miga-base 0.7.25.2 → 0.7.25.3

Sign up to get free protection for your applications and to get access to all the features.
Files changed (277) hide show
  1. checksums.yaml +4 -4
  2. data/lib/miga/version.rb +2 -2
  3. data/utils/distance/runner.rb +2 -1
  4. metadata +5 -278
  5. data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Archaea_SCG.hmm +0 -41964
  6. data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Bacteria_SCG.hmm +0 -32439
  7. data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Complete_SCG_DB.hmm +0 -62056
  8. data/utils/FastAAI/FastAAI/FastAAI +0 -1336
  9. data/utils/FastAAI/README.md +0 -84
  10. data/utils/FastAAI/kAAI_v1.0_virus.py +0 -1296
  11. data/utils/enveomics/Docs/recplot2.md +0 -244
  12. data/utils/enveomics/Examples/aai-matrix.bash +0 -66
  13. data/utils/enveomics/Examples/ani-matrix.bash +0 -66
  14. data/utils/enveomics/Examples/essential-phylogeny.bash +0 -105
  15. data/utils/enveomics/Examples/unus-genome-phylogeny.bash +0 -100
  16. data/utils/enveomics/LICENSE.txt +0 -73
  17. data/utils/enveomics/Makefile +0 -52
  18. data/utils/enveomics/Manifest/Tasks/aasubs.json +0 -103
  19. data/utils/enveomics/Manifest/Tasks/blasttab.json +0 -786
  20. data/utils/enveomics/Manifest/Tasks/distances.json +0 -161
  21. data/utils/enveomics/Manifest/Tasks/fasta.json +0 -766
  22. data/utils/enveomics/Manifest/Tasks/fastq.json +0 -243
  23. data/utils/enveomics/Manifest/Tasks/graphics.json +0 -126
  24. data/utils/enveomics/Manifest/Tasks/mapping.json +0 -67
  25. data/utils/enveomics/Manifest/Tasks/ogs.json +0 -382
  26. data/utils/enveomics/Manifest/Tasks/other.json +0 -829
  27. data/utils/enveomics/Manifest/Tasks/remote.json +0 -355
  28. data/utils/enveomics/Manifest/Tasks/sequence-identity.json +0 -501
  29. data/utils/enveomics/Manifest/Tasks/tables.json +0 -308
  30. data/utils/enveomics/Manifest/Tasks/trees.json +0 -68
  31. data/utils/enveomics/Manifest/Tasks/variants.json +0 -111
  32. data/utils/enveomics/Manifest/categories.json +0 -156
  33. data/utils/enveomics/Manifest/examples.json +0 -154
  34. data/utils/enveomics/Manifest/tasks.json +0 -4
  35. data/utils/enveomics/Pipelines/assembly.pbs/CONFIG.mock.bash +0 -69
  36. data/utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl +0 -1
  37. data/utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl +0 -1
  38. data/utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl +0 -1
  39. data/utils/enveomics/Pipelines/assembly.pbs/README.md +0 -189
  40. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-2.bash +0 -112
  41. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-3.bash +0 -23
  42. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-4.bash +0 -44
  43. data/utils/enveomics/Pipelines/assembly.pbs/RUNME.bash +0 -50
  44. data/utils/enveomics/Pipelines/assembly.pbs/kSelector.R +0 -37
  45. data/utils/enveomics/Pipelines/assembly.pbs/newbler.pbs +0 -68
  46. data/utils/enveomics/Pipelines/assembly.pbs/newbler_preparator.pl +0 -49
  47. data/utils/enveomics/Pipelines/assembly.pbs/soap.pbs +0 -80
  48. data/utils/enveomics/Pipelines/assembly.pbs/stats.pbs +0 -57
  49. data/utils/enveomics/Pipelines/assembly.pbs/velvet.pbs +0 -63
  50. data/utils/enveomics/Pipelines/blast.pbs/01.pbs.bash +0 -38
  51. data/utils/enveomics/Pipelines/blast.pbs/02.pbs.bash +0 -73
  52. data/utils/enveomics/Pipelines/blast.pbs/03.pbs.bash +0 -21
  53. data/utils/enveomics/Pipelines/blast.pbs/BlastTab.recover_job.pl +0 -72
  54. data/utils/enveomics/Pipelines/blast.pbs/CONFIG.mock.bash +0 -98
  55. data/utils/enveomics/Pipelines/blast.pbs/FastA.split.pl +0 -1
  56. data/utils/enveomics/Pipelines/blast.pbs/README.md +0 -127
  57. data/utils/enveomics/Pipelines/blast.pbs/RUNME.bash +0 -109
  58. data/utils/enveomics/Pipelines/blast.pbs/TASK.check.bash +0 -128
