miga-base 0.7.26.0 → 1.0.0.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (337) hide show
  1. checksums.yaml +4 -4
  2. data/lib/miga/_data/aai-intax.blast.tsv.gz +0 -0
  3. data/lib/miga/_data/aai-intax.diamond.tsv.gz +0 -0
  4. data/lib/miga/_data/aai-novel.blast.tsv.gz +0 -0
  5. data/lib/miga/_data/aai-novel.diamond.tsv.gz +0 -0
  6. data/lib/miga/cli/action/classify_wf.rb +2 -2
  7. data/lib/miga/cli/action/derep_wf.rb +1 -1
  8. data/lib/miga/cli/action/doctor.rb +57 -14
  9. data/lib/miga/cli/action/doctor/base.rb +47 -23
  10. data/lib/miga/cli/action/init.rb +11 -7
  11. data/lib/miga/cli/action/init/files_helper.rb +1 -0
  12. data/lib/miga/cli/action/ncbi_get.rb +3 -3
  13. data/lib/miga/cli/action/tax_dist.rb +2 -2
  14. data/lib/miga/cli/action/wf.rb +5 -4
  15. data/lib/miga/common.rb +1 -0
  16. data/lib/miga/daemon.rb +11 -4
  17. data/lib/miga/dataset/result.rb +10 -6
  18. data/lib/miga/json.rb +5 -4
  19. data/lib/miga/metadata.rb +5 -1
  20. data/lib/miga/parallel.rb +36 -0
  21. data/lib/miga/project.rb +8 -8
  22. data/lib/miga/project/base.rb +4 -4
  23. data/lib/miga/project/result.rb +2 -2
  24. data/lib/miga/sqlite.rb +10 -2
  25. data/lib/miga/version.rb +23 -9
  26. data/scripts/aai_distances.bash +16 -18
  27. data/scripts/ani_distances.bash +16 -17
  28. data/scripts/assembly.bash +31 -16
  29. data/scripts/haai_distances.bash +3 -27
  30. data/scripts/miga.bash +6 -4
  31. data/scripts/p.bash +1 -1
  32. data/scripts/read_quality.bash +9 -18
  33. data/scripts/trimmed_fasta.bash +14 -30
  34. data/scripts/trimmed_reads.bash +36 -36
  35. data/test/parallel_test.rb +31 -0
  36. data/test/project_test.rb +2 -1
  37. data/test/remote_dataset_test.rb +1 -1
  38. data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Archaea_SCG.hmm +41964 -0
  39. data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Bacteria_SCG.hmm +32439 -0
  40. data/utils/FastAAI/00.Libraries/01.SCG_HMMs/Complete_SCG_DB.hmm +62056 -0
  41. data/utils/FastAAI/FastAAI/FastAAI +1336 -0
  42. data/utils/FastAAI/README.md +84 -0
  43. data/utils/FastAAI/kAAI_v1.0_virus.py +1296 -0
  44. data/utils/distance/commands.rb +1 -0
  45. data/utils/distance/database.rb +0 -1
  46. data/utils/distance/runner.rb +2 -4
  47. data/utils/enveomics/Docs/recplot2.md +244 -0
  48. data/utils/enveomics/Examples/aai-matrix.bash +66 -0
  49. data/utils/enveomics/Examples/ani-matrix.bash +66 -0
  50. data/utils/enveomics/Examples/essential-phylogeny.bash +105 -0
  51. data/utils/enveomics/Examples/unus-genome-phylogeny.bash +100 -0
  52. data/utils/enveomics/LICENSE.txt +73 -0
  53. data/utils/enveomics/Makefile +52 -0
  54. data/utils/enveomics/Manifest/Tasks/aasubs.json +103 -0
  55. data/utils/enveomics/Manifest/Tasks/blasttab.json +786 -0
  56. data/utils/enveomics/Manifest/Tasks/distances.json +161 -0
  57. data/utils/enveomics/Manifest/Tasks/fasta.json +802 -0
  58. data/utils/enveomics/Manifest/Tasks/fastq.json +291 -0
  59. data/utils/enveomics/Manifest/Tasks/graphics.json +126 -0
  60. data/utils/enveomics/Manifest/Tasks/mapping.json +137 -0
  61. data/utils/enveomics/Manifest/Tasks/ogs.json +382 -0
  62. data/utils/enveomics/Manifest/Tasks/other.json +906 -0
  63. data/utils/enveomics/Manifest/Tasks/remote.json +355 -0
  64. data/utils/enveomics/Manifest/Tasks/sequence-identity.json +638 -0
  65. data/utils/enveomics/Manifest/Tasks/tables.json +308 -0
  66. data/utils/enveomics/Manifest/Tasks/trees.json +68 -0
  67. data/utils/enveomics/Manifest/Tasks/variants.json +111 -0
  68. data/utils/enveomics/Manifest/categories.json +165 -0
  69. data/utils/enveomics/Manifest/examples.json +154 -0
  70. data/utils/enveomics/Manifest/tasks.json +4 -0
  71. data/utils/enveomics/Pipelines/assembly.pbs/CONFIG.mock.bash +69 -0
  72. data/utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl +1 -0
  73. data/utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl +1 -0
  74. data/utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl +1 -0
  75. data/utils/enveomics/Pipelines/assembly.pbs/README.md +189 -0
  76. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-2.bash +112 -0
  77. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-3.bash +23 -0
  78. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-4.bash +44 -0
  79. data/utils/enveomics/Pipelines/assembly.pbs/RUNME.bash +50 -0
