Mercurial > repos > iuc > scanpy_inspect

comparison inspect.xml @ 14:1c36180febfb 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 91121b1e72696f17478dae383badaa71e9f96dbb
author iuc
date Sat, 14 Sep 2024 12:40:40 +0000
parents 03ed427eb5e7
children b6035c5e7e12
comparison
equal deleted inserted replaced
13:9329ecce0019 14:1c36180febfb
1 <tool id="scanpy_inspect" name="Inspect and manipulate" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@profile@"> 1 <tool id="scanpy_inspect" name="Scanpy Inspect and manipulate" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
2 <description> with scanpy</description>
3 <macros> 2 <macros>
4 <import>macros.xml</import> 3 <import>macros.xml</import>
5 <xml name="score_genes_params"> 4 <xml name="params_score_genes">
6 <param argument="n_bins" type="integer" value="25" label="Number of expression level bins for sampling" help=""/> 5 <param argument="n_bins" type="integer" value="25" label="Number of expression level bins for sampling"/>
7 <param argument="random_state" type="integer" value="0" label="Random seed for sampling" help=""/> 6 <param argument="random_state" type="integer" value="0" label="Random seed for sampling"/>
8 <expand macro="param_use_raw"/> 7 <expand macro="param_use_raw"/>
9 </xml> 8 </xml>
10 <token name="@CMD_score_genes_inputs@"><![CDATA[ 9 <token name="@CMD_PARAMS_SCORE_GENES@"><![CDATA[
11 n_bins=$method.n_bins, 10 n_bins=$method.n_bins,
12 random_state=$method.random_state, 11 random_state=$method.random_state,
13 use_raw=$method.use_raw, 12 use_raw=$method.use_raw,
14 copy=False 13 copy=False
15 ]]></token> 14 ]]>
15 </token>
16 <xml name="corr_method"> 16 <xml name="corr_method">
17 <param argument="corr_method" type="select" label="P-value correction method"> 17 <param argument="corr_method" type="select" label="P-value correction method">
18 <option value="benjamini-hochberg">Benjamini-Hochberg</option> 18 <option value="benjamini-hochberg" selected="true">Benjamini-Hochberg</option>
19 <option value="bonferroni">Bonferroni</option> 19 <option value="bonferroni">Bonferroni</option>
20 </param> 20 </param>
21 </xml> 21 </xml>
22 <xml name="fit_intercept"> 22 <xml name="fit_intercept">
23 <param argument="fit_intercept" type="boolean" truevalue="True" falsevalue="False" checked="true" 23 <param argument="fit_intercept" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Should a constant (a.k.a. bias or intercept) be added to the decision function?"/>
24 label="Should a constant (a.k.a. bias or intercept) be added to the decision function?" help=""/>
25 </xml> 24 </xml>
26 <xml name="max_iter"> 25 <xml name="max_iter">
27 <param argument="max_iter" type="integer" min="0" value="100" label="Maximum number of iterations taken for the solvers to converge" help=""/> 26 <param argument="max_iter" type="integer" min="0" value="100" label="Maximum number of iterations taken for the solvers to converge"/>
28 </xml> 27 </xml>
29 <xml name="multi_class"> 28 <xml name="multi_class">
30 <param argument="multi_class" type="select" label="Multi class" help=""> 29 <param argument="multi_class" type="select" label="Multi class">
30 <option value="auto" selected="true">auto: selects ‘ovr’ if the data is binary and otherwise selects ‘multinomial’</option>
31 <option value="ovr">ovr: a binary problem is fit for each label</option> 31 <option value="ovr">ovr: a binary problem is fit for each label</option>
32 <option value="multinomial">multinomial: the multinomial loss fit across the entire probability distribution, even when the data is binary</option> 32 <option value="multinomial">multinomial: the multinomial loss fit across the entire probability distribution, even when the data is binary</option>
33 <option value="auto">auto: selects ‘ovr’ if the data is binary and otherwise selects ‘multinomial’</option>
34 </param> 33 </param>
35 </xml> 34 </xml>
36 <xml name="penalty"> 35 <xml name="penalty">
37 <param argument="penalty" type="select" label="Norm used in the penalization" help=""> 36 <param argument="penalty" type="select" label="Norm used in the penalization">
37 <option value="l2" selected="true">l2</option>
38 <option value="l1">l1</option> 38 <option value="l1">l1</option>
39 <option value="l2">l2</option> 39 <yield/>
40 <option value="customized">customized</option>
41 </param>
42 </xml>
43 <xml name="custom_penalty">
44 <param argument="pen" type="text" value="" label="Norm used in the penalization" help="">
45 <expand macro="sanitize_query" />
46 </param> 40 </param>
47 </xml> 41 </xml>
48 <xml name="random_state"> 42 <xml name="random_state">
49 <param argument="random_state" type="integer" value="" optional="true" 43 <param argument="random_state" type="integer" value="" optional="true" label="The seed of the pseudo random number generator to use when shuffling the data"/>
50 label="The seed of the pseudo random number generator to use when shuffling the data" help=""/>
51 </xml> 44 </xml>
52 </macros> 45 </macros>
53 <expand macro="bio_tools"/> 46 <expand macro="bio_tools"/>
54 <expand macro="requirements"/> 47 <expand macro="requirements">
48 <requirement type="package" version="1.5.1">scikit-learn</requirement>
49 </expand>
55 <expand macro="version_command"/> 50 <expand macro="version_command"/>
56 <command detect_errors="exit_code"><![CDATA[ 51 <command detect_errors="exit_code"><![CDATA[
57 @CMD@ 52 @CMD@
58 ]]></command> 53 ]]></command>
59 <configfiles> 54 <configfiles>
60 <configfile name="script_file"><![CDATA[ 55 <configfile name="script_file"><![CDATA[
61 @CMD_imports@ 56 @CMD_IMPORTS@
62 @CMD_read_inputs@ 57 @CMD_READ_INPUTS@
63 58
64 #if $method.method == "pp.calculate_qc_metrics" 59 #if str($method.method) == 'pp.calculate_qc_metrics':
65 sc.pp.calculate_qc_metrics( 60 sc.pp.calculate_qc_metrics(
66 adata=adata, 61 adata=adata,
67 expr_type='$method.expr_type', 62 expr_type='$method.expr_type',
68 var_type='$method.var_type', 63 var_type='$method.var_type',
69 #if $method.qc_vars 64 #if str($method.qc_vars) != '':
70 #set $qc_vars = [str(x.strip()) for x in str($method.qc_vars).split(',')] 65 #set $qc_vars = [str(x.strip()) for x in str($method.qc_vars).split(',')]
71 qc_vars=$qc_vars, 66 qc_vars=$qc_vars,
72 #end if 67 #end if
73 #if $method.percent_top 68 #if str($method.percent_top) != '':
74 #set $percent_top = [int(x.strip()) for x in str($method.percent_top).split(',')] 69 #set $percent_top = [int(x.strip()) for x in str($method.percent_top).split(',')]
75 percent_top=$percent_top, 70 percent_top=$percent_top,
76 #end if 71 #end if
72 #if str($method.layer) != '':
73 layer='$method.layer',
74 #end if
75 use_raw=$method.use_raw,
76 log1p=$method.log1p,
77 inplace=True) 77 inplace=True)
78 78
79 #else if $method.method == "tl.score_genes" 79 #else if str($method.method) == 'pp.neighbors':
80 sc.pp.neighbors(
81 adata=adata,
82 n_neighbors=$method.n_neighbors,
83 #if str($method.n_pcs) != '':
84 n_pcs=$method.n_pcs,
85 #end if
86 #if str($method.use_rep) != '':
87 use_rep='$method.use_rep',
88 #end if
89 knn=$method.knn,
90 method='$method.pp_neighbors_method',
91 metric='$method.metric',
92 random_state=$method.random_state,
93 #if str($method.key_added) != '':
94 key_added='$method.key_added',
95 #end if
96 copy=False)
97
98 #else if str($method.method) == 'tl.score_genes':
80 sc.tl.score_genes( 99 sc.tl.score_genes(
81 adata=adata, 100 adata=adata,
82 #set $gene_list = [str(x.strip()) for x in str($method.gene_list).split(',')] 101 #set $gene_list = [str(x.strip()) for x in str($method.gene_list).split(',')]
83 gene_list=$gene_list, 102 gene_list=$gene_list,
84 ctrl_size=$method.ctrl_size, 103 ctrl_size=$method.ctrl_size,
104 #if str($method.gene_pool) != '':
105 #set $gene_pool = [str(x.strip()) for x in str($method.gene_pool).split(',')]
106 gene_pool=$gene_pool,
107 #end if
85 score_name='$method.score_name', 108 score_name='$method.score_name',
86 #if $method.gene_pool 109 @CMD_PARAMS_SCORE_GENES@)
87 #set $gene_pool = [str(x.strip()) for x in $method.gene_pool.split(',')] 110
88 gene_pool=$gene_pool, 111 #else if str($method.method) == 'tl.score_genes_cell_cycle':
89 #end if 112 #if str($method.s_genes.format) == 'file':
90 @CMD_score_genes_inputs@)
91
92 #else if $method.method == "tl.score_genes_cell_cycle"
93 #if str($method.s_genes.format) == 'file'
94 with open('$method.s_genes.file', 'r') as s_genes_f: 113 with open('$method.s_genes.file', 'r') as s_genes_f:
95 s_genes = [str(x.strip()) for x in s_genes_f.readlines()] 114 s_genes = [str(x.strip()) for x in s_genes_f.readlines()]
96 print(s_genes) 115 print(s_genes)
97 #end if 116 #end if
98 117
99 #if str($method.g2m_genes.format) == 'file' 118 #if str($method.g2m_genes.format) == 'file':
100 with open('$method.g2m_genes.file', 'r') as g2m_genes_f: 119 with open('$method.g2m_genes.file', 'r') as g2m_genes_f:
101 g2m_genes = [str(x.strip()) for x in g2m_genes_f.readlines()] 120 g2m_genes = [str(x.strip()) for x in g2m_genes_f.readlines()]
102 print(g2m_genes) 121 print(g2m_genes)
103 #end if 122 #end if
104 123
105 sc.tl.score_genes_cell_cycle( 124 sc.tl.score_genes_cell_cycle(
106 adata=adata, 125 adata=adata,
107 #if str($method.s_genes.format) == 'text' 126 #if str($method.s_genes.format) == 'text':
