Mercurial > repos > michal_klinka > trtools

comparison DumpSTR/dumpSTR.xml @ 1:8e8cf43f6836 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/Kulivox/TRToolsGalaxyWrapper commit df706bf76531920d935ec6d2eb41b9b1420aa390
author michal_klinka
date Sun, 15 May 2022 15:23:59 +0000
parents ecf8c4f9f8ba
children
comparison
equal deleted inserted replaced
0:ecf8c4f9f8ba 1:8e8cf43f6836
1 <?xml version="1.0" ?>
2 <tool id="dumpSTR" name="DumpSTR" version="@tool_version@"> 1 <tool id="dumpSTR" name="DumpSTR" version="@tool_version@">
3 <description>DumpSTR filters VCF files with TR genotypes, performing call-level and locus-level filtering, and 2 <description>DumpSTR filters VCF files with TR genotypes, performing call-level and locus-level filtering, and
4 outputs a filtered VCF file. 3 outputs a filtered VCF file.
5 </description> 4 </description>
6 5
394 </outputs> 393 </outputs>
395 394
396 395
397 <tests> 396 <tests>
398 <test> 397 <test>
399 <section name="main_params"> 398 <section name="input_output">
400 <param name="vcf" value="NA12891_chr21_hipstr.sorted.vcf.gz"/> 399 <param name="vcf" value="NA12891_chr21_hipstr.sorted.vcf.gz"/>
401 <param name="out" value="test_result"/> 400 <param name="out" value="test_result"/>
402 <param name="vcftype" value="hipstr"/> 401 <param name="vcftype" value="hipstr"/>
403 <param name="zip" value="false"/> 402 <param name="zip" value="false"/>
404 </section> 403 </section>
405 <section name="filter_opt"> 404 <section name="locus_level_filters__tool_agnostic_">
406 <param name="min_locus_callrate" value="0.1"/> 405 <param name="min_locus_callrate" value="0.1"/>
407 <param name="use_length" value="true"/> 406 <param name="use_length" value="true"/>
408 <param name="drop_filtered" value="true"/> 407 <param name="drop_filtered" value="true"/>
409 </section> 408 </section>
410 <section name="filter_call_level"> 409 <section name="call_level_filters_specific_to_hipstr_output">
411 <section name="hipstr_filters"> 410 <param name="hipstr_max_call_flank_indel" value="0.2"/>
412 <param name="hipstr_max_call_flank_indel" value="0.2"/> 411 <param name="hipstr_min_call_Q" value="0.4"/>
413 <param name="hipstr_min_call_Q" value="0.4"/>
414 </section>
415 </section> 412 </section>
416 413
417 <output name="stdout" file="stdout.txt"/> 414 <output name="stdout" file="stdout.txt"/>
418 415
419 <output name="main_output"> 416 <output name="main_output">
420 <discovered_dataset designation="test_result.loclog" file="test_result.loclog.tab"/> 417 <discovered_dataset designation="test_result.loclog" file="test_result.loclog.tab"/>
421 <discovered_dataset designation="test_result.samplog" file="test_result.samplog.tab"/> 418 <discovered_dataset designation="test_result.samplog" file="test_result.samplog.tab"/>
422 <discovered_dataset designation="test_result"> 419 <discovered_dataset designation="test_result">
423 <assert_contents> 420 <assert_contents>
424 <has_size value="4061730" delta="200"/> 421 <has_size value="4062163" delta="1000"/>