  59. data/utils/enveomics/Pipelines/blast.pbs/TASK.dry.bash +0 -16
  60. data/utils/enveomics/Pipelines/blast.pbs/TASK.eo.bash +0 -22
  61. data/utils/enveomics/Pipelines/blast.pbs/TASK.pause.bash +0 -26
  62. data/utils/enveomics/Pipelines/blast.pbs/TASK.run.bash +0 -89
  63. data/utils/enveomics/Pipelines/blast.pbs/sentinel.pbs.bash +0 -29
  64. data/utils/enveomics/Pipelines/idba.pbs/README.md +0 -49
  65. data/utils/enveomics/Pipelines/idba.pbs/RUNME.bash +0 -95
  66. data/utils/enveomics/Pipelines/idba.pbs/run.pbs +0 -56
  67. data/utils/enveomics/Pipelines/trim.pbs/README.md +0 -54
  68. data/utils/enveomics/Pipelines/trim.pbs/RUNME.bash +0 -70
  69. data/utils/enveomics/Pipelines/trim.pbs/run.pbs +0 -130
  70. data/utils/enveomics/README.md +0 -42
  71. data/utils/enveomics/Scripts/AAsubs.log2ratio.rb +0 -171
  72. data/utils/enveomics/Scripts/Aln.cat.rb +0 -163
  73. data/utils/enveomics/Scripts/Aln.convert.pl +0 -35
  74. data/utils/enveomics/Scripts/AlphaDiversity.pl +0 -152
  75. data/utils/enveomics/Scripts/BedGraph.tad.rb +0 -93
  76. data/utils/enveomics/Scripts/BedGraph.window.rb +0 -71
  77. data/utils/enveomics/Scripts/BlastPairwise.AAsubs.pl +0 -102
  78. data/utils/enveomics/Scripts/BlastTab.addlen.rb +0 -63
  79. data/utils/enveomics/Scripts/BlastTab.advance.bash +0 -48
  80. data/utils/enveomics/Scripts/BlastTab.best_hit_sorted.pl +0 -55
  81. data/utils/enveomics/Scripts/BlastTab.catsbj.pl +0 -104
  82. data/utils/enveomics/Scripts/BlastTab.cogCat.rb +0 -76
  83. data/utils/enveomics/Scripts/BlastTab.filter.pl +0 -47
  84. data/utils/enveomics/Scripts/BlastTab.kegg_pep2path_rest.pl +0 -194
  85. data/utils/enveomics/Scripts/BlastTab.metaxaPrep.pl +0 -104
  86. data/utils/enveomics/Scripts/BlastTab.pairedHits.rb +0 -157
  87. data/utils/enveomics/Scripts/BlastTab.recplot2.R +0 -48
  88. data/utils/enveomics/Scripts/BlastTab.seqdepth.pl +0 -86
  89. data/utils/enveomics/Scripts/BlastTab.seqdepth_ZIP.pl +0 -119
  90. data/utils/enveomics/Scripts/BlastTab.seqdepth_nomedian.pl +0 -86
  91. data/utils/enveomics/Scripts/BlastTab.subsample.pl +0 -47
  92. data/utils/enveomics/Scripts/BlastTab.sumPerHit.pl +0 -114
  93. data/utils/enveomics/Scripts/BlastTab.taxid2taxrank.pl +0 -90
  94. data/utils/enveomics/Scripts/BlastTab.topHits_sorted.rb +0 -101
  95. data/utils/enveomics/Scripts/Chao1.pl +0 -97
  96. data/utils/enveomics/Scripts/CharTable.classify.rb +0 -234
  97. data/utils/enveomics/Scripts/EBIseq2tax.rb +0 -83
  98. data/utils/enveomics/Scripts/FastA.N50.pl +0 -56
  99. data/utils/enveomics/Scripts/FastA.extract.rb +0 -152
  100. data/utils/enveomics/Scripts/FastA.filter.pl +0 -52
  101. data/utils/enveomics/Scripts/FastA.filterLen.pl +0 -28
  102. data/utils/enveomics/Scripts/FastA.filterN.pl +0 -60
  103. data/utils/enveomics/Scripts/FastA.fragment.rb +0 -92
  104. data/utils/enveomics/Scripts/FastA.gc.pl +0 -42
  105. data/utils/enveomics/Scripts/FastA.interpose.pl +0 -93
  106. data/utils/enveomics/Scripts/FastA.length.pl +0 -38
  107. data/utils/enveomics/Scripts/FastA.mask.rb +0 -89
  108. data/utils/enveomics/Scripts/FastA.per_file.pl +0 -36
  109. data/utils/enveomics/Scripts/FastA.qlen.pl +0 -57
  110. data/utils/enveomics/Scripts/FastA.rename.pl +0 -65
  111. data/utils/enveomics/Scripts/FastA.revcom.pl +0 -23
  112. data/utils/enveomics/Scripts/FastA.sample.rb +0 -83
  113. data/utils/enveomics/Scripts/FastA.slider.pl +0 -85
  114. data/utils/enveomics/Scripts/FastA.split.pl +0 -55
  115. data/utils/enveomics/Scripts/FastA.split.rb +0 -79
  116. data/utils/enveomics/Scripts/FastA.subsample.pl +0 -131
  117. data/utils/enveomics/Scripts/FastA.tag.rb +0 -65
  118. data/utils/enveomics/Scripts/FastA.wrap.rb +0 -48
  119. data/utils/enveomics/Scripts/FastQ.filter.pl +0 -54
  120. data/utils/enveomics/Scripts/FastQ.interpose.pl +0 -90
