miga-base 0.7.26.0 → 0.7.26.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (276) hide show
  1. checksums.yaml +4 -4
  2. data/lib/miga/version.rb +1 -1
  3. data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Archaea_SCG.hmm +41964 -0
  4. data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Bacteria_SCG.hmm +32439 -0
  5. data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Complete_SCG_DB.hmm +62056 -0
  6. data/utils/FastAAI/FastAAI/FastAAI +1336 -0
  7. data/utils/FastAAI/README.md +84 -0
  8. data/utils/FastAAI/kAAI_v1.0_virus.py +1296 -0
  9. data/utils/enveomics/Docs/recplot2.md +244 -0
  10. data/utils/enveomics/Examples/aai-matrix.bash +66 -0
  11. data/utils/enveomics/Examples/ani-matrix.bash +66 -0
  12. data/utils/enveomics/Examples/essential-phylogeny.bash +105 -0
  13. data/utils/enveomics/Examples/unus-genome-phylogeny.bash +100 -0
  14. data/utils/enveomics/LICENSE.txt +73 -0
  15. data/utils/enveomics/Makefile +52 -0
  16. data/utils/enveomics/Manifest/Tasks/aasubs.json +103 -0
  17. data/utils/enveomics/Manifest/Tasks/blasttab.json +786 -0
  18. data/utils/enveomics/Manifest/Tasks/distances.json +161 -0
  19. data/utils/enveomics/Manifest/Tasks/fasta.json +766 -0
  20. data/utils/enveomics/Manifest/Tasks/fastq.json +243 -0
  21. data/utils/enveomics/Manifest/Tasks/graphics.json +126 -0
  22. data/utils/enveomics/Manifest/Tasks/mapping.json +67 -0
  23. data/utils/enveomics/Manifest/Tasks/ogs.json +382 -0
  24. data/utils/enveomics/Manifest/Tasks/other.json +829 -0
  25. data/utils/enveomics/Manifest/Tasks/remote.json +355 -0
  26. data/utils/enveomics/Manifest/Tasks/sequence-identity.json +501 -0
  27. data/utils/enveomics/Manifest/Tasks/tables.json +308 -0
  28. data/utils/enveomics/Manifest/Tasks/trees.json +68 -0
  29. data/utils/enveomics/Manifest/Tasks/variants.json +111 -0
  30. data/utils/enveomics/Manifest/categories.json +156 -0
  31. data/utils/enveomics/Manifest/examples.json +154 -0
  32. data/utils/enveomics/Manifest/tasks.json +4 -0
  33. data/utils/enveomics/Pipelines/assembly.pbs/CONFIG.mock.bash +69 -0
  34. data/utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl +1 -0
  35. data/utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl +1 -0
  36. data/utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl +1 -0
  37. data/utils/enveomics/Pipelines/assembly.pbs/README.md +189 -0
  38. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-2.bash +112 -0
  39. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-3.bash +23 -0
  40. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-4.bash +44 -0
  41. data/utils/enveomics/Pipelines/assembly.pbs/RUNME.bash +50 -0
  42. data/utils/enveomics/Pipelines/assembly.pbs/kSelector.R +37 -0
  43. data/utils/enveomics/Pipelines/assembly.pbs/newbler.pbs +68 -0
  44. data/utils/enveomics/Pipelines/assembly.pbs/newbler_preparator.pl +49 -0
  45. data/utils/enveomics/Pipelines/assembly.pbs/soap.pbs +80 -0
  46. data/utils/enveomics/Pipelines/assembly.pbs/stats.pbs +57 -0
  47. data/utils/enveomics/Pipelines/assembly.pbs/velvet.pbs +63 -0
  48. data/utils/enveomics/Pipelines/blast.pbs/01.pbs.bash +38 -0
  49. data/utils/enveomics/Pipelines/blast.pbs/02.pbs.bash +73 -0
  50. data/utils/enveomics/Pipelines/blast.pbs/03.pbs.bash +21 -0
  51. data/utils/enveomics/Pipelines/blast.pbs/BlastTab.recover_job.pl +72 -0
  52. data/utils/enveomics/Pipelines/blast.pbs/CONFIG.mock.bash +98 -0
  53. data/utils/enveomics/Pipelines/blast.pbs/FastA.split.pl +1 -0
  54. data/utils/enveomics/Pipelines/blast.pbs/README.md +127 -0
  55. data/utils/enveomics/Pipelines/blast.pbs/RUNME.bash +109 -0
  56. data/utils/enveomics/Pipelines/blast.pbs/TASK.check.bash +128 -0
  57. data/utils/enveomics/Pipelines/blast.pbs/TASK.dry.bash +16 -0
  58. data/utils/enveomics/Pipelines/blast.pbs/TASK.eo.bash +22 -0
  59. data/utils/enveomics/Pipelines/blast.pbs/TASK.pause.bash +26 -0
  60. data/utils/enveomics/Pipelines/blast.pbs/TASK.run.bash +89 -0
  61. data/utils/enveomics/Pipelines/blast.pbs/sentinel.pbs.bash +29 -0
  62. data/utils/enveomics/Pipelines/idba.pbs/README.md +49 -0
  63. data/utils/enveomics/Pipelines/idba.pbs/RUNME.bash +95 -0
  64. data/utils/enveomics/Pipelines/idba.pbs/run.pbs +56 -0
  65. data/utils/enveomics/Pipelines/trim.pbs/README.md +54 -0
  66. data/utils/enveomics/Pipelines/trim.pbs/RUNME.bash +70 -0
  67. data/utils/enveomics/Pipelines/trim.pbs/run.pbs +130 -0
  68. data/utils/enveomics/README.md +42 -0
  69. data/utils/enveomics/Scripts/AAsubs.log2ratio.rb +171 -0
  70. data/utils/enveomics/Scripts/Aln.cat.rb +163 -0
  71. data/utils/enveomics/Scripts/Aln.convert.pl +35 -0
  72. data/utils/enveomics/Scripts/AlphaDiversity.pl +152 -0
  73. data/utils/enveomics/Scripts/BedGraph.tad.rb +93 -0
  74. data/utils/enveomics/Scripts/BedGraph.window.rb +71 -0
  75. data/utils/enveomics/Scripts/BlastPairwise.AAsubs.pl +102 -0
  76. data/utils/enveomics/Scripts/BlastTab.addlen.rb +63 -0
  77. data/utils/enveomics/Scripts/BlastTab.advance.bash +48 -0
  78. data/utils/enveomics/Scripts/BlastTab.best_hit_sorted.pl +55 -0
  79. data/utils/enveomics/Scripts/BlastTab.catsbj.pl +104 -0
  80. data/utils/enveomics/Scripts/BlastTab.cogCat.rb +76 -0
  81. data/utils/enveomics/Scripts/BlastTab.filter.pl +47 -0
  82. data/utils/enveomics/Scripts/BlastTab.kegg_pep2path_rest.pl +194 -0
