Mercurial > repos > iuc > ncbi_datasets

comparison datasets_gene.xml @ 20:35d32c807c23 draft default tip

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/main/tools/ncbi_datasets commit 5a65a62588a36d757f96681bf72f537c12c91beb
author iuc
date Fri, 26 Dec 2025 17:16:51 +0000
parents 9a10a6449901
children
comparison
equal deleted inserted replaced
19:ced734560c9d 20:35d32c807c23
2 <description>download gene sequences and metadata</description> 2 <description>download gene sequences and metadata</description>
3 <macros> 3 <macros>
4 <import>macros.xml</import> 4 <import>macros.xml</import>
5 </macros> 5 </macros>
6 <expand macro="bio_tools"/> 6 <expand macro="bio_tools"/>
7 <expand macro="requirements"></expand> 7 <expand macro="requirements"/>
8 <expand macro="version_command"/> 8 <expand macro="version_command"/>
9 <command><![CDATA[ 9 <command><![CDATA[
10 #import re 10 #import re
11 @SETUP_CERTIFICATES@ 11 @SETUP_CERTIFICATES@
12 datasets download gene $query.subcommand.download_by 12 datasets download gene $query.subcommand.download_by
39 #end if 39 #end if
40 #end if 40 #end if
41 41
42 #if $filters.fasta_filter_cond.fasta_filter_select 42 #if $filters.fasta_filter_cond.fasta_filter_select
43 #if $filters.fasta_filter_cond.fasta_filter_select == 'text' 43 #if $filters.fasta_filter_cond.fasta_filter_select == 'text'
44 --fasta-filter #echo ",".join(f"'{x}'" for x in $filters.fasta_filter_cond.fasta_filter.split(',') if x) 44 --fasta-filter #echo ",".join(f"'{x}'" for x in str($filters.fasta_filter_cond.fasta_filter).split(',') if x)
45 #else 45 #else
46 --fasta-filter-file '$filters.fasta_filter_cond.fasta_filter_file' 46 --fasta-filter-file '$filters.fasta_filter_cond.fasta_filter_file'
47 #end if 47 #end if
48 #end if 48 #end if
49 49
95 <expand macro="text_or_file" what="Gene Symbol" what_extended="NCBI Gene Symbol" help=""/> 95 <expand macro="text_or_file" what="Gene Symbol" what_extended="NCBI Gene Symbol" help=""/>
96 <expand macro="ortholog"/> 96 <expand macro="ortholog"/>
97 <param argument="--taxon" type="text" value="human" label="Species for gene symbol" help="NCBI taxid, common or scientific name"> 97 <param argument="--taxon" type="text" value="human" label="Species for gene symbol" help="NCBI taxid, common or scientific name">
98 <sanitizer invalid_char=""> 98 <sanitizer invalid_char="">
99 <valid initial="string.letters"> 99 <valid initial="string.letters">
100 <add value=" " /> 100 <add value=" "/>
101 <add value="-" /> 101 <add value="-"/>
102 </valid> 102 </valid>
103 </sanitizer> 103 </sanitizer>
104 </param> 104 </param>
105 </when> 105 </when>
106 <when value="accession"> 106 <when value="accession">
107 <expand macro="text_or_file" what="Gene Accession" what_extended="NCBI Gene Accession" help=""/> 107 <expand macro="text_or_file" what="Gene Accession" what_extended="NCBI Gene Accession" help=""/>
108 <expand macro="ortholog"/> 108 <expand macro="ortholog"/>
109 <param argument="--taxon-filter" type="text" value="" label="Limit gene sequences and annotation report file to specified taxon" help="any rank, only available for WP accessions"> 109 <param argument="--taxon-filter" type="text" value="" label="Limit gene sequences and annotation report file to specified taxon" help="any rank, only available for WP accessions">
110 <sanitizer invalid_char=""> 110 <sanitizer invalid_char="">
111 <valid initial="string.letters"> 111 <valid initial="string.letters">
112 <add value=" " /> 112 <add value=" "/>
113 <add value="-" /> 113 <add value="-"/>
114 </valid> 114 </valid>
115 </sanitizer> 115 </sanitizer>
116 </param> 116 </param>
117 <param argument="--include-flanks-bp" type="integer" optional="true" min="0" value="" label="Length of flanking nucleotides" help="WP accessions only"/> 117 <param argument="--include-flanks-bp" type="integer" optional="true" min="0" value="" label="Length of flanking nucleotides" help="WP accessions only"/>
