Mercurial > repos > iuc > scanpy_inspect

comparison inspect.xml @ 17:6551272ddc04 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 55ba4cd74d5d8f7baff164b1864c36759d1c7fd9
author iuc
date Fri, 18 Oct 2024 10:35:15 +0000
parents b6035c5e7e12
children 8f8b607d7408
comparison
equal deleted inserted replaced
16:e5a00f205a9e 17:6551272ddc04
219 #if str($method.key_added) != '': 219 #if str($method.key_added) != '':
220 key_added='$method.key_added', 220 key_added='$method.key_added',
221 #end if 221 #end if
222 copy=False) 222 copy=False)
223 223
224 #if str($method.get_df.get_df_select) == 'True':
225 cluster_DEG = sc.get.rank_genes_groups_df(adata,
226 group=None, # return all groups
227 #if str($method.get_df.key) != '':
228 key='$method.get_df.key',
229 #end if
230 #if str($method.get_df.pval_cutoff) != '':
231 pval_cutoff=$method.get_df.pval_cutoff,
232 #end if
233 #if str($method.get_df.log2fc_min) != '':
234 log2fc_min=$method.get_df.log2fc_min,
235 #end if
236 #if str($method.get_df.log2fc_max) != '':
237 log2fc_max=$method.get_df.log2fc_max,
238 #end if
239 @CMD_PARAM_GENE_SYMBOLS@
240 )
241
242 cluster_DEG.to_csv('DEG.tsv', sep="\t", index=False)
243 #end if
244
224 #else if str($method.method) == "tl.marker_gene_overlap": 245 #else if str($method.method) == "tl.marker_gene_overlap":
225 reference_markers = {} 246 reference_markers = {}
226 #for $i, $s in enumerate($method.reference_markers) 247 #for $i, $s in enumerate($method.reference_markers)
227 #set $list=[x.strip() for x in str($s.values).split(',')] 248 #set $list=[x.strip() for x in str($s.values).split(',')]
228 reference_markers['$s.key'] = $list 249 reference_markers['$s.key'] = $list
290 print("stats before sqrt:", "min=", adata.X.min(), "max=", adata.X.max(), "mean=", adata.X.mean()) 311 print("stats before sqrt:", "min=", adata.X.min(), "max=", adata.X.max(), "mean=", adata.X.mean())
291 312
292 sc.pp.sqrt( 313 sc.pp.sqrt(
293 adata, 314 adata,
294 copy=False) 315 copy=False)
316
317 print("stats after sqrt:", "min=", adata.X.min(), "max=", adata.X.max(), "mean=", adata.X.mean())
295 #end if 318 #end if
296
297 print("stats after sqrt:", "min=", adata.X.min(), "max=", adata.X.max(), "mean=", adata.X.mean())
298 319
299 @CMD_ANNDATA_WRITE_OUTPUTS@ 320 @CMD_ANNDATA_WRITE_OUTPUTS@
300 ]]> 321 ]]>
301 </configfile> 322 </configfile>
302 </configfiles> 323 </configfiles>
390 </when> 411 </when>
391 </conditional> 412 </conditional>
392 <expand macro="params_score_genes"/> 413 <expand macro="params_score_genes"/>
393 </when> 414 </when>
394 <when value="tl.rank_genes_groups"> 415 <when value="tl.rank_genes_groups">
416 <conditional name="get_df">
417 <param name="get_df_select" type="select" label="Get ranked genes as a Tabular file?">
418 <option value="False" selected="true">False</option>
419 <option value="True">True</option>
420 </param>
421 <when value="False"/>
422 <when value="True">
423 <param argument="key" type="text" value="" optional="true" label="Key differential expression groups were stored under"/>
424 <param argument="pval_cutoff" type="float" min="0.0" value="" optional="true" label="Return only adjusted p-values below the cutoff."/>
425 <param argument="log2fc_min" type="float" value="" optional="true" label="Minimum logfc to return."/>
426 <param argument="log2fc_max" type="float" value="" optional="true" label="Maximum logfc to return."/>
427 <expand macro="param_gene_symbols" label="Column name in [.var] DataFrame that stores gene symbols."/>
428 </when>
429 </conditional>
395 <param argument="groupby" type="text" value="" label="The key of the observations grouping to consider"> 430 <param argument="groupby" type="text" value="" label="The key of the observations grouping to consider">
396 <expand macro="sanitize_query"/> 431 <expand macro="sanitize_query"/>
397 </param> 432 </param>
