miga-base 1.2.17.0 → 1.2.17.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (299) 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 +3659 -0
  7. data/utils/FastAAI/FastAAI-legacy/FastAAI +1336 -0
  8. data/utils/FastAAI/FastAAI-legacy/kAAI_v1.0_virus.py +1296 -0
  9. data/utils/FastAAI/README.md +84 -0
  10. data/utils/enveomics/Docs/recplot2.md +244 -0
  11. data/utils/enveomics/Examples/aai-matrix.bash +66 -0
  12. data/utils/enveomics/Examples/ani-matrix.bash +66 -0
  13. data/utils/enveomics/Examples/essential-phylogeny.bash +105 -0
  14. data/utils/enveomics/Examples/unus-genome-phylogeny.bash +100 -0
  15. data/utils/enveomics/LICENSE.txt +73 -0
  16. data/utils/enveomics/Makefile +52 -0
  17. data/utils/enveomics/Manifest/Tasks/aasubs.json +103 -0
  18. data/utils/enveomics/Manifest/Tasks/blasttab.json +790 -0
  19. data/utils/enveomics/Manifest/Tasks/distances.json +161 -0
  20. data/utils/enveomics/Manifest/Tasks/fasta.json +802 -0
  21. data/utils/enveomics/Manifest/Tasks/fastq.json +291 -0
  22. data/utils/enveomics/Manifest/Tasks/graphics.json +126 -0
  23. data/utils/enveomics/Manifest/Tasks/mapping.json +137 -0
  24. data/utils/enveomics/Manifest/Tasks/ogs.json +382 -0
  25. data/utils/enveomics/Manifest/Tasks/other.json +906 -0
  26. data/utils/enveomics/Manifest/Tasks/remote.json +355 -0
  27. data/utils/enveomics/Manifest/Tasks/sequence-identity.json +650 -0
  28. data/utils/enveomics/Manifest/Tasks/tables.json +308 -0
  29. data/utils/enveomics/Manifest/Tasks/trees.json +68 -0
  30. data/utils/enveomics/Manifest/Tasks/variants.json +111 -0
  31. data/utils/enveomics/Manifest/categories.json +165 -0
  32. data/utils/enveomics/Manifest/examples.json +162 -0
  33. data/utils/enveomics/Manifest/tasks.json +4 -0
  34. data/utils/enveomics/Pipelines/assembly.pbs/CONFIG.mock.bash +69 -0
  35. data/utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl +1 -0
  36. data/utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl +1 -0
  37. data/utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl +1 -0
  38. data/utils/enveomics/Pipelines/assembly.pbs/README.md +189 -0
  39. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-2.bash +112 -0
  40. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-3.bash +23 -0
  41. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-4.bash +44 -0
  42. data/utils/enveomics/Pipelines/assembly.pbs/RUNME.bash +50 -0
  43. data/utils/enveomics/Pipelines/assembly.pbs/kSelector.R +37 -0
  44. data/utils/enveomics/Pipelines/assembly.pbs/newbler.pbs +68 -0
  45. data/utils/enveomics/Pipelines/assembly.pbs/newbler_preparator.pl +49 -0
  46. data/utils/enveomics/Pipelines/assembly.pbs/soap.pbs +80 -0
  47. data/utils/enveomics/Pipelines/assembly.pbs/stats.pbs +57 -0
  48. data/utils/enveomics/Pipelines/assembly.pbs/velvet.pbs +63 -0
  49. data/utils/enveomics/Pipelines/blast.pbs/01.pbs.bash +38 -0
  50. data/utils/enveomics/Pipelines/blast.pbs/02.pbs.bash +73 -0
  51. data/utils/enveomics/Pipelines/blast.pbs/03.pbs.bash +21 -0
  52. data/utils/enveomics/Pipelines/blast.pbs/BlastTab.recover_job.pl +72 -0
  53. data/utils/enveomics/Pipelines/blast.pbs/CONFIG.mock.bash +98 -0
  54. data/utils/enveomics/Pipelines/blast.pbs/FastA.split.pl +1 -0
  55. data/utils/enveomics/Pipelines/blast.pbs/README.md +127 -0
  56. data/utils/enveomics/Pipelines/blast.pbs/RUNME.bash +109 -0
  57. data/utils/enveomics/Pipelines/blast.pbs/TASK.check.bash +128 -0
  58. data/utils/enveomics/Pipelines/blast.pbs/TASK.dry.bash +16 -0
  59. data/utils/enveomics/Pipelines/blast.pbs/TASK.eo.bash +22 -0
  60. data/utils/enveomics/Pipelines/blast.pbs/TASK.pause.bash +26 -0
  61. data/utils/enveomics/Pipelines/blast.pbs/TASK.run.bash +89 -0
  62. data/utils/enveomics/Pipelines/blast.pbs/sentinel.pbs.bash +29 -0
  63. data/utils/enveomics/Pipelines/idba.pbs/README.md +49 -0
  64. data/utils/enveomics/Pipelines/idba.pbs/RUNME.bash +95 -0
  65. data/utils/enveomics/Pipelines/idba.pbs/run.pbs +56 -0
  66. data/utils/enveomics/Pipelines/trim.pbs/README.md +54 -0
  67. data/utils/enveomics/Pipelines/trim.pbs/RUNME.bash +70 -0
  68. data/utils/enveomics/Pipelines/trim.pbs/run.pbs +130 -0
  69. data/utils/enveomics/README.md +42 -0
  70. data/utils/enveomics/Scripts/AAsubs.log2ratio.rb +171 -0
  71. data/utils/enveomics/Scripts/Aln.cat.rb +221 -0
  72. data/utils/enveomics/Scripts/Aln.convert.pl +35 -0
  73. data/utils/enveomics/Scripts/AlphaDiversity.pl +152 -0
  74. data/utils/enveomics/Scripts/BedGraph.tad.rb +93 -0
  75. data/utils/enveomics/Scripts/BedGraph.window.rb +71 -0
  76. data/utils/enveomics/Scripts/BlastPairwise.AAsubs.pl +102 -0
  77. data/utils/enveomics/Scripts/BlastTab.addlen.rb +63 -0
  78. data/utils/enveomics/Scripts/BlastTab.advance.bash +48 -0
  79. data/utils/enveomics/Scripts/BlastTab.best_hit_sorted.pl +55 -0
  80. data/utils/enveomics/Scripts/BlastTab.catsbj.pl +104 -0
  81. data/utils/enveomics/Scripts/BlastTab.cogCat.rb +76 -0
  82. data/utils/enveomics/Scripts/BlastTab.filter.pl +47 -0
  83. data/utils/enveomics/Scripts/BlastTab.kegg_pep2path_rest.pl +194 -0
  84. data/utils/enveomics/Scripts/BlastTab.metaxaPrep.pl +104 -0
  85. data/utils/enveomics/Scripts/BlastTab.pairedHits.rb +157 -0
  86. data/utils/enveomics/Scripts/BlastTab.recplot2.R +48 -0
  87. data/utils/enveomics/Scripts/BlastTab.seqdepth.pl +86 -0
  88. data/utils/enveomics/Scripts/BlastTab.seqdepth_ZIP.pl +119 -0