118 </when> 118 </when>
131 <when value=""/> 131 <when value=""/>
132 <when value="text"> 132 <when value="text">
133 <param argument="--fasta-filter" type="text" label="RefSeq nucleotide and protein accessions" help="Comma separated"> 133 <param argument="--fasta-filter" type="text" label="RefSeq nucleotide and protein accessions" help="Comma separated">
134 <sanitizer invalid_char=""> 134 <sanitizer invalid_char="">
135 <valid initial="string.letters,string.digits"> 135 <valid initial="string.letters,string.digits">
136 <add value="," /> 136 <add value=","/>
137 </valid> 137 </valid>
138 </sanitizer> 138 </sanitizer>
139 </param> 139 </param>
140 </when> 140 </when>
141 <when value="file"> 141 <when value="file">
207 </data> 207 </data>
208 <data name="cds_fasta" label="NCBI Gene Datasets: CDS fasta" format="fasta" from_work_dir="ncbi_dataset/data/cds.fna"> 208 <data name="cds_fasta" label="NCBI Gene Datasets: CDS fasta" format="fasta" from_work_dir="ncbi_dataset/data/cds.fna">
209 <filter>file_choices['kingdom_cond']['include'] and "cds" in file_choices['kingdom_cond']['include']</filter> 209 <filter>file_choices['kingdom_cond']['include'] and "cds" in file_choices['kingdom_cond']['include']</filter>
210 </data> 210 </data>
211 <data name="threep_utr_fasta" label="NCBI Gene Datasets: 3' UTR fasta" format="fasta" from_work_dir="ncbi_dataset/data/3p_utr.fna"> 211 <data name="threep_utr_fasta" label="NCBI Gene Datasets: 3' UTR fasta" format="fasta" from_work_dir="ncbi_dataset/data/3p_utr.fna">
212 <filter>file_choices['kingdom_cond']['include'] and "5p-utr" in file_choices['kingdom_cond']['include']</filter> 212 <filter>file_choices['kingdom_cond']['include'] and "3p-utr" in file_choices['kingdom_cond']['include']</filter>
213 </data> 213 </data>
214 <data name="fivep_utr_fasta" label="NCBI Gene Datasets: 5' UTR fasta" format="fasta" from_work_dir="ncbi_dataset/data/5p_utr.fna"> 214 <data name="fivep_utr_fasta" label="NCBI Gene Datasets: 5' UTR fasta" format="fasta" from_work_dir="ncbi_dataset/data/5p_utr.fna">
215 <filter>file_choices['kingdom_cond']['include'] and "5p-utr" in file_choices['kingdom_cond']['include']</filter> 215 <filter>file_choices['kingdom_cond']['include'] and "5p-utr" in file_choices['kingdom_cond']['include']</filter>
216 </data> 216 </data>
217 </outputs> 217 </outputs>
233 <has_n_columns n="8"/> 233 <has_n_columns n="8"/>
234 </assert_contents> 234 </assert_contents>
235 </output> 235 </output>
236 <output name="rna_fasta"> 236 <output name="rna_fasta">
237 <assert_contents> 237 <assert_contents>
238 <has_text text=">"/> 238 <has_text text="&gt;"/>
239 </assert_contents> 239 </assert_contents>
240 </output> 240 </output>
241 <output name="protein_fasta"> 241 <output name="protein_fasta">
242 <assert_contents> 242 <assert_contents>
243 <has_text text=">"/> 243 <has_text text="&gt;"/>
244 </assert_contents> 244 </assert_contents>
245 </output> 245 </output>
246 </test> 246 </test>
247 <!-- 2: datasets download gene gene-id 2597 14433 --> 247 <!-- 2: datasets download gene gene-id 2597 14433 -->
248 <test expect_num_outputs="3"> 248 <test expect_num_outputs="3">
261 <has_n_columns n="8"/> 261 <has_n_columns n="8"/>
262 </assert_contents> 262 </assert_contents>
263 </output> 263 </output>
264 <output name="rna_fasta"> 264 <output name="rna_fasta">
265 <assert_contents> 265 <assert_contents>
266 <has_text text=">"/> 266 <has_text text="&gt;"/>
267 </assert_contents> 267 </assert_contents>
268 </output> 268 </output>
269 <output name="protein_fasta"> 269 <output name="protein_fasta">
270 <assert_contents> 270 <assert_contents>
271 <has_text text=">"/> 271 <has_text text="&gt;"/>
272 </assert_contents> 272 </assert_contents>
273 </output> 273 </output>
274 </test> 274 </test>
