Mercurial > repos > iuc > bakta

comparison bakta.xml @ 5:728dacaf08a9 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/blob/master/tools/bakta commit 5ab93133efa5de410e992919c4e841807fb43b55
author iuc
date Sat, 16 Sep 2023 09:01:39 +0000
parents 3f0aa1b3e816
children 92eee5f31117
comparison
equal deleted inserted replaced
4:3f0aa1b3e816 5:728dacaf08a9
210 <filter>output_files['output_selection'] and "log_txt" in output_files['output_selection']</filter> 210 <filter>output_files['output_selection'] and "log_txt" in output_files['output_selection']</filter>
211 </data> 211 </data>
212 </outputs> 212 </outputs>
213 <tests> 213 <tests>
214 <test expect_num_outputs="13"> <!-- TEST_1 database + input --> 214 <test expect_num_outputs="13"> <!-- TEST_1 database + input -->
215 <section name="input_option" >
216 <param name="bakta_db_select" value="V5.0_2022-08-19"/>
217 <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/>
218 <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/>
219 <param name="min_contig_length" value="250"/>
220 </section>
221 <section name="output_files">
222 <param name="output_selection" value="file_tsv,file_gff3,file_gbff,file_embl,file_fna,file_ffn,file_faa,hypo_tsv,hypo_fa,sum_txt,file_json,file_plot,log_txt"/>
223 </section>
224 <output name="annotation_tsv" value="TEST_1/TEST_1.tsv" lines_diff="2"/>
225 <output name="annotation_gff3" value="TEST_1/TEST_1.gff3" lines_diff="2"/>
226 <output name="annotation_gbff" value="TEST_1/TEST_1.gbff" lines_diff="8"/>
227 <output name="annotation_embl" value="TEST_1/TEST_1.embl" lines_diff="6"/>
228 <output name="annotation_fna" value="TEST_1/TEST_1.fna"/>
229 <output name="annotation_ffn" value="TEST_1/TEST_1.ffn"/>
230 <output name="annotation_faa" value="TEST_1/TEST_1.faa"/>
231 <output name="hypotheticals_tsv" value="TEST_1/TEST_1.hypotheticals.tsv" lines_diff="4"/>
232 <output name="hypotheticals_faa" value="TEST_1/TEST_1.hypotheticals.faa"/>
233 <output name="summary_txt" value="TEST_1/TEST_1.txt" lines_diff="4"/>
234 <output name="annotation_plot" value="TEST_1/TEST_1_plot.svg" ftype="svg" compare="sim_size"/>
235 <output name="annotation_json" value="TEST_1/TEST_1.json" lines_diff="6"/>
236 <output name="logfile" value="TEST_1/TEST_1.log" lines_diff="15"/>
237 </test>
238 <test expect_num_outputs="4"> <!-- TEST_2 another input, add organism info some annotations and skip 2 steps -->
239 <section name="input_option" >
240 <param name="bakta_db_select" value="V5.0_2022-08-19"/>
241 <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/>
242 <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/>
243 <param name="min_contig_length" value="250"/>
244 </section>
245 <section name="organism">
246 <param name="genus" value="Escherichia"/>
247 <param name="species" value="coli O157:H7"/>
248 <param name="strain" value="Sakai"/>
249 <param name="plasmid" value="pOSAK1"/>
250 </section>
251 <section name="annotation">
252 <param name="keep_contig_headers" value="true"/>
253 </section>
254 <section name="workflow">
255 <param name="skip_analysis" value="--skip-trna,--skip-tmrna"/>
256 </section>
257 <output name="annotation_tsv" value="TEST_2/TEST_2.tsv" lines_diff="4">
258 <assert_contents>
259 <has_text_matching expression="IHHALP_00005"/>
260 </assert_contents>
261 </output>
262 <output name="annotation_gff3" value="TEST_2/TEST_2.gff3" lines_diff="4">
263 <assert_contents>
264 <has_text_matching expression="ID=NC_002127.1;Name=NC_002127.1;Is_circular=true"/>
265 </assert_contents>
266 </output>
267 <output name="annotation_ffn" value="TEST_2/TEST_2.ffn"/>
268 <output name="annotation_plot" value="TEST_2/TEST_2_plot.svg" ftype="svg" compare="sim_size"/>
269 </test>
270 <test expect_num_outputs="4"> <!-- TEST_3 test all skip steps -->
271 <section name="input_option" >
272 <param name="bakta_db_select" value="V5.0_2022-08-19"/>
273 <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/>
274 <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/>