  80. data/utils/enveomics/Pipelines/assembly.pbs/kSelector.R +37 -0
  81. data/utils/enveomics/Pipelines/assembly.pbs/newbler.pbs +68 -0
  82. data/utils/enveomics/Pipelines/assembly.pbs/newbler_preparator.pl +49 -0
  83. data/utils/enveomics/Pipelines/assembly.pbs/soap.pbs +80 -0
  84. data/utils/enveomics/Pipelines/assembly.pbs/stats.pbs +57 -0
  85. data/utils/enveomics/Pipelines/assembly.pbs/velvet.pbs +63 -0
  86. data/utils/enveomics/Pipelines/blast.pbs/01.pbs.bash +38 -0
  87. data/utils/enveomics/Pipelines/blast.pbs/02.pbs.bash +73 -0
  88. data/utils/enveomics/Pipelines/blast.pbs/03.pbs.bash +21 -0
  89. data/utils/enveomics/Pipelines/blast.pbs/BlastTab.recover_job.pl +72 -0
  90. data/utils/enveomics/Pipelines/blast.pbs/CONFIG.mock.bash +98 -0
  91. data/utils/enveomics/Pipelines/blast.pbs/FastA.split.pl +1 -0
  92. data/utils/enveomics/Pipelines/blast.pbs/README.md +127 -0
  93. data/utils/enveomics/Pipelines/blast.pbs/RUNME.bash +109 -0
  94. data/utils/enveomics/Pipelines/blast.pbs/TASK.check.bash +128 -0
  95. data/utils/enveomics/Pipelines/blast.pbs/TASK.dry.bash +16 -0
  96. data/utils/enveomics/Pipelines/blast.pbs/TASK.eo.bash +22 -0
  97. data/utils/enveomics/Pipelines/blast.pbs/TASK.pause.bash +26 -0
  98. data/utils/enveomics/Pipelines/blast.pbs/TASK.run.bash +89 -0
  99. data/utils/enveomics/Pipelines/blast.pbs/sentinel.pbs.bash +29 -0
  100. data/utils/enveomics/Pipelines/idba.pbs/README.md +49 -0
  101. data/utils/enveomics/Pipelines/idba.pbs/RUNME.bash +95 -0
  102. data/utils/enveomics/Pipelines/idba.pbs/run.pbs +56 -0
  103. data/utils/enveomics/Pipelines/trim.pbs/README.md +54 -0
  104. data/utils/enveomics/Pipelines/trim.pbs/RUNME.bash +70 -0
  105. data/utils/enveomics/Pipelines/trim.pbs/run.pbs +130 -0
  106. data/utils/enveomics/README.md +42 -0
  107. data/utils/enveomics/Scripts/AAsubs.log2ratio.rb +171 -0
  108. data/utils/enveomics/Scripts/Aln.cat.rb +221 -0
  109. data/utils/enveomics/Scripts/Aln.convert.pl +35 -0
  110. data/utils/enveomics/Scripts/AlphaDiversity.pl +152 -0
  111. data/utils/enveomics/Scripts/BedGraph.tad.rb +93 -0
  112. data/utils/enveomics/Scripts/BedGraph.window.rb +71 -0
  113. data/utils/enveomics/Scripts/BlastPairwise.AAsubs.pl +102 -0
  114. data/utils/enveomics/Scripts/BlastTab.addlen.rb +63 -0
  115. data/utils/enveomics/Scripts/BlastTab.advance.bash +48 -0
  116. data/utils/enveomics/Scripts/BlastTab.best_hit_sorted.pl +55 -0
  117. data/utils/enveomics/Scripts/BlastTab.catsbj.pl +104 -0
  118. data/utils/enveomics/Scripts/BlastTab.cogCat.rb +76 -0
  119. data/utils/enveomics/Scripts/BlastTab.filter.pl +47 -0
  120. data/utils/enveomics/Scripts/BlastTab.kegg_pep2path_rest.pl +194 -0
  121. data/utils/enveomics/Scripts/BlastTab.metaxaPrep.pl +104 -0
  122. data/utils/enveomics/Scripts/BlastTab.pairedHits.rb +157 -0
  123. data/utils/enveomics/Scripts/BlastTab.recplot2.R +48 -0
  124. data/utils/enveomics/Scripts/BlastTab.seqdepth.pl +86 -0
  125. data/utils/enveomics/Scripts/BlastTab.seqdepth_ZIP.pl +119 -0
  126. data/utils/enveomics/Scripts/BlastTab.seqdepth_nomedian.pl +86 -0
  127. data/utils/enveomics/Scripts/BlastTab.subsample.pl +47 -0
  128. data/utils/enveomics/Scripts/BlastTab.sumPerHit.pl +114 -0
  129. data/utils/enveomics/Scripts/BlastTab.taxid2taxrank.pl +90 -0
  130. data/utils/enveomics/Scripts/BlastTab.topHits_sorted.rb +101 -0
  131. data/utils/enveomics/Scripts/Chao1.pl +97 -0
  132. data/utils/enveomics/Scripts/CharTable.classify.rb +234 -0
  133. data/utils/enveomics/Scripts/EBIseq2tax.rb +83 -0
  134. data/utils/enveomics/Scripts/FastA.N50.pl +60 -0
  135. data/utils/enveomics/Scripts/FastA.extract.rb +152 -0
  136. data/utils/enveomics/Scripts/FastA.filter.pl +52 -0
  137. data/utils/enveomics/Scripts/FastA.filterLen.pl +28 -0
  138. data/utils/enveomics/Scripts/FastA.filterN.pl +60 -0
  139. data/utils/enveomics/Scripts/FastA.fragment.rb +100 -0
  140. data/utils/enveomics/Scripts/FastA.gc.pl +42 -0
  141. data/utils/enveomics/Scripts/FastA.interpose.pl +93 -0
  142. data/utils/enveomics/Scripts/FastA.length.pl +38 -0
  143. data/utils/enveomics/Scripts/FastA.mask.rb +89 -0
  144. data/utils/enveomics/Scripts/FastA.per_file.pl +36 -0
  145. data/utils/enveomics/Scripts/FastA.qlen.pl +57 -0
  146. data/utils/enveomics/Scripts/FastA.rename.pl +65 -0