  83. data/utils/enveomics/Scripts/BlastTab.metaxaPrep.pl +104 -0
  84. data/utils/enveomics/Scripts/BlastTab.pairedHits.rb +157 -0
  85. data/utils/enveomics/Scripts/BlastTab.recplot2.R +48 -0
  86. data/utils/enveomics/Scripts/BlastTab.seqdepth.pl +86 -0
  87. data/utils/enveomics/Scripts/BlastTab.seqdepth_ZIP.pl +119 -0
  88. data/utils/enveomics/Scripts/BlastTab.seqdepth_nomedian.pl +86 -0
  89. data/utils/enveomics/Scripts/BlastTab.subsample.pl +47 -0
  90. data/utils/enveomics/Scripts/BlastTab.sumPerHit.pl +114 -0
  91. data/utils/enveomics/Scripts/BlastTab.taxid2taxrank.pl +90 -0
  92. data/utils/enveomics/Scripts/BlastTab.topHits_sorted.rb +101 -0
  93. data/utils/enveomics/Scripts/Chao1.pl +97 -0
  94. data/utils/enveomics/Scripts/CharTable.classify.rb +234 -0
  95. data/utils/enveomics/Scripts/EBIseq2tax.rb +83 -0
  96. data/utils/enveomics/Scripts/FastA.N50.pl +56 -0
  97. data/utils/enveomics/Scripts/FastA.extract.rb +152 -0
  98. data/utils/enveomics/Scripts/FastA.filter.pl +52 -0
  99. data/utils/enveomics/Scripts/FastA.filterLen.pl +28 -0
  100. data/utils/enveomics/Scripts/FastA.filterN.pl +60 -0
  101. data/utils/enveomics/Scripts/FastA.fragment.rb +92 -0
  102. data/utils/enveomics/Scripts/FastA.gc.pl +42 -0
  103. data/utils/enveomics/Scripts/FastA.interpose.pl +93 -0
  104. data/utils/enveomics/Scripts/FastA.length.pl +38 -0
  105. data/utils/enveomics/Scripts/FastA.mask.rb +89 -0
  106. data/utils/enveomics/Scripts/FastA.per_file.pl +36 -0
  107. data/utils/enveomics/Scripts/FastA.qlen.pl +57 -0
  108. data/utils/enveomics/Scripts/FastA.rename.pl +65 -0
  109. data/utils/enveomics/Scripts/FastA.revcom.pl +23 -0
  110. data/utils/enveomics/Scripts/FastA.sample.rb +83 -0
  111. data/utils/enveomics/Scripts/FastA.slider.pl +85 -0
  112. data/utils/enveomics/Scripts/FastA.split.pl +55 -0
  113. data/utils/enveomics/Scripts/FastA.split.rb +79 -0
  114. data/utils/enveomics/Scripts/FastA.subsample.pl +131 -0
  115. data/utils/enveomics/Scripts/FastA.tag.rb +65 -0
  116. data/utils/enveomics/Scripts/FastA.wrap.rb +48 -0
  117. data/utils/enveomics/Scripts/FastQ.filter.pl +54 -0
  118. data/utils/enveomics/Scripts/FastQ.interpose.pl +90 -0
  119. data/utils/enveomics/Scripts/FastQ.offset.pl +90 -0
  120. data/utils/enveomics/Scripts/FastQ.split.pl +53 -0
  121. data/utils/enveomics/Scripts/FastQ.tag.rb +63 -0
  122. data/utils/enveomics/Scripts/FastQ.test-error.rb +81 -0
  123. data/utils/enveomics/Scripts/FastQ.toFastA.awk +24 -0
  124. data/utils/enveomics/Scripts/GFF.catsbj.pl +127 -0
  125. data/utils/enveomics/Scripts/GenBank.add_fields.rb +84 -0
  126. data/utils/enveomics/Scripts/HMM.essential.rb +351 -0
  127. data/utils/enveomics/Scripts/HMM.haai.rb +168 -0
  128. data/utils/enveomics/Scripts/HMMsearch.extractIds.rb +83 -0
  129. data/utils/enveomics/Scripts/JPlace.distances.rb +88 -0
  130. data/utils/enveomics/Scripts/JPlace.to_iToL.rb +320 -0
  131. data/utils/enveomics/Scripts/M5nr.getSequences.rb +81 -0
  132. data/utils/enveomics/Scripts/MeTaxa.distribution.pl +198 -0
  133. data/utils/enveomics/Scripts/MyTaxa.fragsByTax.pl +35 -0
  134. data/utils/enveomics/Scripts/MyTaxa.seq-taxrank.rb +49 -0
  135. data/utils/enveomics/Scripts/NCBIacc2tax.rb +92 -0
  136. data/utils/enveomics/Scripts/Newick.autoprune.R +27 -0
  137. data/utils/enveomics/Scripts/RAxML-EPA.to_iToL.pl +228 -0
  138. data/utils/enveomics/Scripts/RecPlot2.compareIdentities.R +32 -0
  139. data/utils/enveomics/Scripts/RefSeq.download.bash +48 -0
  140. data/utils/enveomics/Scripts/SRA.download.bash +57 -0
  141. data/utils/enveomics/Scripts/TRIBS.plot-test.R +36 -0
  142. data/utils/enveomics/Scripts/TRIBS.test.R +39 -0
  143. data/utils/enveomics/Scripts/Table.barplot.R +31 -0
  144. data/utils/enveomics/Scripts/Table.df2dist.R +30 -0
  145. data/utils/enveomics/Scripts/Table.filter.pl +61 -0
  146. data/utils/enveomics/Scripts/Table.merge.pl +77 -0
  147. data/utils/enveomics/Scripts/Table.replace.rb +69 -0
  148. data/utils/enveomics/Scripts/Table.round.rb +63 -0
  149. data/utils/enveomics/Scripts/Table.split.pl +57 -0
  150. data/utils/enveomics/Scripts/Taxonomy.silva2ncbi.rb +227 -0
  151. data/utils/enveomics/Scripts/VCF.KaKs.rb +147 -0
  152. data/utils/enveomics/Scripts/VCF.SNPs.rb +88 -0
  153. data/utils/enveomics/Scripts/aai.rb +418 -0
  154. data/utils/enveomics/Scripts/ani.rb +362 -0
  155. data/utils/enveomics/Scripts/clust.rand.rb +102 -0
  156. data/utils/enveomics/Scripts/gi2tax.rb +103 -0
  157. data/utils/enveomics/Scripts/in_silico_GA_GI.pl +96 -0
  158. data/utils/enveomics/Scripts/lib/data/dupont_2012_essential.hmm.gz +0 -0
  159. data/utils/enveomics/Scripts/lib/data/lee_2019_essential.hmm.gz +0 -0
  160. data/utils/enveomics/Scripts/lib/enveomics.R +1 -0
  161. data/utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb +24 -0
  162. data/utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb +253 -0
  163. data/utils/enveomics/Scripts/lib/enveomics_rb/og.rb +182 -0
  164. data/utils/enveomics/Scripts/lib/enveomics_rb/remote_data.rb +74 -0
  165. data/utils/enveomics/Scripts/lib/enveomics_rb/seq_range.rb +237 -0
  166. data/utils/enveomics/Scripts/lib/enveomics_rb/stat.rb +30 -0
  167. data/utils/enveomics/Scripts/lib/enveomics_rb/vcf.rb +135 -0
