miga-base 1.2.15.2 → 1.2.15.4

Sign up to get free protection for your applications and to get access to all the features.
Files changed (306) hide show
  1. checksums.yaml +4 -4
  2. data/lib/miga/cli/action/download/gtdb.rb +4 -1
  3. data/lib/miga/cli/action/gtdb_get.rb +4 -0
  4. data/lib/miga/daemon.rb +4 -1
  5. data/lib/miga/lair.rb +6 -4
  6. data/lib/miga/remote_dataset/download.rb +3 -2
  7. data/lib/miga/remote_dataset.rb +25 -7
  8. data/lib/miga/taxonomy.rb +6 -0
  9. data/lib/miga/version.rb +2 -2
  10. metadata +6 -302
  11. data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Archaea_SCG.hmm +0 -41964
  12. data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Bacteria_SCG.hmm +0 -32439
  13. data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Complete_SCG_DB.hmm +0 -62056
  14. data/utils/FastAAI/FastAAI +0 -3659
  15. data/utils/FastAAI/FastAAI-legacy/FastAAI +0 -1336
  16. data/utils/FastAAI/FastAAI-legacy/kAAI_v1.0_virus.py +0 -1296
  17. data/utils/FastAAI/README.md +0 -84
  18. data/utils/enveomics/Docs/recplot2.md +0 -244
  19. data/utils/enveomics/Examples/aai-matrix.bash +0 -66
  20. data/utils/enveomics/Examples/ani-matrix.bash +0 -66
  21. data/utils/enveomics/Examples/essential-phylogeny.bash +0 -105
  22. data/utils/enveomics/Examples/unus-genome-phylogeny.bash +0 -100
  23. data/utils/enveomics/LICENSE.txt +0 -73
  24. data/utils/enveomics/Makefile +0 -52
  25. data/utils/enveomics/Manifest/Tasks/aasubs.json +0 -103
  26. data/utils/enveomics/Manifest/Tasks/blasttab.json +0 -790
  27. data/utils/enveomics/Manifest/Tasks/distances.json +0 -161
  28. data/utils/enveomics/Manifest/Tasks/fasta.json +0 -802
  29. data/utils/enveomics/Manifest/Tasks/fastq.json +0 -291
  30. data/utils/enveomics/Manifest/Tasks/graphics.json +0 -126
  31. data/utils/enveomics/Manifest/Tasks/mapping.json +0 -137
  32. data/utils/enveomics/Manifest/Tasks/ogs.json +0 -382
  33. data/utils/enveomics/Manifest/Tasks/other.json +0 -906
  34. data/utils/enveomics/Manifest/Tasks/remote.json +0 -355
  35. data/utils/enveomics/Manifest/Tasks/sequence-identity.json +0 -650
  36. data/utils/enveomics/Manifest/Tasks/tables.json +0 -308
  37. data/utils/enveomics/Manifest/Tasks/trees.json +0 -68
  38. data/utils/enveomics/Manifest/Tasks/variants.json +0 -111
  39. data/utils/enveomics/Manifest/categories.json +0 -165
  40. data/utils/enveomics/Manifest/examples.json +0 -162
  41. data/utils/enveomics/Manifest/tasks.json +0 -4
  42. data/utils/enveomics/Pipelines/assembly.pbs/CONFIG.mock.bash +0 -69
  43. data/utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl +0 -1
  44. data/utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl +0 -1
  45. data/utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl +0 -1
  46. data/utils/enveomics/Pipelines/assembly.pbs/README.md +0 -189
  47. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-2.bash +0 -112
  48. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-3.bash +0 -23
  49. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-4.bash +0 -44
  50. data/utils/enveomics/Pipelines/assembly.pbs/RUNME.bash +0 -50
  51. data/utils/enveomics/Pipelines/assembly.pbs/kSelector.R +0 -37
  52. data/utils/enveomics/Pipelines/assembly.pbs/newbler.pbs +0 -68
  53. data/utils/enveomics/Pipelines/assembly.pbs/newbler_preparator.pl +0 -49
  54. data/utils/enveomics/Pipelines/assembly.pbs/soap.pbs +0 -80
  55. data/utils/enveomics/Pipelines/assembly.pbs/stats.pbs +0 -57
  56. data/utils/enveomics/Pipelines/assembly.pbs/velvet.pbs +0 -63
  57. data/utils/enveomics/Pipelines/blast.pbs/01.pbs.bash +0 -38
  58. data/utils/enveomics/Pipelines/blast.pbs/02.pbs.bash +0 -73
  59. data/utils/enveomics/Pipelines/blast.pbs/03.pbs.bash +0 -21
  60. data/utils/enveomics/Pipelines/blast.pbs/BlastTab.recover_job.pl +0 -72
  61. data/utils/enveomics/Pipelines/blast.pbs/CONFIG.mock.bash +0 -98
  62. data/utils/enveomics/Pipelines/blast.pbs/FastA.split.pl +0 -1
  63. data/utils/enveomics/Pipelines/blast.pbs/README.md +0 -127
  64. data/utils/enveomics/Pipelines/blast.pbs/RUNME.bash +0 -109
  65. data/utils/enveomics/Pipelines/blast.pbs/TASK.check.bash +0 -128
  66. data/utils/enveomics/Pipelines/blast.pbs/TASK.dry.bash +0 -16
  67. data/utils/enveomics/Pipelines/blast.pbs/TASK.eo.bash +0 -22
  68. data/utils/enveomics/Pipelines/blast.pbs/TASK.pause.bash +0 -26
  69. data/utils/enveomics/Pipelines/blast.pbs/TASK.run.bash +0 -89
  70. data/utils/enveomics/Pipelines/blast.pbs/sentinel.pbs.bash +0 -29
  71. data/utils/enveomics/Pipelines/idba.pbs/README.md +0 -49
  72. data/utils/enveomics/Pipelines/idba.pbs/RUNME.bash +0 -95