  147. data/utils/enveomics/Scripts/FastA.revcom.pl +23 -0
  148. data/utils/enveomics/Scripts/FastA.sample.rb +98 -0
  149. data/utils/enveomics/Scripts/FastA.slider.pl +85 -0
  150. data/utils/enveomics/Scripts/FastA.split.pl +55 -0
  151. data/utils/enveomics/Scripts/FastA.split.rb +79 -0
  152. data/utils/enveomics/Scripts/FastA.subsample.pl +131 -0
  153. data/utils/enveomics/Scripts/FastA.tag.rb +65 -0
  154. data/utils/enveomics/Scripts/FastA.toFastQ.rb +69 -0
  155. data/utils/enveomics/Scripts/FastA.wrap.rb +48 -0
  156. data/utils/enveomics/Scripts/FastQ.filter.pl +54 -0
  157. data/utils/enveomics/Scripts/FastQ.interpose.pl +90 -0
  158. data/utils/enveomics/Scripts/FastQ.maskQual.rb +89 -0
  159. data/utils/enveomics/Scripts/FastQ.offset.pl +90 -0
  160. data/utils/enveomics/Scripts/FastQ.split.pl +53 -0
  161. data/utils/enveomics/Scripts/FastQ.tag.rb +70 -0
  162. data/utils/enveomics/Scripts/FastQ.test-error.rb +81 -0
  163. data/utils/enveomics/Scripts/FastQ.toFastA.awk +24 -0
  164. data/utils/enveomics/Scripts/GFF.catsbj.pl +127 -0
  165. data/utils/enveomics/Scripts/GenBank.add_fields.rb +84 -0
  166. data/utils/enveomics/Scripts/HMM.essential.rb +351 -0
  167. data/utils/enveomics/Scripts/HMM.haai.rb +168 -0
  168. data/utils/enveomics/Scripts/HMMsearch.extractIds.rb +83 -0
  169. data/utils/enveomics/Scripts/JPlace.distances.rb +88 -0
  170. data/utils/enveomics/Scripts/JPlace.to_iToL.rb +320 -0
  171. data/utils/enveomics/Scripts/M5nr.getSequences.rb +81 -0
  172. data/utils/enveomics/Scripts/MeTaxa.distribution.pl +198 -0
  173. data/utils/enveomics/Scripts/MyTaxa.fragsByTax.pl +35 -0
  174. data/utils/enveomics/Scripts/MyTaxa.seq-taxrank.rb +49 -0
  175. data/utils/enveomics/Scripts/NCBIacc2tax.rb +92 -0
  176. data/utils/enveomics/Scripts/Newick.autoprune.R +27 -0
  177. data/utils/enveomics/Scripts/RAxML-EPA.to_iToL.pl +228 -0
  178. data/utils/enveomics/Scripts/RecPlot2.compareIdentities.R +32 -0
  179. data/utils/enveomics/Scripts/RefSeq.download.bash +48 -0
  180. data/utils/enveomics/Scripts/SRA.download.bash +55 -0
  181. data/utils/enveomics/Scripts/TRIBS.plot-test.R +36 -0
  182. data/utils/enveomics/Scripts/TRIBS.test.R +39 -0
  183. data/utils/enveomics/Scripts/Table.barplot.R +31 -0
  184. data/utils/enveomics/Scripts/Table.df2dist.R +30 -0
  185. data/utils/enveomics/Scripts/Table.filter.pl +61 -0
  186. data/utils/enveomics/Scripts/Table.merge.pl +77 -0
  187. data/utils/enveomics/Scripts/Table.prefScore.R +60 -0
  188. data/utils/enveomics/Scripts/Table.replace.rb +69 -0
  189. data/utils/enveomics/Scripts/Table.round.rb +63 -0
  190. data/utils/enveomics/Scripts/Table.split.pl +57 -0
  191. data/utils/enveomics/Scripts/Taxonomy.silva2ncbi.rb +227 -0
  192. data/utils/enveomics/Scripts/VCF.KaKs.rb +147 -0
  193. data/utils/enveomics/Scripts/VCF.SNPs.rb +88 -0
  194. data/utils/enveomics/Scripts/aai.rb +419 -0
  195. data/utils/enveomics/Scripts/ani.rb +362 -0
  196. data/utils/enveomics/Scripts/anir.rb +137 -0
  197. data/utils/enveomics/Scripts/clust.rand.rb +102 -0
  198. data/utils/enveomics/Scripts/gi2tax.rb +103 -0
  199. data/utils/enveomics/Scripts/in_silico_GA_GI.pl +96 -0
  200. data/utils/enveomics/Scripts/lib/data/dupont_2012_essential.hmm.gz +0 -0
  201. data/utils/enveomics/Scripts/lib/data/lee_2019_essential.hmm.gz +0 -0
  202. data/utils/enveomics/Scripts/lib/enveomics.R +1 -0
  203. data/utils/enveomics/Scripts/lib/enveomics_rb/anir.rb +293 -0
  204. data/utils/enveomics/Scripts/lib/enveomics_rb/bm_set.rb +175 -0
  205. data/utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb +24 -0
  206. data/utils/enveomics/Scripts/lib/enveomics_rb/errors.rb +17 -0
  207. data/utils/enveomics/Scripts/lib/enveomics_rb/gmm_em.rb +30 -0
  208. data/utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb +253 -0
  209. data/utils/enveomics/Scripts/lib/enveomics_rb/match.rb +63 -0
  210. data/utils/enveomics/Scripts/lib/enveomics_rb/og.rb +182 -0
  211. data/utils/enveomics/Scripts/lib/enveomics_rb/rbm.rb +49 -0
  212. data/utils/enveomics/Scripts/lib/enveomics_rb/remote_data.rb +74 -0
  213. data/utils/enveomics/Scripts/lib/enveomics_rb/seq_range.rb +237 -0
  214. data/utils/enveomics/Scripts/lib/enveomics_rb/stats.rb +3 -0
  215. data/utils/enveomics/Scripts/lib/enveomics_rb/stats/rand.rb +31 -0
