Mercurial > repos > iuc > funannotate_predict
comparison funannotate_predict.xml @ 0:40b87aef5241 draft
"planemo upload commit 9613152729099079c7465c3d5d42005ef22ca91e"
author | iuc |
---|---|
date | Thu, 26 Aug 2021 06:55:33 +0000 |
parents | |
children | 1a59958c1f76 |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:40b87aef5241 |
---|---|
1 <tool id="funannotate_predict" name="Funannotate predict annotation" profile="20.01" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@"> | |
2 <description></description> | |
3 <macros> | |
4 <import>macros.xml</import> | |
5 </macros> | |
6 <requirements> | |
7 <expand macro="requirements" /> | |
8 </requirements> | |
9 <version_command><![CDATA[funannotate check --show-versions]]></version_command> | |
10 <command><![CDATA[ | |
11 #if $genemark.genemark_license: | |
12 if [ -z "\$GENEMARK_PATH" ] ; then echo "GeneMark is not installed on this Galaxy server." >&2 ; exit 1 ; fi && | |
13 if [ ! -f "\$GENEMARK_PATH/gmes_petap.pl" ] ; then echo "GeneMark is not installed properly on this Galaxy server." >&2 ; exit 1 ; fi && | |
14 ## GeneMark only search for license in ~/.gm_key | |
15 cp '${genemark.genemark_license}' ~/.gm_key && | |
16 #end if | |
17 | |
18 #if $uglyTestingHack == "true": | |
19 ## funannotate_db contains some hard coded path, need to rewrite one for tests (not in real life when using data manager) | |
20 ## Need to copy too as the test_data is read only on CI | |
21 cp -r '${database.fields.path}' './hacked_database' && | |
22 sed -i.bak 's|/tmp/prout|'`pwd`'/hacked_database|' './hacked_database/trained_species/fly/info.json' && | |
23 #end if | |
24 | |
25 funannotate predict | |
26 --input '${input}' | |
27 --out output | |
28 | |
29 #if $uglyTestingHack == "true": | |
30 --database `pwd`'/hacked_database' | |
31 #else | |
32 --database '$database.fields.path' | |
33 #end if | |
34 | |
35 --species '${organism.species}' | |
36 --isolate '${organism.isolate}' | |
37 --strain '${organism.strain}' | |
38 --organism '${organism.organism}' | |
39 --ploidy ${organism.ploidy} | |
40 --SeqCenter '${organism.SeqCenter}' | |
41 --SeqAccession '${organism.SeqAccession}' | |
42 --name '${organism.name}' | |
43 --numbering ${organism.numbering} | |
44 | |
45 #if $parameters: | |
46 --parameters '${parameters}' | |
47 #end if | |
48 | |
49 #if $evidences.rna_bam: | |
50 --rna_bam ${evidences.rna_bam} | |
51 #end if | |
52 | |
53 #set est_list = "" | |
54 #if len($evidences.transcript_evidence) > 0: | |
55 #for $estev in $evidences.transcript_evidence: | |
56 #if $estev: | |
57 #set est_list += " '" + str($estev) + "'" | |
58 #end if | |
59 #end for | |
60 #end if | |
61 #if $est_list: | |
62 --transcript_evidence $est_list | |
63 #end if | |
64 | |
65 #if $evidences.prot_evidence == 'custom': | |
66 --protein_evidence | |
67 #for $protev in $evidences.protein_evidence: | |
68 '${protev}' | |
69 #end for | |
70 #end if | |
71 --p2g_pident ${evidences.p2g_pident} | |
72 --p2g_prefilter ${evidences.p2g_prefilter} | |
73 | |
74 #if $augustus.augustus_species != 'none': | |
75 --augustus_species '${augustus.augustus_species}' | |
76 #end if | |
77 --min_training_models ${augustus.min_training_models} | |
78 ${augustus.optimize_augustus} | |
79 | |
80 #if $genemark.genemark_license: | |
81 --genemark_mode '${genemark.genemark_mode}' | |
82 #if $genemark.genemark_mod: | |
83 --genemark_mod '${genemark.genemark_mod}' | |
84 #end if | |
85 --soft_mask ${genemark.soft_mask} | |
86 #end if | |
87 | |
88 --busco_seed_species '${busco.busco_seed_species}' | |
89 --busco_db '${busco.busco_db}' | |
90 | |
91 $evm.repeats2evm | |
92 #if $evm.evm_partitioning.evm_partition == "yes": | |
93 --evm-partition-interval ${evm.evm_partitioning.evm_partition_interval} | |