275 <!-- 3: same as above + give accessions by file, 2 different outputs and ortholog--> 275 <!-- 3: same as above + give accessions by file, 2 different outputs and ortholog-->
276 <test expect_num_outputs="3"> 276 <test expect_num_outputs="3">
282 </conditional> 282 </conditional>
283 <param name="ortholog" value="Haplorrhini,Strepsirrhini"/> 283 <param name="ortholog" value="Haplorrhini,Strepsirrhini"/>
284 </conditional> 284 </conditional>
285 <section name="file_choices"> 285 <section name="file_choices">
286 <conditional name="kingdom_cond"> 286 <conditional name="kingdom_cond">
287 <param name="kingdom_sel" value="gene"/>
287 <param name="include" value="gene,cds"/> 288 <param name="include" value="gene,cds"/>
288 </conditional> 289 </conditional>
289 </section> 290 </section>
290 <output name="gene_data_report"> 291 <output name="gene_data_report">
291 <assert_contents> 292 <assert_contents>
295 <has_n_columns n="8"/> 296 <has_n_columns n="8"/>
296 </assert_contents> 297 </assert_contents>
297 </output> 298 </output>
298 <output name="gene_fasta"> 299 <output name="gene_fasta">
299 <assert_contents> 300 <assert_contents>
300 <has_text text=">"/> 301 <has_text text="&gt;"/>
301 </assert_contents> 302 </assert_contents>
302 </output> 303 </output>
303 <output name="cds_fasta"> 304 <output name="cds_fasta">
304 <assert_contents> 305 <assert_contents>
305 <has_text text=">"/> 306 <has_text text="&gt;"/>
306 </assert_contents> 307 </assert_contents>
307 </output> 308 </output>
308 </test> 309 </test>
309 <!-- 4: datasets download gene symbol tp53 --> 310 <!-- 4: datasets download gene symbol tp53 -->
310 <test expect_num_outputs="1"> 311 <test expect_num_outputs="3">
311 <conditional name="query|subcommand"> 312 <conditional name="query|subcommand">
312 <param name="download_by" value="symbol"/> 313 <param name="download_by" value="symbol"/>
313 <conditional name="text_or_file"> 314 <conditional name="text_or_file">
314 <param name="text_or_file" value="text"/> 315 <param name="text_or_file" value="text"/>
315 <param name="accession" value="tp53"/> 316 <param name="accession" value="tp53"/>
316 </conditional> 317 </conditional>
317 </conditional> 318 </conditional>
318 <section name="file_choices">
319 <conditional name="kingdom_cond">
320 <param name="include" value=""/>
321 </conditional>
322 </section>
323 <output name="gene_data_report"> 319 <output name="gene_data_report">
324 <assert_contents> 320 <assert_contents>
325 <has_text text="human"/> 321 <has_text text="human"/>
326 <has_n_lines n="2"/> 322 <has_n_lines n="2"/>
327 <has_n_columns n="8"/> 323 <has_n_columns n="8"/>
359 <has_n_columns n="39"/> 355 <has_n_columns n="39"/>
360 </assert_contents> 356 </assert_contents>
361 </output> 357 </output>
362 <output name="threep_utr_fasta"> 358 <output name="threep_utr_fasta">
363 <assert_contents> 359 <assert_contents>
364 <has_text text=">"/> 360 <has_text text="&gt;"/>
365 </assert_contents> 361 </assert_contents>
366 </output> 362 </output>
367 <output name="fivep_utr_fasta"> 363 <output name="fivep_utr_fasta">
368 <assert_contents> 364 <assert_contents>
369 <has_text text=">"/> 365 <has_text text="&gt;"/>
370 </assert_contents> 366 </assert_contents>
371 </output> 367 </output>
372 </test> 368 </test>
373 <!-- 6: datasets download gene symbol brca1 \-\-ortholog --> 369 <!-- 6: datasets download gene symbol brca1 \-\-ortholog -->
374 <test expect_num_outputs="1"> 370 <test expect_num_outputs="3">
375 <conditional name="query|subcommand"> 371 <conditional name="query|subcommand">
376 <param name="download_by" value="symbol"/> 372 <param name="download_by" value="symbol"/>
377 <conditional name="text_or_file"> 373 <conditional name="text_or_file">
378 <param name="text_or_file" value="text"/> 374 <param name="text_or_file" value="text"/>
379 <param name="accession" value="brca1"/> 375 <param name="accession" value="brca1"/>
380 </conditional> 376 </conditional>