  216. data/utils/enveomics/Scripts/lib/enveomics_rb/stats/sample.rb +152 -0
  217. data/utils/enveomics/Scripts/lib/enveomics_rb/utils.rb +73 -0
  218. data/utils/enveomics/Scripts/lib/enveomics_rb/vcf.rb +135 -0
  219. data/utils/enveomics/Scripts/ogs.annotate.rb +88 -0
  220. data/utils/enveomics/Scripts/ogs.core-pan.rb +160 -0
  221. data/utils/enveomics/Scripts/ogs.extract.rb +125 -0
  222. data/utils/enveomics/Scripts/ogs.mcl.rb +186 -0
  223. data/utils/enveomics/Scripts/ogs.rb +104 -0
  224. data/utils/enveomics/Scripts/ogs.stats.rb +131 -0
  225. data/utils/enveomics/Scripts/rbm-legacy.rb +172 -0
  226. data/utils/enveomics/Scripts/rbm.rb +100 -0
  227. data/utils/enveomics/Scripts/sam.filter.rb +148 -0
  228. data/utils/enveomics/Tests/Makefile +10 -0
  229. data/utils/enveomics/Tests/Mgen_M2288.faa +3189 -0
  230. data/utils/enveomics/Tests/Mgen_M2288.fna +8282 -0
  231. data/utils/enveomics/Tests/Mgen_M2321.fna +8288 -0
  232. data/utils/enveomics/Tests/Nequ_Kin4M.faa +2970 -0
  233. data/utils/enveomics/Tests/Xanthomonas_oryzae-PilA.tribs.Rdata +0 -0
  234. data/utils/enveomics/Tests/Xanthomonas_oryzae-PilA.txt +7 -0
  235. data/utils/enveomics/Tests/Xanthomonas_oryzae.aai-mat.tsv +17 -0
  236. data/utils/enveomics/Tests/Xanthomonas_oryzae.aai.tsv +137 -0
  237. data/utils/enveomics/Tests/a_mg.cds-go.blast.tsv +123 -0
  238. data/utils/enveomics/Tests/a_mg.reads-cds.blast.tsv +200 -0
  239. data/utils/enveomics/Tests/a_mg.reads-cds.counts.tsv +55 -0
  240. data/utils/enveomics/Tests/alkB.nwk +1 -0
  241. data/utils/enveomics/Tests/anthrax-cansnp-data.tsv +13 -0
  242. data/utils/enveomics/Tests/anthrax-cansnp-key.tsv +17 -0
  243. data/utils/enveomics/Tests/hiv1.faa +59 -0
  244. data/utils/enveomics/Tests/hiv1.fna +134 -0
  245. data/utils/enveomics/Tests/hiv2.faa +70 -0
  246. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv +233 -0
  247. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.lim +1 -0
  248. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.rec +233 -0
  249. data/utils/enveomics/Tests/phyla_counts.tsv +10 -0
  250. data/utils/enveomics/Tests/primate_lentivirus.ogs +11 -0
  251. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv1.rbm +9 -0
  252. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv2.rbm +8 -0
  253. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-siv.rbm +6 -0
  254. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-hiv2.rbm +9 -0
  255. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-siv.rbm +6 -0
  256. data/utils/enveomics/Tests/primate_lentivirus.rbm/siv-siv.rbm +6 -0
  257. data/utils/enveomics/build_enveomics_r.bash +45 -0
  258. data/utils/enveomics/enveomics.R/DESCRIPTION +31 -0
  259. data/utils/enveomics/enveomics.R/NAMESPACE +39 -0
  260. data/utils/enveomics/enveomics.R/R/autoprune.R +155 -0
  261. data/utils/enveomics/enveomics.R/R/barplot.R +184 -0
  262. data/utils/enveomics/enveomics.R/R/cliopts.R +135 -0
  263. data/utils/enveomics/enveomics.R/R/df2dist.R +154 -0
  264. data/utils/enveomics/enveomics.R/R/growthcurve.R +331 -0
  265. data/utils/enveomics/enveomics.R/R/prefscore.R +79 -0
  266. data/utils/enveomics/enveomics.R/R/recplot.R +354 -0
  267. data/utils/enveomics/enveomics.R/R/recplot2.R +1631 -0
  268. data/utils/enveomics/enveomics.R/R/tribs.R +583 -0
  269. data/utils/enveomics/enveomics.R/R/utils.R +80 -0
  270. data/utils/enveomics/enveomics.R/README.md +81 -0
  271. data/utils/enveomics/enveomics.R/data/growth.curves.rda +0 -0
  272. data/utils/enveomics/enveomics.R/data/phyla.counts.rda +0 -0
  273. data/utils/enveomics/enveomics.R/man/cash-enve.GrowthCurve-method.Rd +16 -0
  274. data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2-method.Rd +16 -0
  275. data/utils/enveomics/enveomics.R/man/cash-enve.RecPlot2.Peak-method.Rd +16 -0
  276. data/utils/enveomics/enveomics.R/man/enve.GrowthCurve-class.Rd +25 -0
  277. data/utils/enveomics/enveomics.R/man/enve.TRIBS-class.Rd +46 -0
  278. data/utils/enveomics/enveomics.R/man/enve.TRIBS.merge.Rd +23 -0
  279. data/utils/enveomics/enveomics.R/man/enve.TRIBStest-class.Rd +47 -0
  280. data/utils/enveomics/enveomics.R/man/enve.__prune.iter.Rd +23 -0
  281. data/utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd +23 -0
  282. data/utils/enveomics/enveomics.R/man/enve.__tribs.Rd +40 -0
