Mercurial > repos > galaxyp > eggnog_mapper

comparison eggnog_macros.xml @ 13:844fa988236b draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/eggnog_mapper/eggnog_mapper commit 468bd31b8858adbba2854f118e4cbe31f4cd68cb
author galaxyp
date Mon, 04 Sep 2023 12:47:09 +0000
parents 9d1fbff733cf
children d9c3016f7283
comparison
equal deleted inserted replaced
12:9d1fbff733cf 13:844fa988236b
1 <?xml version="1.0"?> 1 <?xml version="1.0"?>
2 <macros> 2 <macros>
3 <token name="@TOOL_VERSION@">2.1.8</token> 3 <token name="@TOOL_VERSION@">2.1.8</token>
4 <token name="@VERSION_SUFFIX@">3</token> 4 <token name="@VERSION_SUFFIX@">3</token>
5 <token name="@EGGNOG_DB_VERSION@">5.0.2</token> 5 <token name="@EGGNOG_DB_VERSION@">5.0.2</token>
6 <token name="@PROFILE@">22.01</token>
6 <!-- 7 <!--
7 # DB versionning was super confusing for eggnog-mapper 2.0.x: 8 # DB versionning was super confusing for eggnog-mapper 2.0.x:
8 # eggnog-mapper 1.* needed a db v4.5 (based on eggnog v4.5) 9 # eggnog-mapper 1.* needed a db v4.5 (based on eggnog v4.5)
9 # eggnog-mapper 2.x needed a db v2.0 (based on eggnog v5.0) 10 # eggnog-mapper 2.x needed a db v2.0 (based on eggnog v5.0)
10 # (db v4.5 are not compatible with eggnog-mapper 2.0) 11 # (db v4.5 are not compatible with eggnog-mapper 2.0)
63 </assert_contents> 64 </assert_contents>
64 </output> 65 </output>
65 </test> 66 </test>
66 </xml> 67 </xml>
67 68
69
70 <xml name="stdout_assertion">
71 <assert_stdout>
72 <has_line line="# emapper-@TOOL_VERSION@"/>
73 <has_line line="FINISHED"/>
74 <yield/>
75 </assert_stdout>
76 </xml>
77 <xml name="db_macro">
78 <param name="eggnog_data" type="select" label="Version of eggNOG Database">
79 <options from_data_table="eggnog_mapper_db_versioned">
80 <filter type="static_value" column="3" value="@IDX_VERSION@" />
81 </options>
82 </param>
83 </xml>
84 <token name="@DB_TOKEN@"><![CDATA[
85 --data_dir '$eggnog_data.fields.path'
86 ]]></token>
87
88 <!-- macros and tokens for search -->
89
68 <xml name="fasta_input"> 90 <xml name="fasta_input">
69 <param argument="-i" name="input" type="data" format="fasta" label="Fasta sequences to annotate"/> 91 <param argument="-i" name="input" type="data" format="fasta" label="Fasta sequences to annotate"/>
70 <conditional name="input_trans"> 92 <conditional name="input_trans">
71 <param argument="--itype" type="select" label="Type of sequences"> 93 <param argument="--itype" type="select" label="Type of sequences">
72 <option value="proteins" selected="true">proteins</option> 94 <option value="proteins" selected="true">proteins</option>
103 <param argument="--subject_cover" type="integer" optional="true" min="0" max="100" label="Minimum subject coverage" help="Report only alignments above the given percentage of subject cover" /> 125 <param argument="--subject_cover" type="integer" optional="true" min="0" max="100" label="Minimum subject coverage" help="Report only alignments above the given percentage of subject cover" />
104 <param argument="--pident" type="integer" optional="true" min="0" max="100" label="Minimum query coverage" help="Report only alignments above the given percentage of identity" /> 126 <param argument="--pident" type="integer" optional="true" min="0" max="100" label="Minimum query coverage" help="Report only alignments above the given percentage of identity" />
105 <param argument="--evalue" type="float" optional="true" min="0" label="Minimum query coverage" help="Report only alignments below or equal the e-value" /> 127 <param argument="--evalue" type="float" optional="true" min="0" label="Minimum query coverage" help="Report only alignments below or equal the e-value" />
106 <param argument="--score" type="float" value="0.001" optional="true" min="0" label="Minimum query coverage" help="Report only alignments above or equal the score" /> 128 <param argument="--score" type="float" value="0.001" optional="true" min="0" label="Minimum query coverage" help="Report only alignments above or equal the score" />