  73. data/utils/enveomics/Pipelines/idba.pbs/run.pbs +0 -56
  74. data/utils/enveomics/Pipelines/trim.pbs/README.md +0 -54
  75. data/utils/enveomics/Pipelines/trim.pbs/RUNME.bash +0 -70
  76. data/utils/enveomics/Pipelines/trim.pbs/run.pbs +0 -130
  77. data/utils/enveomics/README.md +0 -42
  78. data/utils/enveomics/Scripts/AAsubs.log2ratio.rb +0 -171
  79. data/utils/enveomics/Scripts/Aln.cat.rb +0 -221
  80. data/utils/enveomics/Scripts/Aln.convert.pl +0 -35
  81. data/utils/enveomics/Scripts/AlphaDiversity.pl +0 -152
  82. data/utils/enveomics/Scripts/BedGraph.tad.rb +0 -93
  83. data/utils/enveomics/Scripts/BedGraph.window.rb +0 -71
  84. data/utils/enveomics/Scripts/BlastPairwise.AAsubs.pl +0 -102
  85. data/utils/enveomics/Scripts/BlastTab.addlen.rb +0 -63
  86. data/utils/enveomics/Scripts/BlastTab.advance.bash +0 -48
  87. data/utils/enveomics/Scripts/BlastTab.best_hit_sorted.pl +0 -55
  88. data/utils/enveomics/Scripts/BlastTab.catsbj.pl +0 -104
  89. data/utils/enveomics/Scripts/BlastTab.cogCat.rb +0 -76
  90. data/utils/enveomics/Scripts/BlastTab.filter.pl +0 -47
  91. data/utils/enveomics/Scripts/BlastTab.kegg_pep2path_rest.pl +0 -194
  92. data/utils/enveomics/Scripts/BlastTab.metaxaPrep.pl +0 -104
  93. data/utils/enveomics/Scripts/BlastTab.pairedHits.rb +0 -157
  94. data/utils/enveomics/Scripts/BlastTab.recplot2.R +0 -48
  95. data/utils/enveomics/Scripts/BlastTab.seqdepth.pl +0 -86
  96. data/utils/enveomics/Scripts/BlastTab.seqdepth_ZIP.pl +0 -119
  97. data/utils/enveomics/Scripts/BlastTab.seqdepth_nomedian.pl +0 -86
  98. data/utils/enveomics/Scripts/BlastTab.subsample.pl +0 -47
  99. data/utils/enveomics/Scripts/BlastTab.sumPerHit.pl +0 -114
  100. data/utils/enveomics/Scripts/BlastTab.taxid2taxrank.pl +0 -90
  101. data/utils/enveomics/Scripts/BlastTab.topHits_sorted.rb +0 -123
  102. data/utils/enveomics/Scripts/Chao1.pl +0 -97
  103. data/utils/enveomics/Scripts/CharTable.classify.rb +0 -234
  104. data/utils/enveomics/Scripts/EBIseq2tax.rb +0 -83
  105. data/utils/enveomics/Scripts/FastA.N50.pl +0 -60
  106. data/utils/enveomics/Scripts/FastA.extract.rb +0 -152
  107. data/utils/enveomics/Scripts/FastA.filter.pl +0 -52
  108. data/utils/enveomics/Scripts/FastA.filterLen.pl +0 -28
  109. data/utils/enveomics/Scripts/FastA.filterN.pl +0 -60
  110. data/utils/enveomics/Scripts/FastA.fragment.rb +0 -100
  111. data/utils/enveomics/Scripts/FastA.gc.pl +0 -42
  112. data/utils/enveomics/Scripts/FastA.interpose.pl +0 -93
  113. data/utils/enveomics/Scripts/FastA.length.pl +0 -38
  114. data/utils/enveomics/Scripts/FastA.mask.rb +0 -89
  115. data/utils/enveomics/Scripts/FastA.per_file.pl +0 -36
  116. data/utils/enveomics/Scripts/FastA.qlen.pl +0 -57
  117. data/utils/enveomics/Scripts/FastA.rename.pl +0 -65
  118. data/utils/enveomics/Scripts/FastA.revcom.pl +0 -23
  119. data/utils/enveomics/Scripts/FastA.sample.rb +0 -98
  120. data/utils/enveomics/Scripts/FastA.slider.pl +0 -85
  121. data/utils/enveomics/Scripts/FastA.split.pl +0 -55
  122. data/utils/enveomics/Scripts/FastA.split.rb +0 -79
  123. data/utils/enveomics/Scripts/FastA.subsample.pl +0 -131
  124. data/utils/enveomics/Scripts/FastA.tag.rb +0 -65
  125. data/utils/enveomics/Scripts/FastA.toFastQ.rb +0 -69
  126. data/utils/enveomics/Scripts/FastA.wrap.rb +0 -48
  127. data/utils/enveomics/Scripts/FastQ.filter.pl +0 -54
  128. data/utils/enveomics/Scripts/FastQ.interpose.pl +0 -90
  129. data/utils/enveomics/Scripts/FastQ.maskQual.rb +0 -89
  130. data/utils/enveomics/Scripts/FastQ.offset.pl +0 -90
  131. data/utils/enveomics/Scripts/FastQ.split.pl +0 -53
  132. data/utils/enveomics/Scripts/FastQ.tag.rb +0 -70
  133. data/utils/enveomics/Scripts/FastQ.test-error.rb +0 -81
  134. data/utils/enveomics/Scripts/FastQ.toFastA.awk +0 -24
  135. data/utils/enveomics/Scripts/GFF.catsbj.pl +0 -127
  136. data/utils/enveomics/Scripts/GenBank.add_fields.rb +0 -84
  137. data/utils/enveomics/Scripts/HMM.essential.rb +0 -351
  138. data/utils/enveomics/Scripts/HMM.haai.rb +0 -168
  139. data/utils/enveomics/Scripts/HMMsearch.extractIds.rb +0 -83
  140. data/utils/enveomics/Scripts/JPlace.distances.rb +0 -88
  141. data/utils/enveomics/Scripts/JPlace.to_iToL.rb +0 -320
  142. data/utils/enveomics/Scripts/M5nr.getSequences.rb +0 -81
  143. data/utils/enveomics/Scripts/MeTaxa.distribution.pl +0 -198
  144. data/utils/enveomics/Scripts/MyTaxa.fragsByTax.pl +0 -35
  145. data/utils/enveomics/Scripts/MyTaxa.seq-taxrank.rb +0 -49
  146. data/utils/enveomics/Scripts/NCBIacc2tax.rb +0 -92
  147. data/utils/enveomics/Scripts/Newick.autoprune.R +0 -27
  148. data/utils/enveomics/Scripts/RAxML-EPA.to_iToL.pl +0 -228