398 <expand macro="param_use_raw"/> 433 <expand macro="param_use_raw"/>
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."> 434 <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.">
556 </conditional> 591 </conditional>
557 <expand macro="inputs_common_advanced"/> 592 <expand macro="inputs_common_advanced"/>
558 </inputs> 593 </inputs>
559 <outputs> 594 <outputs>
560 <expand macro="anndata_outputs"/> 595 <expand macro="anndata_outputs"/>
596 <data name="ranked_gene" format="tabular" from_work_dir="DEG.tsv" label="${tool.name} (${method.method}) on ${on_string}: Ranked genes">
597 <filter> method['method'] == 'tl.rank_genes_groups' and method['get_df']['get_df_select'] == 'True'</filter>
598 </data>
561 </outputs> 599 </outputs>
562 <tests> 600 <tests>
563 <!-- test 1 --> 601 <!-- test 1 -->
564 <test expect_num_outputs="2"> 602 <test expect_num_outputs="2">
565 <param name="adata" value="sparce_csr_matrix.h5ad"/> 603 <param name="adata" value="sparce_csr_matrix.h5ad"/>
1026 <assert_contents> 1064 <assert_contents>
1027 <has_h5_keys keys="obs/index"/> 1065 <has_h5_keys keys="obs/index"/>
1028 </assert_contents> 1066 </assert_contents>
1029 </output> 1067 </output>
1030 </test> 1068 </test>
1069
1070 <!-- test 16 -->
1071 <test expect_num_outputs="3">
1072 <param name="adata" value="krumsiek11.h5ad"/>
1073 <conditional name="method">
1074 <param name="method" value="tl.rank_genes_groups"/>
1075 <conditional name="get_df">
1076 <param name="get_df_select" value="True"/>
1077 </conditional>
1078 <param name="groupby" value="cell_type"/>
1079 <param name="n_genes" value="100"/>
1080 <conditional name="tl_rank_genes_groups_method">
1081 <param name="method" value="t-test_overestim_var"/>
1082 </conditional>
1083 </conditional>
1084 <section name="advanced_common">
1085 <param name="show_log" value="true"/>
1086 </section>
1087 <output name="hidden_output">
1088 <assert_contents>
1089 <has_text_matching expression="sc.tl.rank_genes_groups"/>
1090 <has_text_matching expression="groupby='cell_type'"/>
1091 <has_text_matching expression="use_raw=False"/>
1092 <has_text_matching expression="reference='rest'"/>
1093 <has_text_matching expression="n_genes=100"/>
1094 <has_text_matching expression="method='t-test_overestim_var'"/>
1095 <has_text_matching expression="corr_method='benjamini-hochberg'"/>
1096 <has_text_matching expression="sc.get.rank_genes_groups_df"/>
1097 </assert_contents>
1098 </output>
1099 <output name="anndata_out" ftype="h5ad">
1100 <assert_contents>
1101 <has_h5_keys keys="uns/rank_genes_groups"/>
1102 </assert_contents>
1103 </output>
1104 <output name="ranked_gene" ftype="tabular">
1105 <assert_contents>
1106 <has_line_matching expression="group\tnames\tscores\tlogfoldchanges\tpvals\tpvals_adj"/>
1107 <has_line_matching expression="Ery\tEKLF\t39.086777\t4.8413053\t1.7995717323073084e-66\t1.979528905538039e-65"/>
1108 </assert_contents>
1109 </output>
1110 </test>
1111
1112 <!-- test 17 -->
1113 <test expect_num_outputs="3">
1114 <param name="adata" value="krumsiek11.h5ad"/>
1115 <conditional name="method">
1116 <param name="method" value="tl.rank_genes_groups"/>
1117 <conditional name="get_df">
1118 <param name="get_df_select" value="True"/>
1119 </conditional>
1120 <param name="groupby" value="cell_type"/>
1121 <param name="groups" value="Ery"/>
1122 <conditional name="ref">
1123 <param name="rest" value="group_id"/>
1124 <param name="reference" value="Mk"/>
1125 </conditional>
1126 <param name="n_genes" value="100"/>
1127 <conditional name="tl_rank_genes_groups_method">
1128 <param name="method" value="logreg"/>
1129 <conditional name="solver">
1130 <param name="solver" value="liblinear"/>
1131 <conditional name="penalty">
1132 <param name="penalty" value="l2"/>
1133 <param name="random_state" value="1"/>
1134 </conditional>
1135 </conditional>