  168. data/utils/enveomics/Scripts/ogs.annotate.rb +88 -0
  169. data/utils/enveomics/Scripts/ogs.core-pan.rb +160 -0
  170. data/utils/enveomics/Scripts/ogs.extract.rb +125 -0
  171. data/utils/enveomics/Scripts/ogs.mcl.rb +186 -0
  172. data/utils/enveomics/Scripts/ogs.rb +104 -0
  173. data/utils/enveomics/Scripts/ogs.stats.rb +131 -0
  174. data/utils/enveomics/Scripts/rbm.rb +146 -0
  175. data/utils/enveomics/Tests/Makefile +10 -0
  176. data/utils/enveomics/Tests/Mgen_M2288.faa +3189 -0
  177. data/utils/enveomics/Tests/Mgen_M2288.fna +8282 -0
  178. data/utils/enveomics/Tests/Mgen_M2321.fna +8288 -0
  179. data/utils/enveomics/Tests/Nequ_Kin4M.faa +2970 -0
  180. data/utils/enveomics/Tests/Xanthomonas_oryzae-PilA.tribs.Rdata +0 -0
  181. data/utils/enveomics/Tests/Xanthomonas_oryzae-PilA.txt +7 -0
  182. data/utils/enveomics/Tests/Xanthomonas_oryzae.aai-mat.tsv +17 -0
  183. data/utils/enveomics/Tests/Xanthomonas_oryzae.aai.tsv +137 -0
  184. data/utils/enveomics/Tests/a_mg.cds-go.blast.tsv +123 -0
  185. data/utils/enveomics/Tests/a_mg.reads-cds.blast.tsv +200 -0
  186. data/utils/enveomics/Tests/a_mg.reads-cds.counts.tsv +55 -0
  187. data/utils/enveomics/Tests/alkB.nwk +1 -0
  188. data/utils/enveomics/Tests/anthrax-cansnp-data.tsv +13 -0
  189. data/utils/enveomics/Tests/anthrax-cansnp-key.tsv +17 -0
  190. data/utils/enveomics/Tests/hiv1.faa +59 -0
  191. data/utils/enveomics/Tests/hiv1.fna +134 -0
  192. data/utils/enveomics/Tests/hiv2.faa +70 -0
  193. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv +233 -0
  194. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.lim +1 -0
  195. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.rec +233 -0
  196. data/utils/enveomics/Tests/phyla_counts.tsv +10 -0
  197. data/utils/enveomics/Tests/primate_lentivirus.ogs +11 -0
  198. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv1.rbm +9 -0
  199. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv2.rbm +8 -0
  200. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-siv.rbm +6 -0
  201. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-hiv2.rbm +9 -0
  202. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-siv.rbm +6 -0
  203. data/utils/enveomics/Tests/primate_lentivirus.rbm/siv-siv.rbm +6 -0
  204. data/utils/enveomics/build_enveomics_r.bash +45 -0
  205. data/utils/enveomics/enveomics.R/DESCRIPTION +31 -0
  206. data/utils/enveomics/enveomics.R/NAMESPACE +39 -0
  207. data/utils/enveomics/enveomics.R/R/autoprune.R +155 -0
  208. data/utils/enveomics/enveomics.R/R/barplot.R +184 -0
  209. data/utils/enveomics/enveomics.R/R/cliopts.R +135 -0
  210. data/utils/enveomics/enveomics.R/R/df2dist.R +154 -0
  211. data/utils/enveomics/enveomics.R/R/growthcurve.R +331 -0
  212. data/utils/enveomics/enveomics.R/R/recplot.R +354 -0
  213. data/utils/enveomics/enveomics.R/R/recplot2.R +1631 -0
  214. data/utils/enveomics/enveomics.R/R/tribs.R +583 -0
  215. data/utils/enveomics/enveomics.R/R/utils.R +50 -0
  216. data/utils/enveomics/enveomics.R/README.md +80 -0
  217. data/utils/enveomics/enveomics.R/data/growth.curves.rda +0 -0
  218. data/utils/enveomics/enveomics.R/data/phyla.counts.rda +0 -0
  219. data/utils/enveomics/enveomics.R/man/cash-enve.GrowthCurve-method.Rd +17 -0
  220. data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2-method.Rd +17 -0
  221. data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2.Peak-method.Rd +17 -0
  222. data/utils/enveomics/enveomics.R/man/enve.GrowthCurve-class.Rd +25 -0
  223. data/utils/enveomics/enveomics.R/man/enve.TRIBS-class.Rd +46 -0
  224. data/utils/enveomics/enveomics.R/man/enve.TRIBS.merge.Rd +23 -0
  225. data/utils/enveomics/enveomics.R/man/enve.TRIBStest-class.Rd +47 -0
  226. data/utils/enveomics/enveomics.R/man/enve.__prune.iter.Rd +23 -0
  227. data/utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd +23 -0
  228. data/utils/enveomics/enveomics.R/man/enve.__tribs.Rd +32 -0
  229. data/utils/enveomics/enveomics.R/man/enve.barplot.Rd +91 -0
  230. data/utils/enveomics/enveomics.R/man/enve.cliopts.Rd +57 -0
  231. data/utils/enveomics/enveomics.R/man/enve.col.alpha.Rd +24 -0
  232. data/utils/enveomics/enveomics.R/man/enve.col2alpha.Rd +19 -0
  233. data/utils/enveomics/enveomics.R/man/enve.df2dist.Rd +39 -0
  234. data/utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd +38 -0
  235. data/utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd +40 -0
  236. data/utils/enveomics/enveomics.R/man/enve.growthcurve.Rd +67 -0
  237. data/utils/enveomics/enveomics.R/man/enve.prune.dist.Rd +37 -0
  238. data/utils/enveomics/enveomics.R/man/enve.recplot.Rd +122 -0
  239. data/utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd +45 -0
  240. data/utils/enveomics/enveomics.R/man/enve.recplot2.ANIr.Rd +24 -0
  241. data/utils/enveomics/enveomics.R/man/enve.recplot2.Rd +68 -0
  242. data/utils/enveomics/enveomics.R/man/enve.recplot2.__counts.Rd +25 -0
  243. data/utils/enveomics/enveomics.R/man/enve.recplot2.__peakHist.Rd +21 -0
  244. data/utils/enveomics/enveomics.R/man/enve.recplot2.__whichClosestPeak.Rd +19 -0
  245. data/utils/enveomics/enveomics.R/man/enve.recplot2.changeCutoff.Rd +19 -0
  246. data/utils/enveomics/enveomics.R/man/enve.recplot2.compareIdentities.Rd +41 -0
  247. data/utils/enveomics/enveomics.R/man/enve.recplot2.coordinates.Rd +29 -0