94 #else: | |
95 --no-evm-partitions | |
96 #end if | |
97 #if $evm.weights: | |
98 --weights '${evm.weights}' | |
99 #end if | |
100 | |
101 #if $other_predictors.stringtie: | |
102 --stringtie '${other_predictors.stringtie}' | |
103 #end if | |
104 #if $other_predictors.maker_gff: | |
105 --maker_gff '${other_predictors.maker_gff}' | |
106 #end if | |
107 #if $other_predictors.pasa_gff: | |
108 --pasa_gff '${other_predictors.pasa_gff}:${other_predictors.pasa_gff_weight}' | |
109 #end if | |
110 #if $other_predictors.other_gff: | |
111 --other_gff '${other_predictors.other_gff}:${other_predictors.other_gff_weight}' | |
112 #end if | |
113 | |
114 --min_intronlen ${filtering.min_intronlen} | |
115 --max_intronlen ${filtering.max_intronlen} | |
116 --min_protlen ${filtering.min_protlen} | |
117 ${filtering.keep_no_stops} | |
118 --repeat_filter ${filtering.repeat_filter} | |
119 | |
120 --cpus \${GALAXY_SLOTS:-2} | |
121 | |
122 && | |
123 | |
124 mv output/predict_results/*.gbk out.gbk && | |
125 mv output/predict_results/*.tbl out.tbl && | |
126 mv output/predict_results/*.gff3 out.gff3 && | |
127 mv output/predict_results/*.proteins.fa out.proteins.fa && | |
128 mv output/predict_results/*.mrna-transcripts.fa out.mrna-transcripts.fa && | |
129 mv output/predict_results/*.cds-transcripts.fa out.cds-transcripts.fa && | |
130 mv output/predict_results/*.discrepency.report.txt out.discrepency.report.txt && | |
131 mv output/predict_results/*.error.summary.txt out.error.summary.txt && | |
132 mv output/predict_results/*.validation.txt out.validation.txt && | |
133 mv output/predict_results/*.stats.json out.stats.json | |
134 ]]></command> | |
135 <inputs> | |
136 <param argument="--input" type="data" format="fasta" label="Assembly to annotate" help="The assembly should be soft-masked (with RepeatMasker for example)" /> | |
137 | |
138 <param name="database" label="Funannotate database" type="select"> | |
139 <options from_data_table="funannotate"> | |
140 <column name="value" index="0" /> | |
141 <column name="name" index="1" /> | |
142 <column name="path" index="3" /> | |
143 <filter type="sort_by" column="0" /> | |
144 <filter type="static_value" column="2" value="1.0" /> | |
145 </options> | |
146 </param> | |
147 | |
148 <section name="organism" expanded="true" title="Organism"> | |
149 <param argument="--species" type="text" optional="false" label="Name of the species to annotate" help="e.g. Genus species"> | |
150 <validator type="empty_field" /> | |
151 </param> | |
152 <param argument="--isolate" type="text" label="Isolate name" help="If relevant (e.g. Af293)" /> | |
153 <param argument="--strain" type="text" label="Strain name" help="If relevant (e.g. FGSCA4)" /> | |
154 <param argument="--organism" type="boolean" checked="false" truevalue="fungus" falsevalue="other" label="Is it a fungus species?" /> | |
155 <param argument="--ploidy" type="integer" value="1" label="Ploidy of assembly" /> | |
156 <param argument="--SeqCenter" type="text" value="CFMR" label="Sequencing facility for NCBI tbl file" /> | |
157 <param argument="--SeqAccession" type="text" value="12345" label="Sequence accession number for NCBI tbl file" /> | |
158 <param argument="--name" type="text" value="FUN_" label="Locus tag prefix" help="Will prefix all the gene names" /> | |
159 <param argument="--numbering" type="integer" value="1" label="Specify where gene numbering starts" /> | |
160 </section> | |
161 | |
162 <section name="evidences" expanded="true" title="Evidences"> | |
163 <param argument="--rna_bam" type="data" format="bam" optional="true" label="RNA-seq mapped to genome to train Augustus/GeneMark-ET" /> | |