  149. data/utils/enveomics/Scripts/RecPlot2.compareIdentities.R +0 -32
  150. data/utils/enveomics/Scripts/RefSeq.download.bash +0 -48
  151. data/utils/enveomics/Scripts/SRA.download.bash +0 -55
  152. data/utils/enveomics/Scripts/TRIBS.plot-test.R +0 -36
  153. data/utils/enveomics/Scripts/TRIBS.test.R +0 -39
  154. data/utils/enveomics/Scripts/Table.barplot.R +0 -31
  155. data/utils/enveomics/Scripts/Table.df2dist.R +0 -30
  156. data/utils/enveomics/Scripts/Table.filter.pl +0 -61
  157. data/utils/enveomics/Scripts/Table.merge.pl +0 -77
  158. data/utils/enveomics/Scripts/Table.prefScore.R +0 -60
  159. data/utils/enveomics/Scripts/Table.replace.rb +0 -69
  160. data/utils/enveomics/Scripts/Table.round.rb +0 -63
  161. data/utils/enveomics/Scripts/Table.split.pl +0 -57
  162. data/utils/enveomics/Scripts/Taxonomy.silva2ncbi.rb +0 -227
  163. data/utils/enveomics/Scripts/VCF.KaKs.rb +0 -147
  164. data/utils/enveomics/Scripts/VCF.SNPs.rb +0 -88
  165. data/utils/enveomics/Scripts/aai.rb +0 -421
  166. data/utils/enveomics/Scripts/ani.rb +0 -362
  167. data/utils/enveomics/Scripts/anir.rb +0 -137
  168. data/utils/enveomics/Scripts/clust.rand.rb +0 -102
  169. data/utils/enveomics/Scripts/gi2tax.rb +0 -103
  170. data/utils/enveomics/Scripts/in_silico_GA_GI.pl +0 -96
  171. data/utils/enveomics/Scripts/lib/data/dupont_2012_essential.hmm.gz +0 -0
  172. data/utils/enveomics/Scripts/lib/data/lee_2019_essential.hmm.gz +0 -0
  173. data/utils/enveomics/Scripts/lib/enveomics.R +0 -1
  174. data/utils/enveomics/Scripts/lib/enveomics_rb/anir.rb +0 -293
  175. data/utils/enveomics/Scripts/lib/enveomics_rb/bm_set.rb +0 -175
  176. data/utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb +0 -24
  177. data/utils/enveomics/Scripts/lib/enveomics_rb/errors.rb +0 -17
  178. data/utils/enveomics/Scripts/lib/enveomics_rb/gmm_em.rb +0 -30
  179. data/utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb +0 -253
  180. data/utils/enveomics/Scripts/lib/enveomics_rb/match.rb +0 -88
  181. data/utils/enveomics/Scripts/lib/enveomics_rb/og.rb +0 -182
  182. data/utils/enveomics/Scripts/lib/enveomics_rb/rbm.rb +0 -49
  183. data/utils/enveomics/Scripts/lib/enveomics_rb/remote_data.rb +0 -74
  184. data/utils/enveomics/Scripts/lib/enveomics_rb/seq_range.rb +0 -237
  185. data/utils/enveomics/Scripts/lib/enveomics_rb/stats/rand.rb +0 -31
  186. data/utils/enveomics/Scripts/lib/enveomics_rb/stats/sample.rb +0 -152
  187. data/utils/enveomics/Scripts/lib/enveomics_rb/stats.rb +0 -3
  188. data/utils/enveomics/Scripts/lib/enveomics_rb/utils.rb +0 -74
  189. data/utils/enveomics/Scripts/lib/enveomics_rb/vcf.rb +0 -135
  190. data/utils/enveomics/Scripts/ogs.annotate.rb +0 -88
  191. data/utils/enveomics/Scripts/ogs.core-pan.rb +0 -160
  192. data/utils/enveomics/Scripts/ogs.extract.rb +0 -125
  193. data/utils/enveomics/Scripts/ogs.mcl.rb +0 -186
  194. data/utils/enveomics/Scripts/ogs.rb +0 -104
  195. data/utils/enveomics/Scripts/ogs.stats.rb +0 -131
  196. data/utils/enveomics/Scripts/rbm-legacy.rb +0 -172
  197. data/utils/enveomics/Scripts/rbm.rb +0 -108
  198. data/utils/enveomics/Scripts/sam.filter.rb +0 -148
  199. data/utils/enveomics/Tests/Makefile +0 -10
  200. data/utils/enveomics/Tests/Mgen_M2288.faa +0 -3189
  201. data/utils/enveomics/Tests/Mgen_M2288.fna +0 -8282
  202. data/utils/enveomics/Tests/Mgen_M2321.fna +0 -8288
  203. data/utils/enveomics/Tests/Nequ_Kin4M.faa +0 -2970
  204. data/utils/enveomics/Tests/Xanthomonas_oryzae-PilA.tribs.Rdata +0 -0
  205. data/utils/enveomics/Tests/Xanthomonas_oryzae-PilA.txt +0 -7
  206. data/utils/enveomics/Tests/Xanthomonas_oryzae.aai-mat.tsv +0 -17
  207. data/utils/enveomics/Tests/Xanthomonas_oryzae.aai.tsv +0 -137
  208. data/utils/enveomics/Tests/a_mg.cds-go.blast.tsv +0 -123
  209. data/utils/enveomics/Tests/a_mg.reads-cds.blast.tsv +0 -200
  210. data/utils/enveomics/Tests/a_mg.reads-cds.counts.tsv +0 -55
  211. data/utils/enveomics/Tests/alkB.nwk +0 -1
  212. data/utils/enveomics/Tests/anthrax-cansnp-data.tsv +0 -13
  213. data/utils/enveomics/Tests/anthrax-cansnp-key.tsv +0 -17
  214. data/utils/enveomics/Tests/hiv1.faa +0 -59
  215. data/utils/enveomics/Tests/hiv1.fna +0 -134
  216. data/utils/enveomics/Tests/hiv2.faa +0 -70
  217. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv +0 -233
  218. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.lim +0 -1
  219. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.rec +0 -233
  220. data/utils/enveomics/Tests/phyla_counts.tsv +0 -10
  221. data/utils/enveomics/Tests/primate_lentivirus.ogs +0 -11
  222. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv1.rbm +0 -9