  121. data/utils/enveomics/Scripts/FastQ.offset.pl +0 -90
  122. data/utils/enveomics/Scripts/FastQ.split.pl +0 -53
  123. data/utils/enveomics/Scripts/FastQ.tag.rb +0 -63
  124. data/utils/enveomics/Scripts/FastQ.test-error.rb +0 -81
  125. data/utils/enveomics/Scripts/FastQ.toFastA.awk +0 -24
  126. data/utils/enveomics/Scripts/GFF.catsbj.pl +0 -127
  127. data/utils/enveomics/Scripts/GenBank.add_fields.rb +0 -84
  128. data/utils/enveomics/Scripts/HMM.essential.rb +0 -351
  129. data/utils/enveomics/Scripts/HMM.haai.rb +0 -168
  130. data/utils/enveomics/Scripts/HMMsearch.extractIds.rb +0 -83
  131. data/utils/enveomics/Scripts/JPlace.distances.rb +0 -88
  132. data/utils/enveomics/Scripts/JPlace.to_iToL.rb +0 -320
  133. data/utils/enveomics/Scripts/M5nr.getSequences.rb +0 -81
  134. data/utils/enveomics/Scripts/MeTaxa.distribution.pl +0 -198
  135. data/utils/enveomics/Scripts/MyTaxa.fragsByTax.pl +0 -35
  136. data/utils/enveomics/Scripts/MyTaxa.seq-taxrank.rb +0 -49
  137. data/utils/enveomics/Scripts/NCBIacc2tax.rb +0 -92
  138. data/utils/enveomics/Scripts/Newick.autoprune.R +0 -27
  139. data/utils/enveomics/Scripts/RAxML-EPA.to_iToL.pl +0 -228
  140. data/utils/enveomics/Scripts/RecPlot2.compareIdentities.R +0 -32
  141. data/utils/enveomics/Scripts/RefSeq.download.bash +0 -48
  142. data/utils/enveomics/Scripts/SRA.download.bash +0 -57
  143. data/utils/enveomics/Scripts/TRIBS.plot-test.R +0 -36
  144. data/utils/enveomics/Scripts/TRIBS.test.R +0 -39
  145. data/utils/enveomics/Scripts/Table.barplot.R +0 -31
  146. data/utils/enveomics/Scripts/Table.df2dist.R +0 -30
  147. data/utils/enveomics/Scripts/Table.filter.pl +0 -61
  148. data/utils/enveomics/Scripts/Table.merge.pl +0 -77
  149. data/utils/enveomics/Scripts/Table.replace.rb +0 -69
  150. data/utils/enveomics/Scripts/Table.round.rb +0 -63
  151. data/utils/enveomics/Scripts/Table.split.pl +0 -57
  152. data/utils/enveomics/Scripts/Taxonomy.silva2ncbi.rb +0 -227
  153. data/utils/enveomics/Scripts/VCF.KaKs.rb +0 -147
  154. data/utils/enveomics/Scripts/VCF.SNPs.rb +0 -88
  155. data/utils/enveomics/Scripts/aai.rb +0 -418
  156. data/utils/enveomics/Scripts/ani.rb +0 -362
  157. data/utils/enveomics/Scripts/clust.rand.rb +0 -102
  158. data/utils/enveomics/Scripts/gi2tax.rb +0 -103
  159. data/utils/enveomics/Scripts/in_silico_GA_GI.pl +0 -96
  160. data/utils/enveomics/Scripts/lib/data/dupont_2012_essential.hmm.gz +0 -0
  161. data/utils/enveomics/Scripts/lib/data/lee_2019_essential.hmm.gz +0 -0
  162. data/utils/enveomics/Scripts/lib/enveomics.R +0 -1
  163. data/utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb +0 -24
  164. data/utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb +0 -253
  165. data/utils/enveomics/Scripts/lib/enveomics_rb/og.rb +0 -182
  166. data/utils/enveomics/Scripts/lib/enveomics_rb/remote_data.rb +0 -74
  167. data/utils/enveomics/Scripts/lib/enveomics_rb/seq_range.rb +0 -237
  168. data/utils/enveomics/Scripts/lib/enveomics_rb/stat.rb +0 -30
  169. data/utils/enveomics/Scripts/lib/enveomics_rb/vcf.rb +0 -135
  170. data/utils/enveomics/Scripts/ogs.annotate.rb +0 -88
  171. data/utils/enveomics/Scripts/ogs.core-pan.rb +0 -160
  172. data/utils/enveomics/Scripts/ogs.extract.rb +0 -125
  173. data/utils/enveomics/Scripts/ogs.mcl.rb +0 -186
  174. data/utils/enveomics/Scripts/ogs.rb +0 -104
  175. data/utils/enveomics/Scripts/ogs.stats.rb +0 -131
  176. data/utils/enveomics/Scripts/rbm.rb +0 -146
  177. data/utils/enveomics/Tests/Makefile +0 -10
  178. data/utils/enveomics/Tests/Mgen_M2288.faa +0 -3189
  179. data/utils/enveomics/Tests/Mgen_M2288.fna +0 -8282
  180. data/utils/enveomics/Tests/Mgen_M2321.fna +0 -8288
  181. data/utils/enveomics/Tests/Nequ_Kin4M.faa +0 -2970
  182. data/utils/enveomics/Tests/Xanthomonas_oryzae-PilA.tribs.Rdata +0 -0
  183. data/utils/enveomics/Tests/Xanthomonas_oryzae-PilA.txt +0 -7