1136 </conditional>
1137 </conditional>
1138 <section name="advanced_common">
1139 <param name="show_log" value="true"/>
1140 </section>
1141 <output name="hidden_output">
1142 <assert_contents>
1143 <has_text_matching expression="sc.tl.rank_genes_groups"/>
1144 <has_text_matching expression="groupby='cell_type'"/>
1145 <has_text_matching expression="use_raw=False"/>
1146 <has_text_matching expression="n_genes=100"/>
1147 <has_text_matching expression="method='logreg'"/>
1148 <has_text_matching expression="solver='liblinear'"/>
1149 <has_text_matching expression="penalty='l2'"/>
1150 <has_text_matching expression="dual=False"/>
1151 <has_text_matching expression="fit_intercept=True"/>
1152 <has_text_matching expression="intercept_scaling=1.0"/>
1153 <has_text_matching expression="tol=0.0001"/>
1154 <has_text_matching expression="C=1.0"/>
1155 <has_text_matching expression="groups=\['Ery'\]"/>
1156 <has_text_matching expression="reference='Mk'"/>
1157 <has_text_matching expression="sc.get.rank_genes_groups_df"/>
1158 </assert_contents>
1159 </output>
1160 <output name="anndata_out" ftype="h5ad">
1161 <assert_contents>
1162 <has_h5_keys keys="uns/rank_genes_groups"/>
1163 </assert_contents>
1164 </output>
1165 <output name="ranked_gene" ftype="tabular">
1166 <assert_contents>
1167 <has_text_matching expression="names\tscores"/>
1168 <has_text_matching expression="Fli1\t3.5328505"/>
1169 </assert_contents>
1170 </output>
1171 </test>
1172
1173 <!-- test 18 -->
1174 <test expect_num_outputs="3">
1175 <param name="adata" value="krumsiek11.h5ad"/>
1176 <conditional name="method">
1177 <param name="method" value="tl.rank_genes_groups"/>
1178 <conditional name="get_df">
1179 <param name="get_df_select" value="True"/>
1180 <param name="pval_cutoff" value="0.05"/>
1181 <param name="log2fc_min" value="1"/>
1182 <param name="log2fc_max" value="3"/>
1183 </conditional>
1184 <param name="groupby" value="cell_type"/>
1185 <param name="n_genes" value="100"/>
1186 <conditional name="tl_rank_genes_groups_method">
1187 <param name="method" value="t-test_overestim_var"/>
1188 </conditional>
1189 </conditional>
1190 <section name="advanced_common">
1191 <param name="show_log" value="true"/>
1192 </section>
1193 <output name="hidden_output">
1194 <assert_contents>
1195 <has_text_matching expression="sc.tl.rank_genes_groups"/>
1196 <has_text_matching expression="groupby='cell_type'"/>
1197 <has_text_matching expression="use_raw=False"/>
1198 <has_text_matching expression="reference='rest'"/>
1199 <has_text_matching expression="n_genes=100"/>
1200 <has_text_matching expression="method='t-test_overestim_var'"/>
1201 <has_text_matching expression="corr_method='benjamini-hochberg'"/>
1202 <has_text_matching expression="sc.get.rank_genes_groups_df"/>
1203 <has_text_matching expression="pval_cutoff=0.05"/>
1204 <has_text_matching expression="log2fc_min=1"/>
1205 <has_text_matching expression="log2fc_max=3"/>
1206 </assert_contents>
1207 </output>
1208 <output name="anndata_out" ftype="h5ad">
1209 <assert_contents>
1210 <has_h5_keys keys="uns/rank_genes_groups"/>
1211 </assert_contents>
1212 </output>
1213 <output name="ranked_gene" ftype="tabular">
1214 <assert_contents>
1215 <has_line_matching expression="group\tnames\tscores\tlogfoldchanges\tpvals\tpvals_adj"/>
1216 <has_line_matching expression="Ery\tFog1\t21.071571\t2.8023682\t5.701001345880348e-35\t3.135550740234191e-34"/>
1217 </assert_contents>
1218 </output>
1219 </test>
1031 </tests> 1220 </tests>
1032 <help><![CDATA[ 1221 <help><![CDATA[
1033 Calculate quality control metrics., using `pp.calculate_qc_metrics` 1222 Calculate quality control metrics., using `pp.calculate_qc_metrics`
1034 =================================================================== 1223 ===================================================================
1035 1224