107 </xml> 129 </xml>
130
131 <xml name="ortho_macro">
132 <conditional name="ortho_method">
133 <param argument="-m" type="select" label="Basis for annotation">
134 <yield name="search_options"/>
135 <yield name="reuse_options"/>
136 </param>
137 <yield name="search_whens"/>
138 <yield name="reuse_whens"/>
139 </conditional>
140 </xml>
141
142 <xml name="ortho_search_macro">
143 <expand macro="ortho_macro">
144 <token name="search_options">
145 <expand macro="search_options_macro"/>
146 </token>
147 <token name="search_whens">
148 <expand macro="search_whens_macro"/>
149 </token>
150 </expand>
151 </xml>
152
153 <xml name="ortho_annotate_macro">
154 <expand macro="ortho_macro">
155 <token name="reuse_options">
156 <expand macro="reuse_options_macro"/>
157 </token>
158 <token name="reuse_whens">
159 <expand macro="reuse_whens_macro"/>
160 </token>
161 </expand>
162 </xml>
163
164 <xml name="ortho_full_macro">
165 <expand macro="ortho_macro">
166 <token name="search_options">
167 <expand macro="search_options_macro"/>
168 </token>
169 <token name="reuse_options">
170 <expand macro="reuse_options_macro"/>
171 </token>
172 <token name="search_whens">
173 <expand macro="search_whens_macro"/>
174 </token>
175 <token name="reuse_whens">
176 <expand macro="reuse_whens_macro"/>
177 </token>
178 </expand>
179 </xml>
180
181 <xml name="search_options_macro">
182 <option value="diamond">Seed orthologs computed with Diamond (diamond)</option>
183 <option value="mmseqs">Seed orthologs computed with MMseqs2 (mmseqs)</option>
184 </xml>
185
186 <xml name="reuse_options_macro">
187 <option value="no_search">Use existing seed orthologs (no_search)</option>
188 <option value="cache">Use cached annotations (cache). See also --md5</option>
189 </xml>
190
191 <xml name="search_whens_macro">
192 <when value="diamond">
193 <expand macro="fasta_input"/>
194 <conditional name="matrix_gapcosts">
195 <param argument="--matrix" type="select" label="Scoring matrix and gap costs">
196 <option value="BLOSUM90">BLOSUM90</option>
197 <option value="BLOSUM80">BLOSUM80</option>
198 <option value="BLOSUM62" selected="true">BLOSUM62</option>
199 <option value="BLOSUM50">BLOSUM50</option>
200 <option value="BLOSUM45">BLOSUM45</option>
201 <option value="PAM250">PAM250</option>
202 <option value="PAM70">PAM70</option>
203 <option value="PAM30">PAM30</option>
204 </param>
205 <when value="BLOSUM90">
206 <param name="gap_costs" type="select" label="Gap Costs">
207 <option value="--gapopen 9 --gapextend 2">Existence: 9 Extension: 2</option>
208 <option value="--gapopen 8 --gapextend 2">Existence: 8 Extension: 2</option>
209 <option value="--gapopen 7 --gapextend 2">Existence: 7 Extension: 2</option>
210 <option value="--gapopen 6 --gapextend 2">Existence: 6 Extension: 2</option>
211 <option value="--gapopen 11 --gapextend 1">Existence: 11 Extension: 1</option>
212 <option value="--gapopen 10 --gapextend 1" selected="true">Existence: 10 Extension: 1</option>
213 <option value="--gapopen 9 --gapextend 1">Existence: 9 Extension: 1</option>
214 </param>
215 </when>
216 <when value="BLOSUM80">
217 <param name="gap_costs" type="select" label="Gap Costs">
218 <option value="--gapopen 8 --gapextend 2">Existence: 8 Extension: 2</option>
219 <option value="--gapopen 7 --gapextend 2">Existence: 7 Extension: 2</option>
220 <option value="--gapopen 6 --gapextend 2">Existence: 6 Extension: 2</option>
221 <option value="--gapopen 11 --gapextend 1">Existence: 11 Extension: 1</option>
222 <option value="--gapopen 10 --gapextend 1" selected="true">Existence: 10 Extension: 1</option>
223 <option value="--gapopen 9 --gapextend 1">Existence: 9 Extension: 1</option>
224 </param>
225 </when>