  184. data/utils/enveomics/Tests/Xanthomonas_oryzae.aai-mat.tsv +0 -17
  185. data/utils/enveomics/Tests/Xanthomonas_oryzae.aai.tsv +0 -137
  186. data/utils/enveomics/Tests/a_mg.cds-go.blast.tsv +0 -123
  187. data/utils/enveomics/Tests/a_mg.reads-cds.blast.tsv +0 -200
  188. data/utils/enveomics/Tests/a_mg.reads-cds.counts.tsv +0 -55
  189. data/utils/enveomics/Tests/alkB.nwk +0 -1
  190. data/utils/enveomics/Tests/anthrax-cansnp-data.tsv +0 -13
  191. data/utils/enveomics/Tests/anthrax-cansnp-key.tsv +0 -17
  192. data/utils/enveomics/Tests/hiv1.faa +0 -59
  193. data/utils/enveomics/Tests/hiv1.fna +0 -134
  194. data/utils/enveomics/Tests/hiv2.faa +0 -70
  195. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv +0 -233
  196. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.lim +0 -1
  197. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.rec +0 -233
  198. data/utils/enveomics/Tests/phyla_counts.tsv +0 -10
  199. data/utils/enveomics/Tests/primate_lentivirus.ogs +0 -11
  200. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv1.rbm +0 -9
  201. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv2.rbm +0 -8
  202. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-siv.rbm +0 -6
  203. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-hiv2.rbm +0 -9
  204. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-siv.rbm +0 -6
  205. data/utils/enveomics/Tests/primate_lentivirus.rbm/siv-siv.rbm +0 -6
  206. data/utils/enveomics/build_enveomics_r.bash +0 -45
  207. data/utils/enveomics/enveomics.R/DESCRIPTION +0 -31
  208. data/utils/enveomics/enveomics.R/NAMESPACE +0 -39
  209. data/utils/enveomics/enveomics.R/R/autoprune.R +0 -155
  210. data/utils/enveomics/enveomics.R/R/barplot.R +0 -184
  211. data/utils/enveomics/enveomics.R/R/cliopts.R +0 -135
  212. data/utils/enveomics/enveomics.R/R/df2dist.R +0 -154
  213. data/utils/enveomics/enveomics.R/R/growthcurve.R +0 -331
  214. data/utils/enveomics/enveomics.R/R/recplot.R +0 -354
  215. data/utils/enveomics/enveomics.R/R/recplot2.R +0 -1631
  216. data/utils/enveomics/enveomics.R/R/tribs.R +0 -583
  217. data/utils/enveomics/enveomics.R/R/utils.R +0 -50
  218. data/utils/enveomics/enveomics.R/README.md +0 -80
  219. data/utils/enveomics/enveomics.R/data/growth.curves.rda +0 -0
  220. data/utils/enveomics/enveomics.R/data/phyla.counts.rda +0 -0
  221. data/utils/enveomics/enveomics.R/man/cash-enve.GrowthCurve-method.Rd +0 -17
  222. data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2-method.Rd +0 -17
  223. data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2.Peak-method.Rd +0 -17
  224. data/utils/enveomics/enveomics.R/man/enve.GrowthCurve-class.Rd +0 -25
  225. data/utils/enveomics/enveomics.R/man/enve.TRIBS-class.Rd +0 -46
  226. data/utils/enveomics/enveomics.R/man/enve.TRIBS.merge.Rd +0 -23
  227. data/utils/enveomics/enveomics.R/man/enve.TRIBStest-class.Rd +0 -47
  228. data/utils/enveomics/enveomics.R/man/enve.__prune.iter.Rd +0 -23
  229. data/utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd +0 -23
  230. data/utils/enveomics/enveomics.R/man/enve.__tribs.Rd +0 -32
  231. data/utils/enveomics/enveomics.R/man/enve.barplot.Rd +0 -91
  232. data/utils/enveomics/enveomics.R/man/enve.cliopts.Rd +0 -57
  233. data/utils/enveomics/enveomics.R/man/enve.col.alpha.Rd +0 -24
  234. data/utils/enveomics/enveomics.R/man/enve.col2alpha.Rd +0 -19
  235. data/utils/enveomics/enveomics.R/man/enve.df2dist.Rd +0 -39
  236. data/utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd +0 -38
  237. data/utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd +0 -40
  238. data/utils/enveomics/enveomics.R/man/enve.growthcurve.Rd +0 -67
  239. data/utils/enveomics/enveomics.R/man/enve.prune.dist.Rd +0 -37
  240. data/utils/enveomics/enveomics.R/man/enve.recplot.Rd +0 -122