  283. data/utils/enveomics/enveomics.R/man/enve.barplot.Rd +103 -0
  284. data/utils/enveomics/enveomics.R/man/enve.cliopts.Rd +67 -0
  285. data/utils/enveomics/enveomics.R/man/enve.col.alpha.Rd +24 -0
  286. data/utils/enveomics/enveomics.R/man/enve.col2alpha.Rd +19 -0
  287. data/utils/enveomics/enveomics.R/man/enve.df2dist.Rd +45 -0
  288. data/utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd +44 -0
  289. data/utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd +47 -0
  290. data/utils/enveomics/enveomics.R/man/enve.growthcurve.Rd +75 -0
  291. data/utils/enveomics/enveomics.R/man/enve.prefscore.Rd +50 -0
  292. data/utils/enveomics/enveomics.R/man/enve.prune.dist.Rd +44 -0
  293. data/utils/enveomics/enveomics.R/man/enve.recplot.Rd +139 -0
  294. data/utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd +45 -0
  295. data/utils/enveomics/enveomics.R/man/enve.recplot2.ANIr.Rd +24 -0
  296. data/utils/enveomics/enveomics.R/man/enve.recplot2.Rd +77 -0
  297. data/utils/enveomics/enveomics.R/man/enve.recplot2.__counts.Rd +25 -0
  298. data/utils/enveomics/enveomics.R/man/enve.recplot2.__peakHist.Rd +21 -0
  299. data/utils/enveomics/enveomics.R/man/enve.recplot2.__whichClosestPeak.Rd +19 -0
  300. data/utils/enveomics/enveomics.R/man/enve.recplot2.changeCutoff.Rd +19 -0
  301. data/utils/enveomics/enveomics.R/man/enve.recplot2.compareIdentities.Rd +47 -0
  302. data/utils/enveomics/enveomics.R/man/enve.recplot2.coordinates.Rd +29 -0
  303. data/utils/enveomics/enveomics.R/man/enve.recplot2.corePeak.Rd +18 -0
  304. data/utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd +45 -0
  305. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd +36 -0
  306. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_e.Rd +19 -0
  307. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__em_m.Rd +19 -0
  308. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__emauto_one.Rd +27 -0
  309. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mow_one.Rd +52 -0
  310. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.__mower.Rd +17 -0
  311. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.em.Rd +51 -0
  312. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.emauto.Rd +43 -0
  313. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.mower.Rd +82 -0
  314. data/utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd +59 -0
  315. data/utils/enveomics/enveomics.R/man/enve.recplot2.seqdepth.Rd +27 -0
  316. data/utils/enveomics/enveomics.R/man/enve.recplot2.windowDepthThreshold.Rd +36 -0
  317. data/utils/enveomics/enveomics.R/man/enve.selvector.Rd +23 -0
  318. data/utils/enveomics/enveomics.R/man/enve.tribs.Rd +68 -0
  319. data/utils/enveomics/enveomics.R/man/enve.tribs.test.Rd +28 -0
  320. data/utils/enveomics/enveomics.R/man/enve.truncate.Rd +27 -0
  321. data/utils/enveomics/enveomics.R/man/growth.curves.Rd +14 -0
  322. data/utils/enveomics/enveomics.R/man/phyla.counts.Rd +13 -0
  323. data/utils/enveomics/enveomics.R/man/plot.enve.GrowthCurve.Rd +78 -0
  324. data/utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd +46 -0
  325. data/utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd +45 -0
  326. data/utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd +125 -0
  327. data/utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd +19 -0
  328. data/utils/enveomics/enveomics.R/man/summary.enve.TRIBS.Rd +19 -0
  329. data/utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd +19 -0
  330. data/utils/enveomics/globals.mk +8 -0
  331. data/utils/enveomics/manifest.json +9 -0
  332. data/utils/multitrim/Multitrim How-To.pdf +0 -0
  333. data/utils/multitrim/README.md +67 -0
  334. data/utils/multitrim/multitrim.py +1555 -0
  335. data/utils/multitrim/multitrim.yml +13 -0
  336. data/utils/requirements.txt +4 -3
  337. metadata +304 -3
@@ -0,0 +1,103 @@
1
+ % Generated by roxygen2: do not edit by hand
2
+ % Please edit documentation in R/barplot.R
3
+ \name{enve.barplot}
4
+ \alias{enve.barplot}
5
+ \title{Enveomics: Barplot}
6
+ \usage{
7
+ enve.barplot(
8
+ x,
9
+ sizes,
10
+ top = 25,
11
+ colors.per.group = 9,
12
+ bars.width = 4,
13
+ legend.ncol = 1,
14
+ other.col = "#000000",
15
+ add.trend = FALSE,
16
+ organic.trend = FALSE,
17
+ sort.by = median,
18
+ min.report = 101,
19
+ order = NULL,
20
+ col,
21
+ ...