226 <when value="BLOSUM62">
227 <param name="gap_costs" type="select" label="Gap Costs">
228 <option value="--gapopen 11 --gapextend 2">Existence: 11 Extension: 2</option>
229 <option value="--gapopen 10 --gapextend 2">Existence: 10 Extension: 2</option>
230 <option value="--gapopen 9 --gapextend 2">Existence: 9 Extension: 2</option>
231 <option value="--gapopen 8 --gapextend 2">Existence: 8 Extension: 2</option>
232 <option value="--gapopen 7 --gapextend 2">Existence: 7 Extension: 2</option>
233 <option value="--gapopen 6 --gapextend 2">Existence: 6 Extension: 2</option>
234 <option value="--gapopen 13 --gapextend 1">Existence: 13 Extension: 1</option>
235 <option value="--gapopen 12 --gapextend 1">Existence: 12 Extension: 1</option>
236 <option value="--gapopen 11 --gapextend 1" selected="true">Existence: 11 Extension: 1</option>
237 <option value="--gapopen 10 --gapextend 1">Existence: 10 Extension: 1</option>
238 <option value="--gapopen 9 --gapextend 1">Existence: 9 Extension: 1</option>
239 </param>
240 </when>
241 <when value="BLOSUM50">
242 <param name="gap_costs" type="select" label="Gap Costs">
243 <option value="--gapopen 13 --gapextend 3">Existence: 13 Extension: 3</option>
244 <option value="--gapopen 12 --gapextend 3">Existence: 12 Extension: 3</option>
245 <option value="--gapopen 11 --gapextend 3">Existence: 11 Extension: 3</option>
246 <option value="--gapopen 10 --gapextend 3">Existence: 10 Extension: 3</option>
247 <option value="--gapopen 9 --gapextend 3">Existence: 9 Extension: 3</option>
248 <option value="--gapopen 16 --gapextend 2">Existence: 16 Extension: 2</option>
249 <option value="--gapopen 15 --gapextend 2">Existence: 15 Extension: 2</option>
250 <option value="--gapopen 14 --gapextend 2">Existence: 14 Extension: 2</option>
251 <option value="--gapopen 13 --gapextend 2" selected="true">Existence: 13 Extension: 2</option>
252 <option value="--gapopen 12 --gapextend 2">Existence: 12 Extension: 2</option>
253 <option value="--gapopen 19 --gapextend 1">Existence: 19 Extension: 1</option>
254 <option value="--gapopen 18 --gapextend 1">Existence: 18 Extension: 1</option>
255 <option value="--gapopen 17 --gapextend 1">Existence: 17 Extension: 1</option>
256 <option value="--gapopen 16 --gapextend 1">Existence: 16 Extension: 1</option>
257 <option value="--gapopen 15 --gapextend 1">Existence: 15 Extension: 1</option>
258 </param>
259 </when>
260 <when value="BLOSUM45">
261 <param name="gap_costs" type="select" label="Gap Costs">
262 <option value="--gapopen 13 --gapextend 3">Existence: 13 Extension: 3</option>
263 <option value="--gapopen 12 --gapextend 3">Existence: 12 Extension: 3</option>
264 <option value="--gapopen 11 --gapextend 3">Existence: 11 Extension: 3</option>
265 <option value="--gapopen 10 --gapextend 3">Existence: 10 Extension: 3</option>
266 <option value="--gapopen 15 --gapextend 2" selected="true">Existence: 15 Extension: 2</option>
267 <option value="--gapopen 14 --gapextend 2">Existence: 14 Extension: 2</option>
268 <option value="--gapopen 13 --gapextend 2">Existence: 13 Extension: 2</option>
269 <option value="--gapopen 12 --gapextend 2">Existence: 12 Extension: 2</option>
270 <option value="--gapopen 19 --gapextend 1">Existence: 19 Extension: 1</option>
271 <option value="--gapopen 18 --gapextend 1">Existence: 18 Extension: 1</option>
272 <option value="--gapopen 17 --gapextend 1">Existence: 17 Extension: 1</option>
273 <option value="--gapopen 16 --gapextend 1">Existence: 16 Extension: 1</option>
274 </param>
275 </when>
276 <when value="PAM250">
277 <param name="gap_costs" type="select" label="Gap Costs">
278 <option value="--gapopen 15 --gapextend 3">Existence: 15 Extension: 3</option>
279 <option value="--gapopen 14 --gapextend 3">Existence: 14 Extension: 3</option>
280 <option value="--gapopen 13 --gapextend 3">Existence: 13 Extension: 3</option>