  241. data/utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd +0 -45
  242. data/utils/enveomics/enveomics.R/man/enve.recplot2.ANIr.Rd +0 -24
  243. data/utils/enveomics/enveomics.R/man/enve.recplot2.Rd +0 -68
  244. data/utils/enveomics/enveomics.R/man/enve.recplot2.__counts.Rd +0 -25
  245. data/utils/enveomics/enveomics.R/man/enve.recplot2.__peakHist.Rd +0 -21
  246. data/utils/enveomics/enveomics.R/man/enve.recplot2.__whichClosestPeak.Rd +0 -19
  247. data/utils/enveomics/enveomics.R/man/enve.recplot2.changeCutoff.Rd +0 -19
  248. data/utils/enveomics/enveomics.R/man/enve.recplot2.compareIdentities.Rd +0 -41
  249. data/utils/enveomics/enveomics.R/man/enve.recplot2.coordinates.Rd +0 -29
  250. data/utils/enveomics/enveomics.R/man/enve.recplot2.corePeak.Rd +0 -18
  251. data/utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd +0 -40
  252. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd +0 -36
  253. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_e.Rd +0 -19
  254. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_m.Rd +0 -19
  255. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__emauto_one.Rd +0 -27
  256. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mow_one.Rd +0 -41
  257. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mower.Rd +0 -17
  258. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.em.Rd +0 -43
  259. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.emauto.Rd +0 -37
  260. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.mower.Rd +0 -74
  261. data/utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd +0 -59
  262. data/utils/enveomics/enveomics.R/man/enve.recplot2.seqdepth.Rd +0 -27
  263. data/utils/enveomics/enveomics.R/man/enve.recplot2.windowDepthThreshold.Rd +0 -32
  264. data/utils/enveomics/enveomics.R/man/enve.tribs.Rd +0 -59
  265. data/utils/enveomics/enveomics.R/man/enve.tribs.test.Rd +0 -28
  266. data/utils/enveomics/enveomics.R/man/enve.truncate.Rd +0 -27
  267. data/utils/enveomics/enveomics.R/man/growth.curves.Rd +0 -14
  268. data/utils/enveomics/enveomics.R/man/phyla.counts.Rd +0 -13
  269. data/utils/enveomics/enveomics.R/man/plot.enve.GrowthCurve.Rd +0 -63
  270. data/utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd +0 -38
  271. data/utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd +0 -38
  272. data/utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd +0 -111
  273. data/utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd +0 -19
  274. data/utils/enveomics/enveomics.R/man/summary.enve.TRIBS.Rd +0 -19
  275. data/utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd +0 -19
  276. data/utils/enveomics/globals.mk +0 -8
  277. data/utils/enveomics/manifest.json +0 -9
@@ -1,355 +0,0 @@
1
- {
2
- "tasks": [
3
- {
4
- "task": "BlastTab.kegg_pep2path_rest.pl",
5
- "description": ["Takes a BLAST against KEGG_PEP (or KO) and retrieves",
6
- "the pathways in which the subject peptides are involved."],
7
- "requires": [
8
- { "perl_lib": "JSON" },
9
- { "perl_lib": "LWP::Simple" }
10
- ],
11
- "help_arg": "",
12
- "options": [
13
- {
14
- "name": "blast.txt",
15
- "arg": "in_file",
16
- "mandatory": true,
17
- "description": "Input tabular BLAST file."
18
- },
19
- {
20
- "name": "Cache file",
21
- "arg": "out_file",
22
- "description": ["(optional) File containing the saved cache. If",
23
- "unset, the cache won't be recoverable across instances of this",
24
- "script. It is strongly recommended to set a file. Multiple",
25
- "parallel instances of this script may use the same cache file."]
26
- },
27
- ">",
28
- {
29
- "name": "output.txt",
30
- "arg": "out_file",
31
- "mandatory": true,
32
- "description": ["Tab-delimited output file, with the columns: (1)",
33
- "Query ID, (2) Subject ID, (3) Pathway ID, (4) Pathway (reference)",
34
- "description, (5) Organism."]