  223. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv2.rbm +0 -8
  224. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-siv.rbm +0 -6
  225. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-hiv2.rbm +0 -9
  226. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-siv.rbm +0 -6
  227. data/utils/enveomics/Tests/primate_lentivirus.rbm/siv-siv.rbm +0 -6
  228. data/utils/enveomics/build_enveomics_r.bash +0 -45
  229. data/utils/enveomics/enveomics.R/DESCRIPTION +0 -31
  230. data/utils/enveomics/enveomics.R/NAMESPACE +0 -39
  231. data/utils/enveomics/enveomics.R/R/autoprune.R +0 -155
  232. data/utils/enveomics/enveomics.R/R/barplot.R +0 -184
  233. data/utils/enveomics/enveomics.R/R/cliopts.R +0 -135
  234. data/utils/enveomics/enveomics.R/R/df2dist.R +0 -154
  235. data/utils/enveomics/enveomics.R/R/growthcurve.R +0 -331
  236. data/utils/enveomics/enveomics.R/R/prefscore.R +0 -79
  237. data/utils/enveomics/enveomics.R/R/recplot.R +0 -354
  238. data/utils/enveomics/enveomics.R/R/recplot2.R +0 -1631
  239. data/utils/enveomics/enveomics.R/R/tribs.R +0 -583
  240. data/utils/enveomics/enveomics.R/R/utils.R +0 -80
  241. data/utils/enveomics/enveomics.R/README.md +0 -81
  242. data/utils/enveomics/enveomics.R/data/growth.curves.rda +0 -0
  243. data/utils/enveomics/enveomics.R/data/phyla.counts.rda +0 -0
  244. data/utils/enveomics/enveomics.R/man/cash-enve.GrowthCurve-method.Rd +0 -16
  245. data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2-method.Rd +0 -16
  246. data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2.Peak-method.Rd +0 -16
  247. data/utils/enveomics/enveomics.R/man/enve.GrowthCurve-class.Rd +0 -25
  248. data/utils/enveomics/enveomics.R/man/enve.TRIBS-class.Rd +0 -46
  249. data/utils/enveomics/enveomics.R/man/enve.TRIBS.merge.Rd +0 -23
  250. data/utils/enveomics/enveomics.R/man/enve.TRIBStest-class.Rd +0 -47
  251. data/utils/enveomics/enveomics.R/man/enve.__prune.iter.Rd +0 -23
  252. data/utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd +0 -23
  253. data/utils/enveomics/enveomics.R/man/enve.__tribs.Rd +0 -40
  254. data/utils/enveomics/enveomics.R/man/enve.barplot.Rd +0 -103
  255. data/utils/enveomics/enveomics.R/man/enve.cliopts.Rd +0 -67
  256. data/utils/enveomics/enveomics.R/man/enve.col.alpha.Rd +0 -24
  257. data/utils/enveomics/enveomics.R/man/enve.col2alpha.Rd +0 -19
  258. data/utils/enveomics/enveomics.R/man/enve.df2dist.Rd +0 -45
  259. data/utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd +0 -44
  260. data/utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd +0 -47
  261. data/utils/enveomics/enveomics.R/man/enve.growthcurve.Rd +0 -75
  262. data/utils/enveomics/enveomics.R/man/enve.prefscore.Rd +0 -50
  263. data/utils/enveomics/enveomics.R/man/enve.prune.dist.Rd +0 -44
  264. data/utils/enveomics/enveomics.R/man/enve.recplot.Rd +0 -139
  265. data/utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd +0 -45
  266. data/utils/enveomics/enveomics.R/man/enve.recplot2.ANIr.Rd +0 -24
  267. data/utils/enveomics/enveomics.R/man/enve.recplot2.Rd +0 -77
  268. data/utils/enveomics/enveomics.R/man/enve.recplot2.__counts.Rd +0 -25
  269. data/utils/enveomics/enveomics.R/man/enve.recplot2.__peakHist.Rd +0 -21
  270. data/utils/enveomics/enveomics.R/man/enve.recplot2.__whichClosestPeak.Rd +0 -19
  271. data/utils/enveomics/enveomics.R/man/enve.recplot2.changeCutoff.Rd +0 -19
  272. data/utils/enveomics/enveomics.R/man/enve.recplot2.compareIdentities.Rd +0 -47
  273. data/utils/enveomics/enveomics.R/man/enve.recplot2.coordinates.Rd +0 -29
  274. data/utils/enveomics/enveomics.R/man/enve.recplot2.corePeak.Rd +0 -18
  275. data/utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd +0 -45
  276. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd +0 -36
  277. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_e.Rd +0 -19
  278. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_m.Rd +0 -19
  279. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__emauto_one.Rd +0 -27
  280. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mow_one.Rd +0 -52
  281. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mower.Rd +0 -17
  282. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.em.Rd +0 -51
  283. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.emauto.Rd +0 -43
  284. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.mower.Rd +0 -82
  285. data/utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd +0 -59
  286. data/utils/enveomics/enveomics.R/man/enve.recplot2.seqdepth.Rd +0 -27
  287. data/utils/enveomics/enveomics.R/man/enve.recplot2.windowDepthThreshold.Rd +0 -36