281 <option value="--gapopen 12 --gapextend 3">Existence: 12 Extension: 3</option>
282 <option value="--gapopen 17 --gapextend 2">Existence: 17 Extension: 2</option>
283 <option value="--gapopen 16 --gapextend 2">Existence: 16 Extension: 2</option>
284 <option value="--gapopen 15 --gapextend 2">Existence: 15 Extension: 2</option>
285 <option value="--gapopen 14 --gapextend 2" selected="true">Existence: 14 Extension: 2</option>
286 <option value="--gapopen 13 --gapextend 2">Existence: 13 Extension: 2</option>
287 <option value="--gapopen 21 --gapextend 1">Existence: 21 Extension: 1</option>
288 <option value="--gapopen 20 --gapextend 1">Existence: 20 Extension: 1</option>
289 <option value="--gapopen 19 --gapextend 1">Existence: 19 Extension: 1</option>
290 <option value="--gapopen 18 --gapextend 1">Existence: 18 Extension: 1</option>
291 <option value="--gapopen 17 --gapextend 1">Existence: 17 Extension: 1</option>
292 </param>
293 </when>
294 <when value="PAM70">
295 <param name="gap_costs" type="select" label="Gap Costs">
296 <option value="--gapopen 12 --gapextend 3">Existence: 12 Extension: 3</option>
297 <option value="--gapopen 11 --gapextend 2">Existence: 11 Extension: 2</option>
298 <option value="--gapopen 8 --gapextend 2">Existence: 8 Extension: 2</option>
299 <option value="--gapopen 7 --gapextend 2">Existence: 7 Extension: 2</option>
300 <option value="--gapopen 6 --gapextend 2">Existence: 6 Extension: 2</option>
301 <option value="--gapopen 11 --gapextend 1">Existence: 11 Extension: 1</option>
302 <option value="--gapopen 10 --gapextend 1" selected="true">Existence: 10 Extension: 1</option>
303 <option value="--gapopen 9 --gapextend 1">Existence: 9 Extension: 1</option>
304 </param>
305 </when>
306 <when value="PAM30">
307 <param name="gap_costs" type="select" label="Gap Costs">
308 <option value="--gapopen 15 --gapextend 3">Existence: 15 Extension: 3</option>
309 <option value="--gapopen 13 --gapextend 3">Existence: 13 Extension: 3</option>
310 <option value="--gapopen 14 --gapextend 2">Existence: 14 Extension: 2</option>
311 <option value="--gapopen 7 --gapextend 2">Existence: 7 Extension: 2</option>
312 <option value="--gapopen 6 --gapextend 2">Existence: 6 Extension: 2</option>
313 <option value="--gapopen 5 --gapextend 2">Existence: 5 Extension: 2</option>
314 <option value="--gapopen 14 --gapextend 1">Existence: 14 Extension: 1</option>
315 <option value="--gapopen 10 --gapextend 1">Existence: 10 Extension: 1</option>
316 <option value="--gapopen 9 --gapextend 1" selected="true">Existence: 9 Extension: 1</option>
317 <option value="--gapopen 8 --gapextend 1">Existence: 8 Extension: 1</option>
318 </param>
319 </when>
320 </conditional>
321 <param argument="--sensmode" type="select" label="Diamond's sensitivity mode">
322 <option value="default">default</option>
323 <option value="fast">fast</option>
324 <option value="mid-sensitive">mid-sensitive</option>
325 <option value="sensitive" selected="true">sensitive</option>
326 <option value="more-sensitive">more-sensitive</option>
327 <option value="very-sensitive">very-sensitive</option>
328 <option value="ultra-sensitive">ultra-sensitive</option>
329 </param>
330 <param argument="--dmnd_iterate" type="boolean" truevalue="--dmnd_iterate yes" falsevalue="--dmnd_iterate no" checked="false"
331 label="Run diamond in iterative mode, up to the sensitivity level"/>
332 <param argument="--dmnd_ignore_warnings" type="boolean" truevalue="--dmnd_ignore_warnings" falsevalue="" checked="false"
333 label="Ignore Diamond warnings on sequence content (e.g. when a protein contains only ATGC symbols)"/>
334 <expand macro="common_search_options"/>
335 </when>
336 <when value="mmseqs">
337 <expand macro="fasta_input"/>
338 <param argument="--start_sens" type="integer" value="3" min="0" max="100" label="Starting sensitivity" />