425 <has_text text="##fileformat=VCFv4.1"/> 422 <has_text text="##fileformat=VCFv4.1"/>
426 <has_n_lines n="9046"/> 423 <has_n_lines n="9047" delta="1"/>
427 </assert_contents> 424 </assert_contents>
428 </discovered_dataset> 425 </discovered_dataset>
429 </output> 426 </output>
430 <output name="stderr" file="stderr.txt"/> 427 <output name="stderr" file="stderr.txt"/>
431 428
432 </test> 429 </test>
433 </tests> 430 </tests>
434 431
435 432
436 <help>usage: main.py [-h] --vcf VCF --out OUT [--zip] [--vcftype VCFTYPE] [--min-locus-callrate MIN_LOCUS_CALLRATE] 433 <help>usage: pygalgen [-h] --vcf VCF --out OUT [--zip] [--vcftype VCFTYPE] [--min-locus-callrate MIN_LOCUS_CALLRATE]
437 [--min-locus-hwep MIN_LOCUS_HWEP] [--min-locus-het MIN_LOCUS_HET] [--max-locus-het MAX_LOCUS_HET] [--use-length] 434 [--min-locus-hwep MIN_LOCUS_HWEP] [--min-locus-het MIN_LOCUS_HET] [--max-locus-het MAX_LOCUS_HET]
438 [--filter-regions FILTER_REGIONS] [--filter-regions-names FILTER_REGIONS_NAMES] [--filter-hrun] 435 [--use-length] [--filter-regions FILTER_REGIONS] [--filter-regions-names FILTER_REGIONS_NAMES]
439 [--drop-filtered] [--hipstr-max-call-flank-indel HIPSTR_MAX_CALL_FLANK_INDEL] 436 [--filter-hrun] [--drop-filtered] [--hipstr-max-call-flank-indel HIPSTR_MAX_CALL_FLANK_INDEL]
440 [--hipstr-max-call-stutter HIPSTR_MAX_CALL_STUTTER] [--hipstr-min-supp-reads HIPSTR_MIN_SUPP_READS] 437 [--hipstr-max-call-stutter HIPSTR_MAX_CALL_STUTTER] [--hipstr-min-supp-reads HIPSTR_MIN_SUPP_READS]
441 [--hipstr-min-call-DP HIPSTR_MIN_CALL_DP] [--hipstr-max-call-DP HIPSTR_MAX_CALL_DP] 438 [--hipstr-min-call-DP HIPSTR_MIN_CALL_DP] [--hipstr-max-call-DP HIPSTR_MAX_CALL_DP]
442 [--hipstr-min-call-Q HIPSTR_MIN_CALL_Q] [--gangstr-min-call-DP GANGSTR_MIN_CALL_DP] [--gangstr-max-call-DP 439 [--hipstr-min-call-Q HIPSTR_MIN_CALL_Q] [--gangstr-min-call-DP GANGSTR_MIN_CALL_DP]
443 GANGSTR_MAX_CALL_DP] [--gangstr-min-call-Q GANGSTR_MIN_CALL_Q] 440 [--gangstr-max-call-DP GANGSTR_MAX_CALL_DP] [--gangstr-min-call-Q GANGSTR_MIN_CALL_Q]
444 [--gangstr-expansion-prob-het GANGSTR_EXPANSION_PROB_HET] [--gangstr-expansion-prob-hom 441 [--gangstr-expansion-prob-het GANGSTR_EXPANSION_PROB_HET]
445 GANGSTR_EXPANSION_PROB_HOM] [--gangstr-expansion-prob-total GANGSTR_EXPANSION_PROB_TOTAL] 442 [--gangstr-expansion-prob-hom GANGSTR_EXPANSION_PROB_HOM]
446 [--gangstr-filter-span-only] 443 [--gangstr-expansion-prob-total GANGSTR_EXPANSION_PROB_TOTAL] [--gangstr-filter-span-only]
447 [--gangstr-filter-spanbound-only] [--gangstr-filter-badCI] [--gangstr-readlen GANGSTR_READLEN] 444 [--gangstr-filter-spanbound-only] [--gangstr-filter-badCI] [--gangstr-readlen GANGSTR_READLEN]
448 [--advntr-min-call-DP ADVNTR_MIN_CALL_DP] [--advntr-max-call-DP ADVNTR_MAX_CALL_DP] 445 [--advntr-min-call-DP ADVNTR_MIN_CALL_DP] [--advntr-max-call-DP ADVNTR_MAX_CALL_DP]