  248. data/utils/enveomics/enveomics.R/man/enve.recplot2.corePeak.Rd +18 -0
  249. data/utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd +40 -0
  250. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd +36 -0
  251. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_e.Rd +19 -0
  252. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_m.Rd +19 -0
  253. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__emauto_one.Rd +27 -0
  254. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mow_one.Rd +41 -0
  255. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mower.Rd +17 -0
  256. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.em.Rd +43 -0
  257. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.emauto.Rd +37 -0
  258. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.mower.Rd +74 -0
  259. data/utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd +59 -0
  260. data/utils/enveomics/enveomics.R/man/enve.recplot2.seqdepth.Rd +27 -0
  261. data/utils/enveomics/enveomics.R/man/enve.recplot2.windowDepthThreshold.Rd +32 -0
  262. data/utils/enveomics/enveomics.R/man/enve.tribs.Rd +59 -0
  263. data/utils/enveomics/enveomics.R/man/enve.tribs.test.Rd +28 -0
  264. data/utils/enveomics/enveomics.R/man/enve.truncate.Rd +27 -0
  265. data/utils/enveomics/enveomics.R/man/growth.curves.Rd +14 -0
  266. data/utils/enveomics/enveomics.R/man/phyla.counts.Rd +13 -0
  267. data/utils/enveomics/enveomics.R/man/plot.enve.GrowthCurve.Rd +63 -0
  268. data/utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd +38 -0
  269. data/utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd +38 -0
  270. data/utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd +111 -0
  271. data/utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd +19 -0
  272. data/utils/enveomics/enveomics.R/man/summary.enve.TRIBS.Rd +19 -0
  273. data/utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd +19 -0
  274. data/utils/enveomics/globals.mk +8 -0
  275. data/utils/enveomics/manifest.json +9 -0
  276. metadata +277 -4
@@ -0,0 +1,161 @@
1
+ {
2
+ "tasks": [
3
+ {
4
+ "task": "TRIBS.test.R",
5
+ "description": ["Estimates the empirical difference between all the",
6
+ "distances in a set of objects and a subset, together with its",
7
+ "statistical significance."],
8
+ "help_arg": "--help",
9
+ "requires": [
10
+ { "r_package": "optparse" },
11
+ { "r_package": "enveomics.R" }
12
+ ],
13
+ "see_also": ["TRIBS.plot-test.R"],
14
+ "options": [
15
+ {
16
+ "opt": "--dist",
17
+ "arg": "in_file",
18
+ "mandatory": true,
19
+ "description": "A tab-delimited matrix of distances."
20
+ },
21
+ {
22
+ "opt": "--selection",
23
+ "arg": "in_file",
24
+ "mandatory": true,
25
+ "description": "A list of names with the selection to evaluate."
26
+ },
27
+ {
28
+ "opt": "--replicates",
29
+ "arg": "integer",
30
+ "default": 1000,
31
+ "description": "Number of replications per point."
32
+ },
33
+ {
34
+ "opt": "--summary-fx",
35
+ "arg": "string",
36
+ "description": ["Function to summarize the distance distributions in",
37
+ "a given replicate. By default, the median distance is estimated."]
38
+ },
39
+ {
40
+ "opt": "--dist-method",
41
+ "arg": "string",
42
+ "default": "euclidean",
43
+ "description": ["Distance method between random points and samples",
44
+ "in the transformed space. See the R function 'dist'."]
45
+ },
46
+ {
47
+ "opt": "--dimensions",
48
+ "arg": "integer",
49
+ "description": ["Dimensions to use in the NMDS. By default, 5% of",
50
+ "the selection length."]
51
+ },
52
+ {
53
+ "opt": "--threads",
54
+ "arg": "integer",
55
+ "default": 2,
56
+ "description": "Number of threads to use."
57
+ },
58
+ {
59
+ "opt": "--verbosity",
60
+ "arg": "integer",
61
+ "default": 1,
62
+ "description": ["Verbosity. Use 0 to run quietly, increase for",
63
+ "additional information."]
64
+ },
65
+ {
66
+ "arg": "out_file",
67
+ "mandatory": true,
68
+ "description": "Output file with the TRIBS test R object."
69
+ },
70
+ {
71
+ "name": "Bins",
72
+ "arg": "integer",
73
+ "default": 50,
74
+ "description": "Number of bins to evaluate in the range of distances."
75
+ }
76
+ ]
77
+ },
78
+ {
79
+ "task": "TRIBS.plot-test.R",
80
+ "description": "Plots an `enve.TRIBStest` object.",
81
+ "requires": [
82
+ { "r_package": "optparse" },
83
+ { "r_package": "enveomics.R" }
84
+ ],
85
+ "see_also": ["TRIBS.test.R"],
86
+ "help_arg": "--help",
87
+ "options": [
88
+ {
89
+ "name": "Input TRIBS Test",
90
+ "opt": "--x",
91
+ "arg": "in_file",
92
+ "mandatory": true,
93
+ "description": "'enve.TRIBStest' object to plot."
94
+ },
95
+ {
96
+ "opt": "--type",
97
+ "arg": "select",
98
+ "values": ["overlap","difference"],
99
+ "default": "overlap",
100
+ "description": ["What to plot. 'overlap' generates a plot of the two",
101
+ "contrasting empirical PDFs (to compare against each other),",
102
+ "'difference' produces a plot of the differences between the",
103
+ "empirical PDFs (to compare against zero)."]
104
+ },
105
+ {
106
+ "opt": "--col",
107
+ "arg": "string",
108
+ "default": "#00000044",
109
+ "description": "Main color of the plot if type='difference'."
110
+ },
111
+ {
112
+ "opt": "--col1",
113
+ "arg": "string",
114
+ "description": ["First color of the plot if 'Type' is overlap. 'Col'",
115
+ "by default."]