339 <param argument="--sens_steps" type="integer" value="3" min="0" max="100" label="Number of sensitivity steps" />
340 <param argument="--final_sens" type="integer" value="7" min="0" max="100" label="Final sensititivy step" />
341 <expand macro="common_search_options"/>
342 </when>
343 </xml>
344
345 <xml name="reuse_whens_macro">
346 <when value="no_search">
347 <param argument="--annotate_hits_table" type="data" multiple="true" format="tabular" label="Seed orthologs">
348 <validator type="expression" message="No seed orthologs">value.metadata.columns == 11</validator>
349 <!-- would be cool to replace with this validator:
350 <validator type="expression" message="No seed orthologs">value.metadata.column_names == '@SEED_ORTHOLOG_COLUMNS@'.split()</validator>
351 but this does not work (yet) in tool tests since column_names can not be set in uploads -->
352 </param>
353 </when>
354 <when value="cache">
355 <expand macro="fasta_input"/>
356 <param argument="--cache" type="data" format="tabular" label="EggNOG Annotations with md5 hashes" help="Annotations computed with EggNOG mapper with enabled --md5 option">
357 <validator type="expression" message="No seed orthologs">value.metadata.columns == 22</validator>
358 </param>
359 <param name="output_no_annotations" type="boolean" checked="true" label="Output sequences without annotation" help="Produce an additional FASTA file with the sequences of queries for which an existing annotation was not found using cache mode. This file can be used as input of another eggNOG-mapper run without using the cache, trying to annotate the sequences."/>
360 </when>
361 </xml>
362
363 <token name="@MERGE_ANNOTATIONS@"><![CDATA[
364 #if $ortho_method.m == "no_search"
365 cat
366 #for aht in $ortho_method.annotate_hits_table
367 $aht
368 #end for
369 > annotate_hits_table.tsv
370 &&
371 #end if
372 ]]></token>
373
374 <token name="@ORTHO_SEARCH_TOKEN@"><![CDATA[
375 -m '$ortho_method.m'
376 #if $ortho_method.m in ['diamond', 'mmseqs', 'cache']:
377 -i '$ortho_method.input'
378 --itype '$ortho_method.input_trans.itype'
379 #if $ortho_method.input_trans.itype in ['CDS', 'genome', 'metagenome']:
380 $ortho_method.input_trans.translate
381 #end if
382 #if $ortho_method.input_trans.itype in ['genome', 'metagenome']:
383 --genepred $ortho_method.input_trans.genepred
384 #end if
385 #elif $ortho_method.m == "no_search"
386 --annotate_hits_table annotate_hits_table.tsv
387 #end if
388
389 #if $ortho_method.m == 'cache'
390 --cache '$ortho_method.cache'
391 #end if
392 #if $ortho_method.m == 'no_search'
393 --annotate_hits_table annotate_hits_table.tsv
394 #end if
395
396 #if $ortho_method.m in ['diamond', 'mmseqs']:
397 ## Diamond option
398 #if $ortho_method.m == "diamond":
399 --matrix '$ortho_method.matrix_gapcosts.matrix'
400 $ortho_method.matrix_gapcosts.gap_costs
401 --sensmode $ortho_method.sensmode
402 $ortho_method.dmnd_iterate
403 $ortho_method.dmnd_ignore_warnings
404 #elif $ortho_method.m == "mmseqs":
405 --start_sens $ortho_method.start_sens
406 --sens_steps $ortho_method.sens_steps
407 --final_sens $ortho_method.final_sens
408 #end if
409
410 ## Common options for search filtering (applies to diamond and mmseqs only)
411 #if str($ortho_method.query_cover):
412 --query_cover $ortho_method.query_cover
413 #end if
414 #if str($ortho_method.subject_cover):
415 --subject_cover $ortho_method.subject_cover
416 #end if
417 #if str($ortho_method.pident):
418 --pident $ortho_method.pident
419 #end if
420 #if str($ortho_method.evalue):
421 --evalue $ortho_method.evalue
422 #end if
423 #if str($ortho_method.score):
424 --score $ortho_method.score
425 #end if
426 #end if
427 ]]></token>
428
429 <!-- output options applying to search step -->
430 <xml name="output_options_macro">
431 <section name="output_options" expanded="false" title="Output Options">