108 #set $s_genes = [str(x.strip()) for x in $method.s_genes.text.split(',')] 127 #set $s_genes = [str(x.strip()) for x in str($method.s_genes.text).split(',')]
109 s_genes=$s_genes, 128 s_genes=$s_genes,
110 #else if str($method.s_genes.format) == 'file' 129 #else if str($method.s_genes.format) == 'file':
111 s_genes=s_genes, 130 s_genes=s_genes,
112 #end if 131 #end if
113 #if str($method.g2m_genes.format) == 'text' 132 #if str($method.g2m_genes.format) == 'text':
114 #set $g2m_genes = [str(x.strip()) for x in $method.g2m_genes.text.split(',')] 133 #set $g2m_genes = [str(x.strip()) for x in str($method.g2m_genes.text).split(',')]
115 g2m_genes=$g2m_genes, 134 g2m_genes=$g2m_genes,
116 #else if str($method.g2m_genes.format) == 'file' 135 #else if str($method.g2m_genes.format) == 'file':
117 g2m_genes=g2m_genes, 136 g2m_genes=g2m_genes,
118 #end if 137 #end if
119 @CMD_score_genes_inputs@) 138 @CMD_PARAMS_SCORE_GENES@)
120 139
121 #else if $method.method == 'pp.neighbors' 140 #else if str($method.method) == 'tl.rank_genes_groups':
122 sc.pp.neighbors(
123 adata=adata,
124 n_neighbors=$method.n_neighbors,
125 #if str($method.n_pcs) != ''
126 n_pcs=$method.n_pcs,
127 #end if
128 #if $method.use_rep
129 use_rep='$method.use_rep',
130 #end if
131 knn=$method.knn,
132 random_state=$method.random_state,
133 method='$method.pp_neighbors_method',
134 metric='$method.metric',
135 copy=False)
136
137 #else if $method.method == 'tl.rank_genes_groups'
138 sc.tl.rank_genes_groups( 141 sc.tl.rank_genes_groups(
139 adata=adata, 142 adata=adata,
143 #if str($method.groupby) != '':
140 groupby='$method.groupby', 144 groupby='$method.groupby',
141 #if $method.groups 145 #end if
146 use_raw=$method.use_raw,
147 #if str($method.groups) != '':
142 #set $group=[x.strip() for x in str($method.groups).split(',')] 148 #set $group=[x.strip() for x in str($method.groups).split(',')]
143 groups=$group, 149 groups='$group',
144 #end if 150 #end if
145 #if $method.ref.rest == 'rest' 151 #if str($method.layer) != '':
152 layer='$method.layer',
153 #end if
154 #if str($method.ref.rest) == 'rest':
146 reference='$method.ref.rest', 155 reference='$method.ref.rest',
147 #else 156 #else
148 reference='$method.ref.reference', 157 reference='$method.ref.reference',
149 #end if 158 #end if
159 #if str($method.n_genes) != '':
150 n_genes=$method.n_genes, 160 n_genes=$method.n_genes,
161 #end if
151 method='$method.tl_rank_genes_groups_method.method', 162 method='$method.tl_rank_genes_groups_method.method',
152 #if $method.tl_rank_genes_groups_method.method != 'logreg' 163 #if str($method.tl_rank_genes_groups_method.method) != 'logreg':
153 corr_method='$method.tl_rank_genes_groups_method.corr_method', 164 corr_method='$method.tl_rank_genes_groups_method.corr_method',
154 #else 165 #end if
166 #if str($method.tl_rank_genes_groups_method.method) == 'wilcoxon':
167 tie_correct=$method.tl_rank_genes_groups_method.tie_correct,
168 #end if
169 #if str($method.tl_rank_genes_groups_method.method) == 'logreg':
155 solver='$method.tl_rank_genes_groups_method.solver.solver', 170 solver='$method.tl_rank_genes_groups_method.solver.solver',
156 #if $method.tl_rank_genes_groups_method.solver.solver == 'newton-cg' 171 #if str($method.tl_rank_genes_groups_method.solver.solver) == 'lbfgs':
157 penalty='l2', 172 penalty='$method.tl_rank_genes_groups_method.solver.penalty',
158 fit_intercept=$method.tl_rank_genes_groups_method.solver.fit_intercept, 173 fit_intercept=$method.tl_rank_genes_groups_method.solver.fit_intercept,
159 max_iter=$method.tl_rank_genes_groups_method.solver.max_iter, 174 max_iter=$method.tl_rank_genes_groups_method.solver.max_iter,
160 multi_class='$method.tl_rank_genes_groups_method.solver.multi_class', 175 multi_class='$method.tl_rank_genes_groups_method.solver.multi_class',
161 #else if $method.tl_rank_genes_groups_method.solver.solver == 'lbfgs' 176 #else if str($method.tl_rank_genes_groups_method.solver.solver) == 'newton-cg':
162 penalty='l2', 177 penalty='$method.tl_rank_genes_groups_method.solver.penalty',
163 fit_intercept=$method.tl_rank_genes_groups_method.solver.fit_intercept, 178 fit_intercept=$method.tl_rank_genes_groups_method.solver.fit_intercept,
164 max_iter=$method.tl_rank_genes_groups_method.solver.max_iter, 179 max_iter=$method.tl_rank_genes_groups_method.solver.max_iter,
165 multi_class='$method.tl_rank_genes_groups_method.solver.multi_class', 180 multi_class='$method.tl_rank_genes_groups_method.solver.multi_class',
166 #else if $method.tl_rank_genes_groups_method.solver.solver == 'liblinear' 181 #else if str($method.tl_rank_genes_groups_method.solver.solver) == 'liblinear':
167 #if $method.tl_rank_genes_groups_method.solver.penalty.penalty == 'l1' 182 #if str($method.tl_rank_genes_groups_method.solver.penalty.penalty) == 'l1':
168 penalty='l1', 183 penalty='l1',
169 #else if $method.tl_rank_genes_groups_method.solver.penalty.penalty == 'l2' 184 #else:
170 penalty='l2', 185 penalty='l2',
171 dual=$method.tl_rank_genes_groups_method.solver.penalty.dual, 186 dual=$method.tl_rank_genes_groups_method.solver.penalty.dual,
172 #else
173 penalty='$method.tl_rank_genes_groups_method.solver.penalty.pen',
174 #end if 187 #end if
175 fit_intercept=$method.tl_rank_genes_groups_method.solver.intercept_scaling.fit_intercept, 188 fit_intercept=$method.tl_rank_genes_groups_method.solver.intercept_scaling.fit_intercept,
176 #if $method.tl_rank_genes_groups_method.solver.intercept_scaling.fit_intercept == 'True' 189 #if str($method.tl_rank_genes_groups_method.solver.intercept_scaling.fit_intercept) == 'True':
177 intercept_scaling=$method.tl_rank_genes_groups_method.solver.intercept_scaling.intercept_scaling, 190 intercept_scaling=$method.tl_rank_genes_groups_method.solver.intercept_scaling.intercept_scaling,
178 #end if 191 #end if
179 #if str($method.tl_rank_genes_groups_method.solver.random_state) != '' 192 #if str($method.tl_rank_genes_groups_method.solver.random_state) != '':
180 random_state=$method.tl_rank_genes_groups_method.solver.random_state, 193 random_state=$method.tl_rank_genes_groups_method.solver.random_state,
181 #end if 194 #end if
182 #else if $method.tl_rank_genes_groups_method.solver.solver == 'sag' 195 #else if str($method.tl_rank_genes_groups_method.solver.solver) == 'sag':
183 penalty='l2', 196 penalty='$method.tl_rank_genes_groups_method.solver.penalty.penalty',
184 fit_intercept=$method.tl_rank_genes_groups_method.solver.fit_intercept, 197 fit_intercept=$method.tl_rank_genes_groups_method.solver.fit_intercept,
185 #if str($method.tl_rank_genes_groups_method.solver.random_state) != '' 198 #if str($method.tl_rank_genes_groups_method.solver.random_state) != '':
186 random_state=$method.tl_rank_genes_groups_method.solver.random_state, 199 random_state=$method.tl_rank_genes_groups_method.solver.random_state,
187 #end if 200 #end if
188 max_iter=$method.tl_rank_genes_groups_method.solver.max_iter, 201 max_iter=$method.tl_rank_genes_groups_method.solver.max_iter,
189 multi_class='$method.tl_rank_genes_groups_method.solver.multi_class', 202 multi_class=$method.tl_rank_genes_groups_method.solver.multi_class,
190 #else if $method.tl_rank_genes_groups_method.solver.solver == 'saga' 203 #else if str($method.tl_rank_genes_groups_method.solver.solver) == 'saga':
191 #if $method.tl_rank_genes_groups_method.solver.penalty.penalty == 'l1' 204 #if str($method.tl_rank_genes_groups_method.solver.penalty.penalty) == 'l1':
192 penalty='l1', 205 penalty='l1',
193 #else if $method.tl_rank_genes_groups_method.solver.penalty.penalty == 'l2' 206 #else if str($method.tl_rank_genes_groups_method.solver.penalty.penalty) == 'l2':
194 penalty='l2', 207 penalty='l2',
195 #else 208 #else if str($method.tl_rank_genes_groups_method.solver.penalty.penalty) == 'elasticnet':
196 penalty='$method.tl_rank_genes_groups_method.solver.penalty.pen', 209 penalty='elasticnet',
210 #else:
211 penalty='None',
197 #end if 212 #end if
198 fit_intercept=$method.tl_rank_genes_groups_method.solver.fit_intercept, 213 fit_intercept=$method.tl_rank_genes_groups_method.solver.fit_intercept,
199 multi_class='$method.tl_rank_genes_groups_method.solver.multi_class', 214 multi_class=$method.tl_rank_genes_groups_method.solver.multi_class,
200 #end if 215 #end if
201 tol=$method.tl_rank_genes_groups_method.tol, 216 tol=$method.tl_rank_genes_groups_method.tol,
202 C=$method.tl_rank_genes_groups_method.c, 217 C=$method.tl_rank_genes_groups_method.c,
203 #end if 218 #end if
204 use_raw=$method.use_raw) 219 #if str($method.key_added) != '':
205 220 key_added='$method.key_added',
206 #else if $method.method == "tl.marker_gene_overlap" 221 #end if
222 copy=False)
223
224 #else if str($method.method) == "tl.marker_gene_overlap":
207 reference_markers = {} 225 reference_markers = {}
208 #for $i, $s in enumerate($method.reference_markers) 226 #for $i, $s in enumerate($method.reference_markers)
209 #set $list=[x.strip() for x in str($s.values).split(',')] 227 #set $list=[x.strip() for x in str($s.values).split(',')]
210 reference_markers['$s.key'] = $list 228 reference_markers['$s.key'] = $list
211 #end for 229 #end for
212 230
213 sc.tl.marker_gene_overlap( 231 # Temporary fix for the issue with "inplace=True" for Pandas dataframes.