  89. data/utils/enveomics/Scripts/BlastTab.seqdepth_nomedian.pl +86 -0
  90. data/utils/enveomics/Scripts/BlastTab.subsample.pl +47 -0
  91. data/utils/enveomics/Scripts/BlastTab.sumPerHit.pl +114 -0
  92. data/utils/enveomics/Scripts/BlastTab.taxid2taxrank.pl +90 -0
  93. data/utils/enveomics/Scripts/BlastTab.topHits_sorted.rb +123 -0
  94. data/utils/enveomics/Scripts/Chao1.pl +97 -0
  95. data/utils/enveomics/Scripts/CharTable.classify.rb +234 -0
  96. data/utils/enveomics/Scripts/EBIseq2tax.rb +83 -0
  97. data/utils/enveomics/Scripts/FastA.N50.pl +60 -0
  98. data/utils/enveomics/Scripts/FastA.extract.rb +152 -0
  99. data/utils/enveomics/Scripts/FastA.filter.pl +52 -0
  100. data/utils/enveomics/Scripts/FastA.filterLen.pl +28 -0
  101. data/utils/enveomics/Scripts/FastA.filterN.pl +60 -0
  102. data/utils/enveomics/Scripts/FastA.fragment.rb +100 -0
  103. data/utils/enveomics/Scripts/FastA.gc.pl +42 -0
  104. data/utils/enveomics/Scripts/FastA.interpose.pl +93 -0
  105. data/utils/enveomics/Scripts/FastA.length.pl +38 -0
  106. data/utils/enveomics/Scripts/FastA.mask.rb +89 -0
  107. data/utils/enveomics/Scripts/FastA.per_file.pl +36 -0
  108. data/utils/enveomics/Scripts/FastA.qlen.pl +57 -0
  109. data/utils/enveomics/Scripts/FastA.rename.pl +65 -0
  110. data/utils/enveomics/Scripts/FastA.revcom.pl +23 -0
  111. data/utils/enveomics/Scripts/FastA.sample.rb +98 -0
  112. data/utils/enveomics/Scripts/FastA.slider.pl +85 -0
  113. data/utils/enveomics/Scripts/FastA.split.pl +55 -0
  114. data/utils/enveomics/Scripts/FastA.split.rb +79 -0
  115. data/utils/enveomics/Scripts/FastA.subsample.pl +131 -0
  116. data/utils/enveomics/Scripts/FastA.tag.rb +65 -0
  117. data/utils/enveomics/Scripts/FastA.toFastQ.rb +69 -0
  118. data/utils/enveomics/Scripts/FastA.wrap.rb +48 -0
  119. data/utils/enveomics/Scripts/FastQ.filter.pl +54 -0
  120. data/utils/enveomics/Scripts/FastQ.interpose.pl +90 -0
  121. data/utils/enveomics/Scripts/FastQ.maskQual.rb +89 -0
  122. data/utils/enveomics/Scripts/FastQ.offset.pl +90 -0
  123. data/utils/enveomics/Scripts/FastQ.split.pl +53 -0
  124. data/utils/enveomics/Scripts/FastQ.tag.rb +70 -0
  125. data/utils/enveomics/Scripts/FastQ.test-error.rb +81 -0
  126. data/utils/enveomics/Scripts/FastQ.toFastA.awk +24 -0
  127. data/utils/enveomics/Scripts/GFF.catsbj.pl +127 -0
  128. data/utils/enveomics/Scripts/GenBank.add_fields.rb +84 -0
  129. data/utils/enveomics/Scripts/HMM.essential.rb +351 -0
  130. data/utils/enveomics/Scripts/HMM.haai.rb +168 -0
  131. data/utils/enveomics/Scripts/HMMsearch.extractIds.rb +83 -0
  132. data/utils/enveomics/Scripts/JPlace.distances.rb +88 -0
  133. data/utils/enveomics/Scripts/JPlace.to_iToL.rb +320 -0
  134. data/utils/enveomics/Scripts/M5nr.getSequences.rb +81 -0
  135. data/utils/enveomics/Scripts/MeTaxa.distribution.pl +198 -0
  136. data/utils/enveomics/Scripts/MyTaxa.fragsByTax.pl +35 -0
  137. data/utils/enveomics/Scripts/MyTaxa.seq-taxrank.rb +49 -0
  138. data/utils/enveomics/Scripts/NCBIacc2tax.rb +92 -0
  139. data/utils/enveomics/Scripts/Newick.autoprune.R +27 -0
  140. data/utils/enveomics/Scripts/RAxML-EPA.to_iToL.pl +228 -0
  141. data/utils/enveomics/Scripts/RecPlot2.compareIdentities.R +32 -0
  142. data/utils/enveomics/Scripts/RefSeq.download.bash +48 -0
  143. data/utils/enveomics/Scripts/SRA.download.bash +55 -0
  144. data/utils/enveomics/Scripts/TRIBS.plot-test.R +36 -0
  145. data/utils/enveomics/Scripts/TRIBS.test.R +39 -0
  146. data/utils/enveomics/Scripts/Table.barplot.R +31 -0
  147. data/utils/enveomics/Scripts/Table.df2dist.R +30 -0
  148. data/utils/enveomics/Scripts/Table.filter.pl +61 -0
  149. data/utils/enveomics/Scripts/Table.merge.pl +77 -0
  150. data/utils/enveomics/Scripts/Table.prefScore.R +60 -0
  151. data/utils/enveomics/Scripts/Table.replace.rb +69 -0
  152. data/utils/enveomics/Scripts/Table.round.rb +63 -0
  153. data/utils/enveomics/Scripts/Table.split.pl +57 -0
  154. data/utils/enveomics/Scripts/Taxonomy.silva2ncbi.rb +227 -0
  155. data/utils/enveomics/Scripts/VCF.KaKs.rb +147 -0
  156. data/utils/enveomics/Scripts/VCF.SNPs.rb +88 -0
  157. data/utils/enveomics/Scripts/aai.rb +421 -0
  158. data/utils/enveomics/Scripts/ani.rb +362 -0
  159. data/utils/enveomics/Scripts/anir.rb +137 -0
  160. data/utils/enveomics/Scripts/clust.rand.rb +102 -0
  161. data/utils/enveomics/Scripts/gi2tax.rb +103 -0
  162. data/utils/enveomics/Scripts/in_silico_GA_GI.pl +96 -0
  163. data/utils/enveomics/Scripts/lib/data/dupont_2012_essential.hmm.gz +0 -0
  164. data/utils/enveomics/Scripts/lib/data/lee_2019_essential.hmm.gz +0 -0
  165. data/utils/enveomics/Scripts/lib/enveomics.R +1 -0
  166. data/utils/enveomics/Scripts/lib/enveomics_rb/anir.rb +293 -0
  167. data/utils/enveomics/Scripts/lib/enveomics_rb/bm_set.rb +175 -0
  168. data/utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb +24 -0
  169. data/utils/enveomics/Scripts/lib/enveomics_rb/errors.rb +17 -0
  170. data/utils/enveomics/Scripts/lib/enveomics_rb/gmm_em.rb +30 -0
  171. data/utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb +253 -0
  172. data/utils/enveomics/Scripts/lib/enveomics_rb/match.rb +88 -0
  173. data/utils/enveomics/Scripts/lib/enveomics_rb/og.rb +182 -0
  174. data/utils/enveomics/Scripts/lib/enveomics_rb/rbm.rb +49 -0
  175. data/utils/enveomics/Scripts/lib/enveomics_rb/remote_data.rb +74 -0
  176. data/utils/enveomics/Scripts/lib/enveomics_rb/seq_range.rb +237 -0
