miga-base 0.7.26.3 → 1.0.0.sr1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (105) hide show
  1. checksums.yaml +4 -4
  2. data/lib/miga/_data/aai-intax.blast.tsv.gz +0 -0
  3. data/lib/miga/_data/aai-intax.diamond.tsv.gz +0 -0
  4. data/lib/miga/_data/aai-novel.blast.tsv.gz +0 -0
  5. data/lib/miga/_data/aai-novel.diamond.tsv.gz +0 -0
  6. data/lib/miga/cli/action/doctor.rb +50 -19
  7. data/lib/miga/cli/action/doctor/base.rb +20 -18
  8. data/lib/miga/cli/action/init.rb +11 -7
  9. data/lib/miga/cli/action/init/files_helper.rb +1 -0
  10. data/lib/miga/cli/action/ncbi_get.rb +3 -3
  11. data/lib/miga/cli/action/tax_dist.rb +2 -2
  12. data/lib/miga/cli/action/wf.rb +5 -4
  13. data/lib/miga/daemon.rb +11 -4
  14. data/lib/miga/dataset/result.rb +10 -6
  15. data/lib/miga/json.rb +1 -2
  16. data/lib/miga/metadata.rb +5 -1
  17. data/lib/miga/parallel.rb +11 -6
  18. data/lib/miga/project.rb +8 -8
  19. data/lib/miga/project/base.rb +4 -4
  20. data/lib/miga/project/result.rb +2 -2
  21. data/lib/miga/sqlite.rb +7 -0
  22. data/lib/miga/version.rb +23 -9
  23. data/scripts/aai_distances.bash +16 -18
  24. data/scripts/ani_distances.bash +16 -17
  25. data/scripts/assembly.bash +31 -16
  26. data/scripts/haai_distances.bash +3 -27
  27. data/scripts/miga.bash +6 -4
  28. data/scripts/p.bash +1 -1
  29. data/scripts/read_quality.bash +9 -18
  30. data/scripts/trimmed_fasta.bash +14 -30
  31. data/scripts/trimmed_reads.bash +36 -36
  32. data/test/parallel_test.rb +31 -0
  33. data/test/project_test.rb +2 -1
  34. data/utils/distance/commands.rb +1 -0
  35. data/utils/distance/runner.rb +2 -4
  36. data/utils/enveomics/Manifest/Tasks/fasta.json +39 -3
  37. data/utils/enveomics/Manifest/Tasks/fastq.json +50 -2
  38. data/utils/enveomics/Manifest/Tasks/mapping.json +70 -0
  39. data/utils/enveomics/Manifest/Tasks/other.json +77 -0
  40. data/utils/enveomics/Manifest/Tasks/sequence-identity.json +138 -1
  41. data/utils/enveomics/Manifest/categories.json +13 -4
  42. data/utils/enveomics/Scripts/Aln.cat.rb +206 -148
  43. data/utils/enveomics/Scripts/FastA.N50.pl +33 -29
  44. data/utils/enveomics/Scripts/FastA.fragment.rb +69 -61
  45. data/utils/enveomics/Scripts/FastA.sample.rb +61 -46
  46. data/utils/enveomics/Scripts/FastA.toFastQ.rb +69 -0
  47. data/utils/enveomics/Scripts/FastQ.maskQual.rb +89 -0
  48. data/utils/enveomics/Scripts/FastQ.tag.rb +59 -52
  49. data/utils/enveomics/Scripts/SRA.download.bash +6 -8
  50. data/utils/enveomics/Scripts/Table.prefScore.R +60 -0
  51. data/utils/enveomics/Scripts/aai.rb +3 -2
  52. data/utils/enveomics/Scripts/anir.rb +137 -0
  53. data/utils/enveomics/Scripts/lib/enveomics_rb/anir.rb +293 -0
  54. data/utils/enveomics/Scripts/lib/enveomics_rb/bm_set.rb +175 -0
  55. data/utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb +17 -17
  56. data/utils/enveomics/Scripts/lib/enveomics_rb/errors.rb +17 -0
  57. data/utils/enveomics/Scripts/lib/enveomics_rb/gmm_em.rb +30 -0