432 <param argument="--no_file_comments" type="boolean" truevalue="--no_file_comments" falsevalue="" checked="true"
433 label="Exclude header lines and stats from output files"/>
434 <yield/>
435 </section>
436 </xml>
437 <!-- output options applying search and annotate step -->
438 <xml name="output_options_annotate_macro">
439 <expand macro="output_options_macro">
440 <param argument="--report_orthologs" type="boolean" truevalue="--report_orthologs" falsevalue="" checked="false" label="Output a file with the list of orthologs for each hit"/>
441 <param argument="--md5" type="boolean" truevalue="--md5" falsevalue="" checked="false" label="Add md5 hash of each query to annotations"/>
442 </expand>
443 </xml>
444
108 <token name="@SEED_ORTHOLOG_COLUMNS@">query_name,seed_eggNOG_ortholog,seed_ortholog_evalue,seed_ortholog_score,query_start,query_end,seed_start,seed_end,pident,query_cov,seed_cov</token> 445 <token name="@SEED_ORTHOLOG_COLUMNS@">query_name,seed_eggNOG_ortholog,seed_ortholog_evalue,seed_ortholog_score,query_start,query_end,seed_start,seed_end,pident,query_cov,seed_cov</token>
109 446
110 <xml name="stdout_assertion"> 447 <xml name="ortho_search_output_macro">
111 <assert_stdout> 448 <data name="seed_orthologs" format="tabular" label="${tool.name} on ${on_string}: seed_orthologs" from_work_dir="results.emapper.seed_orthologs">
112 <has_line line="# emapper-@TOOL_VERSION@"/> 449 <filter>ortho_method['m'] not in ['no_search', 'cache']</filter>
113 <has_line line="FINISHED"/> 450 <actions>
114 <yield/> 451 <action name="column_names" type="metadata" default="@SEED_ORTHOLOG_COLUMNS@"/>
115 </assert_stdout> 452 </actions>
116 </xml> 453 </data>
117 <xml name="seed_orthologs_assertion"> 454 </xml>
455
456 <xml name="seed_orthologs_assertion" token_nocomments="true">
118 <output name="seed_orthologs" ftype="tabular"> 457 <output name="seed_orthologs" ftype="tabular">
119 <assert_contents> 458 <assert_contents>
120 <has_line line="#qseqid&#009;sseqid&#009;evalue&#009;bitscore&#009;qstart&#009;qend&#009;sstart&#009;send&#009;pident&#009;qcov&#009;scov"/> 459 <has_line line="#qseqid&#009;sseqid&#009;evalue&#009;bitscore&#009;qstart&#009;qend&#009;sstart&#009;send&#009;pident&#009;qcov&#009;scov"/>
121 <has_line_matching expression="(\S+\t){2}[-+.e\d]+\t[.\d]+(\t\d+){4}(\t[.\d]+){3}" n="1"/> 460 <has_line_matching expression="(\S+\t){2}[-+.e\d]+\t[.\d]+(\t\d+){4}(\t[.\d]+){3}" n="1"/>
461 <has_line_matching expression="##.*" negate="@NOCOMMENTS@"/>
122 </assert_contents> 462 </assert_contents>
123 </output> 463 </output>
124 </xml> 464 </xml>
125 <xml name="annotations_assertion" token_columns="21" token_add_metadata_columm_names="" token_add_column_names="" token_add_column_re=""> 465
466 <token name="@HELP_SEARCH_OUTPUTS@"><![CDATA[
467 **seed orthologs**
468
469 each line in the file provides the best match of each query within the best Orthologous Group (OG)
470 reported in the [project].hmm_hits file, obtained running PHMMER against all sequences within the best OG.
471 The seed ortholog is used to fetch fine-grained orthology relationships from eggNOG.
472 If using the diamond search mode, seed orthologs are directly
473 obtained from the best matching sequences by running DIAMOND against the whole eggNOG protein space.
474 ]]></token>
475
476 <!-- macros and tokens for annotate -->
477
478 <xml name="annotation_options_macro">
479 <param argument="--seed_ortholog_evalue" type="float" value="0.001" min="0" label="Min E-value threshold">
480 <help>
481 Min E-value expected when searching for seed eggNOG ortholog. Applies to phmmer/diamond searches.
482 Queries not having a significant seed orthologs (E-value less than threshold) will not be annotated.
483 </help>
484 </param>
485 <param argument="--seed_ortholog_score" type="float" optional="true" min="0" label="Minimum bit score threshold">