449 [--advntr-min-spanning ADVNTR_MIN_SPANNING] [--advntr-min-flanking ADVNTR_MIN_FLANKING] [--advntr-min-ML 446 [--advntr-min-spanning ADVNTR_MIN_SPANNING] [--advntr-min-flanking ADVNTR_MIN_FLANKING]
450 ADVNTR_MIN_ML] [--eh-min-ADFL EH_MIN_ADFL] [--eh-min-ADIR EH_MIN_ADIR] [--eh-min-ADSP EH_MIN_ADSP] 447 [--advntr-min-ML ADVNTR_MIN_ML] [--eh-min-ADFL EH_MIN_ADFL] [--eh-min-ADIR EH_MIN_ADIR]
451 [--eh-min-call-LC EH_MIN_CALL_LC] [--eh-max-call-LC EH_MAX_CALL_LC] [--popstr-min-call-DP POPSTR_MIN_CALL_DP] 448 [--eh-min-ADSP EH_MIN_ADSP] [--eh-min-call-LC EH_MIN_CALL_LC] [--eh-max-call-LC EH_MAX_CALL_LC]
452 [--popstr-max-call-DP POPSTR_MAX_CALL_DP] [--popstr-require-support POPSTR_REQUIRE_SUPPORT] 449 [--popstr-min-call-DP POPSTR_MIN_CALL_DP] [--popstr-max-call-DP POPSTR_MAX_CALL_DP]
453 [--num-records NUM_RECORDS] [--die-on-warning] [--verbose] [--version] 450 [--popstr-require-support POPSTR_REQUIRE_SUPPORT] [--num-records NUM_RECORDS] [--die-on-warning]
454 451 [--verbose] [--version]
455 options: 452
456 -h, --help show this help message and exit 453 options:
457 454 -h, --help show this help message and exit
458 Input/output: 455
459 --vcf VCF Input STR VCF file 456 Input/output:
460 --out OUT Prefix for output files 457 --vcf VCF Input STR VCF file
461 --zip Produce a bgzipped and tabix indexed output VCF 458 --out OUT Prefix for output files
462 --vcftype VCFTYPE ##!!## Name trh could not be loaded 459 --zip Produce a bgzipped and tabix indexed output VCF
463 460 --vcftype VCFTYPE Name of the genotyper that generated the input VCF
464 Locus-level filters (tool agnostic): 461
465 --min-locus-callrate MIN_LOCUS_CALLRATE 462 Locus-level filters (tool agnostic):
466 Minimum locus call rate 463 --min-locus-callrate MIN_LOCUS_CALLRATE
467 --min-locus-hwep MIN_LOCUS_HWEP 464 Minimum locus call rate
468 Filter loci failing HWE at this p-value threshold 465 --min-locus-hwep MIN_LOCUS_HWEP
469 --min-locus-het MIN_LOCUS_HET 466 Filter loci failing HWE at this p-value threshold
470 Minimum locus heterozygosity 467 --min-locus-het MIN_LOCUS_HET
471 --max-locus-het MAX_LOCUS_HET 468 Minimum locus heterozygosity
472 Maximum locus heterozygosity 469 --max-locus-het MAX_LOCUS_HET
473 --use-length Calculate per-locus stats (het, HWE) collapsing alleles by length 470 Maximum locus heterozygosity
474 --filter-regions FILTER_REGIONS 471 --use-length Calculate per-locus stats (het, HWE) collapsing alleles by length
475 Comma-separated list of BED files of regions to filter. Must be bgzipped and tabix indexed 472 --filter-regions FILTER_REGIONS
476 --filter-regions-names FILTER_REGIONS_NAMES 473 Comma-separated list of BED files of regions to filter. Must be bgzipped and tabix indexed
477 Comma-separated list of filter names for each BED filter file 474 --filter-regions-names FILTER_REGIONS_NAMES
478 --filter-hrun Filter STRs with long homopolymer runs. 475 Comma-separated list of filter names for each BED filter file
479 --drop-filtered Drop filtered records from output 476 --filter-hrun Filter STRs with long homopolymer runs.
