Mercurial > repos > iuc > spapros_selection

comparison selection.xml @ 0:c7527212b66b 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/master/tools/spapros/ commit aed7fe13fa0ed09d77a31eeecaf3ec3fba7eed3b
author iuc
date Mon, 16 Sep 2024 11:37:46 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:c7527212b66b
1 <tool id="spapros_selection" name="Selection" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@profile@">
2 <description>of marker genes with spapros</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements">
7 </expand>
8 <expand macro="version_command"/>
9 <command detect_errors="exit_code"><![CDATA[
10 @CMD@
11 ]]></command>
12 <configfiles>
13 <configfile name="script_file"><![CDATA[
14 @CMD_imports@
15 @CMD_read_inputs@
16
17 random.seed($seed)
18
19 mpl.rcParams['figure.dpi'] = $general_figure_options.dpi
20 plt.rcParams["font.size"] = $general_figure_options.fontsize
21
22 header_markerset='infer'
23 #if $cond_markerset.select_markerset == 'True' and $cond_markerset.header_markerset == 'not_included':
24 header_markerset=None
25 #end if
26
27 selector = sp.se.ProbesetSelector(
28 adata,
29 celltype_key='$celltype_key',
30 #if $genes_key != '':
31 genes_key='$genes_key',
32 #else:
33 genes_key=None,
34 #end if
35 #if $cond_n.select_n == 'True':
36 n=$cond_n.n,
37 #else:
38 n=None,
39 #end if
40 #if $preselected_genes != ''
41 preselected_genes = '$preselected_genes'.split(','),
42 #end if
43 #if $prior_genes != ''
44 prior_genes = '$prior_genes'.split(','),
45 #end if
46 #if $cond_n_pca_genes.select_n_pca_genes == 'True':
47 n_pca_genes=$cond_n_pca_genes.n_pca_genes,
48 #end if
49 #if $min_mean_difference != 0.0:
50 min_mean_difference=$min_mean_difference,
51 #end if
52 n_min_markers=$n_min_markers,
53 #if $celltypes != 'all':
54 celltypes='$celltypes'.split(','),
55 #else
56 celltypes='$celltypes',
57 #end if
58 #if $cond_markerset.select_markerset == 'True':
59 marker_list = {key: [v for v in list(value.values()) if pd.notna(v)] for key, value in pd.read_csv('$cond_markerset.markerset', sep='\t', index_col=0, header=header_markerset).to_dict(orient='index').items()},
60 #end if
61 n_list_markers=$n_list_markers,
62 marker_corr_th=$marker_corr_th,
63 #if $pca_penalties != ''
64 pca_penalties = '$pca_penalties'.split(','),
65 #end if
66 #if $DE_penalties != ''
67 DE_penalties = '$DE_penalties'.split(','),
68 #end if
69 #if $m_penalties_adata_celltypes != ''
70 m_penalties_adata_celltypes = '$m_penalties_adata_celltypes'.split(','),
71 #end if
72 #if $m_penalties_list_celltypes != ''
73 m_penalties_list_celltypes = '$m_penalties_list_celltypes'.split(','),
74 #end if
75 #if $advanced_options.cond_DE_selection_hparams.select_DE_selection_hparams == 'True':
76 DE_selection_hparams={"n": $advanced_options.cond_DE_selection_hparams.n_DE_selection_hparams, "per_group": $advanced_options.cond_DE_selection_hparams.per_group}
77 #end if
78 #if $advanced_options.cond_forest_hparams.select_forest_hparams == 'True':
79 forest_hparams={"n_trees": $advanced_options.cond_forest_hparams.n_trees, "subsample": $advanced_options.cond_forest_hparams.subsample, "test_subsample": $advanced_options.cond_forest_hparams.test_subsample},
80 #end if
81 #if $advanced_options.cond_forest_DE_baseline_hparams.select_forest_DE_baseline_hparams == 'True':
82 forest_DE_baseline_hparams={
83 "n_DE": $advanced_options.cond_forest_DE_baseline_hparams.n_DE,
84 "min_score": $advanced_options.cond_forest_DE_baseline_hparams.min_score,
85 "n_stds": $advanced_options.cond_forest_DE_baseline_hparams.n_stds,
86 "max_step": $advanced_options.cond_forest_DE_baseline_hparams.max_step,
87 "min_outlier_dif": $advanced_options.cond_forest_DE_baseline_hparams.min_outlier_dif,
88 "n_terminal_repeats": $advanced_options.cond_forest_DE_baseline_hparams.n_terminal_repeats,
89 },
90 #end if
91 #if $advanced_options.cond_add_forest_genes_hparams.select_add_forest_genes_hparams == 'True':