486 <help>
487 Min bit score expected when searching for seed eggNOG ortholog.
488 Queries not having a significant seed orthologs will not be annotated.
489 </help>
490 </param>
491 <param argument="--tax_scope" type="integer" optional="true" label="Set taxonomic scope" help="NCBI taxonomy id" />
492 <param argument="--target_orthologs" type="select" label="target orthologs for functional transfer">
493 <option value="one2one">one2one</option>
494 <option value="many2one">many2one</option>
495 <option value="one2many">one2many</option>
496 <option value="many2many">many2many</option>
497 <option value="all" selected="true">all</option>
498 </param>
499 <param argument="--go_evidence" type="select"
500 label="Select the set of GO terms that should be used for annotation">
501 <option value="experimental">experimental = Use only terms inferred from experimental evidence</option>
502 <option value="non-electronic" selected="true">non-electronic = Use only non-electronically curated terms</option>
503 <option value="all" selected="true">All (experimental + non-electronic)</option>
504 </param>
505 </xml>
506 <token name="@ANNOTATION_TOKEN@"><![CDATA[
507 #if str($annotation_options.seed_ortholog_evalue):
508 --seed_ortholog_evalue $annotation_options.seed_ortholog_evalue
509 #end if
510 #if str($annotation_options.seed_ortholog_score):
511 --seed_ortholog_score $annotation_options.seed_ortholog_score
512 #end if
513 #if $annotation_options.tax_scope:
514 --tax_scope=$annotation_options.tax_scope
515 #end if
516 #if $annotation_options.target_orthologs:
517 --target_orthologs=$annotation_options.target_orthologs
518 #end if
519 #if $annotation_options.go_evidence:
520 --go_evidence=$annotation_options.go_evidence
521 #end if
522 \$EGGNOG_DBMEM
523 ]]></token>
524 <xml name="annotation_output_macro">
525 <data name="annotations" format="tabular" label="${tool.name} on ${on_string}: annotations" from_work_dir="results.emapper.annotations">
526 <yield/>
527 <actions>
528 <conditional name="output_options.md5">
529 <when value="True">
530 <action name="column_names" type="metadata" default="query,seed_ortholog,evalue,score,max_annot_lvl,COG_category,Description,Preferred_name,GOs,EC,KEGG_ko,KEGG_Pathway,KEGG_Module,KEGG_Reaction,KEGG_rclass,BRITE,KEGG_TC,CAZy,BiGG_Reaction,PFAMseggNOG_OGs,md5"/>
531 </when>
532 <when value="False">
533 <action name="column_names" type="metadata" default="query,seed_ortholog,evalue,score,max_annot_lvl,COG_category,Description,Preferred_name,GOs,EC,KEGG_ko,KEGG_Pathway,KEGG_Module,KEGG_Reaction,KEGG_rclass,BRITE,KEGG_TC,CAZy,BiGG_Reaction,PFAMseggNOG_OGs"/>
534 </when>
535 </conditional>
536 </actions>
537 </data>
538 <data name="no_annotations" format="fasta" label="${tool.name} on ${on_string}: sequences without annotation" from_work_dir="results.emapper.no_annotations.fasta">
539 <filter>ortho_method['m'] == 'cache' and ortho_method['output_no_annotations']</filter>
540 </data>
541 </xml>
542
543 <xml name="annotation_orthologs_output_macro">
544 <data name="annotations_orthologs" format="tabular" label="${tool.name} on ${on_string}: orthologs" from_work_dir="results.emapper.orthologs">
545 <filter>ortho_method['m'] != 'cache'</filter>
546 <filter>output_options['report_orthologs']</filter>
547 <actions>
548 <action name="column_names" type="metadata" default="query,orth_type,species,orthologs"/>
549 </actions>
550 </data>
551 </xml>
552
553 <xml name="annotations_assertion" token_columns="21" token_add_metadata_columm_names="" token_add_column_names="" token_add_column_re="" token_nocomments="true">
126 <output name="annotations" ftype="tabular"> 554 <output name="annotations" ftype="tabular">
127 <metadata name="columns" value="@COLUMNS@" /> 555 <metadata name="columns" value="@COLUMNS@" />
128 <!-- <metadata name="column_names" value="query,seed_ortholog,evalue,score,max_annot_lvl,COG_category,Description,Preferred_name,GOs,EC,KEGG_ko,KEGG_Pathway,KEGG_Module,KEGG_Reaction,KEGG_rclass,BRITE,KEGG_TC,CAZy,BiGG_Reaction,PFAMseggNOG_OGs@ADD_METADATA_COLUMN_NAMES@" /> --> 556 <!-- <metadata name="column_names" value="query,seed_ortholog,evalue,score,max_annot_lvl,COG_category,Description,Preferred_name,GOs,EC,KEGG_ko,KEGG_Pathway,KEGG_Module,KEGG_Reaction,KEGG_rclass,BRITE,KEGG_TC,CAZy,BiGG_Reaction,PFAMseggNOG_OGs@ADD_METADATA_COLUMN_NAMES@" /> -->