480 477 --drop-filtered Drop filtered records from output
481 Call-level filters specific to HipSTR output: 478
482 --hipstr-max-call-flank-indel HIPSTR_MAX_CALL_FLANK_INDEL 479 Call-level filters specific to HipSTR output:
483 Maximum call flank indel rate 480 --hipstr-max-call-flank-indel HIPSTR_MAX_CALL_FLANK_INDEL
484 --hipstr-max-call-stutter HIPSTR_MAX_CALL_STUTTER 481 Maximum call flank indel rate
485 Maximum call stutter rate 482 --hipstr-max-call-stutter HIPSTR_MAX_CALL_STUTTER
486 --hipstr-min-supp-reads HIPSTR_MIN_SUPP_READS 483 Maximum call stutter rate
487 Minimum supporting reads for each allele 484 --hipstr-min-supp-reads HIPSTR_MIN_SUPP_READS
488 --hipstr-min-call-DP HIPSTR_MIN_CALL_DP 485 Minimum supporting reads for each allele
489 Minimum call coverage 486 --hipstr-min-call-DP HIPSTR_MIN_CALL_DP
490 --hipstr-max-call-DP HIPSTR_MAX_CALL_DP 487 Minimum call coverage
491 Maximum call coverage 488 --hipstr-max-call-DP HIPSTR_MAX_CALL_DP
492 --hipstr-min-call-Q HIPSTR_MIN_CALL_Q 489 Maximum call coverage
493 Minimum call quality score 490 --hipstr-min-call-Q HIPSTR_MIN_CALL_Q
494 491 Minimum call quality score
495 Call-level filters specific to GangSTR output: 492
496 --gangstr-min-call-DP GANGSTR_MIN_CALL_DP 493 Call-level filters specific to GangSTR output:
497 Minimum call coverage 494 --gangstr-min-call-DP GANGSTR_MIN_CALL_DP
498 --gangstr-max-call-DP GANGSTR_MAX_CALL_DP 495 Minimum call coverage
499 Maximum call coverage 496 --gangstr-max-call-DP GANGSTR_MAX_CALL_DP
500 --gangstr-min-call-Q GANGSTR_MIN_CALL_Q 497 Maximum call coverage
501 Minimum call quality score 498 --gangstr-min-call-Q GANGSTR_MIN_CALL_Q
502 --gangstr-expansion-prob-het GANGSTR_EXPANSION_PROB_HET 499 Minimum call quality score
503 Expansion prob-value threshold. Filters calls with probability of heterozygous expansion less than this 500 --gangstr-expansion-prob-het GANGSTR_EXPANSION_PROB_HET
504 --gangstr-expansion-prob-hom GANGSTR_EXPANSION_PROB_HOM 501 Expansion prob-value threshold. Filters calls with probability of heterozygous expansion less
505 Expansion prob-value threshold. Filters calls with probability of homozygous expansion less than this 502 than this
506 --gangstr-expansion-prob-total GANGSTR_EXPANSION_PROB_TOTAL 503 --gangstr-expansion-prob-hom GANGSTR_EXPANSION_PROB_HOM
507 Expansion prob-value threshold. Filters calls with probability of total expansion less than this 504 Expansion prob-value threshold. Filters calls with probability of homozygous expansion less
508 --gangstr-filter-span-only 505 than this
509 Filter out all calls that only have spanning read support 506 --gangstr-expansion-prob-total GANGSTR_EXPANSION_PROB_TOTAL
510 --gangstr-filter-spanbound-only 507 Expansion prob-value threshold. Filters calls with probability of total expansion less than
511 Filter out all reads except spanning and bounding 508 this
512 --gangstr-filter-badCI 509 --gangstr-filter-span-only
513 Filter regions where the ML estimate is not in the CI 510 Filter out all calls that only have spanning read support
514 --gangstr-readlen GANGSTR_READLEN 511 --gangstr-filter-spanbound-only
515 Read length used (bp). Required if using --require-support 512 Filter out all reads except spanning and bounding
516 513 --gangstr-filter-badCI
517 Call-level filters specific to adVNTR output: 514 Filter regions where the ML estimate is not in the CI