164 <param argument="--transcript_evidence" type="data" format="fasta" multiple="true" optional="true" label="mRNA/ESTs to align to genome" /> | |
165 <conditional name="prot_evidence"> | |
166 <param name="prot_evidence_source" type="select" label="Select protein evidences"> | |
167 <option value="uniprot" selected="True">Use UniProtKb/SwissProt (from selected Funannotate database)</option> | |
168 <option value="custom">Custom protein sequences</option> | |
169 </param> | |
170 <when value="uniprot"/> | |
171 <when value="custom"> | |
172 <param argument="--protein_evidence" type="data" format="fasta" multiple="true" label="Proteins to map to genome" /> | |
173 </when> | |
174 </conditional> | |
175 <param argument="--p2g_pident" type="integer" value="80" label="Exonerate percent identity (for proteins)" /> | |
176 <param argument="--p2g_prefilter" type="select" label="Prefilter hists with (for proteins)"> | |
177 <option value="diamond" selected="True">Diamond</option> | |
178 <option value="tblastn">tblastn (slower)</option> | |
179 </param> | |
180 </section> | |
181 | |
182 <param argument="--parameters" type="data" format="json" optional="true" label="Ab-initio training parameters from a previous run" help="If specified, will over-rule any other training presets based on sepcies selection." /> | |
183 | |
184 <section name="other_predictors" expanded="false" title="Other annotations"> | |
185 <param argument="--stringtie" type="data" format="gtf" optional="true" label="StringTie GTF result" /> | |
186 <param argument="--maker_gff" type="data" format="gff3" optional="true" label="MAKER2 GFF file" help="Parse results directly to EVM" /> | |
187 <param argument="--pasa_gff" type="data" format="gff3" optional="true" label="PASA generated gene models" /> | |
188 <param name="pasa_gff_weight" type="integer" value="1" label="Weight for PASA generated gene models" /> | |
189 <param argument="--other_gff" type="data" format="gff3" optional="true" label="Annotation pass-through to EVM" /> | |
190 <param name="other_gff_weight" type="integer" value="1" label="Weight for annotation pass-through to EVM" /> | |
191 </section> | |
192 | |
193 <section name="augustus" expanded="true" title="Augustus settings"> | |
194 <param argument="--augustus_species" type="select" label="Augustus species training set" help="Select a species from the list"> | |
195 <option value="none" selected="True">No corresponding species, train from scratch</option> | |
196 <expand macro="augustus_species"/> | |
197 </param> | |
198 <param argument="--min_training_models" type="integer" value="200" label="Minimum number of models to train Augustus" /> | |
199 <param argument="--optimize_augustus" type="boolean" checked="false" truevalue="--optimize_augustus" falsevalue="" label="Run 'optimize_augustus.pl' to refine training (long runtime)" /> | |
200 </section> | |
201 | |
202 <section name="genemark" expanded="false" title="GeneMark settings"> | |
203 <param name="genemark_license" type="data" format="txt" optional="true" label="GeneMark license file" help="GeneMark is not a free software, to use it download and unzip a license from http://topaz.gatech.edu/GeneMark/license_download.cgi (ES/ET/EP version). GeneMark needs to be installed manually by Galaxy administrators, it might not be available on this server." /> | |
204 <param argument="--genemark_mode" type="select" label="GeneMark mode"> | |
205 <option value="ES" selected="True">ES</option> | |
206 <option value="ET">ET</option> | |
207 </param> | |
208 <param argument="--genemark_mod" type="data" format="txt" optional="true" label="Use pre-existing Genemark training file (e.g. gmhmm.mod)" /> | |
209 <param argument="--soft_mask" type="integer" value="2000" label="Softmasked length threshold for GeneMark" help="GeneMark will skip prediction on repeat regions shorter than this value" /> | |