92 add_forest_genes_hparams={"n_max_per_it": $advanced_options.cond_add_forest_genes_hparams.n_max_per_it, "performance_th": $advanced_options.cond_add_forest_genes_hparams.performance_th, "importance_th": $advanced_options.cond_add_forest_genes_hparams.importance_th},
93 #end if
94 #if $advanced_options.cond_marker_selection_hparams.select_marker_selection_hparams == 'True':
95 marker_selection_hparams={"penalty_threshold": $advanced_options.cond_marker_selection_hparams.penalty_threshold},
96 #end if
97 verbosity=0,
98 seed=$seed,
99 n_jobs=int(os.environ.get('GALAXY_SLOTS', '4'))
100 )
101
102 selector.select_probeset()
103
104 sp.pl.masked_dotplot(
105 adata,
106 selector,
107 ct_key='$figure_options_masked_dotplot.ct_key',
108 imp_threshold=$figure_options_masked_dotplot.imp_threshold,
109 #if $figure_options_masked_dotplot.celltypes != '':
110 celltypes='$figure_options_masked_dotplot.celltypes',
111 #end if
112 #if $figure_options_masked_dotplot.n_genes != 0:
113 n_genes=$figure_options_masked_dotplot.n_genes,
114 #end if
115 #if $figure_options_masked_dotplot.comb_markers_only:
116 comb_markers_only=True,
117 #end if
118 #if $figure_options_masked_dotplot.markers_only:
119 markers_only=True,
120 #end if
121 cmap='$figure_options_masked_dotplot.cmap',
122 comb_marker_color='$figure_options_masked_dotplot.comb_marker_color',
123 marker_color='$figure_options_masked_dotplot.marker_color',
124 non_adata_celltypes_color='$figure_options_masked_dotplot.non_adata_celltypes_color',
125 use_raw=$figure_options_masked_dotplot.use_raw,
126 save='masked_dotplot.$format',
127 )
128
129 selector.plot_gene_overlap(
130 style='$figure_options_plot_gene_overlap.style',
131 save='gene_overlap.$format',
132 show=False
133 )
134
135 probe_genes = selector.probeset.index[selector.probeset.selection]
136 celltypes_DE_1vsall = list(selector.probeset[selector.probeset.selection]['celltypes_DE_1vsall'])
137 celltypes_DE_specific = list(selector.probeset[selector.probeset.selection]['celltypes_DE_specific'])
138 celltypes_DE = list(selector.probeset[selector.probeset.selection]['celltypes_DE'])
139 celltypes_marker = list(selector.probeset[selector.probeset.selection]['celltypes_marker'])
140
141 marker_dict = dict()
142
143 for i,g in enumerate(probe_genes):
144 recognized_celltypes = list(set(celltypes_DE_1vsall[i].split(',') + celltypes_DE_specific[i].split(',') + \
145 celltypes_DE[i].split(',') + celltypes_marker[i].split(',')))
146
147 if (len(recognized_celltypes) > 1 and '' in recognized_celltypes):
148 recognized_celltypes.remove('')
149
150 for c in recognized_celltypes:
151 if c == '':
152 c = 'Unkown'
153 if c not in marker_dict:
154 marker_dict[c] = [g]
155 else:
156 marker_dict[c] = marker_dict[c] + [g]
157
158 # Find the maximum length of lists
159 max_len = max(len(lst) for lst in marker_dict.values())
160 sorted_marker_dict_by_keys = {key: marker_dict[key] for key in sorted(marker_dict.keys())}
161 # Fill smaller lists with empty values
162 for key, value in sorted_marker_dict_by_keys.items():
163 sorted_marker_dict_by_keys[key] = value + [''] * (max_len - len(value))
164 df = pd.DataFrame(sorted_marker_dict_by_keys).T
165 df.to_csv('marker.tsv', sep='\t', index=True)
166
167 ]]></configfile>
168 </configfiles>
169 <inputs>
170 <expand macro="inputs_anndata"/>
171 <expand macro="param_plot_format"/>
172 <param name="celltype_key" type="text" value="celltype" optional="false" label="Key in adata.obs with celltype annotations"/>
173 <param name="genes_key" type="text" optional="true" label="Key in adata.var for preselected genes" help="This is typically highly_variable_genes. Leave empty to not subset genes."/>
174 <conditional name="cond_n">
175 <param name="select_n" type="select" label="Do you want to set the number of finally selected genes?" help="Note that when `No` we automatically infer n as the minimal number of recommended genes.">
176 <option value="False">No</option>