  177. data/utils/enveomics/Scripts/lib/enveomics_rb/stats/rand.rb +31 -0
  178. data/utils/enveomics/Scripts/lib/enveomics_rb/stats/sample.rb +152 -0
  179. data/utils/enveomics/Scripts/lib/enveomics_rb/stats.rb +3 -0
  180. data/utils/enveomics/Scripts/lib/enveomics_rb/utils.rb +74 -0
  181. data/utils/enveomics/Scripts/lib/enveomics_rb/vcf.rb +135 -0
  182. data/utils/enveomics/Scripts/ogs.annotate.rb +88 -0
  183. data/utils/enveomics/Scripts/ogs.core-pan.rb +160 -0
  184. data/utils/enveomics/Scripts/ogs.extract.rb +125 -0
  185. data/utils/enveomics/Scripts/ogs.mcl.rb +186 -0
  186. data/utils/enveomics/Scripts/ogs.rb +104 -0
  187. data/utils/enveomics/Scripts/ogs.stats.rb +131 -0
  188. data/utils/enveomics/Scripts/rbm-legacy.rb +172 -0
  189. data/utils/enveomics/Scripts/rbm.rb +108 -0
  190. data/utils/enveomics/Scripts/sam.filter.rb +148 -0
  191. data/utils/enveomics/Tests/Makefile +10 -0
  192. data/utils/enveomics/Tests/Mgen_M2288.faa +3189 -0
  193. data/utils/enveomics/Tests/Mgen_M2288.fna +8282 -0
  194. data/utils/enveomics/Tests/Mgen_M2321.fna +8288 -0
  195. data/utils/enveomics/Tests/Nequ_Kin4M.faa +2970 -0
  196. data/utils/enveomics/Tests/Xanthomonas_oryzae-PilA.tribs.Rdata +0 -0
  197. data/utils/enveomics/Tests/Xanthomonas_oryzae-PilA.txt +7 -0
  198. data/utils/enveomics/Tests/Xanthomonas_oryzae.aai-mat.tsv +17 -0
  199. data/utils/enveomics/Tests/Xanthomonas_oryzae.aai.tsv +137 -0
  200. data/utils/enveomics/Tests/a_mg.cds-go.blast.tsv +123 -0
  201. data/utils/enveomics/Tests/a_mg.reads-cds.blast.tsv +200 -0
  202. data/utils/enveomics/Tests/a_mg.reads-cds.counts.tsv +55 -0
  203. data/utils/enveomics/Tests/alkB.nwk +1 -0
  204. data/utils/enveomics/Tests/anthrax-cansnp-data.tsv +13 -0
  205. data/utils/enveomics/Tests/anthrax-cansnp-key.tsv +17 -0
  206. data/utils/enveomics/Tests/hiv1.faa +59 -0
  207. data/utils/enveomics/Tests/hiv1.fna +134 -0
  208. data/utils/enveomics/Tests/hiv2.faa +70 -0
  209. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv +233 -0
  210. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.lim +1 -0
  211. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.rec +233 -0
  212. data/utils/enveomics/Tests/phyla_counts.tsv +10 -0
  213. data/utils/enveomics/Tests/primate_lentivirus.ogs +11 -0
  214. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv1.rbm +9 -0
  215. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv2.rbm +8 -0
  216. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-siv.rbm +6 -0
  217. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-hiv2.rbm +9 -0
  218. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-siv.rbm +6 -0
  219. data/utils/enveomics/Tests/primate_lentivirus.rbm/siv-siv.rbm +6 -0
  220. data/utils/enveomics/build_enveomics_r.bash +45 -0
  221. data/utils/enveomics/enveomics.R/DESCRIPTION +31 -0
  222. data/utils/enveomics/enveomics.R/NAMESPACE +39 -0
  223. data/utils/enveomics/enveomics.R/R/autoprune.R +155 -0
  224. data/utils/enveomics/enveomics.R/R/barplot.R +184 -0
  225. data/utils/enveomics/enveomics.R/R/cliopts.R +135 -0
  226. data/utils/enveomics/enveomics.R/R/df2dist.R +154 -0
  227. data/utils/enveomics/enveomics.R/R/growthcurve.R +331 -0
  228. data/utils/enveomics/enveomics.R/R/prefscore.R +79 -0
  229. data/utils/enveomics/enveomics.R/R/recplot.R +354 -0
  230. data/utils/enveomics/enveomics.R/R/recplot2.R +1631 -0
  231. data/utils/enveomics/enveomics.R/R/tribs.R +583 -0
  232. data/utils/enveomics/enveomics.R/R/utils.R +80 -0
  233. data/utils/enveomics/enveomics.R/README.md +81 -0
  234. data/utils/enveomics/enveomics.R/data/growth.curves.rda +0 -0
  235. data/utils/enveomics/enveomics.R/data/phyla.counts.rda +0 -0
  236. data/utils/enveomics/enveomics.R/man/cash-enve.GrowthCurve-method.Rd +16 -0
  237. data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2-method.Rd +16 -0
  238. data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2.Peak-method.Rd +16 -0
  239. data/utils/enveomics/enveomics.R/man/enve.GrowthCurve-class.Rd +25 -0
  240. data/utils/enveomics/enveomics.R/man/enve.TRIBS-class.Rd +46 -0
  241. data/utils/enveomics/enveomics.R/man/enve.TRIBS.merge.Rd +23 -0
  242. data/utils/enveomics/enveomics.R/man/enve.TRIBStest-class.Rd +47 -0
  243. data/utils/enveomics/enveomics.R/man/enve.__prune.iter.Rd +23 -0
  244. data/utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd +23 -0
  245. data/utils/enveomics/enveomics.R/man/enve.__tribs.Rd +40 -0
  246. data/utils/enveomics/enveomics.R/man/enve.barplot.Rd +103 -0
  247. data/utils/enveomics/enveomics.R/man/enve.cliopts.Rd +67 -0
  248. data/utils/enveomics/enveomics.R/man/enve.col.alpha.Rd +24 -0
  249. data/utils/enveomics/enveomics.R/man/enve.col2alpha.Rd +19 -0
  250. data/utils/enveomics/enveomics.R/man/enve.df2dist.Rd +45 -0
  251. data/utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd +44 -0
  252. data/utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd +47 -0
  253. data/utils/enveomics/enveomics.R/man/enve.growthcurve.Rd +75 -0
  254. data/utils/enveomics/enveomics.R/man/enve.prefscore.Rd +50 -0
  255. data/utils/enveomics/enveomics.R/man/enve.prune.dist.Rd +44 -0
  256. data/utils/enveomics/enveomics.R/man/enve.recplot.Rd +139 -0
  257. data/utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd +45 -0
  258. data/utils/enveomics/enveomics.R/man/enve.recplot2.ANIr.Rd +24 -0