518 --advntr-min-call-DP ADVNTR_MIN_CALL_DP 515 --gangstr-readlen GANGSTR_READLEN
519 Minimum call coverage 516 Read length used (bp). Required if using --require-support
520 --advntr-max-call-DP ADVNTR_MAX_CALL_DP 517
521 Maximum call coverage 518 Call-level filters specific to adVNTR output:
522 --advntr-min-spanning ADVNTR_MIN_SPANNING 519 --advntr-min-call-DP ADVNTR_MIN_CALL_DP
523 Minimum spanning read count (SR field) 520 Minimum call coverage
524 --advntr-min-flanking ADVNTR_MIN_FLANKING 521 --advntr-max-call-DP ADVNTR_MAX_CALL_DP
525 Minimum flanking read count (FR field) 522 Maximum call coverage
526 --advntr-min-ML ADVNTR_MIN_ML 523 --advntr-min-spanning ADVNTR_MIN_SPANNING
527 Minimum value of maximum likelihood (ML field) 524 Minimum spanning read count (SR field)
528 525 --advntr-min-flanking ADVNTR_MIN_FLANKING
529 Call-level filters specific to ExpansionHunter output: 526 Minimum flanking read count (FR field)
530 --eh-min-ADFL EH_MIN_ADFL 527 --advntr-min-ML ADVNTR_MIN_ML
531 Minimum number of flanking reads consistent with the allele 528 Minimum value of maximum likelihood (ML field)
532 --eh-min-ADIR EH_MIN_ADIR 529
533 Minimum number of in-repeat reads consistent with the allele 530 Call-level filters specific to ExpansionHunter output:
534 --eh-min-ADSP EH_MIN_ADSP 531 --eh-min-ADFL EH_MIN_ADFL
535 Minimum number of spanning reads consistent with the allele 532 Minimum number of flanking reads consistent with the allele
536 --eh-min-call-LC EH_MIN_CALL_LC 533 --eh-min-ADIR EH_MIN_ADIR
537 Minimum call coverage 534 Minimum number of in-repeat reads consistent with the allele
538 --eh-max-call-LC EH_MAX_CALL_LC 535 --eh-min-ADSP EH_MIN_ADSP
539 Maximum call coverage 536 Minimum number of spanning reads consistent with the allele
540 537 --eh-min-call-LC EH_MIN_CALL_LC
541 Call-level filters specific to PopSTR output: 538 Minimum call coverage
542 --popstr-min-call-DP POPSTR_MIN_CALL_DP 539 --eh-max-call-LC EH_MAX_CALL_LC
543 Minimum call coverage 540 Maximum call coverage
544 --popstr-max-call-DP POPSTR_MAX_CALL_DP 541
545 Maximum call coverage 542 Call-level filters specific to PopSTR output:
546 --popstr-require-support POPSTR_REQUIRE_SUPPORT 543 --popstr-min-call-DP POPSTR_MIN_CALL_DP
547 Require each allele call to have at least n supporting reads 544 Minimum call coverage
548 545 --popstr-max-call-DP POPSTR_MAX_CALL_DP
549 Debugging parameters: 546 Maximum call coverage
550 --num-records NUM_RECORDS 547 --popstr-require-support POPSTR_REQUIRE_SUPPORT
551 Only process this many records 548 Require each allele call to have at least n supporting reads
552 --die-on-warning Quit if a record can't be parsed 549
553 --verbose Print out extra info 550 Debugging parameters:
554 551 --num-records NUM_RECORDS
555 Version: 552 Only process this many records
556 --version show program's version number and exit 553 --die-on-warning Quit if a record can't be parsed
554 --verbose Print out extra info
555
556 Version:
557 --version show program's version number and exit
557 </help> 558 </help>
558 559
559 560
560 <citations> 561 <citations>
561 <citation type="bibtex">@misc{TRTools: a toolkit for genome-wide analysis of tandem repeats, 562 <citation type="bibtex">@misc{TRTools: a toolkit for genome-wide analysis of tandem repeats,