177 <option value="True">Yes</option>
178 </param>
179 <when value="True">
180 <param argument="n" type="integer" value="20" min="1" optional="false" label="Number of finally selected genes" help="Setting n might change the gene ranking since the final added list_markers are added based on the theoretically added genes without list_markers."/>
181 </when>
182 <when value="False"/>
183 </conditional>
184 <param name="preselected_genes" type="text" optional="true" label="Pre selected genes (comma separated)" help="These will also have the highest ranking in the final list."/>
185 <param name="prior_genes" type="text" optional="true" label="Prioritized genes (comma separated)"/>
186 <conditional name="cond_n_pca_genes">
187 <param name="select_n_pca_genes" type="select" label="Do you want to set the number of preselected pca genes?" help="If not, then this step will be skipped.">
188 <option value="True">Yes</option>
189 <option value="False">No</option>
190 </param>
191 <when value="True">
192 <param argument="n_pca_genes" type="integer" value="100" min="1" optional="false" label="Number of preselected pca genes"/>
193 </when>
194 <when value="False"/>
195 </conditional>
196 <param argument="min_mean_difference" type="float" value="0.0" optional="false" label="Minimal difference of mean expression between at least one celltype and the background" help="This minimal difference is applied as an additional binary penalty in pca_penalties, DE_penalties and m_penalties_adata_celltypes."/>
197 <param argument="n_min_markers" type="integer" value="2" min="1" optional="false" label="The minimal number of identified and added markers"/>
198 <param name="celltypes" type="text" value="all" optional="false" label="Cell types for which trees are trained" help="If not `all` then seperate the cell type with a comma (e.g., Glia,Neuron)"/>
199 <conditional name="cond_markerset">
200 <param name="select_markerset" type="select" label="Do you want to provide a set of marker genes?">
201 <option value="False">No</option>
202 <option value="True">Yes</option>
203 </param>
204 <when value="True">
205 <param name="markerset" type="data" format="tabular" label="Markerset tabular file with rows=conditions (e.g., celltypes) and column=features (e.g., genes)"/>
206 <param name="header_markerset" type="select" optional="false" label="Header in the list of markers?">
207 <option value="included">Header included</option>
208 <option value="not_included">Header not included</option>
209 </param>
210 </when>
211 <when value="False"/>
212 </conditional>
213 <param argument="n_list_markers" type="integer" value="2" min="1" optional="false" label="Minimal number of markers per celltype that are at least selected" help="Selected means either selecting genes from the marker list or having correlated genes in the already selected panel."/>
214 <param argument="marker_corr_th" type="float" value="0.5" optional="false" label="Minimal correlation to consider a gene as captured"/>
215 <param name="pca_penalties" type="text" optional="true" label="List of keys for columns in adata.var containing penalty factors that are multiplied with the scores for PCA based gene selection" help="(comma separted)"/>
216 <param name="DE_penalties" type="text" optional="true" label="List of keys for columns in adata.var containing penalty factors that are multiplied with the scores for DE based gene selection (comma separted)" help="(comma separted)"/>
217 <param name="m_penalties_adata_celltypes" type="text" optional="true" label="List of keys for columns in adata.var containing penalty factors to filter out marker genes if a gene's penalty &lt; threshold for celltypes in adata" help="(comma separted)"/>
218 <param name="m_penalties_list_celltypes" type="text" optional="true" label="List of keys for columns in adata.var containing penalty factors to filter out marker genes if a gene's penalty &lt; threshold for celltypes **not** in adata" help="(comma separted)"/>