  288. data/utils/enveomics/enveomics.R/man/enve.selvector.Rd +0 -23
  289. data/utils/enveomics/enveomics.R/man/enve.tribs.Rd +0 -68
  290. data/utils/enveomics/enveomics.R/man/enve.tribs.test.Rd +0 -28
  291. data/utils/enveomics/enveomics.R/man/enve.truncate.Rd +0 -27
  292. data/utils/enveomics/enveomics.R/man/growth.curves.Rd +0 -14
  293. data/utils/enveomics/enveomics.R/man/phyla.counts.Rd +0 -13
  294. data/utils/enveomics/enveomics.R/man/plot.enve.GrowthCurve.Rd +0 -78
  295. data/utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd +0 -46
  296. data/utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd +0 -45
  297. data/utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd +0 -125
  298. data/utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd +0 -19
  299. data/utils/enveomics/enveomics.R/man/summary.enve.TRIBS.Rd +0 -19
  300. data/utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd +0 -19
  301. data/utils/enveomics/globals.mk +0 -8
  302. data/utils/enveomics/manifest.json +0 -9
  303. data/utils/multitrim/Multitrim How-To.pdf +0 -0
  304. data/utils/multitrim/README.md +0 -67
  305. data/utils/multitrim/multitrim.py +0 -1555
  306. data/utils/multitrim/multitrim.yml +0 -13
@@ -1,650 +0,0 @@
1
- {
2
- "tasks": [
3
- {
4
- "task": "aai.rb",
5
- "description": ["Calculates the Average Amino acid Identity between two",
6
- "genomes."],
7
- "help_arg": "--help",
8
- "see_also": ["ani.rb", "rbm.rb"],
9
- "cite": [
10
- ["Konstantinidis & Tiedje, 2005, JBac",
11
- "https://dx.doi.org/10.1128%2FJB.187.18.6258-6264.2005"],
12
- ["Altschul et al, 2000, JMB (BLAST)",
13
- "https://dx.doi.org/10.1016/S0022-2836(05)80360-2"],
14
- ["Kent WJ, 2002, Genome Res (BLAT)",
15
- "https://dx.doi.org/10.1101/gr.229202"],
16
- ["Buchfink B, Xie C, Huson D, 2015, Nat Meth (Diamond)",
17
- "https://dx.doi.org/10.1038/nmeth.3176"]
18
- ],
19
- "options": [
20
- {
21
- "name": "Sequence 1",
22
- "opt": "--seq1",
23
- "arg": "in_file",
24
- "mandatory": true,
25
- "description": "FastA file containing the genome 1 (proteins).",
26
- "note": ["Alternatively, you can supply the NCBI-acc of a genome",
27
- " (nucleotides) with the format ncbi:CP014272 instead of files."]
28
- },
29
- {
30
- "name": "Sequence 2",
31
- "opt": "--seq2",
32
- "arg": "in_file",
33
- "mandatory": true,
34
- "description": "FastA file containing the genome 2.",
35
- "note": ["Alternatively, you can supply the NCBI-acc of a genome",
36
- " (nucleotides) with the format ncbi:NC_004337 instead of files."]
37
- },
38
- {
39
- "name": "Length",
40
- "opt": "--len",
41
- "arg": "integer",
42
- "description": "Minimum alignment length (in aa).",
43
- "default": 0
44
- },
45
- {
46
- "name": "Length fraction",
47
- "opt": "--len-fraction",
48
- "arg": "float",
49
- "description": ["Minimum alignment length as a fraction of the",
50
- "shorter sequence (range 0-1)."],
51
- "default": 0.0
52
- },
53
- {
54
- "name": "Identity",
55
- "opt": "--id",
56
- "arg": "float",
57
- "description": "Minimum alignment identity (in %).",
58
- "default": 20.0
59
- },
60
- {
61
- "name": "Bit-score",
62
- "opt": "--bitscore",
63
- "arg": "float",
64
- "description": "Minimum bit score (in bits).",
65
- "default": 0.0
66
- },
67
- {
68
- "opt": "--hits",
69
- "arg": "float",
70
- "description": "Minimum number of hits.",
71
- "default": 50.0
72
- },
73
- {
74
- "name": "Nucleotides",
75
- "opt": "--nucl",
76
- "description": ["The input sequences are nucleotides (genes), not",
77
- "proteins."]
78
- },
79
- {
80
- "name": "Max ACTG",
81
- "opt": "--max-actg",
82
- "arg": "float",
83
- "default": 0.95,
84
- "description": ["Maximum fraction of ACTGN in the sequences before",
85
- "assuming nucleotides."]
86
- },
87
- {
88
- "name": "Executables",
89
- "opt": "--bin",
90
- "arg": "in_dir",
91
- "description": ["Path to the directory containing the binaries of",
92
- "the search program."]
93
- },
94
- {
95
- "opt": "--program",
96
- "arg": "select",
97
- "values": ["blast+","blast","blat","diamond"],
98
- "default": "blast+",
99
- "description": "Search program to be used.",
100
- "note": ["Make sure that you have installed the search program you",
101
- "want to use. If you have downloaded the program, but it's not",
102
- "installed, please use the Executables option above."]
103
- },
104
- {
105
- "opt": "--threads",
106
- "arg": "integer",
107
- "description": "Number of parallel threads to be used.",
108
- "default": 1
109
- },
110
- {
111
- "name": "SQLite3 DB",
112
- "opt": "--sqlite3",
113
- "arg": "out_file",
114
- "description": ["Path to the SQLite3 database to create (or update)",
115
- "with the results."]
