Mercurial > repos > iuc > preprocess_muon

comparison preprocess_muon.xml @ 0:f86862ab76fb draft default tip

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/main/tools/muon commit fef10e0d450018d1e6ba4cbbda76c7686edc8aae
author iuc
date Sat, 25 Oct 2025 21:00:39 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:f86862ab76fb
1 <tool id="preprocess_muon" name="muon filter and normalize" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
2 <macros>
3 <import>macros.xml</import>
4 </macros>
5 <expand macro="requirements"/>
6 <expand macro="version_command"/>
7 <command detect_errors="exit_code"><![CDATA[
8 @COPY_MUDATA@
9 @CMD@
10 ]]></command>
11 <configfiles>
12 <configfile name="script_file"><![CDATA[
13 @CMD_imports@
14 @CMD_read_inputs@
15
16 #if $method.method == 'pp.intersect_obs'
17 mu.pp.intersect_obs(
18 mdata
19 )
20 ## Update the features. Only union features of the modalities are considered
21 mdata.update_var()
22
23
24 #else if $method.method == 'pp.l2norm'
25 mu.pp.l2norm(
26 mdata,
27 #if $method.mod
28 mod='$method.mod',
29 #end if
30 #if $method.rep
31 rep='$method.rep',
32 #end if
33 n_pcs=$method.n_pcs,
34 copy=False
35 )
36
37 #else if $method.method == 'pp.neighbors'
38 mu.pp.neighbors(
39 mdata,
40 #if str($method.n_neighbors)
41 n_neighbors=$method.n_neighbors,
42 #end if
43 n_bandwidth_neighbors=$method.n_bandwidth_neighbors,
44 n_multineighbors=$method.n_multineighbors,
45 @CMD_neighbor_keys@
46 metric='$method.metric',
47 #if $method.key_added
48 key_added='$method.key_added',
49 #end if
50 weight_key='$method.weight_key',
51 add_weights_to_modalities=$method.add_weights_to_modalities,
52 eps=$method.eps,
53 random_state=$method.random_state,
54 copy=False
55 )
56
57 #else if $method.method == 'pp.sample_obs'
58 mu.pp.sample_obs(
59 mdata,
60 frac=$method.frac,
61 #if $method.groupby
62 groupby='$method.groupby',
63 #end if
64 #if str($method.min_n)
65 min_n=$method.min_n
66 #end if
67 )
68 #end if
69
70 @CMD_mudata_write_outputs@
71 ]]></configfile>
72 </configfiles>
73 <inputs>
74 <expand macro="inputs_mudata"/>
75 <conditional name="method">
76 <param name="method" type="select" label="Method used for plotting">
77 <option value="pp.intersect_obs">Subset: Subset observations present only in all modalities, using 'muon.pp.intersect_obs'</option>
78 <option value="pp.l2norm">Normalize: Normalize observations to unit L2 norm, using 'muon.pp.l2norm'</option>
79 <option value="pp.neighbors">Search: Multimodal nearest neighbor search, using 'muon.pp.neighbors'</option>
80 <option value="pp.sample_obs">Return an object with some of the observations (subsampling). 'muon.pp.sample_obs'</option>
81 </param>
82 <when value="pp.intersect_obs"/>
83 <when value="pp.l2norm">
84 <param argument="mod" type="text" optional="true" label="Names of the modalities to normalize" help="Leave empty to use all modalities">
85 <expand macro="sanitize_string" />
86 </param>
87 <param argument="rep" type="text" optional="true" label="The representation to normalize." help="X or any key for .obsm is valid, for all modalities">
88 <expand macro="sanitize_query" />
89 </param>
90 <param argument="n_pcs" type="integer" min="0" value="0" label="The number of principal components to use." help="This affects the result only if a PCA representation is being normalized"/>
91 </when>
92 <when value="pp.neighbors">
93 <param argument="n_neighbors" type="integer" optional="true" label="Number of nearest neighbors to find"
94 help="If not set, arithmetic mean of per-modality neighbors will be used"/>
95 <param argument="n_bandwidth_neighbors" type="integer" value="20" label="Number of nearest neighbors to use for bandwidth selection"/>
96 <param argument="n_multineighbors" type="integer" value="200" label="Number of nearest neighbors in each modality to consider as candidates for multimodal nearest neighbors"
97 help="Only points in the union of per-modality nearest neighbors are candidates for multimodal nearest neighbors.