219 <param argument="seed" type="integer" value="123" min="0" optional="false" label="Random number seed"/>
220
221 <section name="advanced_options" title="Advanced Options" expanded="false">
222 <conditional name="cond_DE_selection_hparams">
223 <param name="select_DE_selection_hparams" type="select" label="Do you want to tune hyperparameters for the DE based gene selection?">
224 <option value="False">No</option>
225 <option value="True">Yes</option>
226 </param>
227 <when value="True">
228 <param argument="n_DE_selection_hparams" type="integer" value="3" optional="false" label="n"/>
229 <param name="per_group" type="select" label="per_group">
230 <option value="False">No</option>
231 <option value="True">Yes</option>
232 </param>
233 </when>
234 <when value="False"/>
235 </conditional>
236 <conditional name="cond_forest_hparams">
237 <param name="select_forest_hparams" type="select" label="Do you want to tune hyperparameters for the forest based gene selection?">
238 <option value="False">No</option>
239 <option value="True">Yes</option>
240 </param>
241 <when value="True">
242 <param argument="n_trees" type="integer" value="50" optional="false" label="n_trees"/>
243 <param argument="subsample" type="integer" value="1000" optional="false" label="subsample"/>
244 <param argument="test_subsample" type="integer" value="3000" optional="false" label="test_subsample"/>
245 </when>
246 <when value="False"/>
247 </conditional>
248 <conditional name="cond_forest_DE_baseline_hparams">
249 <param name="select_forest_DE_baseline_hparams" type="select" label="Do you want to tune hyperparameters for the DE based gene selection?">
250 <option value="False">No</option>
251 <option value="True">Yes</option>
252 </param>
253 <when value="True">
254 <param argument="n_DE" type="integer" value="1" optional="false" label="n_DE"/>
255 <param argument="min_score" type="float" value="0.9" optional="false" label="min_score"/>
256 <param argument="n_stds" type="float" value="1.0" optional="false" label="n_stds"/>
257 <param argument="max_step" type="integer" value="3" optional="false" label="max_step"/>
258 <param argument="min_outlier_dif" type="float" value="0.02" optional="false" label="min_outlier_dif"/>
259 <param argument="n_terminal_repeats" type="integer" value="3" optional="false" label="n_terminal_repeats"/>
260 </when>
261 <when value="False"/>
262 </conditional>
263 <conditional name="cond_add_forest_genes_hparams">
264 <param name="select_add_forest_genes_hparams" type="select" label="Do you want to tune hyperparameters for adding marker genes to decision trees?">
265 <option value="False">No</option>
266 <option value="True">Yes</option>
267 </param>
268 <when value="True">
269 <param argument="n_max_per_it" type="integer" value="5" optional="false" label="n_max_per_it"/>
270 <param argument="performance_th" type="float" value="0.02" optional="false" label="performance_th"/>
271 <param argument="importance_th" type="integer" value="0" optional="false" label="importance_th"/>
272 </when>
273 <when value="False"/>
274 </conditional>
275 <conditional name="cond_marker_selection_hparams">
276 <param name="select_marker_selection_hparams" type="select" label="Do you want to tune marker selection hyperparameters?">
277 <option value="False">No</option>
278 <option value="True">Yes</option>
279 </param>
280 <when value="True">
281 <param argument="penalty_threshold" type="integer" value="1" optional="false" label="penalty_threshold"/>
282 </when>
283 <when value="False"/>
284 </conditional>
285 </section>
286
287 <section name="general_figure_options" title="General Figure Output Options" expanded="false">
288 <param argument="dpi" type="integer" value="300" min="1" label="Dpi of figures"/>
289 <param argument="fontsize" type="integer" value="100" min="1" label="Font size of figures"/>
290 </section>
291