116
- },
117
- {
118
- "name": "Name 1",
119
- "opt": "--name1",
120
- "arg": "string",
121
- "description": ["Name of Sequence 1 to use in SQLite3 DB. By default",
122
- "determined by filename."]
123
- },
124
- {
125
- "name": "Name 2",
126
- "opt": "--name2",
127
- "arg": "string",
128
- "description": ["Name of Sequence 2 to use in SQLite3 DB. By default",
129
- "determined by filename."]
130
- },
131
- {
132
- "name": "Don't save RBM",
133
- "opt": "--no-save-rbm",
134
- "description": ["Don't save the reciprocal best matches in the",
135
- "--sqlite3 database."]
136
- },
137
- {
138
- "opt": "--lookup-first",
139
- "description": ["Indicates if the AAI should be looked up first in",
140
- "the database. Requires SQLite3 DB, Auto, Name 1, and Name 2.",
141
- "Incompatible with Result, Tab, Out, and RBM."]
142
- },
143
- {
144
- "name": "Precision",
145
- "opt": "--dec",
146
- "arg": "integer",
147
- "default": 2,
148
- "description": "Decimal positions to report."
149
- },
150
- {
151
- "name": "RBM",
152
- "opt": "--rbm",
153
- "arg": "out_file",
154
- "description": "Saves a file with the reciprocal best matches."
155
- },
156
- {
157
- "opt": "--out",
158
- "arg": "out_file",
159
- "description": ["Saves a file describing the alignments used for",
160
- "two-way AAI."]
161
- },
162
- {
163
- "name": "Result",
164
- "opt": "--res",
165
- "arg": "out_file",
166
- "description": "Saves a file with the final results."
167
- },
168
- {
169
- "opt": "--tab",
170
- "arg": "out_file",
171
- "description": ["Saves a file with the final two-way results in a",
172
- "tab-delimited form. The columns are (in that order): AAI,",
173
- "standard deviation, proteins used, proteins in the smallest",
174
- "genome."]
175
- },
176
- {
177
- "opt": "--auto",
178
- "description": ["ONLY outputs the AAI value in STDOUT (or nothing,",
179
- "if calculation fails)."]
180
- },
181
- {
182
- "opt": "--quiet",
183
- "description": "Run quietly (no STDERR output)."
184
- }
185
- ]
186
- },
187
- {
188
- "task": "ani.rb",
189
- "description": ["Calculates the Average Nucleotide Identity between two",
190
- "genomes."],
191
- "help_arg": "--help",
192
- "see_also": ["aai.rb","rbm.rb","HMM.essential.rb"],
193
- "cite": [
194
- ["Konstantinidis & Tiedje, 2005, PNAS",
195
- "http://dx.doi.org/10.1073%2Fpnas.0409727102"],
196
- ["Altschul et al, 2000, JMB (BLAST)",
197
- "http://dx.doi.org/10.1016/S0022-2836(05)80360-2"],
198
- ["Kent WJ, 2002, Genome Res (BLAT)",
199
- "https://dx.doi.org/10.1101/gr.229202"]
200
- ],
201
- "options": [
202
- {
203
- "name": "Sequence 1",
204
- "opt": "--seq1",
205
- "arg": "in_file",
206
- "mandatory": true,
207
- "description": "FastA file containing the genome 1.",
208
- "note": ["Alternatively, you can supply an NCBI-acc with the format",
209
- "ncbi:CP014272 instead of files."]
210
- },
211
- {
212
- "name": "Sequence 2",
213
- "opt": "--seq2",
214
- "arg": "in_file",
215
- "mandatory": true,
216
- "description": "FastA file containing the genome 2.",
217
- "note": ["Alternatively, you can supply an NCBI-acc with the format",
218
- "ncbi:AE005174 instead of files."]
219
- },
220
- {
221
- "name": "Window",
222
- "opt": "--win",
223
- "arg": "integer",
224
- "description": "Window size in the ANI calculation (in bp).",
225
- "default": 1000
226
- },
227
- {
228
- "opt": "--step",
229
- "arg": "integer",
230
- "description": "Step size in the ANI calculation (in bp).",
231
- "default": 200
232
- },
233
- {
234
- "name": "Length",
235
- "opt": "--len",
236
- "arg": "integer",
237
- "description": "Minimum alignment length (in bp).",
238
- "default": 700
239
- },
240
- {
241
- "name": "Identity",
242
- "opt": "--id",
243
- "arg": "float",
244
- "description": "Minimum alignment identity (in %).",
245
- "default": 70.0
246
- },
247
- {
248
- "opt": "--hits",
249
- "arg": "integer",
250
- "description": "Minimum number of hits.",
251
- "default": 50
252
- },
253
- {
254
- "name": "No correction",
255
- "opt": "--nocorrection",
256
- "description": "Report values without post-hoc correction."
257
- },
258
- {
259
- "name": "Min ACTG",
260
- "opt": "--min-actg",
261
- "arg": "float",
262
- "default": 0.95,
263
- "description": ["Minimum fraction of ACTGN in the sequences before",
264
- "assuming proteins."]
265
- },
266
- {
267
- "name": "Executables",
268
- "opt": "--bin",
269
- "arg": "in_dir",
270
- "description": ["Directory containing the binaries of the search",
271
- "program."]
272
- },
273
- {
274
- "opt": "--program",
275
- "arg": "select",
276
- "values": ["blast+", "blast", "blat"],
277
- "default": "blast+",
278
- "description": "Search program to be used.",
279
- "note": ["Make sure that you have installed the search program you",
280
- "want to use. If you have downloaded the program, but it's not",
281
- "installed, please use the Executables option above."]