  259. data/utils/enveomics/enveomics.R/man/enve.recplot2.Rd +77 -0
  260. data/utils/enveomics/enveomics.R/man/enve.recplot2.__counts.Rd +25 -0
  261. data/utils/enveomics/enveomics.R/man/enve.recplot2.__peakHist.Rd +21 -0
  262. data/utils/enveomics/enveomics.R/man/enve.recplot2.__whichClosestPeak.Rd +19 -0
  263. data/utils/enveomics/enveomics.R/man/enve.recplot2.changeCutoff.Rd +19 -0
  264. data/utils/enveomics/enveomics.R/man/enve.recplot2.compareIdentities.Rd +47 -0
  265. data/utils/enveomics/enveomics.R/man/enve.recplot2.coordinates.Rd +29 -0
  266. data/utils/enveomics/enveomics.R/man/enve.recplot2.corePeak.Rd +18 -0
  267. data/utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd +45 -0
  268. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd +36 -0
  269. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_e.Rd +19 -0
  270. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_m.Rd +19 -0
  271. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__emauto_one.Rd +27 -0
  272. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mow_one.Rd +52 -0
  273. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mower.Rd +17 -0
  274. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.em.Rd +51 -0
  275. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.emauto.Rd +43 -0
  276. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.mower.Rd +82 -0
  277. data/utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd +59 -0
  278. data/utils/enveomics/enveomics.R/man/enve.recplot2.seqdepth.Rd +27 -0
  279. data/utils/enveomics/enveomics.R/man/enve.recplot2.windowDepthThreshold.Rd +36 -0
  280. data/utils/enveomics/enveomics.R/man/enve.selvector.Rd +23 -0
  281. data/utils/enveomics/enveomics.R/man/enve.tribs.Rd +68 -0
  282. data/utils/enveomics/enveomics.R/man/enve.tribs.test.Rd +28 -0
  283. data/utils/enveomics/enveomics.R/man/enve.truncate.Rd +27 -0
  284. data/utils/enveomics/enveomics.R/man/growth.curves.Rd +14 -0
  285. data/utils/enveomics/enveomics.R/man/phyla.counts.Rd +13 -0
  286. data/utils/enveomics/enveomics.R/man/plot.enve.GrowthCurve.Rd +78 -0
  287. data/utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd +46 -0
  288. data/utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd +45 -0
  289. data/utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd +125 -0
  290. data/utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd +19 -0
  291. data/utils/enveomics/enveomics.R/man/summary.enve.TRIBS.Rd +19 -0
  292. data/utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd +19 -0
  293. data/utils/enveomics/globals.mk +8 -0
  294. data/utils/enveomics/manifest.json +9 -0
  295. data/utils/multitrim/Multitrim How-To.pdf +0 -0
  296. data/utils/multitrim/README.md +67 -0
  297. data/utils/multitrim/multitrim.py +1555 -0
  298. data/utils/multitrim/multitrim.yml +13 -0
  299. metadata +301 -5
@@ -0,0 +1,583 @@
1
+
2
+ # Use as:
3
+ # > # Estimate reference (null) model:
4
+ # > tab <- read.table('Ecoli-ML-dmatrix.txt', sep='\t', h=T, row.names=1)
5
+ # > dist <- as.dist(tab);
6
+ # > all.dist <- enve.tribs(dist);
7
+ # >
8
+ # > # Estimate subset (test) model:
9
+ # > lee <- read.table('LEE-strains.txt', as.is=T)$V1
10
+ # > lee.dist <- enve.tribs(dist, lee, subsamples=seq(0,1,by=0.05), threads=12,
11
+ # + verbosity=2, pre.tribs=all.dist.merge);
12
+ # ...
13
+ # >
14
+ # > # Plot reference and selection at different subsampling levels:
15
+ # > plot(all.dist, t='boxplot');
16
+ # > plot(lee, new=FALSE, col='darkred');
17
+ # ...
18
+ # >
19
+ # > # Test significance of overclustering (or overdispersion):
20
+ # > lee.test <- enve.tribs.test(dist, lee, pre.tribs=all.dist.merge,
21
+ # + verbosity=2, threads=12);
22
+ # > summary(lee.test);
23
+ # > plot(lee.test);
24
+ # ...
25
+
26
+
27
+
28
+ #==============> Define S4 classes
29
+
30
+ #' Enveomics: TRIBS S4 Class
31
+ #'
32
+ #' Enve-omics representation of "Transformed-space Resampling In Biased Sets
33
+ #' (TRIBS)". This object represents sets of distances between objects,
34
+ #' sampled nearly-uniformly at random in "distance space". Subsampling
35
+ #' without selection is trivial, since both the distances space and the
36
+ #' selection occur in the same transformed space. However, it's useful to
37
+ #' compare randomly subsampled sets against a selected set of objects. This
38
+ #' is intended to identify overdispersion or overclustering (see
39
+ #' \code{\link{enve.TRIBStest}}) of a subset against the entire collection of objects
40
+ #' with minimum impact of sampling biases. This object can be produced by
41
+ #' \code{\link{enve.tribs}} and supports S4 methods \code{plot} and \code{summary}.
42
+ #'
43
+ #' @slot distance \code{(numeric)} Centrality measurement of the distances
44
+ #' between the selected objects (without subsampling).
45
+ #' @slot points \code{(matrix)} Position of the different objects in distance
46
+ #' space.
47
+ #' @slot distances \code{(matrix)} Subsampled distances, where the rows are
48
+ #' replicates and the columns are subsampling levels.
49
+ #' @slot spaceSize \code{(numeric)} Number of objects.
50
+ #' @slot selSize \code{(numeric)} Number of selected objects.
51
+ #' @slot dimensions \code{(numeric)} Number of dimensions in the distance space.
52
+ #' @slot subsamples \code{(numeric)} Subsampling levels (as fractions, from
53
+ #' 0 to 1).
54
+ #' @slot call \code{(call)} Call producing this object.