275 <param name="min_contig_length" value="350"/>
276 </section>
277 <section name="workflow">
278 <param name="skip_analysis" value="--skip-trna,--skip-tmrna,--skip-rrna,--skip-ncrna,--skip-ncrna-region,--skip-crispr,--skip-cds,--skip-sorf,--skip-gap,--skip-ori,--skip-plot"/>
279 </section>
280 <output name="annotation_tsv" value="TEST_3/TEST_3.tsv" lines_diff="4"/>
281 <output name="annotation_gff3" value="TEST_3/TEST_3.gff3" lines_diff="4"/>
282 <output name="annotation_ffn" value="TEST_3/TEST_3.ffn"/>
283 </test>
284 <test expect_num_outputs="4"> <!-- TEST_4 annotations -->
285 <section name="input_option" >
286 <param name="bakta_db_select" value="V5.0_2022-08-19"/>
287 <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/>
288 <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/>
289 </section>
290 <section name="annotation">
291 <param name="complete" value="true"/>
292 <param name="prodigal" value="prodigal.tf"/>
293 <param name="translation_table" value="4"/>
294 <param name="replicons" value="replicons.tsv" ftype="tabular"/>
295 <param name="compliant" value="true"/>
296 <param name="proteins" value="user-proteins.faa" ftype="fasta"/>
297 </section>
298 <output name="annotation_tsv" value="TEST_4/TEST_4.tsv" lines_diff="4"/>
299 <output name="annotation_gff3" value="TEST_4/TEST_4.gff3" lines_diff="4"/>
300 <output name="annotation_ffn" value="TEST_4/TEST_4.ffn"/>
301 <output name="annotation_plot" value="TEST_4/TEST_4_plot.svg" ftype="svg" compare="sim_size"/>
302 </test>
303 <test expect_num_outputs="2"> <!-- TEST_5 skip all steps and keep only the logfile and summary -->
304 <section name="input_option" >
305 <param name="bakta_db_select" value="V5.0_2022-08-19"/>
306 <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/>
307 <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/>
308 </section>
309 <section name="annotation">
310 <param name="complete" value="true"/>
311 <param name="translation_table" value="4"/>
312 </section>
313 <section name="workflow">
314 <param name="skip_analysis" value="--skip-trna,--skip-tmrna,--skip-rrna,--skip-ncrna,--skip-ncrna-region,--skip-crispr,--skip-cds,--skip-sorf,--skip-gap,--skip-ori,--skip-plot"/>
315 </section>
316 <section name="output_files">
317 <param name="output_selection" value="log_txt,sum_txt"/>
318 </section>
319 <output name="logfile" value="TEST_5/TEST_5.log" lines_diff="13"/>
320 <output name="summary_txt" value="TEST_5/TEST_5.txt" lines_diff="4"/>
321 </test>
322 <test expect_num_outputs="13"> <!-- TEST_6 metagenome option -->
323 <section name="input_option" > 215 <section name="input_option" >
324 <param name="bakta_db_select" value="V5.0_2022-08-19"/> 216 <param name="bakta_db_select" value="V5.0_2022-08-19"/>
325 <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/> 217 <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/>
326 <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/> 218 <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/>
327 </section> 219 <param name="min_contig_length" value="250"/>
328 <section name="annotation">
329 <param name="meta" value="true"/>
330 </section> 220 </section>
331 <section name="output_files"> 221 <section name="output_files">
332 <param name="output_selection" value="file_tsv,file_gff3,file_gbff,file_embl,file_fna,file_ffn,file_faa,hypo_tsv,hypo_fa,sum_txt,file_json,file_plot,log_txt"/> 222 <param name="output_selection" value="file_tsv,file_gff3,file_gbff,file_embl,file_fna,file_ffn,file_faa,hypo_tsv,hypo_fa,sum_txt,file_json,file_plot,log_txt"/>
333 </section> 223 </section>
334 <output name="annotation_tsv" value="TEST_6/TEST_6.tsv" lines_diff="2"/> 224 <output name="annotation_tsv" value="TEST_1/TEST_1.tsv" lines_diff="2"/>
335 <output name="annotation_gff3" value="TEST_6/TEST_6.gff3" lines_diff="2"/> 225 <output name="annotation_gff3" value="TEST_1/TEST_1.gff3" lines_diff="2"/>
336 <output name="annotation_gbff" value="TEST_6/TEST_6.gbff" lines_diff="8"/> 226 <output name="annotation_gbff" value="TEST_1/TEST_1.gbff" lines_diff="8"/>