214 adata, 232 # see here: https://github.com/scverse/scanpy/blob/b6193502e11b84fc1b4a011ee9cf08a19da22ebf/src/scanpy/tools/_marker_gene_overlap.py#L167
215 reference_markers, 233 marker_overlap_result = sc.tl.marker_gene_overlap(
216 #if $method.key 234 adata,
217 key='$method.key', 235 reference_markers,
218 #end if 236 #if str($method.key) != '':
219 method='$method.overlap.method', 237 key='$method.key',
220 #if $method.overlap.method == 'overlap_count' and str($method.overlap.normalize) != 'None' 238 #end if
221 normalize='$method.overlap.normalize', 239 method='$method.overlap.method',
222 #end if 240 #if str($method.overlap.method) == 'overlap_count' and str($method.overlap.normalize) != 'None':
223 #if str($method.top_n_markers) != '' 241 normalize='$method.overlap.normalize',
224 top_n_markers=$method.top_n_markers, 242 #end if
225 #end if 243 #if str($method.top_n_markers) != '':
226 #if str($method.adj_pval_threshold) != '' 244 top_n_markers=$method.top_n_markers,
227 adj_pval_threshold=$method.adj_pval_threshold, 245 #end if
228 #end if 246 #if str($method.adj_pval_threshold) != '':
229 #if $method.key_added 247 adj_pval_threshold=$method.adj_pval_threshold,
230 key_added='$method.key_added', 248 #end if
231 #end if 249 #if $method.key_added:
232 inplace=True) 250 key_added='$method.key_added',
233 251 #end if
234 #else if $method.method == "pp.log1p" 252 inplace=False)
253
254 adata.uns['marker_gene_overlap'] = marker_overlap_result
255
256 #else if str($method.method) == "pp.log1p":
235 sc.pp.log1p( 257 sc.pp.log1p(
236 adata, 258 adata,
259 #if str($method.base) != '':
260 base=$method.base,
261 #end if
262 #if str($method.layer) != '':
263 layer='$method.layer',
264 #end if
265 #if str($method.obsm) != '':
266 obsm='$method.obsm',
267 #end if
237 copy=False) 268 copy=False)
238 269
239 #else if $method.method == "pp.scale" 270 #else if str($method.method) == "pp.scale":
240 sc.pp.scale( 271 sc.pp.scale(
241 adata, 272 adata,
242 zero_center=$method.zero_center, 273 zero_center=$method.zero_center,
243 #if str($method.max_value) != '' 274 #if str($method.max_value) != '':
244 max_value=$method.max_value, 275 max_value=$method.max_value,
245 #end if 276 #end if
277 #if str($method.layer) != '':
278 layer='$method.layer',
279 #end if
280 #if str($method.obsm) != '':
281 obsm='$method.obsm',
282 #end if
283 #if str($method.mask_obs) != '':
284 mask_obs='$method.mask_obs',
285 #end if
246 copy=False) 286 copy=False)
247 287
248 #else if $method.method == "pp.sqrt" 288 #else if str($method.method) == "pp.sqrt":
289
290 print("stats before sqrt:", "min=", adata.X.min(), "max=", adata.X.max(), "mean=", adata.X.mean())
291
249 sc.pp.sqrt( 292 sc.pp.sqrt(
250 adata, 293 adata,
251 copy=False) 294 copy=False)
252 #end if 295 #end if
253 296
254 @CMD_anndata_write_outputs@ 297 print("stats after sqrt:", "min=", adata.X.min(), "max=", adata.X.max(), "mean=", adata.X.mean())
255 ]]></configfile> 298
299 @CMD_ANNDATA_WRITE_OUTPUTS@
300 ]]>
301 </configfile>
256 </configfiles> 302 </configfiles>
257 <inputs> 303 <inputs>
258 <expand macro="inputs_anndata"/> 304 <expand macro="inputs_anndata"/>
259 <conditional name="method"> 305 <conditional name="method">
260 <param argument="method" type="select" label="Method used for inspecting"> 306 <param argument="method" type="select" label="Method used for inspecting">
261 <option value="pp.calculate_qc_metrics">Calculate quality control metrics, using 'pp.calculate_qc_metrics'</option> 307 <option value="pp.calculate_qc_metrics">Calculate quality control metrics, using 'pp.calculate_qc_metrics'</option>
262 <option value="pp.neighbors">Compute a neighborhood graph of observations, using 'pp.neighbors'</option> 308 <option value="pp.neighbors">Compute a neighborhood graph of observations, using 'pp.neighbors'</option>
263 <option value="tl.score_genes">Score a set of genes, using 'tl.score_genes'</option> 309 <option value="tl.score_genes">Score a set of genes, using 'tl.score_genes'</option>
264 <option value="tl.score_genes_cell_cycle">Score cell cycle genes, using 'tl.score_genes_cell_cycle'</option> 310 <option value="tl.score_genes_cell_cycle">Score cell cycle genes, using 'tl.score_genes_cell_cycle'</option>
265 <option value="tl.rank_genes_groups">Rank genes for characterizing groups, using 'tl.rank_genes_groups'</option> 311 <option value="tl.rank_genes_groups">Rank genes for characterizing groups, using 'tl.rank_genes_groups'</option>
266 <!--<option value="tl.marker_gene_overlap">Calculate an overlap score between data-deriven marker genes and provided markers, using 'tl.marker_gene_overlap'</option>--> 312 <option value="tl.marker_gene_overlap">Calculate an overlap score between data-deriven marker genes and provided markers, using 'tl.marker_gene_overlap'</option>
267 <option value="pp.log1p">Logarithmize the data matrix, using 'pp.log1p'</option> 313 <option value="pp.log1p">Logarithmize the data matrix, using 'pp.log1p'</option>
268 <option value="pp.scale">Scale data to unit variance and zero mean, using 'pp.scale'</option> 314 <option value="pp.scale">Scale data to unit variance and zero mean, using 'pp.scale'</option>
269 <option value="pp.sqrt">Square root the data matrix, using 'pp.sqrt'</option> 315 <option value="pp.sqrt">Square root the data matrix, using 'pp.sqrt'</option>
270 </param> 316 </param>
271 <when value="pp.calculate_qc_metrics"> 317 <when value="pp.calculate_qc_metrics">
272 <param argument="expr_type" type="text" value="counts" label="Name of kind of values in X"> 318 <param argument="expr_type" type="text" value="counts" label="Name of kind of values in X">
273 <expand macro="sanitize_query" /> 319 <expand macro="sanitize_query"/>
274 </param> 320 </param>
275 <param argument="var_type" type="text" value="genes" label="The kind of thing the variables are"> 321 <param argument="var_type" type="text" value="genes" label="The kind of thing the variables are">
276 <expand macro="sanitize_query" /> 322 <expand macro="sanitize_query"/>
277 </param> 323 </param>
278 <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"> 324 <param argument="qc_vars" type="text" optional="true" value="" label="Keys for boolean columns of '.var' which identify variables you could want to control for" help="Keys separated by a comma">
279 <expand macro="sanitize_query" /> 325 <expand macro="sanitize_query"/>
280 </param> 326 </param>
281 <param argument="percent_top" type="text" value="" label="Proportions of top genes to cover" 327 <param argument="percent_top" type="text" value="" optional="true" label="Proportions of top genes to cover"
282 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"> 328 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">
283 <expand macro="sanitize_vectors" /> 329 <expand macro="sanitize_vectors"/>
284 </param> 330 </param>
331 <expand macro="param_layer"/>
332 <expand macro="param_use_raw"/>
333 <param argument="log1p" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Compute log1p transformed annotations"/>
285 </when> 334 </when>
286 <when value="pp.neighbors"> 335 <when value="pp.neighbors">
287 <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."/> 336 <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."/>
288 <param argument="n_pcs" type="integer" min="0" value="" optional="true" label="Number of PCs to use" help=""/> 337 <param argument="n_pcs" type="integer" min="0" value="" optional="true" label="Number of PCs to use"/>
289 <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"> 338 <expand macro="param_use_rep"/>
290 <expand macro="sanitize_query" />
291 </param>
292 <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."/> 339 <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."/>
293 <param argument="random_state" type="integer" value="0" label="Numpy random seed" help=""/> 340 <param name="pp_neighbors_method" argument="method" type="select" label="Method for computing connectivities">
294 <param name="pp_neighbors_method" argument="method" type="select" label="Method for computing connectivities" help=""> 341 <option value="umap" selected="true">umap (McInnes et al, 2018)</option>
295 <option value="umap">umap (McInnes et al, 2018)</option>
296 <option value="gauss">gauss: Gauss kernel following (Coifman et al 2005) with adaptive width (Haghverdi et al 2016)</option> 342 <option value="gauss">gauss: Gauss kernel following (Coifman et al 2005) with adaptive width (Haghverdi et al 2016)</option>
297 </param> 343 </param>
298 <param argument="metric" type="select" label="Distance metric" help=""> 344 <param argument="metric" type="select" label="Distance metric">
299 <expand macro="distance_metric_options"/> 345 <expand macro="distance_metric_options"/>
300 </param> 346 </param>
347 <param argument="random_state" type="integer" value="0" label="Numpy random seed"/>
348 <param argument="key_added" type="text" value="" optional="true" label="Key to store neighbors, distances and connectivities" help="If specified, the neighbors data is added to .uns[key_added], distances are stored in .obsp[key_added+'_distances'] and connectivities in .obsp[key_added+'_connectivities']"/>
301 </when> 349 </when>
302 <when value="tl.score_genes"> 350 <when value="tl.score_genes">
303 <param argument="gene_list" type="text" value="" label="The list of gene names used for score calculation" help="Genes separated by a comma"> 351 <param argument="gene_list" type="text" value="" optional="false" label="The list of gene names used for score calculation" help="Genes separated by a comma">
304 <expand macro="sanitize_query" /> 352 <expand macro="sanitize_query"/>
305 </param> 353 </param>
306 <param argument="ctrl_size" type="integer" value="50" label="Number of reference genes to be sampled" 354 <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)'."/>
307 help="If 'len(gene_list)' is not too low, you can set 'ctrl_size=len(gene_list)'."/> 355 <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">
308 <param argument="gene_pool" type="text" value="" optional="true" label="Genes for sampling the reference set" 356 <expand macro="sanitize_query"/>
309 help="Default is all genes. Genes separated by a comma"> 357 </param>
310 <expand macro="sanitize_query" /> 358 <param argument="score_name" type="text" value="score" label="Name of the field to be added in '.obs'">
311 </param> 359 <expand macro="sanitize_query"/>
312 <expand macro="score_genes_params"/> 360 </param>
313 <param argument="score_name" type="text" value="score" label="Name of the field to be added in '.obs'" help=""> 361 <expand macro="params_score_genes"/>
314 <expand macro="sanitize_query" />