55
+ #'
56
+ #' @author Luis M. Rodriguez-R [aut, cre]
57
+ #'
58
+ #' @exportClass
59
+
60
+ enve.TRIBS <- setClass("enve.TRIBS",
61
+ representation(
62
+ distance='numeric',
63
+ points='matrix',
64
+ distances='matrix',
65
+ spaceSize='numeric',
66
+ selSize='numeric',
67
+ dimensions='numeric',
68
+ subsamples='numeric',
69
+ call='call')
70
+ ,package='enveomics.R'
71
+ );
72
+
73
+ #' Enveomics: TRIBS Test S4 Class
74
+ #'
75
+ #' Test of significance of overclustering or overdispersion in a selected
76
+ #' set of objects with respect to the entire set (see \code{\link{enve.TRIBS}}). This
77
+ #' object can be produced by \code{\link{enve.tribs.test}} and supports S4 methods
78
+ #' \code{plot} and \code{summary}.
79
+ #'
80
+ #' @slot pval.gt \code{(numeric)}
81
+ #' P-value for the overdispersion test.
82
+ #' @slot pval.lt \code{(numeric)}
83
+ #' P-value for the overclustering test.
84
+ #' @slot all.dist \code{(numeric)}
85
+ #' Empiric PDF of distances for the entire dataset (subsampled at selection
86
+ #' size).
87
+ #' @slot sel.dist \code{(numeric)}
88
+ #' Empiric PDF of distances for the selected objects (without subsampling).
89
+ #' @slot diff.dist \code{(numeric)}
90
+ #' Empiric PDF of the difference between \code{all.dist} and \code{sel.dist}.
91
+ #' The p-values are estimating by comparing areas in this PDF greater than and
92
+ #' lesser than zero.
93
+ #' @slot dist.mids \code{(numeric)}
94
+ #' Midpoints of the empiric PDFs of distances.
95
+ #' @slot diff.mids \code{(numeric)}
96
+ #' Midpoints of the empiric PDF of difference of distances.
97
+ #' @slot call \code{(call)}
98
+ #' Call producing this object.
99
+ #'
100
+ #' @author Luis M. Rodriguez-R [aut, cre]
101
+ #'
102
+ #' @exportClass
103
+
104
+ enve.TRIBStest <- setClass("enve.TRIBStest",
105
+ representation(
106
+ pval.gt='numeric',
107
+ pval.lt='numeric',
108
+ all.dist='numeric',
109
+ sel.dist='numeric',
110
+ diff.dist='numeric',
111
+ dist.mids='numeric',
112
+ diff.mids='numeric',
113
+ call='call')
114
+ ,package='enveomics.R'
115
+ );
116
+
117
+ #==============> Define S4 methods
118
+
119
+ #' Enveomics: TRIBS Summary
120
+ #'
121
+ #' Summary of an \code{\link{enve.TRIBS}} object.
122
+ #'
123
+ #' @param object
124
+ #' \code{\link{enve.TRIBS}} object.
125
+ #' @param ...
126
+ #' No additional parameters are currently supported.
127
+ #'
128
+ #' @author Luis M. Rodriguez-R [aut, cre]
129
+ #'
130
+ #' @method summary enve.TRIBS
131
+ #' @export
132
+
133
+ summary.enve.TRIBS <- function
134
+ (object,
135
+ ...
136
+ ){
137
+ cat('===[ enve.TRIBS ]-------------------------\n');
138
+ cat('Selected',attr(object,'selSize'),'of',
139
+ attr(object,'spaceSize'),'objects in',
140
+ attr(object,'dimensions'),'dimensions.\n');
141
+ cat('Collected',length(attr(object,'subsamples')),'subsamples with',
142
+ nrow(attr(object,'distances')),'replicates each.\n');
143
+ cat('------------------------------------------\n');
144
+ cat('call:',as.character(attr(object,'call')),'\n');
145
+ cat('------------------------------------------\n');
146
+ }
147
+
148
+ #' Enveomics: TRIBS Plot
149
+ #'
150
+ #' Plot an \code{\link{enve.TRIBS}} object.
151
+ #'
152
+ #' @param x
153
+ #' \code{\link{enve.TRIBS}} object to plot.
154
+ #' @param new
155
+ #' Should a new canvas be drawn?
156
+ #' @param type
157
+ #' Type of plot. The \strong{points} plot shows all the replicates, the
158
+ #' \strong{boxplot} plot represents the values found by
159
+ #' \code{\link[grDevices]{boxplot.stats}}.
160
+ #' as areas, and plots the outliers as points.
161
+ #' @param col
162
+ #' Color of the areas and/or the points.
163
+ #' @param pt.cex
164
+ #' Size of the points.
165
+ #' @param pt.pch
166
+ #' Points character.
167
+ #' @param pt.col
168
+ #' Color of the points.
169
+ #' @param ln.col
170
+ #' Color of the lines.
171
+ #' @param ...
172
+ #' Any additional parameters supported by \code{plot}.
173
+ #'
174
+ #' @author Luis M. Rodriguez-R [aut, cre]
175
+ #'
176
+ #' @method plot enve.TRIBS
177
+ #' @export
178
+
179
+ plot.enve.TRIBS <- function
180
+ (x,
181
+ new=TRUE,
182
+ type=c('boxplot', 'points'),
183
+ col='#00000044',
184
+ pt.cex=1/2,
185
+ pt.pch=19,
186
+ pt.col=col,
187
+ ln.col=col,
188
+ ...
189
+ ){
190
+ type <- match.arg(type);
191
+ plot.opts <- list(xlim=range(attr(x,'subsamples'))*attr(x,'selSize'),
192
+ ylim=range(attr(x,'distances')), ..., t='n', x=1);
193
+ if(new) do.call(plot, plot.opts);
194
+ abline(h=attr(x,'distance'), lty=3, col=ln.col);
195
+ replicates <- nrow(attr(x,'distances'));
196
+ if(type=='points'){
197
+ for(i in 1:ncol(attr(x,'distances')))
198
+ points(rep(round(attr(x,'subsamples')[i]*attr(x,'selSize')),
199
+ replicates), attr(x,'distances')[,i], cex=pt.cex, pch=pt.pch,
200
+ col=pt.col);
201
+ }else{
202
+ stats <- matrix(NA, nrow=7, ncol=ncol(attr(x,'distances')));
203
+ for(i in 1:ncol(attr(x,'distances'))){
204
+ b <- boxplot.stats(attr(x,'distances')[,i]);
205
+ points(rep(round(attr(x,'subsamples')[i]*attr(x,'selSize')),
206
+ length(b$out)), b$out, cex=pt.cex, pch=pt.pch, col=pt.col);
207
+ stats[, i] <- c(b$conf, b$stats[c(1,5,2,4,3)]);
208
+ }
209
+ x <- round(attr(x,'subsamples')*attr(x,'selSize'))
210
+ for(i in c(1,3,5))
211
+ polygon(c(x, rev(x)), c(stats[i,], rev(stats[i+1,])), border=NA,
212
+ col=col);
213
+ lines(x, stats[7,], col=ln.col, lwd=2);
214
+ }
215
+ }
216
+
217
+ #' Enveomics: TRIBS Summary Test
218
+ #'
219
+ #' Summary of an \code{\link{enve.TRIBStest}} object.