116
+ },
117
+ {
118
+ "opt": "--col2",
119
+ "arg": "string",
120
+ "default": "#44001144",
121
+ "description": "Second color of the plot if 'Type' is overlap."
122
+ },
123
+ {
124
+ "opt": "--ylab",
125
+ "arg": "string",
126
+ "default": "Probability",
127
+ "description": "Y-axis label."
128
+ },
129
+ {
130
+ "opt": "--xlim",
131
+ "arg": "string",
132
+ "description": "X-axis limits, separate values by comma."
133
+ },
134
+ {
135
+ "opt": "--ylim",
136
+ "arg": "string",
137
+ "description": "Y-axis limits, separate values by comma."
138
+ },
139
+ {
140
+ "arg": "out_file",
141
+ "mandatory": true,
142
+ "description": "Output file in PDF format."
143
+ },
144
+ {
145
+ "name": "Width",
146
+ "arg": "float",
147
+ "default": 7.0,
148
+ "mandatory": true,
149
+ "description": "Width of the plot in inches."
150
+ },
151
+ {
152
+ "name": "Height",
153
+ "arg": "float",
154
+ "default": 7.0,
155
+ "mandatory": true,
156
+ "description": "Height of the plot in inches."
157
+ }
158
+ ]
159
+ }
160
+ ]
161
+ }
@@ -0,0 +1,766 @@
1
+ {
2
+ "tasks": [
3
+ {
4
+ "task": "FastA.N50.pl",
5
+ "description": ["Calculates the N50 value of a set of sequences.",
6
+ "Alternatively, it can calculate other N** values. It also calculates",
7
+ "the total number of sequences and the total added length."],
8
+ "help_arg": "",
9
+ "see_also": ["FastA.length.pl"],
10
+ "options": [
11
+ {
12
+ "name": "Sequences",
13
+ "arg": "in_file",
14
+ "mandatory": true,
15
+ "description": "A FastA file containing the sequences."
16
+ },
17
+ {
18
+ "name": "Minimum length",
19
+ "arg": "integer",
20
+ "description": "Minimum length to take into consideration.",
21
+ "default": 0
22
+ },
23
+ {
24
+ "name": "NXX",
25
+ "arg": "integer",
26
+ "description": "Value NXX to calculate.",
27
+ "default": 50
28
+ }
29
+ ]
30
+ },
31
+ {
32
+ "task": "FastA.filter.pl",
33
+ "description": "Extracts a subset of sequences from a FastA file.",
34
+ "help_arg": "-h",
35
+ "see_also": ["FastQ.filter.pl"],
36
+ "options": [
37
+ {
38
+ "opt": "-r",
39
+ "description": ["Reverse list. Extracts sequences NOT present in the",
40
+ "list."]
41
+ },
42
+ {
43
+ "opt": "-q",
44
+ "description": "Runs quietly."
45
+ },
46
+ {
47
+ "name": "List",
48
+ "arg": "in_file",
49
+ "mandatory": true,
50
+ "description": "List of sequences to extract."
51
+ },
52
+ {
53
+ "name": "Sequences",
54
+ "arg": "in_file",
55
+ "mandatory": true,
56
+ "description": "FastA file containing the superset of sequences."
57
+ },
58
+ ">",
59
+ {
60
+ "name": "Subset",
61
+ "arg": "out_file",
62
+ "mandatory": true,
63
+ "description": "FastA file to be created."
64
+ }
65
+ ]
66
+ },
67
+ {
68
+ "task": "FastA.filterLen.pl",
69
+ "description": "Filters a multi-FastA file by length.",
70
+ "requires": [ { "perl_lib": "Bio::SeqIO" } ],
71
+ "cite": [["Stajich et al, 2002, GRes",
72
+ "http://dx.doi.org/10.1101/gr.361602"]],
73
+ "help_arg": "",
74
+ "options": [
75
+ {
76
+ "arg": "in_file",
77
+ "mandatory": true,
78
+ "description": "Input FastA file."
79
+ },
80
+ {
81
+ "name": "Minimum length",
82
+ "arg": "integer",
83
+ "mandatory": true,
84
+ "description": "Minimum length to report a sequence."
85
+ },
86
+ ">",
87
+ {
88
+ "arg": "out_file",
89
+ "mandatory": true,
90
+ "description": "Filtered FastA file."
91
+ }
92
+ ]
93
+ },
94
+ {
95
+ "task": "FastA.filterN.pl",
96
+ "description": ["Filter sequences by N-content and presence of long",
97
+ "homopolymers."],
98
+ "help_arg": "",
99
+ "options": [
100
+ {
101
+ "name": "Sequences",
102
+ "arg": "in_file",
103
+ "mandatory": true,
104
+ "description": "Input file in FastA format."
105
+ },
106
+ {
107
+ "name": "Content",
108
+ "arg": "float",
109
+ "default": 0.5,
110
+ "mandatory": true,
111
+ "description": ["A number between 0 and 1 indicating the maximum",
112
+ "proportion of Ns (1 to turn off, 0.5 by default)."]
113
+ },
114
+ {
115
+ "name": "Stretch",
116
+ "arg": "integer",
117
+ "default": 100,
118
+ "description": ["A number indicating the maximum number of",
119
+ "consecutive identical nucleotides allowed (0 to turn off, 100 by",
120
+ "default)."]
121
+ },
122
+ ">",
123
+ {
124
+ "name": "Filtered",
125
+ "arg": "out_file",
126
+ "mandatory": true,
127
+ "description": "Filtered set of sequences."
128
+ }
129
+ ]
130
+ },
131
+ {
132
+ "task": "FastA.gc.pl",
133
+ "description": "Estimates the G+C content of sequences.",
134
+ "help_arg": "",
135
+ "options": [
136
+ {
137
+ "name": "seqs.fa",
138
+ "arg": "in_file",
139
+ "multiple_sep": " ",
140
+ "mandatory": true,
141
+ "description": "One or more FastA files."
142
+ },
143
+ ">",
144
+ {
145
+ "name": "gc.txt",
146
+ "arg": "out_file",
147
+ "mandatory": true,
148
+ "description": "A table with the G+C content of the sequences."