98 This will use the same metric that was used for the nearest neighbor search in the respective modality."/>
99 <expand macro="param_neighbor_keys"/>
100 <param argument="metric" type="select" label="Distance measure to use" help="This will only be used in the final step to search for nearest neighbors in the set of candidates.">
101 <option value="euclidean" selected="true">euclidean</option>
102 <option value="braycurtis">braycurtis</option>
103 <option value="canberra">canberra</option>
104 <option value="chebyshev">chebyshev</option>
105 <option value="cityblock">cityblock</option>
106 <option value="correlation">correlation</option>
107 <option value="cosine">cosine</option>
108 <option value="dice">dice</option>
109 <option value="hamming">hamming</option>
110 <option value="jaccard">jaccard</option>
111 <option value="jensenshannon">jensenshannon</option>
112 <option value="kulsinski">kulsinski</option>
113 <option value="mahalanobis">mahalanobis</option>
114 <option value="matching">matching</option>
115 <option value="minkowski">minkowski</option>
116 <option value="rogerstanimoto">rogerstanimoto</option>
117 <option value="russellrao">russellrao</option>
118 <option value="seuclidean">seuclidean</option>
119 <option value="sokalmichener">sokalmichener</option>
120 <option value="sokalsneath">sokalsneath</option>
121 <option value="sqeuclidean">sqeuclidean</option>
122 <option value="wminkowski">wminkowski</option>
123 <option value="yule">yule</option>
124 </param>
125 <expand macro="param_key_added_common"/>
126 <param argument="weight_key" type="text" value="mod_weight" label="Weight key to add to each modality’s .obs or to mdata.obs">
127 <expand macro="sanitize_query" />
128 </param>
129 <param argument="add_weights_to_modalities" type="boolean" truevalue="True" falsevalue="False" checked="false" label="If to add weights to individual modalities" help="By default, the weights will be added to mdata.obs"/>
130 <expand macro="param_eps" eps_value="0.0001"/>
131 <expand macro="param_random_state" seed="42"/>
132 </when>
133 <when value="pp.sample_obs">
134 <param argument="frac" type="float" min="0" max="1" value="0.1" label="A fraction of observations to return"/>
135 <param argument="groupby" type="text" optional="true" label="Categorical column in .obs that is used for prior grouping before sampling observations">
136 <expand macro="sanitize_query"/>
137 </param>
138 <param argument="min_n" type="integer" min="0" optional="true" label="Return min_n observations if fraction frac of observations is below min_n"
139 help="When groupby is not None, min_n is applied per group."/>
140 </when>
141 </conditional>
142 <expand macro="inputs_common_advanced" />
143 </inputs>
144 <outputs>
145 <expand macro="muon_outputs"/>
146 </outputs>
147 <tests>
148 <test expect_num_outputs="2">
149 <!-- test1: intersect_obs -->
150 <param name="mdata" ftype="h5ad" location="https://zenodo.org/records/12570984/files/pbmc3k_chr21.h5mu"/>
151 <param name="method" value="pp.intersect_obs"/>
152 <section name="advanced_common">
153 <param name="show_log" value="true" />
154 </section>
155 <output name="hidden_output">
156 <assert_contents>
157 <has_text_matching expression="mu.pp.intersect_obs"/>
158 </assert_contents>
159 </output>
160 <assert_stdout>
161 <has_text_matching expression="179 × 490"/>
162 <has_text_matching expression="179 x 178"/>
163 <has_text_matching expression="179 x 312"/>
164 </assert_stdout>
165 <output name="mudata_out" ftype="h5ad">
166 <assert_contents>
167 <has_h5_keys keys="mod/rna"/>
168 <has_h5_keys keys="mod/atac"/>
169 </assert_contents>
170 </output>
171 </test>
172 <test expect_num_outputs="2">
173 <!-- test2: l2norm -->
174 <param name="mdata" ftype="h5ad" location="https://zenodo.org/records/12570984/files/pbmc3k_chr21.h5mu"/>
175 <param name="method" value="pp.l2norm"/>
176 <param name="n_pcs" value="5"/>
177 <section name="advanced_common">
178 <param name="show_log" value="true" />
179 </section>
180 <output name="hidden_output">
181 <assert_contents>
182 <has_text_matching expression="mu.pp.l2norm"/>
183 <has_text_matching expression="copy=False"/>
184 <has_text_matching expression="n_pcs=5"/>
185 </assert_contents>
186 </output>
187 <assert_stdout>
188 <has_text_matching expression="179 × 490"/>
189 <has_text_matching expression="179 x 178"/>
190 <has_text_matching expression="179 x 312"/>
191 </assert_stdout>
192 <output name="mudata_out" ftype="h5ad">
193 <assert_contents>
194 <has_h5_keys keys="mod/rna"/>
195 <has_h5_keys keys="mod/atac"/>
196 </assert_contents>
197 </output>
198 </test>
199 <test expect_num_outputs="2">
200 <!-- test3: neighbors -->
201 <param name="mdata" ftype="h5ad" location="https://zenodo.org/records/12570984/files/pbmc3k_chr21_pp.neighbors_in.h5mu"/>
202 <param name="method" value="pp.neighbors"/>
203 <param name="n_neighbors" value="2"/>
204 <param name="n_bandwidth_neighbors" value="3"/>
205 <param name="n_multineighbors" value="5"/>
206 <conditional name="n_keys">
207 <param name="type" value="separate"/>