220
+ #'
221
+ #' @param object
222
+ #' \code{\link{enve.TRIBStest}} object.
223
+ #' @param ...
224
+ #' No additional parameters are currently supported.
225
+ #'
226
+ #' @author Luis M. Rodriguez-R [aut, cre]
227
+ #'
228
+ #' @method summary enve.TRIBStest
229
+ #' @export
230
+
231
+ summary.enve.TRIBStest <- function
232
+ (object,
233
+ ...
234
+ ){
235
+ cat('===[ enve.TRIBStest ]---------------------\n');
236
+ cat('Alternative hypothesis:\n');
237
+ cat(' The distances in the selection are\n');
238
+ if(attr(object, 'pval.gt') > attr(object, 'pval.lt')){
239
+ cat(' smaller than in the entire dataset\n (overclustering)\n');
240
+ }else{
241
+ cat(' larger than in the entire dataset\n (overdispersion)\n');
242
+ }
243
+ p.val <- min(attr(object, 'pval.gt'), attr(object, 'pval.lt'));
244
+ if(p.val==0){
245
+ diff.dist <- attr(object, 'diff.dist');
246
+ p.val.lim <- min(diff.dist[diff.dist>0]);
247
+ cat('\n P-value <= ', signif(p.val.lim, 4), sep='');
248
+ }else{
249
+ p.val.lim <- p.val;
250
+ cat('\n P-value: ', signif(p.val, 4), sep='');
251
+ }
252
+ cat(' ', ifelse(p.val.lim<=0.01, "**", ifelse(p.val.lim<=0.05, "*", "")),
253
+ '\n', sep='');
254
+ cat('------------------------------------------\n');
255
+ cat('call:',as.character(attr(object,'call')),'\n');
256
+ cat('------------------------------------------\n');
257
+ }
258
+
259
+ #' Enveomics: TRIBS Plot Test
260
+ #'
261
+ #' Plots an \code{\link{enve.TRIBStest}} object.
262
+ #'
263
+ #' @param x
264
+ #' \code{\link{enve.TRIBStest}} object to plot.
265
+ #' @param type
266
+ #' What to plot. \code{overlap} generates a plot of the two contrasting empirical
267
+ #' PDFs (to compare against each other), \code{difference} produces a plot of the
268
+ #' differences between the empirical PDFs (to compare against zero).
269
+ #' @param col
270
+ #' Main color of the plot if type=\code{difference}.
271
+ #' @param col1
272
+ #' First color of the plot if type=\code{overlap}.
273
+ #' @param col2
274
+ #' Second color of the plot if type=\code{overlap}.
275
+ #' @param ylab
276
+ #' Y-axis label.
277
+ #' @param xlim
278
+ #' X-axis limits.
279
+ #' @param ylim
280
+ #' Y-axis limits.
281
+ #' @param ...
282
+ #' Any other graphical arguments.
283
+ #'
284
+ #' @author Luis M. Rodriguez-R [aut, cre]
285
+ #'
286
+ #' @method plot enve.TRIBStest
287
+ #' @export
288
+
289
+ plot.enve.TRIBStest <- function
290
+ (x,
291
+ type=c('overlap', 'difference'),
292
+ col='#00000044',
293
+ col1=col,
294
+ col2='#44001144',
295
+ ylab='Probability',
296
+ xlim=range(attr(x, 'dist.mids')),
297
+ ylim=c(0,max(c(attr(x, 'all.dist'), attr(x, 'sel.dist')))),
298
+ ...
299
+ ){
300
+ type <- match.arg(type);
301
+ if(type=='overlap'){
302
+ plot.opts <- list(xlim=xlim, ylim=ylim, ylab=ylab, ..., t='n', x=1);
303
+ do.call(plot, plot.opts);
304
+ bins <- length(attr(x, 'dist.mids'))
305
+ polygon(attr(x, 'dist.mids')[c(1, 1:bins, bins)],
306
+ c(0,attr(x, 'all.dist'),0), col=col1,
307
+ border=do.call(rgb, as.list(c(col2rgb(col1)/256, 0.5))));
308
+ polygon(attr(x, 'dist.mids')[c(1, 1:bins, bins)],
309
+ c(0,attr(x, 'sel.dist'),0), col=col2,
310
+ border=do.call(rgb, as.list(c(col2rgb(col2)/256, 0.5))));
311
+ }else{
312
+ plot.opts <- list(xlim=range(attr(x, 'diff.mids')),
313
+ ylim=c(0,max(attr(x, 'diff.dist'))), ylab=ylab, ..., t='n', x=1);
314
+ do.call(plot, plot.opts);
315
+ bins <- length(attr(x, 'diff.mids'));
316
+ polygon(attr(x, 'diff.mids')[c(1, 1:bins, bins)],
317
+ c(0,attr(x, 'diff.dist'),0), col=col,
318
+ border=do.call(rgb, as.list(c(col2rgb(col)/256, 0.5))));
319
+ }
320
+ }
321
+
322
+ #' Enveomics: TRIBS Merge
323
+ #'
324
+ #' Merges two \code{\link{enve.TRIBS}} objects generated from the same objects at
325
+ #' different subsampling levels.
326
+ #'
327
+ #' @param x
328
+ #' First \code{\link{enve.TRIBS}} object.
329
+ #' @param y
330
+ #' Second \code{\link{enve.TRIBS}} object.
331
+ #'
332
+ #' @return Returns an \code{\link{enve.TRIBS}} object.
333
+ #'
334
+ #' @author Luis M. Rodriguez-R [aut, cre]
335
+ #'
336
+ #' @export
337
+
338
+ enve.TRIBS.merge <- function
339
+ (x,
340
+ y
341
+ ){
342
+ # Check consistency
343
+ if(attr(x,'distance') != attr(y,'distance'))
344
+ stop('Total distances in objects are different.');
345
+ if(any(attr(x,'points') != attr(y,'points')))
346
+ stop('Points in objects are different.');
347
+ if(attr(x,'spaceSize') != attr(y,'spaceSize'))
348
+ stop('Space size in objects are different.');
349
+ if(attr(x,'selSize') != attr(y,'selSize'))
350
+ stop('Selection size in objects are different.');
351
+ if(attr(x,'dimensions') != attr(y,'dimensions'))
352
+ stop('Dimensions in objects are different.');
353
+ if(nrow(attr(x,'distances')) != nrow(attr(y,'distances')))
354
+ stop('Replicates in objects are different.');
355
+ # Merge
356
+ a <- attr(x,'subsamples');
357
+ b <- attr(y,'subsamples');
358
+ o <- order(c(a,b));
359
+ o <- o[!duplicated(c(a,b)[o])] ;
360
+ d <- cbind(attr(x,'distances'), attr(y,'distances'))[, o] ;
361
+ z <- new('enve.TRIBS',
362
+ distance=attr(x,'distance'), points=attr(x,'points'),
363
+ distances=d, spaceSize=attr(x,'spaceSize'),
364
+ selSize=attr(x,'selSize'), dimensions=attr(x,'dimensions'),
365
+ subsamples=c(a,b)[o], call=match.call());
366
+ return(z) ;
367
+ }
368
+
369
+ #==============> Define core functions
370
+
371
+ #' Enveomics: TRIBS Test
372
+ #'
373
+ #' Estimates the empirical difference between all the distances in a set of
374
+ #' objects and a subset, together with its statistical significance.