210 </section> | |
211 | |
212 <section name="busco" expanded="true" title="BUSCO settings"> | |
213 <param argument="--busco_seed_species" type="select" label="Initial Augustus species training set for BUSCO alignment" help="Select the closest species. BUSCO will only be used if no RNASeq (bam) data is given as evidence."> | |
214 <expand macro="augustus_species"/> | |
215 </param> | |
216 <param argument="--busco_db" type="select" label="BUSCO models to align" help="BUSCO will only be used if no RNASeq (bam) data is given as evidence."> | |
217 <expand macro="busco_species"/> | |
218 </param> | |
219 </section> | |
220 | |
221 <section name="evm" expanded="false" title="EVM settings"> | |
222 <param argument="--repeats2evm" type="boolean" checked="false" truevalue="--repeats2evm" falsevalue="" label="Use repeats in EVM consensus model building" help="Not recommended for fungal genomes that have high gene density. You might want to turn this option on for larger genomes or those that have a high repeat content." /> | |
223 <conditional name="evm_partitioning"> | |
224 <param name="evm_partition" type="select" label="Split contigs into partitions for EVM processing?" help="Splits big contigs in smaller overlaping chunks to reduce memory usage and parallelize"> | |
225 <option value="yes" selected="True">Yes</option> | |
226 <option value="no">No</option> | |
227 </param> | |
228 <when value="yes"> | |
229 <param argument="--evm-partition-interval" type="integer" value="1500" label="Min length between genes to make a partition" /> | |
230 </when> | |
231 <when value="no"/> | |
232 </conditional> | |
233 <param argument="--weights" type="text" optional="true" label="Custom ab-initio predictor and EVM weight" help="e.g. augustus:2 pasa:10"> | |
234 <validator type="regex" message="Key must consist of alphanumeric characters only, possibly separated by the period character ('.')">^[\w: ]+$</validator> | |
235 </param> | |
236 </section> | |
237 | |
238 <section name="filtering" expanded="true" title="Filtering"> | |
239 <param argument="--min_intronlen" type="integer" value="10" label="Minimum intron length" /> | |
240 <param argument="--max_intronlen" type="integer" value="3000" label="Maximum intron length" /> | |
241 <param argument="--min_protlen" type="integer" value="50" label="Minimum protein length" /> | |
242 <param argument="--keep_no_stops" type="boolean" checked="false" truevalue="--keep_no_stops" falsevalue="" label="Keep gene models without valid stops" /> | |
243 <param argument="--repeat_filter" type="select" label="Repetitive gene model filtering" help="'overlap' drops gene models that are more than 90% contained within a repeat region; 'blast' compares the amino acid sequences to a small database of known transposons"> | |
244 <option value="overlap blast" selected="True">overlap + blast</option> | |
245 <option value="overlap">overlap</option> | |
246 <option value="blast">blast</option> | |
247 <option value="none">none</option> | |
248 </param> | |
249 </section> | |
250 | |
251 <!-- Need this to change path in the test funannotate_db --> | |
252 <param type="hidden" name="uglyTestingHack" value="" /> | |
253 </inputs> | |
254 <outputs> | |
255 <data name='annot_gbk' format='genbank' label="${tool.name} on ${on_string}: annotation (genbank)" from_work_dir="out.gbk" /> | |
256 <data name='annot_tbl' format='txt' label="${tool.name} on ${on_string}: NCBI tbl annotation file" from_work_dir="out.tbl" /> | |
257 <data name='annot_gff3' format='gff3' label="${tool.name} on ${on_string}: annotation (GFF3)" from_work_dir="out.gff3" /> | |