315 </param>
316 </when> 362 </when>
317 <when value="tl.score_genes_cell_cycle"> 363 <when value="tl.score_genes_cell_cycle">
318 <conditional name='s_genes'> 364 <conditional name='s_genes'>
319 <param name="format" type="select" label="Format for the list of genes associated with S phase"> 365 <param name="format" type="select" label="Format for the list of genes associated with S phase">
366 <option value="text" selected="true">Text</option>
320 <option value="file">File</option> 367 <option value="file">File</option>
321 <option value="text" selected="true">Text</option>
322 </param> 368 </param>
323 <when value="text"> 369 <when value="text">
324 <param name="text" type="text" value="" label="List of genes associated with S phase" help="Genes separated by a comma"> 370 <param name="text" type="text" value="" label="List of genes associated with S phase" help="Genes separated by a comma">
325 <expand macro="sanitize_query" /> 371 <expand macro="sanitize_query"/>
326 </param> 372 </param>
327 </when> 373 </when>
328 <when value="file"> 374 <when value="file">
329 <param name="file" type="data" format="txt" label="File with the list of genes associated with S phase" help="One gene per line"/> 375 <param name="file" type="data" format="txt" label="File with the list of genes associated with S phase" help="One gene per line"/>
330 </when> 376 </when>
331 </conditional> 377 </conditional>
332 <conditional name='g2m_genes'> 378 <conditional name='g2m_genes'>
333 <param name="format" type="select" label="Format for the list of genes associated with G2M phase"> 379 <param name="format" type="select" label="Format for the list of genes associated with G2M phase">
380 <option value="text" selected="true">Text</option>
334 <option value="file">File</option> 381 <option value="file">File</option>
335 <option value="text" selected="true">Text</option>
336 </param> 382 </param>
337 <when value="text"> 383 <when value="text">
338 <param name="text" type="text" value="" label="List of genes associated with G2M phase" help="Genes separated by a comma"> 384 <param name="text" type="text" value="" label="List of genes associated with G2M phase" help="Genes separated by a comma">
339 <expand macro="sanitize_query" /> 385 <expand macro="sanitize_query"/>
340 </param> 386 </param>
341 </when> 387 </when>
342 <when value="file"> 388 <when value="file">
343 <param name="file" type="data" format="txt" label="File with the list of genes associated with G2M phase" help="One gene per line"/> 389 <param name="file" type="data" format="txt" label="File with the list of genes associated with G2M phase" help="One gene per line"/>
344 </when> 390 </when>
345 </conditional> 391 </conditional>
346 <expand macro="score_genes_params"/> 392 <expand macro="params_score_genes"/>
347 </when> 393 </when>
348 <when value="tl.rank_genes_groups"> 394 <when value="tl.rank_genes_groups">
349 <param argument="groupby" type="text" value="" label="The key of the observations grouping to consider" help=""> 395 <param argument="groupby" type="text" value="" label="The key of the observations grouping to consider">
350 <expand macro="sanitize_query" /> 396 <expand macro="sanitize_query"/>
351 </param> 397 </param>
352 <expand macro="param_use_raw"/> 398 <expand macro="param_use_raw"/>
353 <param argument="groups" type="text" value="" label="Subset of groups to which comparison shall be restricted" help="e.g. ['g1', 'g2', 'g3']. If not passed, a ranking will be generated for all groups."> 399 <param argument="groups" type="text" value="" label="Subset of groups to which comparison shall be restricted" help="e.g. ['g1', 'g2', 'g3']. If not passed, a ranking will be generated for all groups.">
354 <expand macro="sanitize_query" /> 400 <expand macro="sanitize_query"/>
401 </param>
402 <param argument="layer" type="text" value="" label="Key from adata.layers whose value will be used to perform tests on">
403 <expand macro="sanitize_query"/>
355 </param> 404 </param>
356 <conditional name="ref"> 405 <conditional name="ref">
357 <param name="rest" type="select" label="Comparison"> 406 <param name="rest" type="select" label="Comparison">
358 <option value="rest">Compare each group to the union of the rest of the group</option> 407 <option value="rest" selected="true">Compare each group to the union of the rest of the group</option>
359 <option value="group_id">Compare with respect to a specific group</option> 408 <option value="group_id">Compare with respect to a specific group</option>
360 </param> 409 </param>
361 <when value="rest"/> 410 <when value="rest"/>
362 <when value="group_id"> 411 <when value="group_id">
363 <param argument="reference" type="text" value="" label="Group identifier with respect to which compare"> 412 <param argument="reference" type="text" value="" label="Group identifier with respect to which compare">
364 <expand macro="sanitize_query" /> 413 <expand macro="sanitize_query"/>
365 </param> 414 </param>
366 </when> 415 </when>
367 </conditional> 416 </conditional>
368 <param argument="n_genes" type="integer" min="0" value="100" label="The number of genes that appear in the returned tables" help=""/> 417 <param argument="n_genes" type="integer" min="0" value="" optional="true" label="The number of genes that appear in the returned tables" help="Defaults to all genes"/>
369 <conditional name="tl_rank_genes_groups_method"> 418 <conditional name="tl_rank_genes_groups_method">
370 <param argument="method" type="select" label="Method"> 419 <param argument="method" type="select" label="Method">
371 <option value="t-test" selected="true">t-test</option> 420 <option value="t-test" selected="true">t-test</option>
372 <option value="wilcoxon">Wilcoxon-Rank-Sum</option> 421 <option value="wilcoxon">Wilcoxon-Rank-Sum</option>
373 <option value="t-test_overestim_var">t-test with overestimate of variance of each group</option> 422 <option value="t-test_overestim_var">t-test with overestimate of variance of each group</option>
376 <when value="t-test"> 425 <when value="t-test">
377 <expand macro="corr_method"/> 426 <expand macro="corr_method"/>
378 </when> 427 </when>
379 <when value="wilcoxon"> 428 <when value="wilcoxon">
380 <expand macro="corr_method"/> 429 <expand macro="corr_method"/>
430 <param argument="tie_correct" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Use tie correction for 'wilcoxon' scores"/>
381 </when> 431 </when>
382 <when value="t-test_overestim_var"> 432 <when value="t-test_overestim_var">
383 <expand macro="corr_method"/> 433 <expand macro="corr_method"/>
384 </when> 434 </when>
385 <when value="logreg"> 435 <when value="logreg">
386 <conditional name="solver"> 436 <conditional name="solver">
387 <param argument="solver" type="select" label="Algorithm to use in the optimization problem" help="For small datasets, ‘liblinear’ is a good choice, whereas ‘sag’ and ‘saga’ are faster for large ones. For multiclass problems, only ‘newton-cg’, ‘sag’, ‘saga’ and ‘lbfgs’ handle multinomial loss; ‘liblinear’ is limited to one-versus-rest schemes. ‘newton-cg’, ‘lbfgs’ and ‘sag’ only handle L2 penalty, whereas ‘liblinear’ and ‘saga’ handle L1 penalty."> 437 <param argument="solver" type="select" label="Algorithm to use in the optimization problem" help="For small datasets, ‘liblinear’ is a good choice, whereas ‘sag’ and ‘saga’ are faster for large ones. For multiclass problems, only ‘newton-cg’, ‘sag’, ‘saga’ and ‘lbfgs’ handle multinomial loss; ‘liblinear’ is limited to one-versus-rest schemes. ‘newton-cg’, ‘lbfgs’ and ‘sag’ only handle L2 penalty, whereas ‘liblinear’ and ‘saga’ handle L1 penalty.">
438 <option value="lbfgs" selected="true">lbfgs</option>
388 <option value="newton-cg">newton-cg</option> 439 <option value="newton-cg">newton-cg</option>
389 <option value="lbfgs">lbfgs</option>
390 <option value="liblinear">liblinear</option> 440 <option value="liblinear">liblinear</option>
391 <option value="sag">sag</option> 441 <option value="sag">sag</option>
392 <option value="saga">saga</option> 442 <option value="saga">saga</option>
393 </param> 443 </param>
394 <when value="newton-cg"> 444 <when value="lbfgs">
445 <param name="penalty" type="boolean" truevalue="l2" falsevalue="None" checked="true" label="use l2 penalty?"/>
395 <expand macro="fit_intercept"/> 446 <expand macro="fit_intercept"/>
396 <expand macro="max_iter"/> 447 <expand macro="max_iter"/>
397 <expand macro="multi_class"/> 448 <expand macro="multi_class"/>
398 </when> 449 </when>
399 <when value="lbfgs"> 450 <when value="newton-cg">
451 <param name="penalty" type="boolean" truevalue="l2" falsevalue="None" checked="true" label="use l2 penalty?"/>
400 <expand macro="fit_intercept"/> 452 <expand macro="fit_intercept"/>
401 <expand macro="max_iter"/> 453 <expand macro="max_iter"/>
402 <expand macro="multi_class"/> 454 <expand macro="multi_class"/>
403 </when> 455 </when>
404 <when value="liblinear"> 456 <when value="liblinear">
407 <when value="l1"/> 459 <when value="l1"/>
408 <when value="l2"> 460 <when value="l2">
409 <param argument="dual" type="boolean" truevalue="True" falsevalue="False" checked="false" 461 <param argument="dual" type="boolean" truevalue="True" falsevalue="False" checked="false"
410 label="Dual (not primal) formulation?" help="Prefer primal when n_samples > n_features"/> 462 label="Dual (not primal) formulation?" help="Prefer primal when n_samples > n_features"/>
411 </when> 463 </when>
412 <when value="customized">
413 <expand macro="custom_penalty"/>
414 </when>
415 </conditional> 464 </conditional>
416 <conditional name="intercept_scaling"> 465 <conditional name="intercept_scaling">
417 <param argument="fit_intercept" type="select" 466 <param argument="fit_intercept" type="select" label="Should a constant (a.k.a. bias or intercept) be added to the decision function?">
418 label="Should a constant (a.k.a. bias or intercept) be added to the decision function?" help=""> 467 <option value="True" selected="true">Yes</option>
419 <option value="True">Yes</option>
420 <option value="False">No</option> 468 <option value="False">No</option>
421 </param> 469 </param>
422 <when value="True"> 470 <when value="True">
423 <param argument="intercept_scaling" type="float" value="1.0" 471 <param argument="intercept_scaling" type="float" value="1.0" label="Intercept scaling" help="x becomes [x, self.intercept_scaling], i.e. a 'synthetic' feature with constant value equal to intercept_scaling is appended to the instance vector. The intercept becomes intercept_scaling * synthetic_feature_weight."/>
424 label="Intercept scaling"