375
+ #'
376
+ #' @param dist
377
+ #' Distances as \code{dist} object.
378
+ #' @param selection
379
+ #' Selection defining the subset.
380
+ #' @param bins
381
+ #' Number of bins to evaluate in the range of distances.
382
+ #' @param ...
383
+ #' Any other parameters supported by \code{\link{enve.tribs}},
384
+ #' except \code{subsamples}.
385
+ #'
386
+ #' @return Returns an \code{\link{enve.TRIBStest}} object.
387
+ #'
388
+ #' @author Luis M. Rodriguez-R [aut, cre]
389
+ #'
390
+ #' @export
391
+
392
+ enve.tribs.test <- function
393
+ (dist,
394
+ selection,
395
+ bins=50,
396
+ ...
397
+ ){
398
+ s.tribs <- enve.tribs(dist, selection, subsamples=c(0,1), ...);
399
+ a.tribs <- enve.tribs(dist,
400
+ subsamples=c(0,attr(s.tribs, 'selSize')/attr(s.tribs, 'spaceSize')), ...);
401
+ s.dist <- attr(s.tribs, 'distances')[, 2];
402
+ a.dist <- attr(a.tribs, 'distances')[, 2];
403
+ range <- range(c(s.dist, a.dist));
404
+ a.f <- hist(a.dist, breaks=seq(range[1], range[2], length.out=bins),
405
+ plot=FALSE);
406
+ s.f <- hist(s.dist, breaks=seq(range[1], range[2], length.out=bins),
407
+ plot=FALSE);
408
+ zp.f <- c(); zz.f <- 0; zn.f <- c();
409
+ p.x <- a.f$counts/sum(a.f$counts);
410
+ p.y <- s.f$counts/sum(s.f$counts);
411
+ for(z in 1:length(a.f$mids)){
412
+ zn.f[z] <- 0;
413
+ zz.f <- 0;
414
+ zp.f[z] <- 0;
415
+ for(k in 1:length(a.f$mids)){
416
+ if(z < k){
417
+ zp.f[z] <- zp.f[z] + p.x[k]*p.y[k-z];
418
+ zn.f[z] <- zn.f[z] + p.x[k-z]*p.y[k];
419
+ }
420
+ zz.f <- zz.f + p.x[k]*p.y[k];
421
+ }
422
+ }
423
+ return(new('enve.TRIBStest',
424
+ pval.gt=sum(c(zz.f, zp.f)), pval.lt=sum(c(zz.f, zn.f)),
425
+ all.dist=p.x, sel.dist=p.y, diff.dist=c(rev(zn.f), zz.f, zp.f),
426
+ dist.mids=a.f$mids,
427
+ diff.mids=seq(diff(range(a.f$mids)), -diff(range(a.f$mids)),
428
+ length.out=1+2*length(a.f$mids)),
429
+ call=match.call()));
430
+ }
431
+
432
+ #' Enveomics: TRIBS
433
+ #'
434
+ #' Subsample any objects in "distance space" to reduce the effect of
435
+ #' sample-clustering. This function was originally designed to subsample
436
+ #' genomes in "phylogenetic distance space", a clear case of strong
437
+ #' clustering bias in sampling, by Luis M. Rodriguez-R and Michael R
438
+ #' Weigand.
439
+ #'
440
+ #' @param dist
441
+ #' Distances as a \code{dist} object.
442
+ #' @param selection
443
+ #' Objects to include in the subsample. By default, all objects are
444
+ #' selected.
445
+ #' @param replicates
446
+ #' Number of replications per point.
447
+ #' @param summary.fx
448
+ #' Function to summarize the distance distributions in a given replicate. By
449
+ #' default, the median distance is estimated.
450
+ #' @param dist.method
451
+ #' Distance method between random points and samples in the transformed
452
+ #' space. See \code{dist}.
453
+ #' @param subsamples
454
+ #' Subsampling fractions.
455
+ #' @param dimensions
456
+ #' Dimensions to use in the NMDS. By default, 5\% of the selection length.
457
+ #' @param metaMDS.opts
458
+ #' Any additional options to pass to metaMDS, as \code{list}.
459
+ #' @param threads
460
+ #' Number of threads to use.
461
+ #' @param verbosity
462
+ #' Verbosity. Use 0 to run quietly, increase for additional information.
463
+ #' @param points
464
+ #' Optional. If passed, the MDS step is skipped and this object is used
465
+ #' instead. It can be the \code{$points} slot of class \code{metaMDS}
466
+ #' (from \code{vegan}).
467
+ #' It must be a matrix or matrix-coercible object, with samples as rows and
468
+ #' dimensions as columns.
469
+ #' @param pre.tribs
470
+ #' Optional. If passed, the points are recovered from this object (except if
471
+ #' \code{points} is also passed. This should be an \code{\link{enve.TRIBS}} object
472
+ #' estimated on the same objects (the selection is unimportant).
473
+ #'
474
+ #' @return Returns an \code{\link{enve.TRIBS}} object.