22
+ )
23
+ }
24
+ \arguments{
25
+ \item{x}{Can be either the input data or the path to the file containing
26
+ the table.
27
+ \itemize{
28
+ \item{If it contains the data, it must be a data frame or an
29
+ object coercible to a data frame.}
30
+ \item{If it is a path, it must point to a
31
+ tab-delimited file containing a header (first row) and row names
32
+ (first column).}
33
+ }}
34
+
35
+ \item{sizes}{A numeric vector containing the real size of the samples
36
+ (columns) in the same order of the input table. If set, the values are
37
+ assumed to be 100\%. Otherwise, the sum of the columns is used.}
38
+
39
+ \item{top}{Maximum number of categories to display. Any additional
40
+ categories will be listed as "Others".}
41
+
42
+ \item{colors.per.group}{Number of categories in the first two saturation
43
+ groups of colors. The third group contains the remaining categories if
44
+ needed.}
45
+
46
+ \item{bars.width}{Width of the barplot with respect to the legend.}
47
+
48
+ \item{legend.ncol}{Number of columns in the legend.}
49
+
50
+ \item{other.col}{Color of the "Others" category.}
51
+
52
+ \item{add.trend}{Controls if semi-transparent areas are to be plotted
53
+ between the bars to connect the regions (trend regions).}
54
+
55
+ \item{organic.trend}{Controls if the trend regions are to be smoothed
56
+ (curves). By default, trend regions have straight edges. If \code{TRUE},
57
+ forces \code{add.trend=TRUE}.}
58
+
59
+ \item{sort.by}{Any function that takes a numeric vector and returns a
60
+ numeric scalar. This function is applied to each row, and the resulting
61
+ values are used to sort the rows (decreasingly). Good options include:
62
+ \code{sd, min, max, mean, median}.}
63
+
64
+ \item{min.report}{Minimum percentage to report the value in the plot.
65
+ Any value above 100 indicates that no values are to be reported.}
66
+
67
+ \item{order}{Controls how the rows should be ordered.
68
+ \itemize{
69
+ \item{If \code{NULL}
70
+ (default), \code{sort.by} is applied per row and the results are
71
+ sorted decreasingly.}
72
+ \item{If \code{NA}, no sorting is performed, i.e., the original
73
+ order is respected.}
74
+ \item{If a vector is provided, it is assumed to be the
75
+ custom order to be used (either by numeric index or by row names).}
76
+ }}
77
+
78
+ \item{col}{Colors to use. If provided, overrides the variables \code{top}
79
+ and \code{colors.per.group}, but \code{other.col} is still used if the
80
+ vector is insufficient for all the rows. An additional palette is available with
81
+ \code{col='coto'} (contributed by Luis (Coto) Orellana).}
82
+
83
+ \item{...}{Any additional parameters to be passed to barplot.}
84
+ }
85
+ \description{
86
+ Creates nice barplots from tab-delimited tables.
87
+ }
88
+ \examples{
89
+ # Load data
90
+ data("phyla.counts", package="enveomics.R", envir=environment())
91
+ # Create a barplot sorted by variance with organic trends
92
+ enve.barplot(
93
+ phyla.counts, # Counts of phyla in four sites
94
+ sizes=c(250,100,75,200), # Total sizes of the datasets of each site
95
+ bars.width=2, # Decrease from default, so the names are fully displayed
96
+ organic.trend=TRUE, # Nice curvy background
97
+ sort.by=var # Sort by variance across sites
98
+ )
99
+
100
+ }
101
+ \author{
102
+ Luis M. Rodriguez-R [aut, cre]
103
+ }
@@ -0,0 +1,67 @@
1
+ % Generated by roxygen2: do not edit by hand
2
+ % Please edit documentation in R/cliopts.R
3
+ \name{enve.cliopts}
4
+ \alias{enve.cliopts}
5
+ \title{Enveomics: Cliopts}
6
+ \usage{
7
+ enve.cliopts(
8
+ fx,
9
+ rd_file,
10
+ positional_arguments,
11
+ usage,
12
+ mandatory = c(),
13
+ vectorize = c(),
14
+ ignore = c(),
15
+ number = c(),
16
+ defaults = list(),
17
+ o_desc = list(),
18
+ p_desc = ""
19
+ )
20
+ }
21
+ \arguments{
22
+ \item{fx}{Function for which the interface should be generated.}
23
+
24
+ \item{rd_file}{(Optional) .Rd file with the standard documentation of
25
+ the function.}
26
+
27
+ \item{positional_arguments}{(Optional) Number of \strong{positional}
28
+ arguments passed to \code{\link[optparse]{parse_args}}
29
+ (package: \pkg{optparse}).}
30
+
31
+ \item{usage}{(Optional) Usage passed to \code{\link[optparse]{OptionParser}}
32
+ (package: \pkg{optparse}).}
33
+
34
+ \item{mandatory}{Mandatory arguments.}
35
+
36
+ \item{vectorize}{Arguments of the function to vectorize (comma-delimited).
37
+ If numeric, use also \code{number}.}
38
+
39
+ \item{ignore}{Arguments of the function to ignore.}
40
+
41
+ \item{number}{Force these arguments as numerics. Useful for numeric
42
+ vectors (see \code{vectorize}) or arguments with no defaults.}
43
+
44
+ \item{defaults}{Defaults to use instead of the ones provided by the
45
+ formals.}
46
+
47
+ \item{o_desc}{Descriptions of the options. Help from \code{rd} is ignored
48
+ for arguments present in this list.}
49
+
50
+ \item{p_desc}{Description Description of the function. Help from \code{rd}
51
+ is ignored for the function description unless this value is an empty string.}
52
+ }
53
+ \value{
54
+ Returns a list with keys:
55
+ \itemize{
56
+ \item{\code{options}, a named list with the values for the function's
57
+ arguments}
58
+ \item{\code{args}, a vector with zero or more strings containing the
59
+ positional arguments}}
60
+ }
61
+ \description{
62
+ Generates nicely formatted command-line interfaces for functions
63
+ (\strong{closures} only).