337 <output name="annotation_embl" value="TEST_6/TEST_6.embl" lines_diff="6"/> 227 <output name="annotation_embl" value="TEST_1/TEST_1.embl" lines_diff="6"/>
338 <output name="annotation_fna" value="TEST_6/TEST_6.fna"/> 228 <output name="annotation_fna" value="TEST_1/TEST_1.fna"/>
339 <output name="annotation_ffn" value="TEST_6/TEST_6.ffn"/> 229 <output name="annotation_ffn" value="TEST_1/TEST_1.ffn"/>
340 <output name="annotation_faa" value="TEST_6/TEST_6.faa"/> 230 <output name="annotation_faa" value="TEST_1/TEST_1.faa"/>
341 <output name="hypotheticals_tsv" value="TEST_6/TEST_6.hypotheticals.tsv" lines_diff="4"/> 231 <output name="hypotheticals_tsv" value="TEST_1/TEST_1.hypotheticals.tsv" lines_diff="4"/>
342 <output name="hypotheticals_faa" value="TEST_6/TEST_6.hypotheticals.faa"/> 232 <output name="hypotheticals_faa" value="TEST_1/TEST_1.hypotheticals.faa"/>
343 <output name="summary_txt" value="TEST_6/TEST_6.txt" lines_diff="4"/> 233 <output name="summary_txt" value="TEST_1/TEST_1.txt" lines_diff="4"/>
344 <output name="annotation_plot" value="TEST_6/TEST_6_plot.svg" ftype="svg" compare="sim_size"/> 234 <output name="annotation_plot" value="TEST_1/TEST_1_plot.svg" ftype="svg" compare="sim_size"/>
345 <output name="annotation_json" value="TEST_6/TEST_6.json" lines_diff="6"/> 235 <output name="annotation_json" value="TEST_1/TEST_1.json" lines_diff="6"/>
346 <output name="logfile" value="TEST_6/TEST_6.log" lines_diff="15"/> 236 <output name="logfile" ftype="txt">
237 <expand macro="assert_content_test"/>
238 </output>
347 </test> 239 </test>
240 <test expect_num_outputs="4"> <!-- TEST_2 another input, add organism info some annotations and skip 2 steps -->
241 <section name="input_option" >
242 <param name="bakta_db_select" value="V5.0_2022-08-19"/>
243 <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/>
244 <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/>
245 <param name="min_contig_length" value="250"/>
246 </section>
247 <section name="organism">
248 <param name="genus" value="Escherichia"/>
249 <param name="species" value="coli O157:H7"/>
250 <param name="strain" value="Sakai"/>
251 <param name="plasmid" value="pOSAK1"/>
252 </section>
253 <section name="annotation">
254 <param name="keep_contig_headers" value="true"/>
255 </section>
256 <section name="workflow">
257 <param name="skip_analysis" value="--skip-trna,--skip-tmrna"/>
258 </section>
259 <output name="annotation_tsv" value="TEST_2/TEST_2.tsv" lines_diff="4">
260 <assert_contents>
261 <has_text_matching expression="IHHALP_00005"/>
262 </assert_contents>
263 </output>
264 <output name="annotation_gff3" value="TEST_2/TEST_2.gff3" lines_diff="4">
265 <assert_contents>
266 <has_text_matching expression="ID=NC_002127.1;Name=NC_002127.1;Is_circular=true"/>
267 </assert_contents>
268 </output>
269 <output name="annotation_ffn" value="TEST_2/TEST_2.ffn"/>
270 <output name="annotation_plot" value="TEST_2/TEST_2_plot.svg" ftype="svg" compare="sim_size"/>
271 </test>
272 <test expect_num_outputs="4"> <!-- TEST_3 test all skip steps -->
273 <section name="input_option" >
274 <param name="bakta_db_select" value="V5.0_2022-08-19"/>
275 <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/>
276 <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/>
277 <param name="min_contig_length" value="350"/>
278 </section>
279 <section name="workflow">
280 <param name="skip_analysis" value="--skip-trna,--skip-tmrna,--skip-rrna,--skip-ncrna,--skip-ncrna-region,--skip-crispr,--skip-cds,--skip-sorf,--skip-gap,--skip-ori,--skip-plot"/>
281 </section>
282 <output name="annotation_tsv" value="TEST_3/TEST_3.tsv" lines_diff="4"/>
283 <output name="annotation_gff3" value="TEST_3/TEST_3.gff3" lines_diff="4"/>
284 <output name="annotation_ffn" value="TEST_3/TEST_3.ffn"/>
285 </test>
286 <test expect_num_outputs="4"> <!-- TEST_4 annotations -->
287 <section name="input_option" >