475
+ #'
476
+ #' @author Luis M. Rodriguez-R [aut, cre]
477
+ #'
478
+ #' @export
479
+
480
+ enve.tribs <- function
481
+ (dist,
482
+ selection=labels(dist),
483
+ replicates=1000,
484
+ summary.fx=median,
485
+ dist.method='euclidean',
486
+ subsamples=seq(0,1,by=0.01),
487
+ dimensions=ceiling(length(selection)*0.05),
488
+ metaMDS.opts=list(),
489
+ threads=2,
490
+ verbosity=1,
491
+ points,
492
+ pre.tribs
493
+ ){
494
+ if(!is(dist, 'dist'))
495
+ stop('`dist` parameter must be a `dist` object.');
496
+ # 1. NMDS
497
+ if(missing(points)){
498
+ if(missing(pre.tribs)){
499
+ if(verbosity > 0)
500
+ cat('===[ Estimating NMDS ]\n');
501
+ if(!suppressPackageStartupMessages(
502
+ requireNamespace("vegan", quietly=TRUE)))
503
+ stop('Unavailable required package: `vegan`.');
504
+ mds.args <- c(metaMDS.opts, list(comm=dist, k=dimensions,
505
+ trace=verbosity));
506
+ points <- do.call(vegan::metaMDS, mds.args)$points;
507
+ }else{
508
+ points <- attr(pre.tribs, 'points');
509
+ dimensions <- ncol(points);
510
+ }
511
+ }else{
512
+ points <- as.matrix(points);
513
+ dimensions <- ncol(points);
514
+ }
515
+ # 2. Pad ranges
516
+ if(verbosity > 0) cat('===[ Padding ranges ]\n');
517
+ dots <- matrix(NA, nrow=nrow(points), ncol=dimensions,
518
+ dimnames=list(rownames(points), 1:dimensions));
519
+ selection <- selection[!is.na(match(selection, rownames(dots)))];
520
+ for(dim in 1:dimensions){
521
+ dimRange <- range(points[,dim]) +
522
+ c(-1,1)*diff(range(points[,1]))/length(selection);
523
+ dots[, dim] <- (points[,dim]-dimRange[1])/diff(dimRange);
524
+ }
525
+ # 3. Select points and summarize distances
526
+ if(verbosity > 0) cat('===[ Sub-sampling ]\n');
527
+ distances <- matrix(NA, nrow=replicates, ncol=length(subsamples),
528
+ dimnames=list(1:replicates, as.character(subsamples)));
529
+ cl <- makeCluster(threads);
530
+ for(frx in subsamples){
531
+ if(verbosity > 1) cat('Sub-sampling at ',(frx*100),'%\n',sep='');
532
+ distances[, as.character(frx)] = parSapply(cl, 1:replicates, enve.__tribs,
533
+ frx, match(selection, rownames(dots)), dimensions, dots, dist.method,
534
+ summary.fx, dist);
535
+ }
536
+ stopCluster(cl);
537
+ # 4. Build object and return
538
+ return(new('enve.TRIBS',
539
+ distance=do.call(summary.fx, list(as.matrix(dist)[selection, selection])),
540
+ points=points, distances=distances, spaceSize=nrow(points),
541
+ selSize=length(selection), dimensions=dimensions, subsamples=subsamples,
542
+ call=match.call()));
543
+ }
544
+
545
+ #' Enveomics: TRIBS - Internal Ancillary Function
546
+ #'
547
+ #' Internal ancillary function (see \code{\link{enve.tribs}}).
548
+ #'
549
+ #' @param rep Replicates
550
+ #' @param frx Fraction
551
+ #' @param selection Selection
552
+ #' @param dimensions Dimensions
553
+ #' @param dots Sampling points
554
+ #' @param dist.method Distance method
555
+ #' @param summary.fx Summary function
556
+ #' @param dist Distance
557
+ #'
558
+ #' @author Luis M. Rodriguez-R [aut, cre]
559
+ #'
560
+ #' @export
561
+
562
+ enve.__tribs <- function
563
+ (rep, frx, selection, dimensions, dots, dist.method, summary.fx, dist){
564
+ sample <- c();
565
+ if(frx==0) return(0);
566
+ for(point in 1:round(frx*length(selection))){
567
+ rand.point <- runif(dimensions);
568
+ closest.dot <- '';
569
+ closest.dist <- Inf;
570
+ for(dot in selection){
571
+ dot.dist <- as.numeric(dist(matrix(c(rand.point, dots[dot,]), nrow=2,
572
+ byrow=TRUE), method=dist.method));
573
+ if(dot.dist < closest.dist){
574
+ closest.dot <- dot;
575
+ closest.dist <- dot.dist;
576
+ }
577
+ }
578
+ sample <- c(sample, closest.dot);
579
+ }
580
+ return( do.call(summary.fx, list(as.matrix(dist)[sample, sample])) );
581
+ }
582
+
583
+
@@ -0,0 +1,80 @@
1
+ #' Enveomics: Color Alpha
2
+ #'
3
+ #' Modify alpha in a color (or vector of colors).
4
+ #'
5
+ #' @param col Color or vector of colors. It can be any value supported by
6
+ #' \code{\link[grDevices]{col2rgb}}, such as \code{darkred} or \code{#009988}.
7
+ #' @param alpha Alpha value to add to the color, from 0 to 1.
8
+ #'
9
+ #' @return Returns a color or a vector of colors in \emph{hex} notation,
10
+ #' including \code{alpha}.
11
+ #'
12
+ #' @author Luis M. Rodriguez-R [aut, cre]
13
+ #'
14
+ #' @export
15
+
16
+ enve.col.alpha <- function
17
+ (col,
18
+ alpha=1/2
19
+ ){
20
+ return(
21
+ apply(col2rgb(col), 2,
22
+ function(x) do.call(rgb, as.list(c(x[1:3]/256, alpha))) ) )
23
+ }
24
+
25
+ #' Enveomics: Truncate
26
+ #'
27
+ #' Removes the \code{n} highest and lowest values from a vector, and applies
28
+ #' summary function. The value of \code{n} is determined such that the central
29
+ #' range is used, corresponding to the \code{f} fraction of values.
30
+ #'
31
+ #' @param x A vector of numbers.
32
+ #' @param f The fraction of values to retain.
33
+ #' @param FUN Summary function to apply to the vectors. To obtain the
34
+ #' truncated vector itself, use \code{c}.
35
+ #'
36
+ #' @return Returns the summary \code{(FUN)} of the truncated vector.
37
+ #'
38
+ #' @author Luis M. Rodriguez-R [aut, cre]
39
+ #'
40
+ #' @export
41
+
42
+ enve.truncate <- function
43
+ (x,
44
+ f=0.95,
45
+ FUN=mean
46
+ ){
47
+ n <- round(length(x)*(1-f)/2)
48
+ y <- sort(x)[ -c(seq(1, n), seq(length(x)+1-n, length(x))) ]
49
+ return(FUN(y))
50
+ }
51
+
52
+ #' Enveomics: Selection vector
53
+ #'
54
+ #' Normalizes a selection vector \code{sel} to a logical vector with indexes
55
+ #' from \code{dim.names}.
56
+ #'
57
+ #' @param sel A vector of numbers, characters, or booleans.
58
+ #' @param dim.names A vector of names from which to select.
59
+ #'
60
+ #' @return Returns a logical vector with the same length as \code{dim.name}.
61
+ #'
62
+ #' @author Luis M. Rodriguez-R [aut, cre]
63
+ #'
64
+ #' @export
65
+
66
+ enve.selvector <- function(sel, dim.names) {
67
+ if(is.logical(sel)) {
68
+ if(length(sel) != length(dim.names))
69
+ stop('sel is logical but differs in length from dim.names')
70
+ sel
71
+ } else if(is.numeric(sel)) {
72
+ if(max(sel) > length(dim.names))
73
+ stop('sel includes numeric index beyond the length of dim.names')
74
+ 1:length(dim.names) %in% sel
75
+ } else {
76
+ if(any(!sel %in% dim.names))
77
+ stop('sel includes character index missing from dim.names')
78
+ dim.names %in% sel
79
+ }
80
+ }