258 <data name='fasta_proteins' format='fasta' label="${tool.name} on ${on_string}: protein sequences" from_work_dir="out.proteins.fa" /> | |
259 <data name='fasta_transcripts_mrna' format='fasta' label="${tool.name} on ${on_string}: transcript mRNA sequences" from_work_dir="out.mrna-transcripts.fa" /> | |
260 <data name='fasta_transcripts_cds' format='fasta' label="${tool.name} on ${on_string}: transcript CDS sequences" from_work_dir="out.cds-transcripts.fa" /> | |
261 <data name='tbl2asn_report' format='txt' label="${tool.name} on ${on_string}: tbl2asn summary report of annotated genome" from_work_dir="out.discrepency.report.txt" /> | |
262 <data name='tbl2asn_error' format='txt' label="${tool.name} on ${on_string}: tbl2asn error summary report" from_work_dir="out.error.summary.txt" /> | |
263 <data name='tbl2asn_validation' format='txt' label="${tool.name} on ${on_string}: tbl2asn genome validation report" from_work_dir="out.validation.txt" /> | |
264 <data name='stats' format='json' label="${tool.name} on ${on_string}: stats" from_work_dir="out.stats.json" /> | |
265 <!-- TODO some day: provide trained models as output, reusable as input to other funannotate runs | |
266 (parameters.json file references files with absolute paths, would probably need to create an archive + edit paths in parameters.json) --> | |
267 <!--data name='abinitio' format='json' label="${tool.name} on ${on_string}: ab-initio training parameters" from_work_dir="output/predict_results/*.parameters.json" /--> | |
268 </outputs> | |
269 <tests> | |
270 <!-- training from scratch --> | |
271 <test> | |
272 <param name="input" value="genome_masked.fa" /> | |
273 <param name="database" value="2021-07-20-120000" /> | |
274 <section name="organism"> | |
275 <param name="species" value="Genus species" /> | |
276 </section> | |
277 <section name="augustus"> | |
278 <param name="min_training_models" value="3" /> | |
279 </section> | |
280 <section name="busco"> | |
281 <param name="busco_seed_species" value="fly" /> | |
282 <param name="busco_db" value="insecta" /> | |
283 </section> | |
284 <!-- non deterministic results, so can't be more precise here --> | |
285 <output name="annot_gbk"> | |
286 <assert_contents> | |
287 <has_text text=" TITLE Direct Submission" /> | |
288 <has_text text="/locus_tag="FUN_000001"" /> | |
289 </assert_contents> | |
290 </output> | |
291 <output name="annot_tbl"> | |
292 <assert_contents> | |
293 <has_text text=">Feature sample" /> | |
294 <has_text text="gnl|ncbi|FUN_000001-T1_mrna" /> | |
295 </assert_contents> | |
296 </output> | |
297 <output name="annot_gff3"> | |
298 <assert_contents> | |
299 <has_text text="##gff-version 3" /> | |
300 <has_text text="ID=FUN_000001-T1;Parent=FUN_000001;product=hypothetical protein;" /> | |
301 </assert_contents> | |
302 </output> | |
303 <output name="fasta_proteins"> | |
304 <assert_contents> | |
305 <has_text text=">FUN_000001-T1 FUN_000001" /> | |
306 </assert_contents> | |
307 </output> | |
308 <output name="fasta_transcripts_mrna"> | |
309 <assert_contents> | |
310 <has_text text=">FUN_000001-T1 FUN_000001" /> | |
311 </assert_contents> | |
312 </output> | |
313 <output name="fasta_transcripts_cds"> | |
314 <assert_contents> | |
315 <has_text text=">FUN_000001-T1 FUN_000001" /> | |
316 </assert_contents> | |
317 </output> | |
318 <!--output name="abinitio" file="predict_scratch/fly.parameters.json" compare="sim_size" /--> | |
319 <output name="tbl2asn_report" file="predict_scratch/Genus_species.discrepency.report.txt" compare="sim_size" /> | |
320 <output name="tbl2asn_error" file="predict_scratch/Genus_species.error.summary.txt" compare="sim_size" delta="500" /> | |
321 <output name="tbl2asn_validation" file="predict_scratch/Genus_species.validation.txt" compare="sim_size" delta="500" /> | |