282
- },
283
- {
284
- "opt": "--threads",
285
- "arg": "integer",
286
- "description": "Number of parallel threads to be used.",
287
- "default": 1
288
- },
289
- {
290
- "name": "SQLite3 DB",
291
- "opt": "--sqlite3",
292
- "arg": "out_file",
293
- "description": ["Path to the SQLite3 database to create (or update)",
294
- "with the results."]
295
- },
296
- {
297
- "name": "Name 1",
298
- "opt": "--name1",
299
- "arg": "string",
300
- "description": ["Name of Sequence 1 to use in SQLite3 DB. By default",
301
- "it's determined by the filename."]
302
- },
303
- {
304
- "name": "Name 2",
305
- "opt": "--name2",
306
- "arg": "string",
307
- "description": ["Name of Sequence 2 to use in SQLite3 DB. By default",
308
- "it's determined by the filename."]
309
- },
310
- {
311
- "name": "Don't save regions",
312
- "opt": "--no-save-regions",
313
- "description": "Don't save the fragments in the SQLite3 database."
314
- },
315
- {
316
- "name": "Don't save RBM",
317
- "opt": "--no-save-rbm",
318
- "description": ["Don't save the reciprocal best matches in the",
319
- "--sqlite3 database."]
320
- },
321
- {
322
- "opt": "--lookup-first",
323
- "description": ["Indicates if the ANI should be looked up first in",
324
- "the database. Requires SQLite3 DB, Auto, Name 1, and Name 2.",
325
- "Incompatible with Result, Tab, and Out."]
326
- },
327
- {
328
- "name": "Precision",
329
- "opt": "--dec",
330
- "arg": "integer",
331
- "description": "Decimal positions to report.",
332
- "default": 2
333
- },
334
- {
335
- "opt": "--out",
336
- "arg": "out_file",
337
- "description": ["Saves a file describing the alignments used for",
338
- "two-way ANI."]
339
- },
340
- {
341
- "name": "Result",
342
- "opt": "--res",
343
- "arg": "out_file",
344
- "description": "Saves a file with the final results."
345
- },
346
- {
347
- "opt": "--tab",
348
- "arg": "out_file",
349
- "description": ["Saves a file with the final two-way results in a",
350
- "tab-delimited form. The columns are (in that order): ANI,",
351
- "standard deviation, fragments used, fragments in the smallest",
352
- "genome."]
353
- },
354
- {
355
- "opt": "--auto",
356
- "description": ["ONLY outputs the ANI value in STDOUT (or nothing,",
357
- "if calculation fails)."]
358
- },
359
- {
360
- "opt": "--quiet",
361
- "description": "Run quietly (no STDERR output)."
362
- }
363
- ]
364
- },
365
- {
366
- "task": "anir.rb",
367
- "description": ["Estimates ANIr: the Average Nucleotide Identity of",
368
- "reads against a genome."],
369
- "help_arg": "--help",
370
- "see_also": ["ani.rb", "sam.filter.rb"],
371
- "options": [
372
- {
373
- "opt": "--reads",
374
- "arg": "in_file",
375
- "description": "Metagenomic reads."
376
- },
377
- {
378
- "opt": "--genome",
379
- "arg": "in_file",
380
- "description": "Genome assembly."
381
- },
382
- {
383
- "opt": "--mapping",
384
- "arg": "in_file",
385
- "description": "Mapping file."
386
- },
387
- {
388
- "opt": "--list",
389
- "arg": "in_file",
390
- "description": "Output file with identities."
391
- },
392
- {
393
- "opt": "--hist",
394
- "arg": "in_file",
395
- "description": "Output file with histogram."
396
- },
397
- {
398
- "opt": "--tab",
399
- "arg": "out_file",
400
- "description": "Output file with results in tabular format."
401
- },
402
- {
403
- "name": "Reads format",
404
- "opt": "--r-format",
405
- "arg": "select",
406
- "description": ["Metagenomic reads format: fastq or fasta.",
407
- "Both options support compression with .gz file extension."],
408
- "values": ["fastq", "fasta"],
409
- "default": "fastq"
410
- },
411
- {
412
- "name": "Reads type",
413
- "opt": "--r-type",
414
- "arg": "select",
415
- "description": ["Type of metagenomic reads: Single reads (single),",
416
- "coupled reads in separate files (-m must be comma-delimited;",
417
- "coupled), or coupled reads in a single interposed file",
418
- "(interleaved)."],
419
- "values": ["single", "coupled", "interleaved"],
420
- "default": "single"
421
- },
422
- {
423
- "name": "Genome format",
424
- "opt": "--g-format",
425
- "arg": "select",
426
- "description": ["Genome assembly format: fasta or list.",
427
- "Both options support compression with .gz file extension.",
428
- "If passed in mapping-read mode, filters only matches to these",
429
- "contigs."],
430
- "values": ["fasta", "list"],
431
- "default": "fasta"
432
- },
433
- {
434
- "name": "Mapping format",
435
- "opt": "--m-format",
436
- "arg": "select",
437
- "description": ["Mapping file format: sam, bam, tab, or list.",
438
- "All except bam support compression with .gz file extension."],
439
- "values": ["sam", "bam", "tab", "list"],
440
- "default": "sam"
441
- },
442
- {
443
- "opt": "--identity",
444
- "arg": "float",
445
- "description": "Set a fixed threshold of percent identity.",
446
- "default": 95.0
447
- },
448
- {
449
- "opt": "--algorithm",
450
- "arg": "select",
451
- "description": ["Set an algorithm to automatically detect identity",
452
- "threshold: Valley detection by E-M of Gaussian Mixture Model",
453
- "(gmm), fixed threshold (see Identity; fix),",
454
- "Pick gmm or fix depending on bimodality (see Bimodality; auto)."],
455
- "values": ["gmm", "fix", "auto"],
456
- "default": "auto"
457
- },
458
- {
459
- "opt": "--bimodality",
460
- "arg": "float",
461
- "description": ["Threshold of bimodality below which the algorithm",
462
- "is set to fix. The coefficient used is the de Michele & Accantino",
463
- "(2014) B index."],
464
- "default": 0.5
465
- },
466
- {
467
- "opt": "--coefficient",
468
- "arg": "select",
469
- "description": ["Coefficient of bimodality for Algorithm auto: ",
470
- "Sarle's bimodality coefficient b (sarle), or",
471
- "de Michele and Accatino (2014 PLoS ONE) B index",
472
- "(use with Bimodality 0.1, dma)."],
473
- "values": ["sarle", "dma"],
474
- "default": "sarle"
475
- },
476
- {
477
- "opt": "--bin-size",
478
- "arg": "float",
479
- "description": "Width of histogram bins (in percent identity).",
480
- "default": 1.0
481
- },
482
- {
483
- "opt": "--threads",
484
- "arg": "integer",
485
- "description": "Threads to use."