149
+ }
150
+ ]
151
+ },
152
+ {
153
+ "task": "FastA.interpose.pl",
154
+ "description": ["Interpose sequences in FastA format from two files into",
155
+ "one output file. If more than two files are provided, the script will",
156
+ "interpose all the input files."],
157
+ "see_also": ["FastA.split.rb","FastQ.interpose.pl"],
158
+ "warn": ["Please note that this script will check for the consistency of",
159
+ "the names (assuming a pair of related reads contains the same name",
160
+ "varying only in a trailing slash (/) followed by a digit. If you want",
161
+ "to turn this feature off just set the checking period to zero. If",
162
+ "you want to decrease the sampling period (to speed the script up) or",
163
+ "increase it (to make it more sensitive to errors) just change the ",
164
+ "checking period accordingly."],
165
+ "help_arg": "",
166
+ "options": [
167
+ {
168
+ "name": "Checking period",
169
+ "opt": "-T",
170
+ "arg": "integer",
171
+ "default": 1000,
172
+ "description": "Sampling period for names evaluation."
173
+ },
174
+ {
175
+ "arg": "out_file",
176
+ "mandatory": true,
177
+ "description": "Output FastA file."
178
+ },
179
+ {
180
+ "name": "Input FastA 1",
181
+ "arg": "in_file",
182
+ "mandatory": true,
183
+ "description": "First FastA file."
184
+ },
185
+ {
186
+ "name": "Input FastA 2",
187
+ "arg": "in_file",
188
+ "mandatory": true,
189
+ "description": "Second FastA file."
190
+ },
191
+ {
192
+ "name": "Additional FastA",
193
+ "arg": "in_file",
194
+ "multiple_sep": " ",
195
+ "description": "Any additional FastA files (or none)."
196
+ }
197
+ ]
198
+ },
199
+ {
200
+ "task": "FastA.length.pl",
201
+ "description": "Returns the length of sequences in (multi-)FastA.",
202
+ "see_also": ["FastA.N50.pl"],
203
+ "help_arg": "",
204
+ "options": [
205
+ {
206
+ "arg": "in_file",
207
+ "multiple_sep": " ",
208
+ "mandatory": true,
209
+ "description": "One or more FastA files."
210
+ },
211
+ ">",
212
+ {
213
+ "arg": "out_file",
214
+ "mandatory": true,
215
+ "description": "A table with the lengths of the sequences."
216
+ }
217
+ ]
218
+ },
219
+ {
220
+ "task": "FastA.mask.rb",
221
+ "description": "Mask sequence region(s) in a FastA file.",
222
+ "help_arg": "--help",
223
+ "options": [
224
+ {
225
+ "opt": "--in",
226
+ "arg": "in_file",
227
+ "mandatory": true,
228
+ "description": "Input FastA file."
229
+ },
230
+ {
231
+ "opt": "--out",
232
+ "arg": "out_file",
233
+ "mandatory": true,
234
+ "description": "Output FastA file."
235
+ },
236
+ {
237
+ "opt": "--regions",
238
+ "arg": "string",
239
+ "mandatory": true,
240
+ "description": ["Regions to mask separated by commas.",
241
+ "Each region must be in the format \"sequence_id:from..to\"."]
242
+ },
243
+ {
244
+ "opt": "--symbol",
245
+ "arg": "string",
246
+ "default": "N",
247
+ "description": "Character used to mask the region(s)."
248
+ },
249
+ {
250
+ "opt": "--trim",
251
+ "description": ["Trim masked regions extending to the edge of a",
252
+ "sequence."]
253
+ },
254
+ {
255
+ "opt": "--wrap",
256
+ "arg": "integer",
257
+ "default": 70,
258
+ "description": ["Line length to wrap sequences. Use 0 to generate",
259
+ "1-line sequences."]
260
+ }
261
+ ]
262
+ },
263
+ {
264
+ "task": "FastA.qlen.pl",
265
+ "description": ["Calculates the quartiles of the length in a set of",
266
+ "sequences. The Q2 is also known as the median. Q0 is the minimum",
267
+ "length, and Q4 is the maximum length. It also calculates TOTAL, the",
268
+ "added length of the sequences in the file, and AVG, the average",
269
+ "length."],
270
+ "help_arg": "",
271
+ "options": [
272
+ {
273
+ "name": "Sequences",
274
+ "arg": "in_file",
275
+ "mandatory": true,
276
+ "description": "A FastA file containing the sequences."
277
+ },
278
+ {
279
+ "name": "Minimum Length",
280
+ "arg": "integer",
281
+ "default": 0,
282
+ "description": "The minimum length to take into consideration."
283
+ }
284
+ ]
285
+ },
286
+ {
287
+ "task": "FastA.rename.pl",
288
+ "description": "Renames a set of sequences in FastA format.",
289
+ "help_arg": "-h",
290
+ "options": [
291
+ {
292
+ "name": "Filter list",
293
+ "opt": "-f",
294
+ "description": "Ignore sequences NOT present in the list."
295
+ },
296
+ {
297
+ "name": "Quiet",
298
+ "opt": "-q",
299
+ "description": "Runs quietly."
300
+ },
301
+ {
302
+ "name": "List.txt",
303
+ "arg": "in_file",
304
+ "mandatory": true,
305
+ "description": ["Tab-delimited list of sequences, with the original",
306
+ "ID in the first column and the ID to use in the second."]
307
+ },
308
+ {
309
+ "name": "Seqs.fa",
310
+ "arg": "in_file",
311
+ "mandatory": true,
312
+ "description": "FastA file containing the superset of sequences."
313
+ },
314
+ ">",
315
+ {
316
+ "name": "Renamed.fa",
317
+ "arg": "out_file",
318
+ "mandatory": true,
319
+ "description": "FastA file to be created."
320
+ }
321
+ ]
322
+ },
323
+ {
324
+ "task": "FastA.revcom.pl",
325
+ "description": "Reverse-complement sequences in FastA format.",
326
+ "requires": [ { "perl_lib": "Bio::SeqIO" } ],
327
+ "cite": [["Stajich et al, 2002, GRes",
328
+ "http://dx.doi.org/10.1101/gr.361602"]],
329
+ "help_arg": "--help",
330
+ "options": [
331
+ "<",
332
+ {
333
+ "arg": "in_file",
334
+ "mandatory": true,
335
+ "description": "Input file in FastA format."
336
+ },
337
+ ">",
338
+ {
339
+ "arg": "out_file",
340
+ "mandatory": true,
341
+ "description": "Output file in FastA format."
342
+ }
343
+ ]
344
+ },
345
+ {
346
+ "task": "FastA.sample.rb",
347
+ "description": ["Samples a random set of sequences from a multi-FastA",
348
+ "file."],
349
+ "help_arg": "--help",
350
+ "see_also": "FastA.subsample.pl",
351
+ "options": [
352
+ {
353
+ "name": "Input File",
354
+ "opt": "--in",
355
+ "arg": "in_file",
356
+ "mandatory": true,
357
+ "description": "Input FastA file."
358
+ },
359
+ {
360
+ "name": "Output file",
361
+ "opt": "--out",
362
+ "arg": "out_file",
363
+ "mandatory": true,
364
+ "description": "Output FastA file."