322 <output name="stats" file="predict_scratch/Genus_species.stats.json" compare="sim_size" /> | |
323 <assert_stderr> | |
324 <has_text text="augustus busco"/> | |
325 <has_text text="glimmerhmm busco"/> | |
326 <has_text text="snap busco"/> | |
327 <has_text text="Running BUSCO to find conserved gene models for training ab-initio predictors"/> | |
328 <has_text text="Skipping CodingQuarry as no --rna_bam passed"/> | |
329 <has_text text="Running Augustus gene prediction using genus_species parameters"/> | |
330 <not_has_text text="Aligning transcript evidence to genome with minimap2"/> | |
331 <not_has_text text="Found 16 alignments, wrote GFF3 and Augustus hints to file"/> | |
332 <not_has_text text="Extracting hints from RNA-seq BAM file using bam2hints"/> | |
333 <has_text text="Mapping 13 proteins to genome using diamond and exonerate"/> | |
334 <has_text text="Found 4 preliminary alignments --> aligning with exonerate"/> | |
335 </assert_stderr> | |
336 </test> | |
337 | |
338 <!-- pre-trained augustus --> | |
339 <test> | |
340 <param name="input" value="genome_masked.fa" /> | |
341 <param name="database" value="2021-07-20-120000" /> | |
342 <section name="organism"> | |
343 <param name="species" value="Genus species" /> | |
344 </section> | |
345 <section name="augustus"> | |
346 <param name="augustus_species" value="fly" /> | |
347 </section> | |
348 <section name="busco"> | |
349 <param name="busco_seed_species" value="fly" /> | |
350 <param name="busco_db" value="insecta" /> | |
351 </section> | |
352 <param name="uglyTestingHack" value="true" /> | |
353 <!-- non deterministic results, so can't be more precise here --> | |
354 <output name="annot_gbk"> | |
355 <assert_contents> | |
356 <has_text text=" TITLE Direct Submission" /> | |
357 <has_text text="/locus_tag="FUN_000001"" /> | |
358 </assert_contents> | |
359 </output> | |
360 <output name="annot_tbl"> | |
361 <assert_contents> | |
362 <has_text text=">Feature sample" /> | |
363 <has_text text="gnl|ncbi|FUN_000001-T1_mrna" /> | |
364 </assert_contents> | |
365 </output> | |
366 <output name="annot_gff3"> | |
367 <assert_contents> | |
368 <has_text text="##gff-version 3" /> | |
369 <has_text text="ID=FUN_000001-T1;Parent=FUN_000001;product=hypothetical protein;" /> | |
370 </assert_contents> | |
371 </output> | |
372 <output name="fasta_proteins"> | |
373 <assert_contents> | |
374 <has_text text=">FUN_000001-T1 FUN_000001" /> | |
375 </assert_contents> | |
376 </output> | |
377 <output name="fasta_transcripts_mrna"> | |
378 <assert_contents> | |
379 <has_text text=">FUN_000001-T1 FUN_000001" /> | |
380 </assert_contents> | |
381 </output> | |
382 <output name="fasta_transcripts_cds"> | |
383 <assert_contents> | |
384 <has_text text=">FUN_000001-T1 FUN_000001" /> | |
385 </assert_contents> | |
386 </output> | |
387 <assert_stderr> | |
388 <has_text text="augustus pretrained"/> | |
389 <has_text text="glimmerhmm busco"/> | |
390 <has_text text="snap busco"/> | |
391 <has_text text="Running BUSCO to find conserved gene models for training ab-initio predictors"/> | |
392 <has_text text="Skipping CodingQuarry as no --rna_bam passed"/> | |
393 <has_text text="Running Augustus gene prediction using fly parameters"/> | |
394 <not_has_text text="Aligning transcript evidence to genome with minimap2"/> | |
395 <not_has_text text="Found 16 alignments, wrote GFF3 and Augustus hints to file"/> | |
396 <not_has_text text="Extracting hints from RNA-seq BAM file using bam2hints"/> | |
397 <has_text text="Mapping 13 proteins to genome using diamond and exonerate"/> | |
398 <has_text text="Found 4 preliminary alignments --> aligning with exonerate"/> | |
399 </assert_stderr> | |
400 </test> | |
401 | |
402 <!-- bam --> | |