35
- }
36
- ]
37
- },
38
- {
39
- "task": "M5nr.getSequences.rb",
40
- "description": ["Downloads a set of sequences from M5nr with a given",
41
- "functional annotation."],
42
- "help_arg": "--help",
43
- "requires": [
44
- { "ruby_gem": "restclient" },
45
- { "ruby_gem": "open-uri" },
46
- { "ruby_gem": "JSON" }
47
- ],
48
- "options": [
49
- {
50
- "opt": "--function",
51
- "arg": "string",
52
- "mandatory": true,
53
- "description": "Functional annotation."
54
- },
55
- {
56
- "name": "Output file",
57
- "opt": "--out",
58
- "arg": "out_file",
59
- "mandatory": true,
60
- "description": "File containing the sequences."
61
- },
62
- {
63
- "opt": "--max",
64
- "arg": "integer",
65
- "default": 0,
66
- "description": ["Maximum number of sequences to download. Set to",
67
- "0 to download all."]
68
- },
69
- {
70
- "opt": "--recover",
71
- "description": "If set, tries to recover a previous FastA."
72
- },
73
- {
74
- "name": "URL",
75
- "opt": "--url",
76
- "arg": "string",
77
- "default": "http://api.metagenomics.anl.gov/m5nr",
78
- "description": "URL for M5nr API."
79
- },
80
- {
81
- "opt": "--quiet",
82
- "description": "Run quietly (no STDERR output)."
83
- }
84
- ]
85
- },
86
- {
87
- "task": "EBIseq2tax.rb",
88
- "description": ["Maps a list of EBI-supported IDs to their corresponding",
89
- "NCBI taxonomy using EBI RESTful API."],
90
- "warn": ["Avoid using this script on millions of entries at a time,",
91
- "since each entry elicits requests to EBI and NCBI servers."],
92
- "requires": [
93
- { "ruby_gem": "nokogiri" }
94
- ],
95
- "see_also": ["NCBIacc2tax.rb"],
96
- "help_arg": "--help",
97
- "options": [
98
- {
99
- "name": "IDs",
100
- "opt": "--ids",
101
- "arg": "string",
102
- "description": "Comma-separated list of EBI IDs.",
103
- "note": "Required unless 'Input file' is passed."
104
- },
105
- {
106
- "name": "Input file",
107
- "opt": "--infile",
108
- "arg": "in_file",
109
- "description": ["Raw text file containing the list of EBI IDs,",
110
- "one per line."],
111
- "note": "Required unless 'IDs' is passed."
112
- },
113
- {
114
- "opt": "--database",
115
- "arg": "string",
116
- "default": "uniprotkb",
117
- "description": "EBI database defining the EBI IDs."
118
- },
119
- {
120
- "opt": "--ranks",
121
- "arg": "string",
122
- "description": "Comma-delimited list of taxonomic ranks to report.",
123
- "default": "superkingdom,phylum,class,order,family,genus,species"
124
- },
125
- {
126
- "opt": "--noheader",
127
- "description": "Do not includ a header in the output."
128
- },
129
- {
130
- "opt": "--taxids",
131
- "description": "Return Taxonomy IDs instead of scientific names."
132
- },
133
- {
134
- "opt": "--quiet",
135
- "description": "Run quietly."
136
- }
137
- ]
138
- },
139
- {
140
- "task": "RefSeq.download.bash",
141
- "description": ["Downloads a collection of sequences and/or annotations",
142
- "from NCBI's RefSeq."],
143
- "help_arg": "",
144
- "requires": [
145
- {
146
- "description": "curl",
147
- "test": "curl --version"
148
- }
149
- ],
150
- "options": [
151
- {
152
- "name": "Organism",
153
- "arg": "string",
154
- "mandatory": true,
155
- "description": ["The organism to download (e.g.,",
156
- "Streptococcus_pneumoniae)."]
157
- },
158
- {
159
- "name": "Extension",
160
- "arg": "string",
161
- "mandatory": true,
162
- "default": ".*.gz",
163
- "description": ["Extension to download. Common extensions include",
164
- ".fna.gz (genomic sequences), .faa.gz (protein sequences),",
165
- ".gff.gz (annotations), and .*.gz (all data)."]
166
- },
167
- {
168
- "name": "Level",
169
- "arg": "string",
170
- "mandatory": true,
171
- "default": "Any",
172
- "description": ["Use only genomes with this assembly level. Common",
173
- "levels are 'Complete Genome' and 'Contig'. By default, any",
174
- "assembly level is allowed ('Any')."]
175
- },
176
- {
177
- "name": "Directory",
178
- "arg": "out_dir",
179
- "description": ["Directory where the files are to be downladed.",
180
- "By default, same as 'Organism'."]
181
- }
182
- ]
183
- },
184
- {
185
- "task": "SRA.download.bash",
186
- "description": ["Downloads the set of runs from a project, sample, or",
187
- "experiment in SRA."],
188
- "help_arg": "",
189
- "requires": [
190
- {
191
- "description": "curl",
192
- "test": "curl --version"
193
- }
194
- ],
195
- "options": [
196
- {
197
- "name": "SRA ID",
198
- "arg": "string",
199
- "mandatory": true,
200
- "description": "ID of the SRA Project, Sample, or Experiment."
