Mercurial > repos > iuc > scanpy_remove_confounders

comparison remove_confounders.xml @ 0:9ca360dde8e3 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/scanpy/ commit 92f85afaed0097d1879317a9f513093fce5481d6
author iuc
date Mon, 04 Mar 2019 10:16:47 -0500
parents
children a89ee42625ad
comparison
equal deleted inserted replaced
-1:000000000000 0:9ca360dde8e3
1 <tool id="scanpy_remove_confounders" name="Remove confounders with scanpy" version="@version@">
2 <description></description>
3 <macros>
4 <import>macros.xml</import>
5 <xml name="score_genes_params">
6 <param argument="n_bins" type="integer" value="25" label="Number of expression level bins for sampling" help=""/>
7 <param argument="random_state" type="integer" value="0" label="Random seed for sampling" help=""/>
8 <expand macro="param_use_raw"/>
9 </xml>
10 <token name="@CMD_score_genes_inputs@"><![CDATA[
11 n_bins=$method.n_bins,
12 random_state=$method.random_state,
13 use_raw=$method.use_raw,
14 copy=False
15 ]]></token>
16 </macros>
17 <expand macro="requirements"/>
18 <command detect_errors="exit_code"><![CDATA[
19 @CMD@
20 ]]></command>
21 <configfiles>
22 <configfile name="script_file"><![CDATA[
23 @CMD_imports@
24 @CMD_read_inputs@
25
26 #if $method.method == "pp.regress_out"
27 sc.pp.regress_out(
28 adata=adata,
29 keys='$method.reg_keys',
30 copy=False)
31 #elif $method.method == "tl.score_genes"
32 sc.tl.score_genes(
33 adata=adata,
34 #set $gene_list = [str(x.strip()) for x in str($method.gene_list).split(',')]
35 gene_list=$gene_list,
36 ctrl_size=$method.ctrl_size,
37 score_name='$method.score_name',
38 #if $method.gene_pool
39 #set $gene_pool = [str(x.strip()) for x in $method.gene_pool.split(',')]
40 gene_pool=$gene_pool,
41 #end if
42 @CMD_score_genes_inputs@)
43 adata.obs.to_csv('$obs', sep='\t')
44 #elif $method.method == "tl.score_genes_cell_cycle"
45 sc.tl.score_genes_cell_cycle(
46 adata=adata,
47 #set $s_genes = [str(x.strip()) for x in $method.s_genes.split(',')]
48 s_genes=$s_genes,
49 #set $g2m_genes = [str(x.strip()) for x in $method.g2m_genes.split(',')]
50 g2m_genes=$g2m_genes,
51 @CMD_score_genes_inputs@)
52 adata.obs.to_csv('$obs', sep='\t')
53 #end if
54
55 @CMD_anndata_write_outputs@
56 ]]></configfile>
57 </configfiles>
58 <inputs>
59 <expand macro="inputs_anndata"/>
60 <conditional name="method">
61 <param argument="method" type="select" label="Method used for plotting">
62 <option value="pp.regress_out">Regress out unwanted sources of variation, using `pp.regress_out`</option>
63 <!--<option value="pp.mnn_correct">, using `pp.mnn_correct`</option>!-->
64 <!--<option value="pp.dca">, using `pp.mnn_correct`</option>!-->
65 <!--<option value="pp.magic">, using `pp.magic`</option>!-->
66 <!--<option value="tl.sim">, using `tl.sim`</option>!-->
67 <!--<option value="pp.calculate_qc_metrics">, using `pp.calculate_qc_metrics`</option>!-->
68 <option value="tl.score_genes">Score a set of genes, using `tl.score_genes`</option>
69 <option value="tl.score_genes_cell_cycle">Score cell cycle genes, using `tl.score_genes_cell_cycle`</option>
70 <!--<option value="tl.cyclone">, using `tl.cyclone`</option>!-->
71 <!--<option value="tl.andbag">, using `tl.andbag`</option>!-->
72 </param>
73 <when value="pp.regress_out">
74 <param argument="reg_keys" type="text" value="" label="Keys for observation annotation on which to regress on" help=""/>
75 </when>
76 <when value="tl.score_genes">
77 <param argument="gene_list" type="text" value="" label="The list of gene names used for score calculation" help="Genes separated by a comma"/>
78 <param argument="ctrl_size" type="integer" value="50" label="Number of reference genes to be sampled"
79 help="If `len(gene_list)` is not too low, you can set `ctrl_size=len(gene_list)`."/>
80 <param argument="gene_pool" type="text" value="" optional="true" label="Genes for sampling the reference set"
81 help="Default is all genes. Genes separated by a comma"/>
82 <expand macro="score_genes_params"/>
83 <param argument="score_name" type="text" value="score" label="Name of the field to be added in `.obs`" help=""/>
84 </when>
85 <when value="tl.score_genes_cell_cycle">
86 <param name="s_genes" type="text" value="" label="List of genes associated with S phase" help="Genes separated by a comma"/>
87 <param name="g2m_genes" type="text" value="" label="List of genes associated with G2M phase" help="Genes separated by a comma"/>
88 <expand macro="score_genes_params"/>
89 </when>
90 </conditional>
91 <expand macro="anndata_output_format"/>
92 </inputs>
93 <outputs>
94 <expand macro="anndata_outputs"/>
95 <data name="obs" format="tabular" label="${tool.name} on ${on_string}: Observations annotation">
96 <filter>method['method'] == 'tl.score_genes' or method['method'] == 'tl.score_genes_cell_cycle'</filter>