  58. data/utils/enveomics/Scripts/lib/enveomics_rb/match.rb +63 -0
  59. data/utils/enveomics/Scripts/lib/enveomics_rb/rbm.rb +49 -0
  60. data/utils/enveomics/Scripts/lib/enveomics_rb/stats.rb +3 -0
  61. data/utils/enveomics/Scripts/lib/enveomics_rb/stats/rand.rb +31 -0
  62. data/utils/enveomics/Scripts/lib/enveomics_rb/stats/sample.rb +152 -0
  63. data/utils/enveomics/Scripts/lib/enveomics_rb/utils.rb +73 -0
  64. data/utils/enveomics/Scripts/rbm-legacy.rb +172 -0
  65. data/utils/enveomics/Scripts/rbm.rb +87 -133
  66. data/utils/enveomics/Scripts/sam.filter.rb +148 -0
  67. data/utils/enveomics/enveomics.R/DESCRIPTION +2 -2
  68. data/utils/enveomics/enveomics.R/NAMESPACE +1 -1
  69. data/utils/enveomics/enveomics.R/R/prefscore.R +79 -0
  70. data/utils/enveomics/enveomics.R/R/utils.R +30 -0
  71. data/utils/enveomics/enveomics.R/README.md +1 -0
  72. data/utils/enveomics/enveomics.R/man/cash-enve.GrowthCurve-method.Rd +0 -1
  73. data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2-method.Rd +0 -1
  74. data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2.Peak-method.Rd +0 -1
  75. data/utils/enveomics/enveomics.R/man/enve.__tribs.Rd +10 -2
  76. data/utils/enveomics/enveomics.R/man/enve.barplot.Rd +16 -4
  77. data/utils/enveomics/enveomics.R/man/enve.cliopts.Rd +13 -3
  78. data/utils/enveomics/enveomics.R/man/enve.df2dist.Rd +8 -2
  79. data/utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd +8 -2
  80. data/utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd +9 -2
  81. data/utils/enveomics/enveomics.R/man/enve.growthcurve.Rd +13 -5
  82. data/utils/enveomics/enveomics.R/man/enve.prefscore.Rd +50 -0
  83. data/utils/enveomics/enveomics.R/man/enve.prune.dist.Rd +9 -2
  84. data/utils/enveomics/enveomics.R/man/enve.recplot.Rd +23 -6
  85. data/utils/enveomics/enveomics.R/man/enve.recplot2.Rd +13 -4
  86. data/utils/enveomics/enveomics.R/man/enve.recplot2.compareIdentities.Rd +8 -2
  87. data/utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd +7 -2
  88. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mow_one.Rd +14 -3
  89. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.em.Rd +10 -2
  90. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.emauto.Rd +8 -2
  91. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.mower.Rd +17 -9
  92. data/utils/enveomics/enveomics.R/man/enve.recplot2.windowDepthThreshold.Rd +6 -2
  93. data/utils/enveomics/enveomics.R/man/enve.selvector.Rd +23 -0
  94. data/utils/enveomics/enveomics.R/man/enve.tribs.Rd +14 -5
  95. data/utils/enveomics/enveomics.R/man/plot.enve.GrowthCurve.Rd +19 -4
  96. data/utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd +11 -3
  97. data/utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd +11 -4
  98. data/utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd +26 -12
  99. data/utils/multitrim/Multitrim How-To.pdf +0 -0
  100. data/utils/multitrim/README.md +67 -0
  101. data/utils/multitrim/multitrim.py +1555 -0