425 help="x becomes [x, self.intercept_scaling], i.e. a 'synthetic' feature with constant value equal to intercept_scaling is appended to the instance vector. The intercept becomes intercept_scaling * synthetic_feature_weight."/>
426 </when> 472 </when>
427 <when value="False"/> 473 <when value="False"/>
428 </conditional> 474 </conditional>
429 <expand macro="random_state"/> 475 <expand macro="random_state"/>
430 </when> 476 </when>
431 <when value="sag"> 477 <when value="sag">
478 <param name="penalty" type="boolean" truevalue="l2" falsevalue="None" checked="true" label="use l2 penalty?"/>
432 <expand macro="fit_intercept"/> 479 <expand macro="fit_intercept"/>
433 <expand macro="random_state"/> 480 <expand macro="random_state"/>
434 <expand macro="max_iter"/> 481 <expand macro="max_iter"/>
435 <expand macro="multi_class"/> 482 <expand macro="multi_class"/>
436 </when> 483 </when>
437 <when value="saga"> 484 <when value="saga">
438 <conditional name="penalty"> 485 <conditional name="penalty">
439 <expand macro="penalty"/> 486 <expand macro="penalty">
487 <option value="elasticnet">elasticnet</option>
488 <option value="None">None</option>
489 </expand>
440 <when value="l1"/> 490 <when value="l1"/>
441 <when value="l2"/> 491 <when value="l2"/>
442 <when value="customized"> 492 <when value="elasticnet"/>
443 <expand macro="custom_penalty"/> 493 <when value="None"/>
444 </when>
445 </conditional> 494 </conditional>
446 <expand macro="fit_intercept"/> 495 <expand macro="fit_intercept"/>
447 <expand macro="multi_class"/> 496 <expand macro="multi_class"/>
448 </when> 497 </when>
449 </conditional> 498 </conditional>
450 <param argument="tol" type="float" value="1e-4" label="Tolerance for stopping criteria" help=""/> 499 <param argument="tol" type="float" value="1e-4" label="Tolerance for stopping criteria"/>
451 <param argument="c" type="float" value="1.0" label="Inverse of regularization strength" 500 <param argument="c" type="float" value="1.0" label="Inverse of regularization strength" help="It must be a positive float. Like in support vector machines, smaller values specify stronger regularization."/>
452 help="It must be a positive float. Like in support vector machines, smaller values specify stronger regularization."/>
453 </when> 501 </when>
454 </conditional> 502 </conditional>
503 <param argument="key_added" type="text" value="" optional="true" label="The key in adata.uns information is saved to"/>
455 </when> 504 </when>
456 <!-- With inplace=True, NotImplementedError: Writing Pandas dataframes to h5ad is currently under development. Please use `inplace=False`. --> 505 <!-- With inplace=True, NotImplementedError: Writing Pandas dataframes to h5ad is currently under development. Please use `inplace=False`. -->
457 <!-- <when value="tl.marker_gene_overlap"> 506 <!-- Issue is fixed in the script -->
507 <when value="tl.marker_gene_overlap">
458 <repeat name="reference_markers" title="Marker genes"> 508 <repeat name="reference_markers" title="Marker genes">
459 <param name="key" type="text" value="" label="Cell identity name" help=""/> 509 <param name="key" type="text" value="" label="Cell identity name"/>
460 <param name="values" type="text" value="" label="List of genes" help="Comma-separated names from 'var'"/> 510 <param name="values" type="text" value="" label="List of genes" help="Comma-separated names from 'var'"/>
461 </repeat> 511 </repeat>
462 <param argument="key" type="text" value="rank_genes_groups" label="Key in adata.uns where the rank_genes_groups output is stored"/> 512 <param argument="key" type="text" value="rank_genes_groups" label="Key in adata.uns where the rank_genes_groups output is stored"/>
463 <conditional name="overlap"> 513 <conditional name="overlap">
464 <param argument="method" type="select" label="Method to calculate marker gene overlap"> 514 <param argument="method" type="select" label="Method to calculate marker gene overlap">
465 <option value="overlap_count">overlap_count: Intersection of the gene set</option> 515 <option value="overlap_count" selected="true">overlap_count: Intersection of the gene set</option>
466 <option value="overlap_coef">overlap_coef: Overlap coefficient</option> 516 <option value="overlap_coef">overlap_coef: Overlap coefficient</option>
467 <option value="jaccard">jaccard: Jaccard index</option> 517 <option value="jaccard">jaccard: Jaccard index</option>
468 </param> 518 </param>
469 <when value="overlap_count"> 519 <when value="overlap_count">
470 <param argument="normalize" type="select" label="Normalization option for the marker gene overlap output"> 520 <param argument="normalize" type="select" label="Normalization option for the marker gene overlap output">
471 <option value="None">None</option> 521 <option value="None" selected="true">None</option>
472 <option value="reference">reference: Normalization of the data by the total number of marker genes given in the reference annotation per group</option> 522 <option value="reference">reference: Normalization of the data by the total number of marker genes given in the reference annotation per group</option>
473 <option value="data">data: Normalization of the data by the total number of marker genes used for each cluster</option> 523 <option value="data">data: Normalization of the data by the total number of marker genes used for each cluster</option>
474 </param> 524 </param>
475 </when> 525 </when>
476 <when value="overlap_coef"/> 526 <when value="overlap_coef"/>
477 <when value="jaccard"/> 527 <when value="jaccard"/>
478 </conditional> 528 </conditional>
479 <param argument="top_n_markers" type="integer" optional="true" label="Number of top data-derived marker genes to use" help="By default all calculated marker genes are used. If adj_pval_threshold is set along with top_n_markers, then adj_pval_threshold is ignored."/> 529 <param argument="top_n_markers" type="integer" optional="true" value="" label="Number of top data-derived marker genes to use" help="By default all calculated marker genes are used. If adj_pval_threshold is set along with top_n_markers, then adj_pval_threshold is ignored."/>
480 <param argument="adj_pval_threshold" type="float" optional="true" label="Significance threshold on the adjusted p-values to select marker genes" help=" This can only be used when adjusted p-values are calculated by 'tl.rank_genes_groups'. If adj_pval_threshold is set along with top_n_markers, then adj_pval_threshold is ignored."/> 530 <param argument="adj_pval_threshold" type="float" optional="true" value="" label="Significance threshold on the adjusted p-values to select marker genes" help=" This can only be used when adjusted p-values are calculated by 'tl.rank_genes_groups'. If adj_pval_threshold is set along with top_n_markers, then adj_pval_threshold is ignored."/>
481 <param argument="key_added" type="text" value="marker_gene_overlap" optional="true" label="Key that will contain the marker overlap scores in 'uns'"/> 531 <param argument="key_added" type="text" optional="true" value="" label="Key that will contain the marker overlap scores in 'uns'"/>
482 </when>--> 532 </when>
483 <when value="pp.log1p"/> 533 <when value="pp.log1p">
534 <param argument="base" type="integer" value="" optional="true" label="Base of the logarithm." help="Natural logarithm is used by default."/>
535 <param argument="layer" type="text" value="" optional="true" label="Entry of layers to transform">
536 <expand macro="sanitize_query"/>
537 </param>
538 <param argument="obsm" type="text" value="" optional="true" label="Entry of obsm to transform">
539 <expand macro="sanitize_query"/>
540 </param>
541 </when>
484 <when value="pp.scale"> 542 <when value="pp.scale">
485 <param argument="zero_center" type="boolean" truevalue="True" falsevalue="False" checked="true" 543 <param argument="zero_center" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Zero center?" help="If not, it omits zero-centering variables, which allows to handle sparse input efficiently."/>
486 label="Zero center?" help="If not, it omits zero-centering variables, which allows to handle sparse input efficiently."/> 544 <param argument="max_value" type="float" value="" optional="true" label="Maximum value" help="Clip (truncate) to this value after scaling. If not set, it does not clip."/>
487 <param argument="max_value" type="float" value="" optional="true" label="Maximum value" 545 <param argument="layer" type="text" value="" label="Which element of layers to scale">
488 help="Clip (truncate) to this value after scaling. If not set, it does not clip."/> 546 <expand macro="sanitize_query"/>
547 </param>
548 <param argument="obsm" type="text" value="" label="Which element of obsm to scale">
549 <expand macro="sanitize_query"/>
550 </param>
551 <param argument="mask_obs" type="text" value="" label="Restrict both the derivation of scaling parameters and the scaling itself to a certain set of observations.">
552 <expand macro="sanitize_query"/>
553 </param>
489 </when> 554 </when>
490 <when value="pp.sqrt"/> 555 <when value="pp.sqrt"/>
491 </conditional> 556 </conditional>
492 <expand macro="inputs_common_advanced"/> 557 <expand macro="inputs_common_advanced"/>
493 </inputs> 558 </inputs>
494 <outputs> 559 <outputs>
495 <expand macro="anndata_outputs"/> 560 <expand macro="anndata_outputs"/>
496 </outputs> 561 </outputs>
497 <tests> 562 <tests>
498 <test expect_num_outputs="2"> 563
499 <!-- test 1 --> 564 <!-- test 1 -->
500 <param name="adata" value="sparce_csr_matrix.h5ad" /> 565 <test expect_num_outputs="2">
566 <param name="adata" value="sparce_csr_matrix.h5ad"/>
501 <conditional name="method"> 567 <conditional name="method">
502 <param name="method" value="pp.calculate_qc_metrics"/> 568 <param name="method" value="pp.calculate_qc_metrics"/>
503 <param name="expr_type" value="counts"/>
504 <param name="var_type" value="genes"/>
505 <param name="qc_vars" value="mito,negative"/> 569 <param name="qc_vars" value="mito,negative"/>
506 <param name="percent_top" value=""/> 570 </conditional>
571 <section name="advanced_common">
572 <param name="show_log" value="true"/>
573 </section>
574 <output name="hidden_output">
575 <assert_contents>
576 <has_text_matching expression="sc.pp.calculate_qc_metrics"/>
577 <has_text_matching expression="expr_type='counts'"/>
578 <has_text_matching expression="var_type='genes'"/>
579 <has_text_matching expression="qc_vars=\['mito', 'negative'\]"/>
580 </assert_contents>
581 </output>
582 <output name="anndata_out" ftype="h5ad">
583 <assert_contents>