486
- },
487
- {
488
- "opt": "--log",
489
- "arg": "out_file",
490
- "description": "Log file to save output."
491
- },
492
- {
493
- "opt": "--quiet",
494
- "description": "Run quietly."
495
- }
496
- ]
497
- },
498
- {
499
- "task": "HMM.haai.rb",
500
- "description": ["Estimates Average Amino Acid Identity (AAI) from the",
501
- "essential genes extracted and aligned by HMM.essential.rb (see",
502
- "Alignments)."],
503
- "help_arg": "--help",
504
- "see_also": ["HMM.essential.rb","aai.rb"],
505
- "options": [
506
- {
507
- "name": "Alignments 1",
508
- "opt": "-1",
509
- "arg": "in_file",
510
- "description": "Input alignments file for genome 1."
511
- },
512
- {
513
- "name": "Alignments 2",
514
- "opt": "-2",
515
- "arg": "in_file",
516
- "description": "Input alignments file for genome 2."
517
- },
518
- {
519
- "name": "Alignment output",
520
- "opt": "--aln-out",
521
- "arg": "out_file",
522
- "description": "Output file containing the aligned proteins."
523
- },
524
- {
525
- "opt": "--components",
526
- "arg": "out_file",
527
- "description": ["Output file containing the components of the",
528
- "estimation. Tab-delimited file with model name, matches, and",
529
- "columns."]
530
- },
531
- {
532
- "opt": "--quiet",
533
- "description": "Run quietly (no STDERR output)."
534
- }
535
- ]
536
- },
537
- {
538
- "task": "rbm.rb",
539
- "description": [
540
- "Finds the reciprocal best matches between two sets of",
541
- "sequences."
542
- ],
543
- "help_arg": "--help",
544
- "cite":[
545
- ["Camacho et al, 2009, BMC Bioinf (BLAST+)",
546
- "https://doi.org/10.1186/1471-2105-10-421"],
547
- ["Altschul et al, 2000, JMB (BLAST)",
548
- "http://dx.doi.org/10.1016/S0022-2836(05)80360-2"],
549
- ["Buchfink B, Xie C, Huson D, 2015, Nat Meth (Diamond)",
550
- "https://dx.doi.org/10.1038/nmeth.3176"],
551
- ["Kent, 2002, Genome Res (BLAT)",
552
- "https://doi.org/10.1101/gr.229202"]
553
- ],
554
- "options": [
555
- {
556
- "name": "Sequence 1",
557
- "opt": "--seq1",
558
- "arg": "in_file",
559
- "mandatory": true,
560
- "description": "FastA file containing the genome 1."
561
- },
562
- {
563
- "name": "Sequence 2",
564
- "opt": "--seq2",
565
- "arg": "in_file",
566
- "mandatory": true,
567
- "description": "FastA file containing the genome 2."
568
- },
569
- {
570
- "name": "Output",
571
- "opt": "--out",
572
- "arg": "out_file",
573
- "mandatory": true,
574
- "description": [
575
- "Reciprocal Best Matches in BLAST tabular format.",
576
- "Supports compression with .gz extension."
577
- ]
578
- },
579
- {
580
- "name": "Nucleotides",
581
- "opt": "--nucl",
582
- "description": [
583
- "Sequences are assumed to be nucleotides (proteins by default)."
584
- ]
585
- },
586
- {
587
- "name": "Length",
588
- "opt": "--len",
589
- "arg": "integer",
590
- "description": "Minimum alignment length (in residues).",
591
- "default": 0
592
- },
593
- {
594
- "name": "Fraction",
595
- "opt": "--fract",
596
- "arg": "float",
597
- "default": 0.0,
598
- "description": [
599
- "Minimum alignment length (as a fraction of the query).",
600
- "If set, requires BLAST+ or Diamond (see Program)."
601
- ]
602
- },
603
- {
604
- "name": "Identity",
605
- "opt": "--id",
606
- "arg": "float",
607
- "description": "Minimum alignment identity (in %).",
608
- "default": 0.0
609
- },
610
- {
611
- "name": "Bit score",
612
- "opt": "--score",
613
- "arg": "float",
614
- "default": 0.0,
615
- "description": "Minimum alignment score (in bits)."
616
- },
617
- {
618
- "name": "Executables",
619
- "opt": "--bin",
620
- "arg": "in_dir",
621
- "description": [
622
- "Directory containing the binaries of the search program."
623
- ]
624
- },
625
- {
626
- "opt": "--program",
627
- "arg": "select",
628
- "values": ["blast+", "blast", "blat", "diamond"],
629
- "default": "blast+",
630
- "description": "Search program to be used. Default: blast+.",
631
- "note": [
632
- "Make sure that you have installed the search program you",
633
- "want to use. If you have downloaded the program, but it's not",
634
- "installed, please use the Executables option above."
635
- ]
636
- },
637
- {
638
- "opt": "--threads",
639
- "arg": "integer",
640
- "description": "Number of parallel threads to be used.",
641
- "default": 1
642
- },
643
- {
644
- "opt": "--quiet",
645
- "description": "Run quietly (no STDERR output)."
646
- }
647
- ]
648
- }
649
- ]
650
- }