  102. data/utils/multitrim/multitrim.yml +13 -0
  103. data/utils/requirements.txt +4 -3
  104. metadata +33 -6
  105. data/utils/enveomics/Scripts/lib/enveomics_rb/stat.rb +0 -30
@@ -0,0 +1,13 @@
1
+ name: multitrim
2
+ dependencies:
3
+ - faqcs
4
+ - falco
5
+ - seqtk
6
+ - fastp
7
+ - pigz
8
+ - multitrim
9
+
10
+ channels:
11
+ - conda-forge
12
+ - bioconda
13
+ - kgerhardt
@@ -13,9 +13,10 @@ Prodigal prodigal http://prodigal.ornl.gov
13
13
  MCL mcl http://micans.org/mcl/
14
14
  Barrnap barrnap http://www.vicbioinformatics.com/software.barrnap.shtml
15
15
  IDBA (reads) idba_ud http://i.cs.hku.hk/~alse/hkubrg/projects/idba
16
- Scythe (reads) scythe https://github.com/vsbuffalo/scythe Required version: 0.991+
17
- FastQC (reads) fastqc http://www.bioinformatics.babraham.ac.uk/projects/fastqc
18
- SolexaQA++ (reads) SolexaQA++ http://solexaqa.sourceforge.net Required version: v3.1.3+
16
+ FaQCs (reads) FaQCs https://github.com/LANL-Bioinformatics/FaQCs
17
+ Falco (reads) falco https://github.com/smithlabcode/falco
18
+ Seqtk (reads) seqtk https://github.com/lh3/seqtk
19
+ Fastp (reads) fastp https://github.com/OpenGene/fastp
19
20
  OpenJDK (rdp) java https://adoptopenjdk.net/ Any Java VM would work
20
21
  MyTaxa (mytaxa) MyTaxa http://enve-omics.ce.gatech.edu/mytaxa
21
22
  Krona (mytaxa) ktImportText https://github.com/marbl/Krona/wiki
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: miga-base
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.7.26.3
4
+ version: 1.0.0.sr1
5
5
  platform: ruby
6
6
  authors:
7
7
  - Luis M. Rodriguez-R
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2021-03-11 00:00:00.000000000 Z
11
+ date: 2021-04-12 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: daemons
@@ -110,8 +110,12 @@ files:
110
110
  - lib/miga.rb
111
111
  - lib/miga/_data/aai-intax-blast.tsv.gz
112
112
  - lib/miga/_data/aai-intax-diamond.tsv.gz
113
+ - lib/miga/_data/aai-intax.blast.tsv.gz
114
+ - lib/miga/_data/aai-intax.diamond.tsv.gz
113
115
  - lib/miga/_data/aai-novel-blast.tsv.gz
114
116
  - lib/miga/_data/aai-novel-diamond.tsv.gz
117
+ - lib/miga/_data/aai-novel.blast.tsv.gz
118
+ - lib/miga/_data/aai-novel.diamond.tsv.gz
115
119
  - lib/miga/cli.rb
116
120
  - lib/miga/cli/action.rb
117
121
  - lib/miga/cli/action/about.rb
@@ -241,6 +245,7 @@ files:
241
245
  - test/lair_test.rb
242
246
  - test/metadata_test.rb
243
247
  - test/net_test.rb
248
+ - test/parallel_test.rb
244
249
  - test/project_test.rb
245
250
  - test/remote_dataset_test.rb
246
251
  - test/result_stats_test.rb
@@ -375,9 +380,11 @@ files:
375
380
  - utils/enveomics/Scripts/FastA.split.rb
376
381
  - utils/enveomics/Scripts/FastA.subsample.pl
377
382
  - utils/enveomics/Scripts/FastA.tag.rb
383
+ - utils/enveomics/Scripts/FastA.toFastQ.rb
378
384
  - utils/enveomics/Scripts/FastA.wrap.rb
379
385
  - utils/enveomics/Scripts/FastQ.filter.pl
380
386
  - utils/enveomics/Scripts/FastQ.interpose.pl