292 <section name="figure_options_masked_dotplot" title="Figure Output Options for masked_dotplot" expanded="false">
293 <param name="ct_key" type="text" value="celltype" optional="false" label="Key in adata.var for preselected genes" help="Column of adata.obs with cell type annotation"/>
294 <param argument="imp_threshold" type="float" value="0.05" min="0.0" optional="false" label="Annotate genes as Spapros marker only for those genes with importance > imp_threshold"/>
295 <param name="celltypes" type="text" optional="true" label="Subset of celltypes (rows of dotplot)"/>
296 <param argument="n_genes" type="integer" value="0" min="0" label="Plot top n_genes genes." help="If 0 then all."/>
297 <param name="comb_markers_only" type="boolean" value="false" label="Do you want to plot only genes that are Spapros markers for the plotted cell types?"/>
298 <param name="markers_only" type="boolean" value="false" label="Do you want to plot only genes that are markers for the plotted cell types?"/>
299 <param name="cmap" type="text" value="Reds" optional="false" label="Colormap of mean expressions"/>
300 <param name="comb_marker_color" type="text" value="darkblue" optional="false" label="Color for Spapros markers"/>
301 <param name="marker_color" type="text" value="blue" optional="false" label="Color for marker genes"/>
302 <param name="non_adata_celltypes_color" type="text" value="grey" optional="false" label="Color for celltypes that don't occur in the data set."/>
303 <param name="use_raw" type="select" label="Do you want to use adata.raw for plotting?">
304 <option value="False">No</option>
305 <option value="True">Yes</option>
306 </param>
307 </section>
308
309 <section name="figure_options_plot_gene_overlap" title="Figure Output Options for plot_gene_overlap" expanded="false">
310 <param name="style" type="select" label="Plot type">
311 <option value="upset">Upset plot</option>
312 <option value="venn">Venn diagram</option>
313 </param>
314 </section>
315
316 <expand macro="inputs_common_advanced"/>
317 </inputs>
318 <outputs>
319 <data name="out_masked_dotplot_png" format="png" from_work_dir="*masked_dotplot.png" label="PNG masked_dotplot from ${tool.name} on ${on_string}">
320 <filter>format == 'png'</filter>
321 </data>
322 <data name="out_masked_dotplot_pdf" format="pdf" from_work_dir="*masked_dotplot.pdf" label="PDF masked_dotplot from ${tool.name} on ${on_string}">
323 <filter>format == 'pdf'</filter>
324 </data>
325 <data name="out_masked_dotplot_svg" format="svg" from_work_dir="*masked_dotplot.svg" label="SVG masked_dotplot from ${tool.name} on ${on_string}">
326 <filter>format == 'svg'</filter>
327 </data>
328 <data name="out_gene_overlap_png" format="png" from_work_dir="*gene_overlap.png" label="PNG gene_overlap from ${tool.name} on ${on_string}">
329 <filter>format == 'png'</filter>
330 </data>
331 <data name="out_gene_overlap_pdf" format="pdf" from_work_dir="*gene_overlap.pdf" label="PDF gene_overlap from ${tool.name} on ${on_string}">
332 <filter>format == 'pdf'</filter>
333 </data>
334 <data name="out_gene_overlap_svg" format="svg" from_work_dir="*gene_overlap.svg" label="SVG gene_overlap from ${tool.name} on ${on_string}">
335 <filter>format == 'svg'</filter>
336 </data>
337 <data name="marker_out" format="tabular" from_work_dir="marker.tsv" label="${tool.name} on ${on_string}: Markers"/>
338 <expand macro="hidden_outputs"/>
339 </outputs>
340 <tests>
341 <test expect_num_outputs="4">
342 <param name="adata" value="tl.rank_genes_groups.newton-cg.pbmc68k_reduced_240cells.h5ad"/>
343 <param name="format" value="png"/>
344 <param name="genes_key" value="highly_variable"/>
345 <param name="show_log" value="true" />
346 <section name="general_figure_options">
347 <param name="dpi" value="100"/>
348 </section>
349 <output name="hidden_output">
350 <assert_contents>
351 <has_text_matching expression="celltype_key='celltype',"/>
352 <has_text_matching expression="genes_key='highly_variable',"/>