64
+ }
65
+ \author{
66
+ Luis M. Rodriguez-R [aut, cre]
67
+ }
@@ -0,0 +1,24 @@
1
+ % Generated by roxygen2: do not edit by hand
2
+ % Please edit documentation in R/utils.R
3
+ \name{enve.col.alpha}
4
+ \alias{enve.col.alpha}
5
+ \title{Enveomics: Color Alpha}
6
+ \usage{
7
+ enve.col.alpha(col, alpha = 1/2)
8
+ }
9
+ \arguments{
10
+ \item{col}{Color or vector of colors. It can be any value supported by
11
+ \code{\link[grDevices]{col2rgb}}, such as \code{darkred} or \code{#009988}.}
12
+
13
+ \item{alpha}{Alpha value to add to the color, from 0 to 1.}
14
+ }
15
+ \value{
16
+ Returns a color or a vector of colors in \emph{hex} notation,
17
+ including \code{alpha}.
18
+ }
19
+ \description{
20
+ Modify alpha in a color (or vector of colors).
21
+ }
22
+ \author{
23
+ Luis M. Rodriguez-R [aut, cre]
24
+ }
@@ -0,0 +1,19 @@
1
+ % Generated by roxygen2: do not edit by hand
2
+ % Please edit documentation in R/growthcurve.R
3
+ \name{enve.col2alpha}
4
+ \alias{enve.col2alpha}
5
+ \title{Enveomics: Color to Alpha}
6
+ \usage{
7
+ enve.col2alpha(x, alpha)
8
+ }
9
+ \arguments{
10
+ \item{x}{A vector of any value base colors.}
11
+
12
+ \item{alpha}{Alpha level to set (in the 0-1 range).}
13
+ }
14
+ \description{
15
+ Takes a vector of colors and sets the alpha.
16
+ }
17
+ \author{
18
+ Luis M. Rodriguez-R [aut, cre]
19
+ }
@@ -0,0 +1,45 @@
1
+ % Generated by roxygen2: do not edit by hand
2
+ % Please edit documentation in R/df2dist.R
3
+ \name{enve.df2dist}
4
+ \alias{enve.df2dist}
5
+ \title{Enveomics: Data Frame to Dist}
6
+ \usage{
7
+ enve.df2dist(
8
+ x,
9
+ obj1.index = 1,
10
+ obj2.index = 2,
11
+ dist.index = 3,
12
+ default.d = NA,
13
+ max.sim = 0
14
+ )
15
+ }
16
+ \arguments{
17
+ \item{x}{A dataframe (or coercible object) with at least three columns:
18
+ \enumerate{
19
+ \item ID of the object 1,
20
+ \item ID of the object 2, and
21
+ \item distance between the two objects.}}
22
+
23
+ \item{obj1.index}{Index of the column containing the ID of the object 1.}
24
+
25
+ \item{obj2.index}{Index of the column containing the ID of the object 2.}
26
+
27
+ \item{dist.index}{Index of the column containing the distance.}
28
+
29
+ \item{default.d}{Default value (for missing values).}
30
+
31
+ \item{max.sim}{If not zero, assumes that the values are similarity
32
+ (not distance) and this is the maximum similarity (corresponding to
33
+ distance 0). Applies transformation:
34
+ \eqn{distance = (max.sim - values)/max.sim.}}
35
+ }
36
+ \value{
37
+ Returns a \strong{dist} object.
38
+ }
39
+ \description{
40
+ Transform a dataframe (or coercible object, like a table) into a
41
+ \strong{dist} object.
42
+ }
43
+ \author{
44
+ Luis M. Rodriguez-R [aut, cre]
45
+ }
@@ -0,0 +1,44 @@
1
+ % Generated by roxygen2: do not edit by hand
2
+ % Please edit documentation in R/df2dist.R
3
+ \name{enve.df2dist.group}
4
+ \alias{enve.df2dist.group}
5
+ \title{Enveomics: Data Frame to Dist (Group)}
6
+ \usage{
7
+ enve.df2dist.group(
8
+ x,
9
+ obj1.index = 1,
10
+ obj2.index = 2,
11
+ dist.index = 3,
12
+ summary = median,
13
+ empty.rm = TRUE
14
+ )
15
+ }
16
+ \arguments{
17
+ \item{x}{A dataframe (or coercible object) with at least three columns:
18
+ \enumerate{
19
+ \item ID of the object 1,
20
+ \item ID of the object 2, and
21
+ \item distance between the two objects.}}
22
+
23
+ \item{obj1.index}{Index of the column containing the ID of the object 1.}
24
+
25
+ \item{obj2.index}{Index of the column containing the ID of the object 2.}
26
+
27
+ \item{dist.index}{Index of the column containing the distance.}
28
+
29
+ \item{summary}{Function summarizing the different distances between the
30
+ two objects.}
31
+
32
+ \item{empty.rm}{Remove rows with empty or \code{NA} groups.}
33
+ }
34
+ \value{
35
+ Returns a \strong{dist} object.
36
+ }
37
+ \description{
38
+ Transform a dataframe (or coercible object, like a table) into a
39
+ \strong{dist} object, where there are 1 or more distances between each pair
40
+ of objects.