387
+ - utils/enveomics/Scripts/FastQ.maskQual.rb
381
388
  - utils/enveomics/Scripts/FastQ.offset.pl
382
389
  - utils/enveomics/Scripts/FastQ.split.pl
383
390
  - utils/enveomics/Scripts/FastQ.tag.rb
@@ -406,6 +413,7 @@ files:
406
413
  - utils/enveomics/Scripts/Table.df2dist.R
407
414
  - utils/enveomics/Scripts/Table.filter.pl
408
415
  - utils/enveomics/Scripts/Table.merge.pl
416
+ - utils/enveomics/Scripts/Table.prefScore.R
409
417
  - utils/enveomics/Scripts/Table.replace.rb
410
418
  - utils/enveomics/Scripts/Table.round.rb
411
419
  - utils/enveomics/Scripts/Table.split.pl
@@ -414,18 +422,28 @@ files:
414
422
  - utils/enveomics/Scripts/VCF.SNPs.rb
415
423
  - utils/enveomics/Scripts/aai.rb
416
424
  - utils/enveomics/Scripts/ani.rb
425
+ - utils/enveomics/Scripts/anir.rb
417
426
  - utils/enveomics/Scripts/clust.rand.rb
418
427
  - utils/enveomics/Scripts/gi2tax.rb
419
428
  - utils/enveomics/Scripts/in_silico_GA_GI.pl
420
429
  - utils/enveomics/Scripts/lib/data/dupont_2012_essential.hmm.gz
421
430
  - utils/enveomics/Scripts/lib/data/lee_2019_essential.hmm.gz
422
431
  - utils/enveomics/Scripts/lib/enveomics.R
432
+ - utils/enveomics/Scripts/lib/enveomics_rb/anir.rb
433
+ - utils/enveomics/Scripts/lib/enveomics_rb/bm_set.rb
423
434
  - utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb
435
+ - utils/enveomics/Scripts/lib/enveomics_rb/errors.rb
436
+ - utils/enveomics/Scripts/lib/enveomics_rb/gmm_em.rb
424
437
  - utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb
438
+ - utils/enveomics/Scripts/lib/enveomics_rb/match.rb
425
439
  - utils/enveomics/Scripts/lib/enveomics_rb/og.rb
440
+ - utils/enveomics/Scripts/lib/enveomics_rb/rbm.rb
426
441
  - utils/enveomics/Scripts/lib/enveomics_rb/remote_data.rb
427
442
  - utils/enveomics/Scripts/lib/enveomics_rb/seq_range.rb
428
- - utils/enveomics/Scripts/lib/enveomics_rb/stat.rb
443
+ - utils/enveomics/Scripts/lib/enveomics_rb/stats.rb
444
+ - utils/enveomics/Scripts/lib/enveomics_rb/stats/rand.rb
445
+ - utils/enveomics/Scripts/lib/enveomics_rb/stats/sample.rb
446
+ - utils/enveomics/Scripts/lib/enveomics_rb/utils.rb
429
447
  - utils/enveomics/Scripts/lib/enveomics_rb/vcf.rb
430
448
  - utils/enveomics/Scripts/ogs.annotate.rb
431
449
  - utils/enveomics/Scripts/ogs.core-pan.rb
@@ -433,7 +451,9 @@ files:
433
451
  - utils/enveomics/Scripts/ogs.mcl.rb
434
452
  - utils/enveomics/Scripts/ogs.rb
435
453
  - utils/enveomics/Scripts/ogs.stats.rb
454
+ - utils/enveomics/Scripts/rbm-legacy.rb
436
455
  - utils/enveomics/Scripts/rbm.rb
456
+ - utils/enveomics/Scripts/sam.filter.rb
437
457
  - utils/enveomics/Tests/Makefile
438
458
  - utils/enveomics/Tests/Mgen_M2288.faa
439
459
  - utils/enveomics/Tests/Mgen_M2288.fna
@@ -471,6 +491,7 @@ files:
471
491
  - utils/enveomics/enveomics.R/R/cliopts.R
472
492
  - utils/enveomics/enveomics.R/R/df2dist.R
473
493
  - utils/enveomics/enveomics.R/R/growthcurve.R
494
+ - utils/enveomics/enveomics.R/R/prefscore.R
474
495