129 <assert_contents> 557 <assert_contents>
130 <has_line line="#query&#009;seed_ortholog&#009;evalue&#009;score&#009;eggNOG_OGs&#009;max_annot_lvl&#009;COG_category&#009;Description&#009;Preferred_name&#009;GOs&#009;EC&#009;KEGG_ko&#009;KEGG_Pathway&#009;KEGG_Module&#009;KEGG_Reaction&#009;KEGG_rclass&#009;BRITE&#009;KEGG_TC&#009;CAZy&#009;BiGG_Reaction&#009;PFAMs@ADD_COLUMN_NAMES@"/> 558 <has_line line="#query&#009;seed_ortholog&#009;evalue&#009;score&#009;eggNOG_OGs&#009;max_annot_lvl&#009;COG_category&#009;Description&#009;Preferred_name&#009;GOs&#009;EC&#009;KEGG_ko&#009;KEGG_Pathway&#009;KEGG_Module&#009;KEGG_Reaction&#009;KEGG_rclass&#009;BRITE&#009;KEGG_TC&#009;CAZy&#009;BiGG_Reaction&#009;PFAMs@ADD_COLUMN_NAMES@"/>
131 <has_line_matching expression="(\S+\t){2}[-+.e\d]+\t[.\d]+(\t\S+){7}\tko:\S+(\t\S+){9}@ADD_COLUMN_RE@" n="1"/> 559 <has_line_matching expression="(\S+\t){2}[-+.e\d]+\t[.\d]+(\t\S+){7}\tko:\S+(\t\S+){9}@ADD_COLUMN_RE@" n="1"/>
560 <has_line_matching expression="##.*" negate="@NOCOMMENTS@"/>
132 </assert_contents> 561 </assert_contents>
133 </output> 562 </output>
134 </xml> 563 </xml>
135 <xml name="annotations_orthologs_assertion"> 564 <xml name="annotations_orthologs_assertion" token_nocomments="true">
136 <output name="annotations_orthologs" ftype="tabular"> 565 <output name="annotations_orthologs" ftype="tabular">
137 <metadata name="columns" value="4" /> 566 <metadata name="columns" value="4" />
138 <metadata name="column_names" value="query,orth_type,species,orthologs" /> 567 <metadata name="column_names" value="query,orth_type,species,orthologs" />
139 <assert_contents> 568 <assert_contents>
140 <has_line line="#query&#009;orth_type&#009;species&#009;orthologs"/> 569 <has_line line="#query&#009;orth_type&#009;species&#009;orthologs"/>
141 <has_line_matching expression="\S+\t(one2one|many2one|one2many|many2many|seed)(\t[^\t]+){2}" n="2"/> 570 <has_line_matching expression="\S+\t(one2one|many2one|one2many|many2many|seed)(\t[^\t]+){2}" n="2"/>
571 <has_line_matching expression="##.*" negate="@NOCOMMENTS@"/>
142 </assert_contents> 572 </assert_contents>
143 </output> 573 </output>
144 </xml> 574 </xml>
575 <token name="@HELP_ANNOTATION_OUTPUTS@"><![CDATA[
576 **annotations**
577
578 This file provides final annotations of each query. Tab-delimited columns in the file are:
579
580 - ``query_name``: query sequence name
581 - ``seed_eggNOG_ortholog``: best protein match in eggNOG
582 - ``seed_ortholog_evalue``: best protein match (e-value)
583 - ``seed_ortholog_score``: best protein match (bit-score)
584 - ``predicted_taxonomic_group``
585 - ``predicted_protein_name``: Predicted protein name for query sequences
586 - ``GO_terms``: Comma delimited list of predicted Gene Ontology terms
587 - ``EC_number``
588 - ``KEGG_KO``
589 - ``KEGG_Pathway``: Comma delimited list of predicted KEGG pathways
590 - ``KEGG_Module``
591 - ``KEGG_Reaction``
592 - ``KEGG_rclass``
593 - ``BRITE``
594 - ``KEGG_TC``
595 - ``CAZy``
596 - ``BiGG_Reactions``
597 - ``Annotation_tax_scope``: The taxonomic scope used to annotate this query sequence
598 - ``Matching_OGs``: Comma delimited list of matching eggNOG Orthologous Groups
599 - ``best_OG|evalue|score``: Best matching Orthologous Groups (deprecated, use smallest from eggnog OGs)
600 - ``COG_functional_categories``: COG functional category inferred from best matching OG
601 - ``eggNOG_free_text_description``
602
603 **orthologs**
604
605 This output is only created if the option ``--report_orthologs`` is checked.
606 It provides the orthologs used for the annotation. It's a tab delimited file with the following columns:
607
608 - ``query``
609 - ``orth_type`` Type of orthologs in this row. See --target_orthologs.
610 - ``species``
611 - ``orthologs`` comma-separated list of orthologs (If an ortholog shows a "*", such ortholog was used to transfer its annotations to the query.)
612
613 **sequences without annotation **
614
615 This output is created if cached annotations are used as input.
616 It is a FASTA file containing all sequences that are not found in the cached annotations.
617 These sequences can then be used as input for another run of the EggNOG mapper
618 computing seed orthologs with diamond, etc.
619 ]]></token>
145 </macros> 620 </macros>