97 </data>
98 </outputs>
99 <tests>
100 <test>
101 <conditional name="input">
102 <param name="format" value="h5ad" />
103 <param name="adata" value="krumsiek11.h5ad" />
104 </conditional>
105 <conditional name="method">
106 <param name="method" value="pp.regress_out"/>
107 <param name="reg_keys" value="cell_type"/>
108 </conditional>
109 <param name="anndata_output_format" value="h5ad" />
110 <assert_stdout>
111 <has_text_matching expression="sc.pp.regress_out"/>
112 <has_text_matching expression="keys='cell_type'"/>
113 </assert_stdout>
114 <output name="anndata_out_h5ad" file="pp.regress_out.krumsiek11.h5ad" ftype="h5" compare="sim_size"/>
115 </test>
116 <test>
117 <conditional name="input">
118 <param name="format" value="h5ad" />
119 <param name="adata" value="krumsiek11.h5ad" />
120 </conditional>
121 <conditional name="method">
122 <param name="method" value="tl.score_genes"/>
123 <param name="gene_list" value="Gata2, Fog1"/>
124 <param name="ctrl_size" value="2"/>
125 <param name="n_bins" value="2"/>
126 <param name="random_state" value="2"/>
127 <param name="use_raw" value="False"/>
128 <param name="score_name" value="score"/>
129 </conditional>
130 <param name="anndata_output_format" value="h5ad"/>
131 <assert_stdout>
132 <has_text_matching expression="sc.tl.score_genes" />
133 <has_text_matching expression="gene_list=\['Gata2', 'Fog1'\]" />
134 <has_text_matching expression="ctrl_size=2" />
135 <has_text_matching expression="score_name='score'" />
136 <has_text_matching expression="n_bins=2" />
137 <has_text_matching expression="random_state=2" />
138 <has_text_matching expression="use_raw=False" />
139 <has_text_matching expression="copy=False" />
140 </assert_stdout>
141 <output name="anndata_out_h5ad" file="tl.score_genes.krumsiek11.h5ad" ftype="h5" compare="sim_size"/>
142 <output name="obs" file="tl.score_genes.krumsiek11.obs.tabular" ftype="tabular" compare="sim_size"/>
143 </test>
144 <test>
145 <conditional name="input">
146 <param name="format" value="h5ad" />
147 <param name="adata" value="krumsiek11.h5ad" />
148 </conditional>
149 <conditional name="method">
150 <param name="method" value="tl.score_genes_cell_cycle"/>
151 <param name="s_genes" value="Gata2, Fog1, EgrNab"/>
152 <param name="g2m_genes" value="Gata2, Fog1, EgrNab"/>
153 <param name="n_bins" value="2"/>
154 <param name="random_state" value="1"/>
155 <param name="use_raw" value="False"/>
156 </conditional>
157 <param name="anndata_output_format" value="h5ad"/>
158 <assert_stdout>
159 <has_text_matching expression="sc.tl.score_genes_cell_cycle"/>
160 <has_text_matching expression="s_genes=\['Gata2', 'Fog1', 'EgrNab'\]"/>
161 <has_text_matching expression="g2m_genes=\['Gata2', 'Fog1', 'EgrNab'\]"/>
162 <has_text_matching expression="n_bins=2"/>
163 <has_text_matching expression="random_state=1"/>
164 <has_text_matching expression="use_raw=False"/>
165 </assert_stdout>
166 <output name="anndata_out_h5ad" file="tl.score_genes_cell_cycle.krumsiek11.h5ad" ftype="h5" compare="sim_size"/>
167 <output name="obs" file="tl.score_genes_cell_cycle.krumsiek11.obs.tabular" ftype="tabular" compare="sim_size"/>
168 </test>
169 </tests>
170 <help><![CDATA[
171 Regress out unwanted sources of variation, using `pp.regress_out`
172 =================================================================
173
174 Regress out unwanted sources of variation, using simple linear regression. This is
175 inspired by Seurat's `regressOut` function in R.
176
177 More details on the `scanpy documentation
178 <https://scanpy.readthedocs.io/en/latest/api/scanpy.api.pp.regress_out.html#scanpy.api.pp.regress_out>`__
179
180 Score a set of genes, using `tl.score_genes`
181 ============================================
182
183 The score is the average expression of a set of genes subtracted with the
184 average expression of a reference set of genes. The reference set is
185 randomly sampled from the `gene_pool` for each binned expression value.
186
187 This reproduces the approach in Seurat (Satija et al, 2015) and has been implemented
188 for Scanpy by Davide Cittaro.
189
190 More details on the `scanpy documentation
191 <https://scanpy.readthedocs.io/en/latest/api/scanpy.api.tl.score_genes.html#scanpy.api.tl.score_genes>`__
192
193 Score cell cycle genes, using `tl.score_genes_cell_cycle`
194 =========================================================
195
196 Given two lists of genes associated to S phase and G2M phase, calculates
197 scores and assigns a cell cycle phase (G1, S or G2M). See
198 `score_genes` for more explanation.
199
200 More details on the `scanpy documentation
201 <https://scanpy.readthedocs.io/en/latest/api/scanpy.api.tl.score_genes_cell_cycle.html#scanpy.api.tl.score_genes_cell_cycle>`__
202 ]]></help>
203 <expand macro="citations"/>
204 </tool>