584 <has_h5_keys keys="obs/n_genes_by_counts,obs/log1p_n_genes_by_counts,obs/total_counts,obs/log1p_total_counts,obs/pct_counts_in_top_50_genes,obs/pct_counts_in_top_100_genes,obs/pct_counts_in_top_200_genes,obs/pct_counts_in_top_500_genes,obs/total_counts_mito,obs/log1p_total_counts_mito,obs/pct_counts_mito,obs/total_counts_negative,obs/log1p_total_counts_negative,obs/pct_counts_negative"/>
585 <has_h5_keys keys="var/n_cells_by_counts,var/mean_counts,var/log1p_mean_counts,var/pct_dropout_by_counts,var/total_counts,var/log1p_total_counts"/>
586 </assert_contents>
587 </output>
588 </test>
589
590 <!-- test 2 -->
591 <test expect_num_outputs="2">
592 <param name="adata" value="sparce_csr_matrix.h5ad"/>
593 <conditional name="method">
594 <param name="method" value="pp.calculate_qc_metrics"/>
595 <param name="qc_vars" value="mito,negative"/>
596 <param name="percent_top" value="50,100,200,300"/>
507 </conditional> 597 </conditional>
508 <section name="advanced_common"> 598 <section name="advanced_common">
509 <param name="show_log" value="true" /> 599 <param name="show_log" value="true" />
510 </section> 600 </section>
511 <output name="hidden_output"> 601 <output name="hidden_output">
512 <assert_contents> 602 <assert_contents>
513 <has_text_matching expression="sc.pp.calculate_qc_metrics" /> 603 <has_text_matching expression="sc.pp.calculate_qc_metrics" />
514 <has_text_matching expression="expr_type='counts'" /> 604 <has_text_matching expression="expr_type='counts'" />
515 <has_text_matching expression="var_type='genes'" /> 605 <has_text_matching expression="var_type='genes'" />
516 <has_text_matching expression="qc_vars=\['mito', 'negative'\]" /> 606 <has_text_matching expression="qc_vars=\['mito', 'negative'\]" />
517 </assert_contents> 607 <has_text_matching expression="percent_top=\[50, 100, 200, 300\]" />
518 </output> 608 </assert_contents>
519 <output name="anndata_out" file="pp.calculate_qc_metrics.sparce_csr_matrix.h5ad" ftype="h5ad" compare="sim_size"/> 609 </output>
520 </test> 610 <output name="anndata_out" ftype="h5ad">
521 <test expect_num_outputs="2"> 611 <assert_contents>
522 <!-- test 2 --> 612 <has_h5_keys keys="obs/n_genes_by_counts,obs/log1p_n_genes_by_counts,obs/total_counts,obs/log1p_total_counts,obs/pct_counts_in_top_50_genes,obs/pct_counts_in_top_100_genes,obs/pct_counts_in_top_200_genes,obs/pct_counts_in_top_300_genes,obs/total_counts_mito,obs/log1p_total_counts_mito,obs/pct_counts_mito,obs/total_counts_negative,obs/log1p_total_counts_negative,obs/pct_counts_negative"/>
523 <param name="adata" value="pp.recipe_weinreb17.paul15_subsample.h5ad" /> 613 <has_h5_keys keys="var/mito,var/negative,var/n_cells_by_counts,var/mean_counts,var/log1p_mean_counts,var/pct_dropout_by_counts,var/total_counts,var/log1p_total_counts"/>
614 </assert_contents>
615 </output>
616 </test>
617
618 <!-- test 3 -->
619 <test expect_num_outputs="2">
620 <param name="adata" value="pp.recipe_weinreb17.paul15_subsample.h5ad"/>
524 <conditional name="method"> 621 <conditional name="method">
525 <param name="method" value="pp.neighbors"/> 622 <param name="method" value="pp.neighbors"/>
526 <param name="n_neighbors" value="15"/> 623 </conditional>
527 <param name="knn" value="True"/> 624 <section name="advanced_common">
528 <param name="random_state" value="0"/> 625 <param name="show_log" value="true"/>
529 <param name="pp_neighbors_method" value="umap"/>
530 <param name="metric" value="euclidean"/>
531 </conditional>
532 <section name="advanced_common">
533 <param name="show_log" value="true" />
534 </section> 626 </section>
535 <output name="hidden_output"> 627 <output name="hidden_output">
536 <assert_contents> 628 <assert_contents>
537 <has_text_matching expression="sc.pp.neighbors"/> 629 <has_text_matching expression="sc.pp.neighbors"/>
538 <has_text_matching expression="n_neighbors=15"/> 630 <has_text_matching expression="n_neighbors=15"/>
540 <has_text_matching expression="random_state=0"/> 632 <has_text_matching expression="random_state=0"/>
541 <has_text_matching expression="method='umap'"/> 633 <has_text_matching expression="method='umap'"/>
542 <has_text_matching expression="metric='euclidean'"/> 634 <has_text_matching expression="metric='euclidean'"/>
543 </assert_contents> 635 </assert_contents>
544 </output> 636 </output>
545 <output name="anndata_out" file="pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"> 637 <output name="anndata_out" ftype="h5ad">
546 <assert_contents> 638 <assert_contents>
547 <has_h5_keys keys="X, obs, obsm, uns, var" /> 639 <has_h5_keys keys="uns/neighbors"/>
548 </assert_contents> 640 <has_h5_keys keys="obsp/connectivities,obsp/distances"/>
549 </output> 641 </assert_contents>
550 </test> 642 </output>
551 <test expect_num_outputs="2"> 643 </test>
552 <!-- test 3 --> 644
553 <param name="adata" value="pp.recipe_weinreb17.paul15_subsample.h5ad" /> 645 <!-- test 4 -->
646 <test expect_num_outputs="2">
647 <param name="adata" value="pp.recipe_weinreb17.paul15_subsample.h5ad"/>
554 <conditional name="method"> 648 <conditional name="method">
555 <param name="method" value="pp.neighbors"/> 649 <param name="method" value="pp.neighbors"/>
556 <param name="n_neighbors" value="15"/>
557 <param name="knn" value="True"/>
558 <param name="pp_neighbors_method" value="gauss"/> 650 <param name="pp_neighbors_method" value="gauss"/>
559 <param name="metric" value="braycurtis"/> 651 <param name="metric" value="braycurtis"/>
560 </conditional> 652 </conditional>
561 <section name="advanced_common"> 653 <section name="advanced_common">
562 <param name="show_log" value="true" /> 654 <param name="show_log" value="true"/>
563 </section> 655 </section>
564 <output name="hidden_output"> 656 <output name="hidden_output">
565 <assert_contents> 657 <assert_contents>
566 <has_text_matching expression="sc.pp.neighbors"/> 658 <has_text_matching expression="sc.pp.neighbors"/>
567 <has_text_matching expression="n_neighbors=15"/> 659 <has_text_matching expression="n_neighbors=15"/>
569 <has_text_matching expression="random_state=0"/> 661 <has_text_matching expression="random_state=0"/>
570 <has_text_matching expression="method='gauss'"/> 662 <has_text_matching expression="method='gauss'"/>
571 <has_text_matching expression="metric='braycurtis'"/> 663 <has_text_matching expression="metric='braycurtis'"/>
572 </assert_contents> 664 </assert_contents>
573 </output> 665 </output>
574 <output name="anndata_out" file="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/> 666 <output name="anndata_out" ftype="h5ad">
575 </test> 667 <assert_contents>
576 <test expect_num_outputs="2"> 668 <has_h5_keys keys="obsp/connectivities,obsp/distances"/>
577 <!-- test 4 --> 669 </assert_contents>
578 <param name="adata" value="krumsiek11.h5ad" /> 670 </output>
671 </test>
672
673 <!-- test 5 -->
674 <test expect_num_outputs="2">
675 <param name="adata" value="krumsiek11.h5ad"/>
579 <conditional name="method"> 676 <conditional name="method">
580 <param name="method" value="tl.score_genes"/> 677 <param name="method" value="tl.score_genes"/>
581 <param name="gene_list" value="Gata2, Fog1"/> 678 <param name="gene_list" value="Gata2, Fog1"/>
582 <param name="ctrl_size" value="2"/> 679 <param name="ctrl_size" value="2"/>
583 <param name="n_bins" value="2"/> 680 <param name="n_bins" value="2"/>
584 <param name="random_state" value="2"/> 681 <param name="random_state" value="2"/>
585 <param name="use_raw" value="False"/> 682 </conditional>
586 <param name="score_name" value="score"/> 683 <section name="advanced_common">
587 </conditional> 684 <param name="show_log" value="true"/>
588 <section name="advanced_common"> 685 </section>
589 <param name="show_log" value="true" /> 686 <output name="hidden_output">
590 </section> 687 <assert_contents>
591 <output name="hidden_output"> 688 <has_text_matching expression="sc.tl.score_genes"/>
592 <assert_contents> 689 <has_text_matching expression="gene_list=\['Gata2', 'Fog1'\]"/>
593 <has_text_matching expression="sc.tl.score_genes" /> 690 <has_text_matching expression="ctrl_size=2"/>
594 <has_text_matching expression="gene_list=\['Gata2', 'Fog1'\]" /> 691 <has_text_matching expression="score_name='score'"/>
595 <has_text_matching expression="ctrl_size=2" /> 692 <has_text_matching expression="n_bins=2"/>
596 <has_text_matching expression="score_name='score'" /> 693 <has_text_matching expression="random_state=2"/>
597 <has_text_matching expression="n_bins=2" /> 694 <has_text_matching expression="use_raw=False"/>
598 <has_text_matching expression="random_state=2" /> 695 <has_text_matching expression="copy=False"/>
599 <has_text_matching expression="use_raw=False" /> 696 </assert_contents>
600 <has_text_matching expression="copy=False" /> 697 </output>
601 </assert_contents> 698 <output name="anndata_out" ftype="h5ad">
602 </output> 699 <assert_contents>
603 <output name="anndata_out" file="tl.score_genes.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/> 700 <has_h5_keys keys="obs/score"/>
604 </test> 701 </assert_contents>
605 <test expect_num_outputs="2"> 702 </output>
606 <!-- test 5 --> 703 </test>
607 <param name="adata" value="krumsiek11.h5ad" /> 704
705 <!-- test 6 -->
706 <test expect_num_outputs="2">
707 <param name="adata" value="krumsiek11.h5ad"/>
608 <conditional name="method"> 708 <conditional name="method">
609 <param name="method" value="tl.score_genes_cell_cycle"/> 709 <param name="method" value="tl.score_genes_cell_cycle"/>
610 <conditional name='s_genes'> 710 <conditional name='s_genes'>
611 <param name="format" value="text"/> 711 <param name="format" value="text"/>
612 <param name="text" value="Gata2, Fog1, EgrNab"/> 712 <param name="text" value="Gata2, Fog1, EgrNab"/>
615 <param name="format" value="text"/> 715 <param name="format" value="text"/>
616 <param name="text" value="Gata2, Fog1, EgrNab"/> 716 <param name="text" value="Gata2, Fog1, EgrNab"/>
617 </conditional> 717 </conditional>
618 <param name="n_bins" value="2"/> 718 <param name="n_bins" value="2"/>
619 <param name="random_state" value="1"/> 719 <param name="random_state" value="1"/>
620 <param name="use_raw" value="False"/> 720 </conditional>
621 </conditional> 721 <section name="advanced_common">
622 <section name="advanced_common"> 722 <param name="show_log" value="true"/>
623 <param name="show_log" value="true" />
624 </section> 723 </section>
625 <output name="hidden_output"> 724 <output name="hidden_output">
626 <assert_contents> 725 <assert_contents>
627 <has_text_matching expression="sc.tl.score_genes_cell_cycle"/> 726 <has_text_matching expression="sc.tl.score_genes_cell_cycle"/>
628 <has_text_matching expression="s_genes=\['Gata2', 'Fog1', 'EgrNab'\]"/> 727 <has_text_matching expression="s_genes=\['Gata2', 'Fog1', 'EgrNab'\]"/>
630 <has_text_matching expression="n_bins=2"/> 729 <has_text_matching expression="n_bins=2"/>