353 <has_text_matching expression="n_pca_genes=100,"/>
354 <has_text_matching expression="seed=123,"/>
355 <has_text_matching expression="cmap='Reds',"/>
356 <has_text_matching expression="save='masked_dotplot.png',"/>
357 <has_text_matching expression="style='upset',"/>
358 <has_text_matching expression="save='gene_overlap.png',"/>
359 </assert_contents>
360 </output>
361 <output name="out_masked_dotplot_png">
362 <assert_contents>
363 <has_image_width width="4055" delta="2"/>
364 <has_image_height height="1108" delta="2"/>
365 </assert_contents>
366 </output>
367 <output name="out_gene_overlap_png">
368 <assert_contents>
369 <has_image_width width="1189" delta="2"/>
370 <has_image_height height="600" delta="2"/>
371 </assert_contents>
372 </output>
373 <output name="marker_out" file="marker_out_test1.tsv" ftype="tabular"/>
374 </test>
375 <test expect_num_outputs="4">
376 <param name="adata" value="tl.rank_genes_groups.newton-cg.pbmc68k_reduced_240cells.h5ad"/>
377 <param name="format" value="png"/>
378 <param name="genes_key" value="highly_variable"/>
379 <param name="select_n" value="True"/>
380 <param name="n" value="10"/>
381 <section name="general_figure_options">
382 <param name="dpi" value="100"/>
383 </section>
384 <param name="show_log" value="true" />
385 <output name="hidden_output">
386 <assert_contents>
387 <has_text_matching expression="celltype_key='celltype',"/>
388 <has_text_matching expression="genes_key='highly_variable',"/>
389 <has_text_matching expression="n_pca_genes=100,"/>
390 <has_text_matching expression="n=10,"/>
391 <has_text_matching expression="seed=123,"/>
392 <has_text_matching expression="cmap='Reds',"/>
393 <has_text_matching expression="save='masked_dotplot.png',"/>
394 <has_text_matching expression="style='upset',"/>
395 <has_text_matching expression="save='gene_overlap.png',"/>
396 </assert_contents>
397 </output>
398 <output name="out_masked_dotplot_png">
399 <assert_contents>
400 <has_image_width width="2914" delta="2"/>
401 <has_image_height height="882" delta="2"/>
402 </assert_contents>
403 </output>
404 <output name="out_gene_overlap_png">
405 <assert_contents>
406 <has_image_width width="1032" delta="2"/>
407 <has_image_height height="600" delta="2"/>
408 </assert_contents>
409 </output>
410 <output name="marker_out" file="marker_out_test2.tsv" ftype="tabular"/>
411 </test>
412 <test expect_num_outputs="4">
413 <param name="adata" value="tl.rank_genes_groups.newton-cg.pbmc68k_reduced_240cells.h5ad"/>
414 <param name="format" value="png"/>
415 <param name="genes_key" value="highly_variable"/>
416 <param name="celltypes" value="CD34+,CD56+ NK"/>
417 <section name="general_figure_options">
418 <param name="dpi" value="100"/>
419 </section>
420 <param name="show_log" value="true" />
421 <output name="hidden_output">
422 <assert_contents>
423 <has_text_matching expression="celltype_key='celltype',"/>
424 <has_text_matching expression="genes_key='highly_variable',"/>
425 <has_text_matching expression="n_pca_genes=100,"/>
426 <has_text_matching expression="seed=123,"/>
427 <has_text_matching expression="cmap='Reds',"/>
428 <has_text_matching expression="save='masked_dotplot.png',"/>
429 <has_text_matching expression="style='upset',"/>
430 <has_text_matching expression="save='gene_overlap.png',"/>
431 </assert_contents>
432 </output>
433 <output name="out_masked_dotplot_png">
434 <assert_contents>
435 <has_image_width width="2776" delta="2"/>
436 <has_image_height height="882" delta="2"/>
437 </assert_contents>
438 </output>
439 <output name="out_gene_overlap_png">
440 <assert_contents>
441 <has_image_width width="929" delta="2"/>
442 <has_image_height height="565" delta="2"/>
443 </assert_contents>
444 </output>
445 <output name="marker_out" file="marker_out_test3.tsv" ftype="tabular"/>
446 </test>
447 <test expect_num_outputs="4">
448 <param name="adata" value="tl.rank_genes_groups.newton-cg.pbmc68k_reduced_240cells.h5ad"/>