381 <param name="ortholog" value="rodentia"/> 377 <param name="ortholog" value="rodentia"/>
382 </conditional> 378 </conditional>
383 <section name="file_choices">
384 <conditional name="kingdom_cond">
385 <param name="include" value=""/>
386 </conditional>
387 </section>
388 <output name="gene_data_report"> 379 <output name="gene_data_report">
389 <assert_contents> 380 <assert_contents>
390 <has_text text="rat"/> 381 <has_text text="rat"/>
391 <has_text text="Brca1"/> 382 <has_text text="Brca1"/>
392 <has_n_lines min="30"/> 383 <has_n_lines min="30"/>
393 <has_n_columns n="8"/> 384 <has_n_columns n="8"/>
394 </assert_contents> 385 </assert_contents>
395 </output> 386 </output>
396 </test> 387 </test>
397 <!-- 7: datasets download gene accession NP_000483.3 --> 388 <!-- 7: datasets download gene accession NP_000483.3 -->
398 <test expect_num_outputs="1"> 389 <test expect_num_outputs="3">
399 <conditional name="query|subcommand"> 390 <conditional name="query|subcommand">
400 <param name="download_by" value="accession"/> 391 <param name="download_by" value="accession"/>
401 <conditional name="text_or_file"> 392 <conditional name="text_or_file">
402 <param name="text_or_file" value="text"/> 393 <param name="text_or_file" value="text"/>
403 <param name="accession" value="NP_000483.3"/> 394 <param name="accession" value="NP_000483.3"/>
404 </conditional> 395 </conditional>
405 </conditional> 396 </conditional>
406 <section name="file_choices">
407 <conditional name="kingdom_cond">
408 <param name="include" value=""/>
409 </conditional>
410 </section>
411 <output name="gene_data_report"> 397 <output name="gene_data_report">
412 <assert_contents> 398 <assert_contents>
413 <has_text text="human"/> 399 <has_text text="human"/>
414 <has_n_lines n="2"/> 400 <has_n_lines n="2"/>
415 <has_n_columns n="8"/> 401 <has_n_columns n="8"/>
416 </assert_contents> 402 </assert_contents>
417 </output> 403 </output>
418 </test> 404 </test>
419 <!-- 8: datasets download gene accession NM_000546.6 NM_000492.4 + ortholog--> 405 <!-- 8: datasets download gene accession NM_000546.6 NM_000492.4 + ortholog-->
420 <test expect_num_outputs="1"> 406 <test expect_num_outputs="3">
421 <conditional name="query|subcommand"> 407 <conditional name="query|subcommand">
422 <param name="download_by" value="accession"/> 408 <param name="download_by" value="accession"/>
423 <conditional name="text_or_file"> 409 <conditional name="text_or_file">
424 <param name="text_or_file" value="text"/> 410 <param name="text_or_file" value="text"/>
425 <param name="accession" value="NM_000546.6 NM_000492.4"/> 411 <param name="accession" value="NM_000546.6 NM_000492.4"/>
426 </conditional> 412 </conditional>
427 <param name="ortholog" value="all"/> 413 <param name="ortholog" value="all"/>
428 </conditional> 414 </conditional>
429 <section name="file_choices">
430 <conditional name="kingdom_cond">
431 <param name="include" value=""/>
432 </conditional>
433 </section>
434 <output name="gene_data_report"> 415 <output name="gene_data_report">
435 <assert_contents> 416 <assert_contents>
436 <has_text text="human"/> 417 <has_text text="human"/>
437 <has_n_lines min="800"/> 418 <has_n_lines min="800"/>
438 <has_n_columns n="8"/> 419 <has_n_columns n="8"/>
439 </assert_contents> 420 </assert_contents>
440 </output> 421 </output>
441 </test> 422 </test>
442
443 <!-- 9: datasets download gene accession WP_003249567.1 + include_flanks_bp --> 423 <!-- 9: datasets download gene accession WP_003249567.1 + include_flanks_bp -->
444 <test expect_num_outputs="4"> 424 <test expect_num_outputs="4">
445 <conditional name="query|subcommand"> 425 <conditional name="query|subcommand">
446 <param name="download_by" value="accession"/> 426 <param name="download_by" value="accession"/>
447 <conditional name="text_or_file"> 427 <conditional name="text_or_file">
464 <has_n_columns n="7"/> 444 <has_n_columns n="7"/>