631 <has_text_matching expression="random_state=1"/> 730 <has_text_matching expression="random_state=1"/>
632 <has_text_matching expression="use_raw=False"/> 731 <has_text_matching expression="use_raw=False"/>
633 </assert_contents> 732 </assert_contents>
634 </output> 733 </output>
635 <output name="anndata_out" file="tl.score_genes_cell_cycle.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/> 734 <output name="anndata_out" ftype="h5ad">
636 </test> 735 <assert_contents>
637 <test expect_num_outputs="2"> 736 <has_h5_keys keys="obs/S_score,obs/G2M_score,obs/phase"/>
638 <!-- test 6 --> 737 </assert_contents>
639 <param name="adata" value="krumsiek11.h5ad" /> 738 </output>
739 </test>
740
741 <!-- test 7 -->
742 <test expect_num_outputs="2">
743 <param name="adata" value="krumsiek11.h5ad"/>
640 <conditional name="method"> 744 <conditional name="method">
641 <param name="method" value="tl.rank_genes_groups"/> 745 <param name="method" value="tl.rank_genes_groups"/>
642 <param name="groupby" value="cell_type"/> 746 <param name="groupby" value="cell_type"/>
643 <param name="use_raw" value="False"/>
644 <conditional name="ref">
645 <param name="rest" value="rest"/>
646 </conditional>
647 <param name="n_genes" value="100"/> 747 <param name="n_genes" value="100"/>
648 <conditional name="tl_rank_genes_groups_method"> 748 <conditional name="tl_rank_genes_groups_method">
649 <param name="method" value="t-test_overestim_var"/> 749 <param name="method" value="t-test_overestim_var"/>
650 <param name="corr_method" value="benjamini-hochberg"/>
651 </conditional> 750 </conditional>
652 </conditional> 751 </conditional>
653 <section name="advanced_common"> 752 <section name="advanced_common">
654 <param name="show_log" value="true" /> 753 <param name="show_log" value="true"/>
655 </section> 754 </section>
656 <output name="hidden_output"> 755 <output name="hidden_output">
657 <assert_contents> 756 <assert_contents>
658 <has_text_matching expression="sc.tl.rank_genes_groups"/> 757 <has_text_matching expression="sc.tl.rank_genes_groups"/>
659 <has_text_matching expression="groupby='cell_type'"/> 758 <has_text_matching expression="groupby='cell_type'"/>
662 <has_text_matching expression="n_genes=100"/> 761 <has_text_matching expression="n_genes=100"/>
663 <has_text_matching expression="method='t-test_overestim_var'"/> 762 <has_text_matching expression="method='t-test_overestim_var'"/>
664 <has_text_matching expression="corr_method='benjamini-hochberg'"/> 763 <has_text_matching expression="corr_method='benjamini-hochberg'"/>
665 </assert_contents> 764 </assert_contents>
666 </output> 765 </output>
667 <output name="anndata_out" file="tl.rank_genes_groups.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/> 766 <output name="anndata_out" ftype="h5ad">
668 </test> 767 <assert_contents>
669 <test expect_num_outputs="2"> 768 <has_h5_keys keys="uns/rank_genes_groups"/>
670 <!-- test 7 --> 769 </assert_contents>
671 <param name="adata" value="pbmc68k_reduced.h5ad" /> 770 </output>
771 </test>
772
773 <!-- test 8 -->
774 <test expect_num_outputs="2">
775 <param name="adata" value="krumsiek11.h5ad"/>
672 <conditional name="method"> 776 <conditional name="method">
673 <param name="method" value="tl.rank_genes_groups"/> 777 <param name="method" value="tl.rank_genes_groups"/>
674 <param name="groupby" value="louvain"/> 778 <param name="groupby" value="cell_type"/>
675 <param name="use_raw" value="True"/>
676 <conditional name="ref">
677 <param name="rest" value="rest"/>
678 </conditional>
679 <param name="n_genes" value="100"/> 779 <param name="n_genes" value="100"/>
680 <conditional name="tl_rank_genes_groups_method"> 780 <conditional name="tl_rank_genes_groups_method">
681 <param name="method" value="logreg"/> 781 <param name="method" value="logreg"/>
682 <conditional name="solver">
683 <param name="solver" value="newton-cg"/>
684 <param name="fit_intercept" value="True"/>
685 <param name="max_iter" value="100"/>
686 <param name="multi_class" value="auto"/>
687 </conditional>
688 <param name="tol" value="1e-4"/>
689 <param name="c" value="1.0"/>
690 </conditional> 782 </conditional>
691 </conditional> 783 </conditional>
692 <section name="advanced_common"> 784 <section name="advanced_common">
693 <param name="show_log" value="true" /> 785 <param name="show_log" value="true"/>
694 </section> 786 </section>
695 <output name="hidden_output"> 787 <output name="hidden_output">
696 <assert_contents> 788 <assert_contents>
697 <has_text_matching expression="sc.tl.rank_genes_groups"/> 789 <has_text_matching expression="sc.tl.rank_genes_groups"/>
698 <has_text_matching expression="groupby='louvain'"/> 790 <has_text_matching expression="groupby='cell_type'"/>
699 <has_text_matching expression="use_raw=True"/> 791 <has_text_matching expression="use_raw=False"/>
700 <has_text_matching expression="reference='rest'"/> 792 <has_text_matching expression="reference='rest'"/>
701 <has_text_matching expression="n_genes=100"/> 793 <has_text_matching expression="n_genes=100"/>
702 <has_text_matching expression="method='logreg'"/> 794 <has_text_matching expression="method='logreg'"/>
703 <has_text_matching expression="solver='newton-cg'"/> 795 <has_text_matching expression="solver='lbfgs'"/>
704 <has_text_matching expression="penalty='l2'"/> 796 <has_text_matching expression="penalty='l2'"/>
705 <has_text_matching expression="fit_intercept=True"/> 797 <has_text_matching expression="fit_intercept=True"/>
706 <has_text_matching expression="max_iter=100"/> 798 <has_text_matching expression="max_iter=100"/>
707 <has_text_matching expression="multi_class='auto'"/> 799 <has_text_matching expression="multi_class='auto'"/>
708 <has_text_matching expression="tol=0.0001"/> 800 <has_text_matching expression="tol=0.0001"/>
709 <has_text_matching expression="C=1.0"/> 801 <has_text_matching expression="C=1.0"/>
710 </assert_contents> 802 </assert_contents>
711 </output> 803 </output>
712 <output name="anndata_out" file="tl.rank_genes_groups.newton-cg.pbmc68k_reduced.h5ad" ftype="h5ad" compare="sim_size" delta="1000000" delta_frac="0.15"> 804 <output name="anndata_out" ftype="h5ad">
713 <assert_contents> 805 <assert_contents>
714 <has_h5_keys keys="X, obs, obsm, raw/X, raw/var, uns, var" /> 806 <has_h5_keys keys="uns/rank_genes_groups"/>
715 </assert_contents> 807 </assert_contents>
716 </output> 808 </output>
717 </test> 809 </test>
718 <test expect_num_outputs="2"> 810
719 <!-- test 8 --> 811 <!-- test 9 -->
720 <param name="adata" value="pbmc68k_reduced.h5ad" /> 812 <test expect_num_outputs="2">
813 <param name="adata" value="krumsiek11.h5ad"/>
721 <conditional name="method"> 814 <conditional name="method">
722 <param name="method" value="tl.rank_genes_groups"/> 815 <param name="method" value="tl.rank_genes_groups"/>
723 <param name="groupby" value="louvain"/> 816 <param name="groupby" value="cell_type"/>
724 <param name="use_raw" value="True"/>
725 <conditional name="ref">
726 <param name="rest" value="rest"/>
727 </conditional>
728 <param name="n_genes" value="100"/> 817 <param name="n_genes" value="100"/>
729 <conditional name="tl_rank_genes_groups_method"> 818 <conditional name="tl_rank_genes_groups_method">
730 <param name="method" value="logreg"/> 819 <param name="method" value="logreg"/>
731 <conditional name="solver"> 820 <conditional name="solver">
732 <param name="solver" value="liblinear"/> 821 <param name="solver" value="liblinear"/>
733 <conditional name="penalty"> 822 <conditional name="penalty">
734 <param name="penalty" value="l2"/> 823 <param name="penalty" value="l2"/>
735 <param name="dual" value="False"/>
736 <conditional name="intercept_scaling">
737 <param name="fit_intercept" value="True"/>
738 <param name="intercept_scaling" value="1.0" />
739 </conditional>
740 <param name="random_state" value="1"/> 824 <param name="random_state" value="1"/>
741 </conditional> 825 </conditional>
742 </conditional> 826 </conditional>
743 <param name="tol" value="1e-4"/>
744 <param name="c" value="1.0"/>
745 </conditional> 827 </conditional>
746 </conditional> 828 </conditional>
747 <section name="advanced_common"> 829 <section name="advanced_common">
748 <param name="show_log" value="true" /> 830 <param name="show_log" value="true"/>
749 </section> 831 </section>
750 <output name="hidden_output"> 832 <output name="hidden_output">
751 <assert_contents> 833 <assert_contents>
752 <has_text_matching expression="sc.tl.rank_genes_groups"/> 834 <has_text_matching expression="sc.tl.rank_genes_groups"/>
753 <has_text_matching expression="groupby='louvain'"/> 835 <has_text_matching expression="groupby='cell_type'"/>
754 <has_text_matching expression="use_raw=True"/> 836 <has_text_matching expression="use_raw=False"/>
755 <has_text_matching expression="reference='rest'"/> 837 <has_text_matching expression="reference='rest'"/>
756 <has_text_matching expression="n_genes=100"/> 838 <has_text_matching expression="n_genes=100"/>
757 <has_text_matching expression="method='logreg'"/> 839 <has_text_matching expression="method='logreg'"/>
758 <has_text_matching expression="solver='liblinear'"/> 840 <has_text_matching expression="solver='liblinear'"/>
759 <has_text_matching expression="penalty='l2'"/> 841 <has_text_matching expression="penalty='l2'"/>
762 <has_text_matching expression="intercept_scaling=1.0"/> 844 <has_text_matching expression="intercept_scaling=1.0"/>
763 <has_text_matching expression="tol=0.0001"/> 845 <has_text_matching expression="tol=0.0001"/>
764 <has_text_matching expression="C=1.0"/> 846 <has_text_matching expression="C=1.0"/>
765 </assert_contents> 847 </assert_contents>
766 </output> 848 </output>
767 <output name="anndata_out" file="tl.rank_genes_groups.liblinear.krumsiek11.h5ad" ftype="h5ad" compare="sim_size" delta="1000000" delta_frac="0.15"> 849 <output name="anndata_out" ftype="h5ad">
768 <assert_contents> 850 <assert_contents>
769 <has_h5_keys keys="X, obs, obsm, raw/X, raw/var, uns, var" /> 851 <has_h5_keys keys="uns/rank_genes_groups"/>
770 </assert_contents> 852 </assert_contents>
771 </output> 853 </output>
772 </test> 854 </test>
773 <!-- test expect_num_outputs="2"> 855
774 < test 9 tl.marker_gene_overlap function was commented because inpace=True does not work> 856 <!-- test 10 -->
775 <param name="adata" value="tl.rank_genes_groups.newton-cg.pbmc68k_reduced.h5ad" /> 857 <test expect_num_outputs="2">
858 <param name="adata" value="tl.rank_genes_groups.newton-cg.pbmc68k_reduced.h5ad"/>
776 <conditional name="method"> 859 <conditional name="method">
777 <param name="method" value="tl.marker_gene_overlap"/> 860 <param name="method" value="tl.marker_gene_overlap"/>