208 <repeat name="modalities">
209 <param name="mod_name" value="rna"/>
210 <param name="neighbor_keys" value="neighbors"/>
211 </repeat>
212 <repeat name="modalities">
213 <param name="mod_name" value="atac"/>
214 <param name="neighbor_keys" value="neighbors"/>
215 </repeat>
216 </conditional>
217 <section name="advanced_common">
218 <param name="show_log" value="true" />
219 </section>
220 <output name="hidden_output">
221 <assert_contents>
222 <has_text_matching expression="mu.pp.neighbors"/>
223 <has_text_matching expression="copy=False"/>
224 <has_text_matching expression="n_neighbors=2"/>
225 <has_text_matching expression="n_bandwidth_neighbors=3"/>
226 <has_text_matching expression="n_multineighbors=5"/>
227 <has_text_matching expression="metric='euclidean'"/>
228 <has_text_matching expression="weight_key='mod_weight'"/>
229 <has_text_matching expression="add_weights_to_modalities=False"/>
230 <has_text_matching expression="eps=0.0001"/>
231 <has_text_matching expression="random_state=42"/>
232 </assert_contents>
233 </output>
234 <assert_stdout>
235 <has_text_matching expression="2711 × 1781"/>
236 <has_text_matching expression="2711 x 555"/>
237 <has_text_matching expression="2711 x 1226"/>
238 </assert_stdout>
239 <output name="mudata_out" ftype="h5ad">
240 <assert_contents>
241 <has_h5_keys keys="mod/rna"/>
242 <has_h5_keys keys="mod/atac"/>
243 </assert_contents>
244 </output>
245 </test>
246 <test expect_num_outputs="2">
247 <!-- test4: sample_obs -->
248 <param name="mdata" ftype="h5ad" location="https://zenodo.org/records/12570984/files/pbmc3k_chr21.h5mu"/>
249 <param name="method" value="pp.sample_obs"/>
250 <param name="frac" value="0.5"/>
251 <param name="min_n" value="10"/>
252 <section name="advanced_common">
253 <param name="show_log" value="true" />
254 </section>
255 <output name="hidden_output">
256 <assert_contents>
257 <has_text_matching expression="mu.pp.sample_obs"/>
258 <has_text_matching expression="frac=0.5"/>
259 <has_text_matching expression="min_n=10"/>
260 </assert_contents>
261 </output>
262 <assert_stdout>
263 <has_text_matching expression="179 × 490"/>
264 <has_text_matching expression="179 x 178"/>
265 <has_text_matching expression="179 x 312"/>
266 </assert_stdout>
267 <output name="mudata_out" ftype="h5ad">
268 <assert_contents>
269 <has_h5_keys keys="mod/rna"/>
270 <has_h5_keys keys="mod/atac"/>
271 </assert_contents>
272 </output>
273 </test>
274 </tests>
275 <help><![CDATA[
276 Filter: Filter observations (samples or cells) in-place using any column in .obs or in .X ('muon.pp.filter_obs')
277 ================================================================================================================
278
279 Filter observations (samples or cells) in-place using any column in .obs or in .X.
280
281 More details on the `muon documentation
282 <https://muon.readthedocs.io/en/latest/api/generated/muon.pp.filter_obs.html#muon.pp.filter_obs>`__
283
284 Filter: Filter variables (features) ('muon.pp.filter_var')
285 ==========================================================
286
287 Filter variables (features, e.g. genes) in-place using any column in .var or row in .X.
288
289 More details on the `muon documentation
290 <https://muon.readthedocs.io/en/latest/api/generated/muon.pp.filter_var.html#muon.pp.filter_var>`__
291
292 Subset: Subset observations (samples or cells) in-place taking observations present only in all modalities ('muon.pp.intersect_obs')
293 ====================================================================================================================================
294
295 Subset observations (samples or cells) in-place taking observations present only in all modalities.
296
297 More details on the `muon documentation
298 <https://muon.readthedocs.io/en/latest/api/generated/muon.pp.intersect_obs.html#muon.pp.intersect_obs>`__
299
300 Normalize: Normalize observations to unit L2 norm ('muon.pp.l2norm')
301 ====================================================================
302
303 Normalize observations to unit L2 norm.
304
305 More details on the `muon documentation
306 <https://muon.readthedocs.io/en/latest/api/generated/muon.pp.l2norm.html#muon.pp.l2norm>`__
307
308 Search: Multimodal nearest neighbor search ('muon.pp.neighbors')
309 ================================================================
310
311 Multimodal nearest neighbor search by implementing the multimodal nearest neighbor method of Hao et al. and Swanson et al.
312 The neighbor search efficiency on this heavily relies on UMAP. In particular, you may want to decrease
313 n_multineighbors for large data set to avoid excessive peak memory use. To achieve results as close as possible
314 to the Seurat implementation, observations must be normalized to unit L2 norm prior to running per-modality
315 nearest-neighbor search.
316
317 More details on the `muon documentation
318 <https://muon.readthedocs.io/en/latest/api/generated/muon.pp.neighbors.html#muon.pp.neighbors>`__
319
320 ]]></help>
321 <expand macro="citations"/>
322 </tool>