465 </assert_contents> 445 </assert_contents>
466 </output> 446 </output>
467 <output name="gene_fasta"> 447 <output name="gene_fasta">
468 <assert_contents> 448 <assert_contents>
469 <has_text text=">"/> 449 <has_text text="&gt;"/>
470 </assert_contents> 450 </assert_contents>
471 </output> 451 </output>
472 <output name="gene_flanks"> 452 <output name="gene_flanks">
473 <assert_contents> 453 <assert_contents>
474 <has_text text=">"/> 454 <has_text text="&gt;"/>
475 </assert_contents> 455 </assert_contents>
476 </output> 456 </output>
477 <output name="protein_fasta"> 457 <output name="protein_fasta">
478 <assert_contents> 458 <assert_contents>
479 <has_text text=">"/> 459 <has_text text="&gt;"/>
480 </assert_contents> 460 </assert_contents>
481 </output> 461 </output>
482 <assert_command> 462 <assert_command>
483 <has_text text="include-flanks-bp 100"/> 463 <has_text text="include-flanks-bp 100"/>
484 </assert_command> 464 </assert_command>
485 </test> 465 </test>
486
487 <!-- 10: datasets download gene taxon human --> 466 <!-- 10: datasets download gene taxon human -->
488 <!-- <test expect_num_outputs="1"> 467 <!-- <test expect_num_outputs="1">
489 <conditional name="query|subcommand"> 468 <conditional name="query|subcommand">
490 <param name="download_by" value="taxon"/> 469 <param name="download_by" value="taxon"/>
491 <param name="taxon_positional" value="human"/> 470 <param name="taxon_positional" value="human"/>
532 <has_text text=">" n="1" /> 511 <has_text text=">" n="1" />
533 </assert_contents> 512 </assert_contents>
534 </output> 513 </output>
535 </test> --> 514 </test> -->
536 </tests> 515 </tests>
537 <help> 516 <help><![CDATA[
538 <![CDATA[ 517 .. class:: infomark
539 **Download Gene Datasets from NCBI** 518
540 519 **What it does**
541 Download a gene dataset (gene sequence, transcipt, amino acid sequences, 520
542 nucleotide coding sequences, 5'-UTR, 3'-UTR) as well as gene and gene 521 Downloads gene data from NCBI using the `datasets`_ command-line tool.
543 product reports. Genes can be referred by gene id, symbol, accession, 522 Retrieve gene sequences, transcripts, proteins, and annotation reports.
544 or taxon. 523
545 ]]> 524 **Query Options**
546 </help> 525
526 ============= ================================================================
527 Method Description
528 ============= ================================================================
529 Gene ID NCBI Gene ID (e.g., 672 for BRCA1)
530 Symbol Gene symbol with taxon (e.g., TP53 in human)
531 Accession RefSeq nucleotide (NM\_) or protein (NP\_/WP\_) accession
532 Taxon All genes for a taxon (large downloads)
533 ============= ================================================================
534
535 ----
536
537 **Key Options**
538
539 - **Ortholog retrieval**: Get orthologous genes across taxa (vertebrates/insects)
540 - **Taxon filter**: Limit WP\_ accession results to specific organisms
541 - **Flanking sequence**: Include nucleotides upstream/downstream (WP\_ only)
542 - **FASTA filter**: Subset output to specific accessions
543
544 **Outputs (Eukaryote)**
545
546 - **Gene Data Report**: Tabular metadata (ID, symbol, description, coordinates)
547 - **Gene Product Report**: Detailed transcript/protein information
548 - **Sequences**: Gene, RNA, protein, CDS, 5'/3' UTR FASTA files
549
550 **Outputs (Prokaryote)**
551
552 Prokaryotic genes (WP\_ accessions) use a different report format with:
553 accession, description, EC number, gene symbol, protein info.
554
555 **Examples**
556
557 Download human BRCA1::
558
559 Query by: Gene ID
560 Gene ID: 672
561
562 Download TP53 orthologs in rodents::
563
564 Query by: Symbol
565 Symbol: tp53
566 Ortholog: rodentia
567
568
569 .. _datasets: https://www.ncbi.nlm.nih.gov/datasets/
570 ]]></help>
547 <expand macro="citations"/> 571 <expand macro="citations"/>
548 </tool> 572 </tool>