449 <param name="format" value="png"/>
450 <param name="genes_key" value="highly_variable"/>
451 <param name="select_markerset" value="True"/>
452 <param name="markerset" value="marker.tsv"/>
453 <param name="header_markerset" value="not_included"/>
454 <section name="general_figure_options">
455 <param name="dpi" value="100"/>
456 </section>
457 <param name="show_log" value="true"/>
458 <output name="hidden_output">
459 <assert_contents>
460 <has_text_matching expression="celltype_key='celltype',"/>
461 <has_text_matching expression="genes_key='highly_variable',"/>
462 <has_text_matching expression="n_pca_genes=100,"/>
463 <has_text_matching expression="seed=123,"/>
464 <has_text_matching expression="cmap='Reds',"/>
465 <has_text_matching expression="save='masked_dotplot.png',"/>
466 <has_text_matching expression="style='upset',"/>
467 <has_text_matching expression="save='gene_overlap.png',"/>
468 </assert_contents>
469 </output>
470 <output name="out_masked_dotplot_png">
471 <assert_contents>
472 <has_image_width width="4055" delta="2"/>
473 <has_image_height height="1108" delta="2"/>
474 </assert_contents>
475 </output>
476 <output name="out_gene_overlap_png">
477 <assert_contents>
478 <has_image_width width="1154" delta="2"/>
479 <has_image_height height="600" delta="2"/>
480 </assert_contents>
481 </output>
482 <output name="marker_out" file="marker_out_test4.tsv" ftype="tabular"/>
483 </test>
484 <test expect_num_outputs="4">
485 <param name="adata" value="tl.rank_genes_groups.newton-cg.pbmc68k_reduced_240cells.h5ad"/>
486 <param name="format" value="png"/>
487 <param name="genes_key" value="highly_variable"/>
488 <section name="advanced_options">
489 <param name="select_DE_selection_hparams" value="True"/>
490 <param name="select_forest_hparams" value="True"/>
491 <param name="select_forest_DE_baseline_hparams" value="True"/>
492 <param name="select_add_forest_genes_hparams" value="True"/>
493 <param name="select_marker_selection_hparams" value="True"/>
494 </section>
495 <section name="general_figure_options">
496 <param name="dpi" value="100"/>
497 </section>
498 <param name="show_log" value="true"/>
499 <output name="hidden_output">
500 <assert_contents>
501 <has_text_matching expression="celltype_key='celltype',"/>
502 <has_text_matching expression="genes_key='highly_variable',"/>
503 <has_text_matching expression="n_pca_genes=100,"/>
504 <has_text_matching expression="seed=123,"/>
505 <has_text_matching expression="cmap='Reds',"/>
506 <has_text_matching expression="save='masked_dotplot.png',"/>
507 <has_text_matching expression="style='upset',"/>
508 <has_text_matching expression="save='gene_overlap.png',"/>
509 </assert_contents>
510 </output>
511 <output name="out_masked_dotplot_png">
512 <assert_contents>
513 <has_image_width width="4055" delta="2"/>
514 <has_image_height height="1108" delta="2"/>
515 </assert_contents>
516 </output>
517 <output name="out_gene_overlap_png">
518 <assert_contents>
519 <has_image_width width="1189" delta="2"/>
520 <has_image_height height="600" delta="2"/>
521 </assert_contents>
522 </output>
523 <output name="marker_out" file="marker_out_test5.tsv" ftype="tabular"/>
524 </test>
525 </tests>
526 <help><![CDATA[
527 Probe set selection for single-cell sequencing data using spapros.
528 ============================================================================================================
529
530 Spapros is a python package that provides a pipeline for probe set selection and evaluation for targeted spatial transcriptomics data.
531
532 Key Features:
533 Select probe sets for spatial transcriptomics which identify cell types of interest, capture general transcriptomic variation, and incorporate prior knowledge
534
535 Evaluate probe sets with an extensive pipeline
536
537 Further documentation can be found here: https://spapros.readthedocs.io/en/latest/index.html.
538
539 ]]></help>
540 <expand macro="citations"/>
541 </tool>