201
- },
202
- {
203
- "name": "dir",
204
- "arg": "out_dir",
205
- "description": ["Directory where the files are to be downladed. By",
206
- "default, same as 'SRA ID'."]
207
- }
208
- ]
209
- },
210
- {
211
- "task": "gi2tax.rb",
212
- "description": ["Maps a list of NCBI GIs to their corresponding taxonomy",
213
- "using the NCBI EUtilities."],
214
- "warn": ["Avoid using this script on millions of entries at a time,",
215
- "since each entry elicits two requests to NCBI's servers.",
216
- "*IMPORTANT NOTE*: NCBI is phasing out support for GIs. Please use",
217
- "acc.ver instead with NCBIacc2tax.rb."],
218
- "requires": [
219
- { "ruby_gem": "nokogiri" },
220
- { "ruby_gem": "json" }
221
- ],
222
- "see_also": ["NCBIacc2tax.rb"],
223
- "help_arg": "--help",
224
- "options": [
225
- {
226
- "name": "GIs",
227
- "opt": "--gis",
228
- "arg": "string",
229
- "description": "Comma-separated list of GIs.",
230
- "note": "Required unless 'Input file' is passed."
231
- },
232
- {
233
- "name": "Input file",
234
- "opt": "--infile",
235
- "arg": "in_file",
236
- "description": ["Raw text file containing the list of GIs, one per",
237
- "line."],
238
- "note": "Required unless 'GIs' is passed."
239
- },
240
- {
241
- "opt": "--protein",
242
- "description": ["Use if the GIs are proteins. Otherwise, GIs are",
243
- "assumed to be from the Nuccore Database."]
244
- },
245
- {
246
- "opt": "--ranks",
247
- "arg": "string",
248
- "description": "Taxonomic ranks to report, separated by commas.",
249
- "default": "superkingdom,phylum,class,order,family,genus,species"
250
- },
251
- {
252
- "name": "No header",
253
- "opt": "--noheader",
254
- "description": "Do not include a header in the output."
255
- },
256
- {
257
- "name": "Tax IDs",
258
- "opt": "--taxids",
259
- "description": "Return Taxonomy IDs instead of scientific names."
260
- },
261
- {
262
- "name": "Exact GI",
263
- "opt": "--exact-gi",
264
- "description": ["Returns only taxonomy associated with the exact GI",
265
- "passed. By default, it attempts to update accession versions if",
266
- "possible."]
267
- },
268
- {
269
- "opt": "--ignore-missing",
270
- "description": ["Does not report missing GIs in the output file. By",
271
- "default, it reports GI and empty values for all other columns."]
272
- },
273
- {
274
- "opt": "--quiet",
275
- "description": "Run quietly."
276
- },
277
- ">",
278
- {
279
- "arg": "out_file",
280
- "mandatory": true,
281
- "description": ["Tab-delimited table with GIs and taxonomic",
282
- "classification."]
283
- }
284
- ]
285
- },
286
- {
287
- "task": "NCBIacc2tax.rb",
288
- "description": ["Maps a list of NCBI accessions to their corresponding",
289
- "taxonomy using the NCBI EUtilities."],
290
- "warn": ["Avoid using this script on millions of entries at a time,",
291
- "since each entry elicits two requests to NCBI's servers."],
292
- "requires": [
293
- { "ruby_gem": "nokogiri" },
294
- { "ruby_gem": "json" }
295
- ],
296
- "see_also": ["EBIseq2tax.rb"],
297
- "help_arg": "--help",
298
- "options": [
299
- {
300
- "name": "Accessions",
301
- "opt": "--acc",
302
- "arg": "string",
303
- "description": "Comma-separated list of accessions.",
304
- "note": "Required unless 'Input file' is passed."
305
- },
306
- {
307
- "name": "Input file",
308
- "opt": "--infile",
309
- "arg": "in_file",
310
- "description": ["Raw text file containing the list of accessions,",
311
- "one per line."],
312
- "note": "Required unless 'Accessions' is passed."
313
- },
314
- {
315
- "opt": "--protein",
316
- "description": ["Use if the accessions are proteins. Otherwise,",
317
- "accessions are assumed to be from the Nuccore Database."]
318
- },
319
- {
320
- "opt": "--ranks",
321
- "arg": "string",
322
- "description": "Taxonomic ranks to report, separated by commas.",
323
- "default": "superkingdom,phylum,class,order,family,genus,species"
324
- },
325
- {
326
- "name": "No header",
327
- "opt": "--noheader",
328
- "description": "Do not include a header in the output."
329
- },
330
- {
331
- "name": "Tax IDs",
332
- "opt": "--taxids",
333
- "description": "Return Taxonomy IDs instead of scientific names."
