="input_object_params"/>
31 <expand macro="output_object_params"/>
32 <param name="flavor" argument="--flavor" type="select" value="seurat" label="Flavor of computing normalised dispersion">
33 <option value="seurat">Seurat</option>
34 <option value="cell_ranger">Cell-ranger</option>
35 </param>
36 <repeat name="parameters" min="1" title="Parameters used to find variable genes">
37 <param name="name" type="select" label="Name of parameter to filter on">
38 <option value="mean">Mean of expression</option>
39 <option value="disp">Dispersion of expression</option>
40 </param>
41 <param name="min" type="float" value="0" label="Min value"/>
42 <param name="max" type="float" value="1e9" label="Max value"/>
43 </repeat>
44 <param name="n_bin" argument="--n-bins" type="integer" value="20" label="Number of bins for binning the mean expression"/>
45 <param name="n_top_gene" argument="--n-top-genes" type="integer" optional="true" label="Number of top variable genes to keep"/>
46 </inputs>
47
48 <outputs>
49 <data name="output_h5" format="h5" from_work_dir="output.h5" label="${tool.name} on ${on_string}: Variable genes"/>
50 </outputs>
51
52 <tests>
53 <test>
54 <param name="input_obj_file" value="normalise_data.h5"/>
55 <param name="input_format" value="anndata"/>
56 <param name="output_format" value="anndata"/>
57 <param name="flavor" value="seurat"/>
58 <param name="n_bin" value="20"/>
59 <repeat name="parameters">
60 <param name="name" value="mean"/>
61 <param name="min" value="0.0125"/>
62 <param name="max" value="3"/>
63 </repeat>
64 <repeat name="parameters">
65 <param name="name" value="disp"/>
66 <param name="min" value="0.5"/>
67 <param name="max" value="1e9"/>
68 </repeat>
69 <output name="output_h5" file="find_variable_genes.h5" ftype="h5" compare="sim_size"/>
70 </test>
71 </tests>
72
73 <help><![CDATA[
74 ============================================================
75 Extract highly variable genes (`pp.filter_genes_dispersion`)
76 ============================================================
77
78 Depending on `flavor`, this reproduces the R-implementations of Seurat and Cell Ranger.
79
80 The normalized dispersion is obtained by scaling with the mean and standard
81 deviation of the dispersions for genes falling into a given bin for mean
82 expression of genes. This means that for each bin of mean expression, highly
83 variable genes are selected.
84
85 @HELP@
86
87 @VERSION_HISTORY@
88 ]]></help>
89 <expand macro="citations">
90 <citation type="doi">10.1038/nbt.3192</citation>
91 <citation type="doi">10.1038/ncomms14049</citation>
92 </expand>
93 </tool>