  - utils/enveomics/enveomics.R/R/recplot.R
475
496
  - utils/enveomics/enveomics.R/R/recplot2.R
476
497
  - utils/enveomics/enveomics.R/R/tribs.R
@@ -496,6 +517,7 @@ files:
496
517
  - utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd
497
518
  - utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd
498
519
  - utils/enveomics/enveomics.R/man/enve.growthcurve.Rd
520
+ - utils/enveomics/enveomics.R/man/enve.prefscore.Rd
499
521
  - utils/enveomics/enveomics.R/man/enve.prune.dist.Rd
500
522
  - utils/enveomics/enveomics.R/man/enve.recplot.Rd
501
523
  - utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd
@@ -521,6 +543,7 @@ files:
521
543
  - utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd
522
544
  - utils/enveomics/enveomics.R/man/enve.recplot2.seqdepth.Rd
523
545
  - utils/enveomics/enveomics.R/man/enve.recplot2.windowDepthThreshold.Rd
546
+ - utils/enveomics/enveomics.R/man/enve.selvector.Rd
524
547
  - utils/enveomics/enveomics.R/man/enve.tribs.Rd
525
548
  - utils/enveomics/enveomics.R/man/enve.tribs.test.Rd
526
549
  - utils/enveomics/enveomics.R/man/enve.truncate.Rd
@@ -537,6 +560,10 @@ files:
537
560
  - utils/enveomics/manifest.json
538
561
  - utils/find-medoid.R
539
562
  - utils/index_metadata.rb
563
+ - utils/multitrim/Multitrim How-To.pdf
564
+ - utils/multitrim/README.md
565
+ - utils/multitrim/multitrim.py
566
+ - utils/multitrim/multitrim.yml
540
567
  - utils/mytaxa_scan.R
541
568
  - utils/mytaxa_scan.rb
542
569
  - utils/plot-taxdist.R
@@ -572,11 +599,11 @@ required_ruby_version: !ruby/object:Gem::Requirement
572
599
  version: '2.3'
573
600
  required_rubygems_version: !ruby/object:Gem::Requirement
574
601
  requirements:
575
- - - ">="
602
+ - - ">"
576
603
  - !ruby/object:Gem::Version
577
- version: '0'
604
+ version: 1.3.1
578
605
  requirements: []
579
- rubygems_version: 3.1.4
606
+ rubygems_version: 3.1.6
580
607
  signing_key:
581
608
  specification_version: 4
582
609
  summary: MiGA
@@ -1,30 +0,0 @@
1
-
2
- module Enve
3
- class Stat
4
- # Generates a random number from the +dist+ distribution with +params+
5
- # parameters. This is simply a wrapper to the r_* functions below.
6
- def self.rand(dist=:unif, *params)
7
- send("r_#{dist}", *params)
8
- end
9
-
10
- # Generates a random number from the uniform distribution between +min+ and
11
- # +max+. By default generates random numbers between 0.0 and 1.0.
12
- def self.r_unif(min=0.0, max=1.0)
13
- min + (max-min)*Random::rand
14
- end
15
-
16
- # Generates a random number from the geometric distribution with support
17
- # {0, 1, 2, ...} and probability of success +p+.
18
- def self.r_geom(p)
19
- (Math::log(1.0 - rand)/Math::log(1.0-p) - 1.0).ceil
20
- end
21
-
22
- # Generates a random number from the shifted geometric distribution with
23
- # support {1, 2, 3, ...} and probability of success +p+.
24
- def self.r_sgeom(p)
25
- (Math::log(1.0 - rand)/Math::log(1.0-p)).ceil
26
- end
27
-
28
- end
29
- end
30
-