403 <test> | |
404 <param name="input" value="genome_masked.fa" /> | |
405 <param name="database" value="2021-07-20-120000" /> | |
406 <section name="organism"> | |
407 <param name="species" value="Genus species" /> | |
408 </section> | |
409 <section name="evidences"> | |
410 <param name="rna_bam" value="SRR7458692.bam" /> | |
411 <param name="transcript_evidence" value="predict_scratch/Genus_species.mrna-transcripts.fa" /> | |
412 <conditional name="prot_evidence"> | |
413 <param name="prot_evidence_source" value="custom" /> | |
414 <param name="protein_evidence" value="predict_scratch/Genus_species.proteins.fa" /> | |
415 </conditional> | |
416 </section> | |
417 <section name="augustus"> | |
418 <param name="min_training_models" value="3" /> | |
419 </section> | |
420 <section name="busco"> | |
421 <param name="busco_seed_species" value="fly" /> | |
422 <param name="busco_db" value="insecta" /> | |
423 </section> | |
424 <!-- non deterministic results, so can't be more precise here --> | |
425 <output name="annot_gbk"> | |
426 <assert_contents> | |
427 <has_text text=" TITLE Direct Submission" /> | |
428 <has_text text="/locus_tag="FUN_000001"" /> | |
429 </assert_contents> | |
430 </output> | |
431 <output name="annot_tbl"> | |
432 <assert_contents> | |
433 <has_text text=">Feature sample" /> | |
434 <has_text text="gnl|ncbi|FUN_000001-T1_mrna" /> | |
435 </assert_contents> | |
436 </output> | |
437 <output name="annot_gff3"> | |
438 <assert_contents> | |
439 <has_text text="##gff-version 3" /> | |
440 <has_text text="ID=FUN_000001-T1;Parent=FUN_000001;product=hypothetical protein;" /> | |
441 </assert_contents> | |
442 </output> | |
443 <output name="fasta_proteins"> | |
444 <assert_contents> | |
445 <has_text text=">FUN_000001-T1 FUN_000001" /> | |
446 </assert_contents> | |
447 </output> | |
448 <output name="fasta_transcripts_mrna"> | |
449 <assert_contents> | |
450 <has_text text=">FUN_000001-T1 FUN_000001" /> | |
451 </assert_contents> | |
452 </output> | |
453 <output name="fasta_transcripts_cds"> | |
454 <assert_contents> | |
455 <has_text text=">FUN_000001-T1 FUN_000001" /> | |
456 </assert_contents> | |
457 </output> | |
458 <assert_stderr> | |
459 <has_text text="augustus busco"/> | |
460 <has_text text="glimmerhmm busco"/> | |
461 <has_text text="snap busco"/> | |
462 <has_text text="Running BUSCO to find conserved gene models for training ab-initio predictors"/> | |
463 <not_has_text text="Skipping CodingQuarry as no --rna_bam passed"/> | |
464 <has_text text="Running Augustus gene prediction using genus_species parameters"/> | |
465 <has_text text="Training Augustus using BUSCO gene models"/> | |
466 <has_text text="Aligning transcript evidence to genome with minimap2"/> | |
467 <has_text text="Found 16 alignments, wrote GFF3 and Augustus hints to file"/> | |
468 <has_text text="Extracting hints from RNA-seq BAM file using bam2hints"/> | |
469 <has_text text="Mapping 13 proteins to genome using diamond and exonerate"/> | |
470 <has_text text="Found 4 preliminary alignments --> aligning with exonerate"/> | |
471 </assert_stderr> | |
472 </test> | |
473 </tests> | |
474 <help><![CDATA[ | |
475 Funannotate_ predict | |
476 -------------------- | |
477 | |
478 Funannotate_ is a pipeline for genome annotation (built specifically for fungi, but will also work with higher eukaryotes). | |
479 | |
480 Script takes genome multi-fasta file and a variety of inputs to do a comprehensive whole | |
481 genome gene prediction. Uses AUGUSTUS, GeneMark, Snap, GlimmerHMM, BUSCO, EVidence Modeler, | |
482 tbl2asn, tRNAScan-SE, Exonerate, minimap2. | |
483 | |
484 .. _Funannotate: http://funannotate.readthedocs.io | |
485 ]]></help> | |
486 <expand macro="citations" /> | |
487 </tool> |