334
- },
335
- {
336
- "opt": "--ignore-missing",
337
- "description": ["Does not report missing accessions in the output",
338
- "file. By default, it reports GI and empty values for all other",
339
- "columns."]
340
- },
341
- {
342
- "opt": "--quiet",
343
- "description": "Run quietly."
344
- },
345
- ">",
346
- {
347
- "arg": "out_file",
348
- "mandatory": true,
349
- "description": ["Tab-delimited table with accessions and taxonomic",
350
- "classification."]
351
- }
352
- ]
353
- }
354
- ]
355
- }
@@ -1,501 +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": "HMM.haai.rb",
367
- "description": ["Estimates Average Amino Acid Identity (AAI) from the",
368
- "essential genes extracted and aligned by HMM.essential.rb (see",
369
- "Alignments)."],
370
- "help_arg": "--help",
371
- "see_also": ["HMM.essential.rb","aai.rb"],
372
- "options": [
373
- {
374
- "name": "Alignments 1",
375
- "opt": "-1",
376
- "arg": "in_file",
377
- "description": "Input alignments file for genome 1."
378
- },
379
- {
380
- "name": "Alignments 2",
381
- "opt": "-2",
382
- "arg": "in_file",
383
- "description": "Input alignments file for genome 2."
384
- },
385
- {
386
- "name": "Alignment output",
387
- "opt": "--aln-out",
388
- "arg": "out_file",
389
- "description": "Output file containing the aligned proteins."
390
- },
391
- {
392
- "opt": "--components",
393
- "arg": "out_file",
394
- "description": ["Output file containing the components of the",
395
- "estimation. Tab-delimited file with model name, matches, and",
396
- "columns."]
397
- },
398
- {
399
- "opt": "--quiet",
400
- "description": "Run quietly (no STDERR output)."
401
- }
402
- ]
403
- },
404
- {
405
- "task": "rbm.rb",
406
- "description": ["Finds the reciprocal best matches between two sets of",
407
- "sequences."],
408
- "help_arg": "--help",
409
- "cite":[
410
- ["Altschul et al, 2000, JMB (BLAST)",
411
- "http://dx.doi.org/10.1016/S0022-2836(05)80360-2"],
412
- ["Buchfink B, Xie C, Huson D, 2015, Nat Meth (Diamond)",
413
- "https://dx.doi.org/10.1038/nmeth.3176"]
414
- ],
415
- "options": [
416
- {
417
- "name": "Sequence 1",
418
- "opt": "--seq1",
419
- "arg": "in_file",
420
- "mandatory": true,
421
- "description": "FastA file containing the genome 1."
422
- },
423
- {
424
- "name": "Sequence 2",
425
- "opt": "--seq2",
426
- "arg": "in_file",
427
- "mandatory": true,
428
- "description": "FastA file containing the genome 2."
429
- },
430
- {
431
- "name": "Nucleotides",
432
- "opt": "--nucl",
433
- "description": ["Sequences are assumed to be nucleotides (proteins",
434
- "by default)."]
435
- },
436
- {
437
- "name": "Length",
438
- "opt": "--len",
439
- "arg": "integer",
440
- "description": "Minimum alignment length (in residues).",
441
- "default": 0
442
- },
443
- {
444
- "name": "Fraction",
445
- "opt": "--fract",
446
- "arg": "float",
447
- "default": 0.0,
448
- "description": ["Minimum alignment length (as a fraction of the",
449
- "query). If set, requires BLAST+ or Diamond (see Program)."]
450
- },
451
- {
452
- "name": "Identity",
453
- "opt": "--id",
454
- "arg": "float",
455
- "description": "Minimum alignment identity (in %).",
456
- "default": 0.0
457
- },
458
- {
459
- "name": "Bit score",
460
- "opt": "--score",
461
- "arg": "float",
462
- "default": 0.0,
463
- "description": "Minimum alignment score (in bits)."
464
- },
465
- {
466
- "name": "Executables",
467
- "opt": "--bin",
468
- "arg": "in_dir",
469
- "description": ["Directory containing the binaries of the search",
470
- "program."]
471
- },
472
- {
473
- "opt": "--program",
474
- "arg": "select",
475
- "values": ["blast+", "blast", "blat", "diamond"],
476
- "default": "blast+",
477
- "description": "Search program to be used. Default: blast+.",
478
- "note": ["Make sure that you have installed the search program you",
479
- "want to use. If you have downloaded the program, but it's not",
480
- "installed, please use the Executables option above."]
481
- },
482
- {
483
- "opt": "--threads",
484
- "arg": "integer",
485
- "description": "Number of parallel threads to be used.",
486
- "default": 1
487
- },
488
- {
489
- "opt": "--quiet",
490
- "description": "Run quietly (no STDERR output)."
491
- },
492
- ">",
493
- {
494
- "arg": "out_file",
495
- "mandatory": true,
496
- "description": "Reciprocal Best Matches in BLAST tabular format."
497
- }
498
- ]
499
- }
500
- ]
501
- }