288 <param name="bakta_db_select" value="V5.0_2022-08-19"/>
289 <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/>
290 <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/>
291 </section>
292 <section name="annotation">
293 <param name="complete" value="true"/>
294 <param name="prodigal" value="prodigal.tf"/>
295 <param name="translation_table" value="4"/>
296 <param name="replicons" value="replicons.tsv" ftype="tabular"/>
297 <param name="compliant" value="true"/>
298 <param name="proteins" value="user-proteins.faa" ftype="fasta"/>
299 </section>
300 <output name="annotation_tsv" value="TEST_4/TEST_4.tsv" lines_diff="4"/>
301 <output name="annotation_gff3" value="TEST_4/TEST_4.gff3" lines_diff="4"/>
302 <output name="annotation_ffn" value="TEST_4/TEST_4.ffn"/>
303 <output name="annotation_plot" value="TEST_4/TEST_4_plot.svg" ftype="svg" compare="sim_size"/>
304 </test>
305 <test expect_num_outputs="2"> <!-- TEST_5 skip all steps and keep only the logfile and summary -->
306 <section name="input_option" >
307 <param name="bakta_db_select" value="V5.0_2022-08-19"/>
308 <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/>
309 <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/>
310 </section>
311 <section name="annotation">
312 <param name="complete" value="true"/>
313 <param name="translation_table" value="4"/>
314 </section>
315 <section name="workflow">
316 <param name="skip_analysis" value="--skip-trna,--skip-tmrna,--skip-rrna,--skip-ncrna,--skip-ncrna-region,--skip-crispr,--skip-cds,--skip-sorf,--skip-gap,--skip-ori,--skip-plot"/>
317 </section>
318 <section name="output_files">
319 <param name="output_selection" value="log_txt,sum_txt"/>
320 </section>
321 <output name="logfile" ftype="txt">
322 <expand macro="assert_content_test"/>
323 </output>
324 <output name="summary_txt" value="TEST_5/TEST_5.txt" lines_diff="4"/>
325 </test>
326 <test expect_num_outputs="13"> <!-- TEST_6 metagenome option -->
327 <section name="input_option" >
328 <param name="bakta_db_select" value="V5.0_2022-08-19"/>
329 <param name="amrfinder_db_select" value="V3.6-2020-03-20.1"/>
330 <param name="input_file" value="NC_002127.1.fna" ftype="fasta"/>
331 </section>
332 <section name="annotation">
333 <param name="meta" value="true"/>
334 </section>
335 <section name="output_files">
336 <param name="output_selection" value="file_tsv,file_gff3,file_gbff,file_embl,file_fna,file_ffn,file_faa,hypo_tsv,hypo_fa,sum_txt,file_json,file_plot,log_txt"/>
337 </section>
338 <output name="annotation_tsv" value="TEST_6/TEST_6.tsv" lines_diff="2"/>
339 <output name="annotation_gff3" value="TEST_6/TEST_6.gff3" lines_diff="2"/>
340 <output name="annotation_gbff" value="TEST_6/TEST_6.gbff" lines_diff="8"/>
341 <output name="annotation_embl" value="TEST_6/TEST_6.embl" lines_diff="6"/>
342 <output name="annotation_fna" value="TEST_6/TEST_6.fna"/>
343 <output name="annotation_ffn" value="TEST_6/TEST_6.ffn"/>
344 <output name="annotation_faa" value="TEST_6/TEST_6.faa"/>
345 <output name="hypotheticals_tsv" value="TEST_6/TEST_6.hypotheticals.tsv" lines_diff="4"/>
346 <output name="hypotheticals_faa" value="TEST_6/TEST_6.hypotheticals.faa"/>
347 <output name="summary_txt" value="TEST_6/TEST_6.txt" lines_diff="4"/>
348 <output name="annotation_plot" value="TEST_6/TEST_6_plot.svg" ftype="svg" compare="sim_size"/>
349 <output name="annotation_json" value="TEST_6/TEST_6.json" lines_diff="6"/>
350 <output name="logfile" ftype="txt">
351 <expand macro="assert_content_test"/>
352 </output>
353 </test>
348 </tests> 354 </tests>
349 <help><![CDATA[**What it does** 355 <help><![CDATA[**What it does**
350 Bakta is a tool for the rapid & standardized annotation of bacterial genomes and plasmids from both isolates and MAGs. 356 Bakta is a tool for the rapid & standardized annotation of bacterial genomes and plasmids from both isolates and MAGs.
351 357
352 *Comprehensive & taxonomy-independent database* 358 *Comprehensive & taxonomy-independent database*