778 <repeat name="reference_markers"> 861 <repeat name="reference_markers">
779 <param name="key" value="CD4 T cells"/> 862 <param name="key" value="CD4 T cells"/>
780 <param name="value" value="IL7R"/> 863 <param name="values" value="IL7R"/>
781 </repeat> 864 </repeat>
782 <repeat name="reference_markers"> 865 <repeat name="reference_markers">
783 <param name="key" value="CD14+ Monocytes"/> 866 <param name="key" value="CD14+ Monocytes"/>
784 <param name="value" value="CD14,LYZ"/> 867 <param name="values" value="CD14,LYZ"/>
785 </repeat> 868 </repeat>
786 <repeat name="reference_markers"> 869 <repeat name="reference_markers">
787 <param name="key" value="B cells"/> 870 <param name="key" value="B cells"/>
788 <param name="value" value="MS4A1"/> 871 <param name="values" value="MS4A1"/>
789 </repeat> 872 </repeat>
790 <conditional name="overlap"> 873 </conditional>
791 <param name="method" value="overlap_count"/> 874 <section name="advanced_common">
792 <param name="normalize" value="None"/> 875 <param name="show_log" value="true"/>
793 </conditional> 876 </section>
794 </conditional>
795 <assert_stdout> 877 <assert_stdout>
796 <has_text_matching expression="tl.marker_gene_overlap"/> 878 <has_text_matching expression="marker_gene_overlap"/>
797 <has_text_matching expression="key='rank_genes_groups'"/>
798 <has_text_matching expression="method='overlap_count'"/>
799 </assert_stdout> 879 </assert_stdout>
800 <output name="anndata_out" file="tl.marker_gene_overlap.pbmc68k_reduced.h5ad" ftype="h5ad" compare="sim_size"/> 880 <output name="hidden_output">
801 </test> --> 881 <assert_contents>
802 <test expect_num_outputs="2"> 882 <has_text_matching expression="sc.tl.marker_gene_overlap"/>
803 <!-- test 10 --> 883 </assert_contents>
804 <param name="adata" value="krumsiek11.h5ad" /> 884 </output>
885 <output name="anndata_out" ftype="h5ad">
886 <assert_contents>
887 <has_h5_keys keys="uns/rank_genes_groups"/>
888 </assert_contents>
889 </output>
890 </test>
891
892 <!-- test 11 -->
893 <test expect_num_outputs="2">
894 <param name="adata" value="krumsiek11.h5ad"/>
805 <conditional name="method"> 895 <conditional name="method">
806 <param name="method" value="pp.log1p"/> 896 <param name="method" value="pp.log1p"/>
807 </conditional> 897 </conditional>
808 <section name="advanced_common"> 898 <section name="advanced_common">
809 <param name="show_log" value="true" /> 899 <param name="show_log" value="true"/>
810 </section> 900 </section>
811 <output name="hidden_output"> 901 <output name="hidden_output">
812 <assert_contents> 902 <assert_contents>
813 <has_text_matching expression="sc.pp.log1p"/> 903 <has_text_matching expression="sc.pp.log1p"/>
814 </assert_contents> 904 </assert_contents>
815 </output> 905 </output>
816 <output name="anndata_out" file="pp.log1p.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/> 906 <output name="anndata_out" ftype="h5ad">
817 </test> 907 <assert_contents>
818 <test expect_num_outputs="2"> 908 <has_h5_keys keys="uns/log1p"/>
819 <!-- test 11 --> 909 </assert_contents>
820 <param name="adata" value="krumsiek11.h5ad" /> 910 </output>
911 </test>
912
913 <!-- test 12 -->
914 <test expect_num_outputs="2">
915 <param name="adata" value="krumsiek11.h5ad"/>
821 <conditional name="method"> 916 <conditional name="method">
822 <param name="method" value="pp.scale"/> 917 <param name="method" value="pp.scale"/>
823 <param name="zero_center" value="true"/> 918 </conditional>
824 </conditional> 919 <section name="advanced_common">
825 <section name="advanced_common"> 920 <param name="show_log" value="true"/>
826 <param name="show_log" value="true" />
827 </section> 921 </section>
828 <output name="hidden_output"> 922 <output name="hidden_output">
829 <assert_contents> 923 <assert_contents>
830 <has_text_matching expression="sc.pp.scale"/> 924 <has_text_matching expression="sc.pp.scale"/>
831 <has_text_matching expression="zero_center=True"/> 925 <has_text_matching expression="zero_center=True"/>
832 </assert_contents> 926 </assert_contents>
833 </output> 927 </output>
834 <output name="anndata_out" file="pp.scale.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/> 928 <output name="anndata_out" ftype="h5ad">
835 </test> 929 <assert_contents>
836 <test expect_num_outputs="2"> 930 <has_h5_keys keys="var/mean,var/std"/>
837 <!-- test 12 --> 931 </assert_contents>
838 <param name="adata" value="krumsiek11.h5ad" /> 932 </output> </test>
933
934 <!-- test 13 -->
935 <test expect_num_outputs="2">
936 <param name="adata" value="krumsiek11.h5ad"/>
839 <conditional name="method"> 937 <conditional name="method">
840 <param name="method" value="pp.scale"/> 938 <param name="method" value="pp.scale"/>
841 <param name="zero_center" value="true"/>
842 <param name="max_value" value="10"/> 939 <param name="max_value" value="10"/>
843 </conditional> 940 </conditional>
844 <section name="advanced_common"> 941 <section name="advanced_common">
845 <param name="show_log" value="true" /> 942 <param name="show_log" value="true"/>
846 </section> 943 </section>
847 <output name="hidden_output"> 944 <output name="hidden_output">
848 <assert_contents> 945 <assert_contents>
849 <has_text_matching expression="sc.pp.scale"/> 946 <has_text_matching expression="sc.pp.scale"/>
850 <has_text_matching expression="zero_center=True"/> 947 <has_text_matching expression="zero_center=True"/>
851 <has_text_matching expression="max_value=10.0"/> 948 <has_text_matching expression="max_value=10.0"/>
852 </assert_contents> 949 </assert_contents>
853 </output> 950 </output>
854 <output name="anndata_out" file="pp.scale_max_value.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/> 951 <output name="anndata_out" ftype="h5ad">
855 </test> 952 <assert_contents>
856 <test expect_num_outputs="2"> 953 <has_h5_keys keys="var/mean,var/std"/>
857 <!-- test 13 --> 954 </assert_contents>
858 <param name="adata" value="krumsiek11.h5ad" /> 955 </output>
956 </test>
957
958 <!-- test 14 -->
959 <test expect_num_outputs="2">
960 <param name="adata" value="random-randint.h5ad"/>
859 <conditional name="method"> 961 <conditional name="method">
860 <param name="method" value="pp.sqrt"/> 962 <param name="method" value="pp.sqrt"/>
861 </conditional> 963 </conditional>
862 <section name="advanced_common"> 964 <section name="advanced_common">
863 <param name="show_log" value="true" /> 965 <param name="show_log" value="true"/>
864 </section> 966 </section>
865 <output name="hidden_output"> 967 <output name="hidden_output">
866 <assert_contents> 968 <assert_contents>
867 <has_text_matching expression="sc.pp.sqrt"/> 969 <has_text_matching expression="sc.pp.sqrt"/>
868 </assert_contents> 970 <has_text_matching expression="stats before sqrt: min= 0.0 max= 999.0 mean= 499.83777"/>
869 </output> 971 <has_text_matching expression="stats after sqrt: min= 0.0 max= 31.606962 mean= 21.079018"/>
870 <output name="anndata_out" file="pp.sqrt.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/> 972 </assert_contents>
871 </test> 973 </output>
872 <test expect_num_outputs="2"> 974 <output name="anndata_out" ftype="h5ad">
873 <!-- test 13 --> 975 <assert_contents>
874 <param name="adata" value="sparce_csr_matrix.h5ad" /> 976 <has_h5_keys keys="obs/index"/>
875 <conditional name="method"> 977 </assert_contents>
876 <param name="method" value="pp.calculate_qc_metrics"/> 978 </output>
877 <param name="expr_type" value="counts"/>
878 <param name="var_type" value="genes"/>
879 <param name="qc_vars" value="mito,negative"/>
880 <param name="percent_top" value="50,100,200,300"/>
881 </conditional>
882 <section name="advanced_common">
883 <param name="show_log" value="true" />
884 </section>
885 <output name="hidden_output">
886 <assert_contents>
887 <has_text_matching expression="sc.pp.calculate_qc_metrics" />
888 <has_text_matching expression="expr_type='counts'" />
889 <has_text_matching expression="var_type='genes'" />
890 <has_text_matching expression="qc_vars=\['mito', 'negative'\]" />
891 <has_text_matching expression="percent_top=\[50, 100, 200, 300\]" />
892 </assert_contents>
893 </output>
894 <output name="anndata_out" file="pp.calculate_qc_metrics.sparce_csr_matrix.h5ad" ftype="h5ad" compare="sim_size"/>
895 </test> 979 </test>
896 </tests> 980 </tests>
897 <help><![CDATA[ 981 <help><![CDATA[
898 Calculate quality control metrics., using `pp.calculate_qc_metrics` 982 Calculate quality control metrics., using `pp.calculate_qc_metrics`
899 =================================================================== 983 ===================================================================
900 984
901 Calculates a number of qc metrics for an AnnData object, largely based on calculateQCMetrics from scater. 985 Calculates a number of qc metrics for an AnnData object, largely based on calculateQCMetrics from scater.
902 Currently is most efficient on a sparse CSR or dense matrix. 986 Currently is most efficient on a sparse CSR or dense matrix.
903 987
904 It updates the observation level metrics with 988 It updates the observation level metrics with
905 989
906 - total_{var_type}_by_{expr_type} (e.g. "total_genes_by_counts", number of genes with positive counts in a cell) 990 - total_{var_type}_by_{expr_type} (e.g. "total_genes_by_counts", number of genes with positive counts in a cell)
981 Calculate an overlap score between data-deriven marker genes and provided markers (`tl.marker_gene_overlap`) 1065 Calculate an overlap score between data-deriven marker genes and provided markers (`tl.marker_gene_overlap`)
982 ============================================================================================================ 1066 ============================================================================================================
983 1067
984 Marker gene overlap scores can be quoted as overlap counts, overlap coefficients, or jaccard indices. The method returns a pandas dataframe which can be used to annotate clusters based on marker gene overlaps. 1068 Marker gene overlap scores can be quoted as overlap counts, overlap coefficients, or jaccard indices. The method returns a pandas dataframe which can be used to annotate clusters based on marker gene overlaps.
985 1069
1070 More details on the `scanpy documentation
1071 <https://scanpy.readthedocs.io/en/stable/generated/scanpy.tl.marker_gene_overlap.html>`__
986 1072
987 Logarithmize the data matrix (`pp.log1p`) 1073 Logarithmize the data matrix (`pp.log1p`)
988 ========================================= 1074 =========================================
989 1075
990 More details on the `scanpy documentation 1076 More details on the `scanpy documentation