365
+ },
366
+ {
367
+ "opt": "--fraction",
368
+ "arg": "float",
369
+ "description": ["Fraction of sequences to sample [0-1].",
370
+ "Mandatory unless Number is provided."]
371
+ },
372
+ {
373
+ "opt": "--number",
374
+ "arg": "integer",
375
+ "description": ["Number of sequences to sample.",
376
+ "Mandatory unless -f is provided."]
377
+ },
378
+ {
379
+ "opt": "--replacement",
380
+ "description": "Sample with replacement."
381
+ },
382
+ {
383
+ "opt": "--quiet",
384
+ "description": "Run quietly (no STDERR output)."
385
+ }
386
+ ]
387
+ },
388
+ {
389
+ "task": "FastA.slider.pl",
390
+ "description": "Slices sequences in fixed- or variable-length windows.",
391
+ "help_arg": "-help",
392
+ "options": [
393
+ {
394
+ "opt": "-seq",
395
+ "arg": "in_file",
396
+ "mandatory": true,
397
+ "description": "Input file in FastA format."
398
+ },
399
+ {
400
+ "opt": "-out",
401
+ "arg": "out_file",
402
+ "mandatory": true,
403
+ "description": "Output file in FastA format."
404
+ },
405
+ {
406
+ "opt": "-win",
407
+ "arg": "integer",
408
+ "default": 18,
409
+ "description": "Window size."
410
+ },
411
+ {
412
+ "opt": "-step",
413
+ "arg": "integer",
414
+ "default": 1,
415
+ "description": "Step size."
416
+ },
417
+ {
418
+ "name": "Length error",
419
+ "opt": "-lerr",
420
+ "arg": "integer",
421
+ "default": 2,
422
+ "description": "Expected error in chunks length."
423
+ },
424
+ {
425
+ "opt": "-comm",
426
+ "arg": "select",
427
+ "values": [0,1],
428
+ "default": 0,
429
+ "description": ["Generate FastA comments (leaded by semi-colon) to",
430
+ "separate input sequences. Set to 0 for no-comments, to 1 for",
431
+ "comments."]
432
+ },
433
+ {
434
+ "opt": "-short",
435
+ "arg": "select",
436
+ "values": [0,1],
437
+ "default": 0,
438
+ "description": ["Use chunks shorter than the window size 'as is'.",
439
+ "Set to 0 to discard those chunks, to 1 to use them."]
440
+ }
441
+ ]
442
+ },
443
+ {
444
+ "task": "FastA.split.rb",
445
+ "description": ["Evenly splits a multi-FastA file into multiple",
446
+ "multi-FastA files."],
447
+ "see_also": ["FastA.interpose.pl","FastQ.split.pl"],
448
+ "help_arg": "--help",
449
+ "options": [
450
+ {
451
+ "opt": "--input",
452
+ "arg": "in_file",
453
+ "mandatory": true,
454
+ "description": "Input FastA file."
455
+ },
456
+ {
457
+ "opt": "--prefix",
458
+ "arg": "out_file",
459
+ "mandatory": true,
460
+ "description": "Prefix of output FastA files."
461
+ },
462
+ {
463
+ "opt": "--number",
464
+ "arg": "integer",
465
+ "default": 12,
466
+ "description": "Number of output files to produce."
467
+ },
468
+ {
469
+ "opt": "--zero-padded",
470
+ "description": "Use zero-padded numbers as output index."
471
+ },
472
+ {
473
+ "opt": "--lowercase-letters",
474
+ "description": "Use lowercase letters as output index."
475
+ },
476
+ {
477
+ "name": "Output format",
478
+ "opt": "--out",
479
+ "arg": "string",
480
+ "default": "%s.%s.fa",
481
+ "description": ["Format of output filenames, where %s are replaced",
482
+ "by prefix and index."]
483
+ },
484
+ {
485
+ "opt": "--quiet",
486
+ "description": "Run quietly (no STDERR output)."
487
+ }
488
+ ]
489
+ },
490
+ {
491
+ "task": "FastA.split.pl",
492
+ "description": "Splits a FastA file into two or more files.",
493
+ "warn": "Deprecated in favor of FastA.split.rb.",
494
+ "see_also": ["FastA.split.rb","FastA.interpose.pl","FastQ.split.pl"],
495
+ "help_arg": "",
496
+ "options": [
497
+ {
498
+ "arg": "in_file",
499
+ "mandatory": true,
500
+ "description": "Input file in FastA format."
501
+ },
502
+ {
503
+ "name": "Out base",
504
+ "arg": "out_file",
505
+ "mandatory": true,
506
+ "description": ["Prefix for the name of the output files. It will be",
507
+ "appended with .<i>.fa, where <i> is a consecutive number starting",
508
+ "in 1."]
509
+ },
510
+ {
511
+ "name": "Number of files",
512
+ "arg": "integer",
513
+ "default": 12,
514
+ "description": "Number of files to generate."
515
+ }
516
+ ]
517
+ },
518
+ {
519
+ "task": "FastA.subsample.pl",
520
+ "description": "Subsamples a set of sequences.",
521
+ "help_arg": "-h",
522
+ "see_also": "FastA.sample.rb",
523
+ "options": [
524
+ {
525
+ "name": "Fraction",
526
+ "opt": "-f",
527
+ "arg": "string",
528
+ "default": "10",
529
+ "description": ["Fraction of the library to be sampled (as",
530
+ "percentage). It can include several values (separated by comma),",
531
+ "as well as ranges of values in the form 'from-to/by'. For",
532
+ "example, the -f value 1-5/1,10-50/10,75,99 will produce 12",
533
+ "subsamples with expected fractions 1%, 2%, 3%, 4%, 5%, 10%, 20%,",
534
+ "30%, 40%, 50%, 75%, and 99%."]
535
+ },
536
+ {
537
+ "name": "Replicates",
538
+ "opt": "-r",
539
+ "arg": "integer",
540
+ "default": 1,
541
+ "description": "Number of replicates per fraction."
542
+ },
543
+ {
544
+ "name": "Out base",
545
+ "opt": "-o",
546
+ "arg": "out_file",
547
+ "description": ["Prefix of the output files to be created. The",
548
+ "output files will have a suffix of the form",
549
+ "'.fraction-replicate.fa', where 'fraction' is the percentage",
550
+ "sampled and 'replicate' is an increasing integer for replicates",
551
+ "of the same fraction. By default: Path to the input file."]
552
+ },
553
+ {
554
+ "name": "Force",
555
+ "opt": "-F",
556
+ "description": "Force overwriting output file(s)."
557
+ },
558
+ {
559
+ "name": "Zeroes",
560
+ "opt": "-z",
561
+ "description": ["Include leading zeroes in the numeric parts of the",
562
+ "output files (e.g., file.002.50-01.fa instead of file.2.50-1.fa),",
563
+ "so that alphabetic sorting of files reflects the sampled",
564
+ "fraction."]
565
+ },
566
+ {
567
+ "name": "Quiet",
568
+ "opt": "-q",
569
+ "description": "Run quietly."
570
+ },
571
+ {
572
+ "arg": "in_file",
573
+ "mandatory": true,
574
+ "multiple_sep": " ",
575
+ "description": "Input multi-FastA file(s)."
576
+ }
577
+ ]
578
+ },
579
+ {
580
+ "task": "FastA.tag.rb",
581
+ "description": "Generates easy-to-parse tagged reads from FastA files.",
582
+ "see_also": ["FastQ.tag.rb"],
583
+ "help_arg": "--help",
584
+ "options": [
585
+ {
586
+ "name": "Input file",
587
+ "opt": "--in",
588
+ "arg": "in_file",
589
+ "mandatory": true,
590
+ "description": "FastA file containing the sequences."
591
+ },
592
+ {
593
+ "name": "Output file",
594
+ "opt": "--out",
595
+ "arg": "out_file",
596
+ "mandatory": true,
597
+ "description": "FastA file to create."
598
+ },
599
+ {
600
+ "opt": "--prefix",
601
+ "arg": "string",
602
+ "description": "Prefix to use in all IDs."
603
+ },
604
+ {
605
+ "opt": "--suffix",
606
+ "arg": "string",
607
+ "description": "Suffix to use in all IDs."
608
+ },
609
+ {
610
+ "opt": "--defline",
611
+ "description": "Keep the original defline after a space."
612
+ },
613
+ {
614
+ "opt": "--list",
615
+ "arg": "in_file",
616
+ "description": "Reads a list of IDS."
617
+ },
618
+ {
619
+ "opt": "--quiet",
620
+ "description": "Run quietly (no STDERR output)."
621
+ }
622
+ ]
623
+ },
624
+ {
625
+ "task": "FastA.per_file.pl",
626
+ "description": ["Extracts all the sequences in a multi-FastA into",
627
+ "multiple single-FastA files."],
628
+ "see_also": "FastA.split.rb",
629
+ "help_arg": "",
630
+ "options": [
631
+ {
632
+ "arg": "out_dir",
633
+ "mandatory": true,
634
+ "description": "Output directory for the individual files."
635
+ },
636
+ {
637
+ "arg": "in_file",
638
+ "mandatory": true,
639
+ "multiple_sep": " ",
640
+ "description": "Input multi-FastA file(s)."
641
+ }
642
+ ]
643
+ },
644
+ {
645
+ "task": "FastA.extract.rb",
646
+ "description": ["Extracts a list of sequences and/or coordinates from",
647
+ "multi-FastA files."],
648
+ "help_arg": "--help",
649
+ "options": [
650
+ {
651
+ "name": "Input file",
652
+ "opt": "--in",
653
+ "arg": "in_file",
654
+ "mandatory": true,
655
+ "description": "Input FastA file."
656
+ },
657
+ {
658
+ "name": "Output file",
659
+ "opt": "--out",
660
+ "arg": "out_file",
661
+ "mandatory": true,
662
+ "description": "Output FastA file."
663
+ },
664
+ {
665
+ "name": "Coordinates",
666
+ "opt": "--coords",
667
+ "arg": "string",
668
+ "description": ["Comma-delimited list of coordinates (mandatory",
669
+ "unless -C is passed).",
670
+ "The format of the coordinates is SEQ:FROM..TO or SEQ:FROM~LEN:",
671
+ "SEQ: Sequence ID, or * (asterisk) to extract range from all",
672
+ "sequences",
673
+ "FROM: Integer, position of the first base to include (can be",
674
+ "negative)",
675
+ "TO: Integer, last base to include (can be negative)",
676
+ "LEN: Length of the range to extract."]
677
+ },
678
+ {
679
+ "name": "Coordinates file",
680
+ "opt": "--coords-file",
681
+ "arg": "in_file",
682
+ "description": ["File containing the coordinates, one per line.",
683
+ "Each line must follow the format described for Coordinates."]
684
+ },
685
+ {
686
+ "opt": "--quiet",
687
+ "description": "Run quietly (no STDERR output)."
688
+ }
689
+ ]
690
+ },
691
+ {
692
+ "task": "FastA.fragment.rb",
693
+ "description": ["Simulates incomplete (fragmented) drafts from complete",
694
+ "genomes."],
695
+ "help_arg": "--help",
696
+ "options": [
697
+ {
698
+ "name": "Input file",
699
+ "opt": "--in",
700
+ "arg": "in_file",
701
+ "mandatory": true,
702
+ "description": "FastA file containing the complete sequences."
703
+ },
704
+ {
705
+ "name": "Output file",
706
+ "opt": "--out",
707
+ "arg": "out_file",
708
+ "mandatory": true,
709
+ "description": "FastA to create."
710
+ },
711
+ {
712
+ "opt": "--completeness",
713
+ "arg": "float",
714
+ "mandatory": true,
715
+ "description": ["Fraction of genome completeness to simulate from 0",
716
+ "to 1."]
717
+ },
718
+ {
719
+ "name": "Minimum length",
720
+ "opt": "--minlen",
721
+ "arg": "integer",
722
+ "description": "Minimum fragment length to report.",
723
+ "default": 500
724
+ },
725
+ {
726
+ "opt": "--sorted",
727
+ "description": ["Keep fragments sorted as in the input file. By",
728
+ "default, fragments are shuffled."]
729
+ },
730
+ {
731
+ "opt": "--quiet",
732
+ "description": "Run quietly (no STDERR output)."
733
+ }
734
+ ]
735
+ },
736
+ {
737
+ "task": "FastA.wrap.rb",
738
+ "description": "Wraps sequences in a FastA to a given line length.",
739
+ "help_arg": "--help",
740
+ "options": [
741
+ {
742
+ "name": "Input FastA",
743
+ "opt": "--in",
744
+ "arg": "in_file",
745
+ "mandatory": true,
746
+ "description": "Input FastA file."
747
+ },
748
+ {
749
+ "name": "Output FastA",
750
+ "opt": "--out",
751
+ "arg": "out_file",
752
+ "mandatory": true,
753
+ "description": "Output FastA file."
754
+ },
755
+ {
756
+ "name": "Wrap length",
757
+ "opt": "--wrap",
758
+ "arg": "integer",
759
+ "description": ["Line length to wrap sequences. Use 0 to generate",
760
+ "1-line sequences."],
761
+ "default": 70
762
+ }
763
+ ]
764
+ }
765
+ ]
766
+ }