41
+ }
42
+ \author{
43
+ Luis M. Rodriguez-R [aut, cre]
44
+ }
@@ -0,0 +1,47 @@
1
+ % Generated by roxygen2: do not edit by hand
2
+ % Please edit documentation in R/df2dist.R
3
+ \name{enve.df2dist.list}
4
+ \alias{enve.df2dist.list}
5
+ \title{Enveomics: Data Frame to Dist (List)}
6
+ \usage{
7
+ enve.df2dist.list(
8
+ x,
9
+ groups,
10
+ obj1.index = 1,
11
+ obj2.index = 2,
12
+ dist.index = 3,
13
+ empty.rm = TRUE,
14
+ ...
15
+ )
16
+ }
17
+ \arguments{
18
+ \item{x}{A dataframe (or coercible object) with at least three columns:
19
+ \enumerate{
20
+ \item ID of the object 1,
21
+ \item ID of the object 2, and
22
+ \item distance between the two objects.}}
23
+
24
+ \item{groups}{Named array where the IDs correspond to the object IDs,
25
+ and the values correspond to the group.}
26
+
27
+ \item{obj1.index}{Index of the column containing the ID of the object 1.}
28
+
29
+ \item{obj2.index}{Index of the column containing the ID of the object 2.}
30
+
31
+ \item{dist.index}{Index of the column containing the distance.}
32
+
33
+ \item{empty.rm}{Remove incomplete matrices.}
34
+
35
+ \item{...}{Any other parameters supported by
36
+ \code{\link{enve.df2dist.group}}.}
37
+ }
38
+ \value{
39
+ Returns a \strong{list} of \strong{dist} objects.
40
+ }
41
+ \description{
42
+ Transform a dataframe (or coercible object, like a table)
43
+ into a \strong{dist} object.
44
+ }
45
+ \author{
46
+ Luis M. Rodriguez-R [aut, cre]
47
+ }
@@ -0,0 +1,75 @@
1
+ % Generated by roxygen2: do not edit by hand
2
+ % Please edit documentation in R/growthcurve.R
3
+ \name{enve.growthcurve}
4
+ \alias{enve.growthcurve}
5
+ \title{Enveomics: Growth Curve}
6
+ \usage{
7
+ enve.growthcurve(
8
+ x,
9
+ times = 1:nrow(x),
10
+ triplicates = FALSE,
11
+ design,
12
+ new.times = seq(min(times), max(times), length.out = length(times) * 10),
13
+ level = 0.95,
14
+ interval = c("confidence", "prediction"),
15
+ plot = TRUE,
16
+ FUN = function(t, K, r, P0) K * P0 * exp(r * t)/(K + P0 * (exp(r * t) - 1)),
17
+ nls.opt = list(),
18
+ ...
19
+ )
20
+ }
21
+ \arguments{
22
+ \item{x}{Data frame (or coercible) containing the observed growth data
23
+ (e.g., O.D. values). Each column is an independent growth curve and each
24
+ row is a time point. \code{NA}'s are allowed.}
25
+
26
+ \item{times}{Vector with the times at which each row was taken. By default,
27
+ all rows are assumed to be part of constantly periodic measurements.}
28
+
29
+ \item{triplicates}{If \code{TRUE}, the columns are assumed to be sorted by
30
+ sample with three replicates by sample. It requires a number of columns
31
+ multiple of 3.}
32
+
33
+ \item{design}{Experimental design of the data. An \strong{array} of mode list
34
+ with sample names as index and the list of column names in each sample as
35
+ the values. By default, each column is assumed to be an independent sample
36
+ if \code{triplicates} is \code{FALSE}, or every three columns are assumed
37
+ to be a sample if \code{triplicates} is \code{TRUE}. In the latter case,
38
+ samples are simply numbered.}
39
+
40
+ \item{new.times}{Values of time for the fitted curve.}
41
+
42
+ \item{level}{Confidence (or prediction) interval in the fitted curve.}
43
+
44
+ \item{interval}{Type of interval to be calculated for the fitted curve.}
45
+
46
+ \item{plot}{Should the growth curve be plotted?}
47
+
48
+ \item{FUN}{Function to fit. By default: logistic growth with paramenters
49
+ \code{K}: carrying capacity,
50
+ \code{r}: intrinsic growth rate, and
51
+ \code{P0}: Initial population.}
52
+
53
+ \item{nls.opt}{Any additional options passed to \code{nls}.}
54
+
55
+ \item{...}{Any additional parameters to be passed to
56
+ \code{plot.enve.GrowthCurve}.}
57
+ }
58
+ \value{
59
+ Returns an \code{\link{enve.GrowthCurve}} object.
60
+ }
61
+ \description{
62
+ Calculates growth curves using the logistic growth function.
63
+ }
64
+ \examples{
65
+ # Load data
66
+ data("growth.curves", package="enveomics.R", envir=environment())
67
+ # Generate growth curves with different colors
68
+ g <- enve.growthcurve(growth.curves[,-1], growth.curves[,1], triplicates=TRUE)
69
+ # Generate black-and-white growth curves with different symbols
70
+ plot(g, pch=15:17, col="black", band.density=45, band.angle=c(-45,45,0))
71
+
72
+ }
73
+ \author{
74
+ Luis M. Rodriguez-R [aut, cre]
75
+ }
@@ -0,0 +1,50 @@
1
+ % Generated by roxygen2: do not edit by hand
2
+ % Please edit documentation in R/prefscore.R
3
+ \name{enve.prefscore}
4
+ \alias{enve.prefscore}
5
+ \title{Enveomics: Pref Score}
6
+ \usage{
7
+ enve.prefscore(
8
+ x,
9
+ set,
10
+ ignore = NULL,
11
+ signif.thr,
12
+ plot = TRUE,
13
+ col.above = rgb(148, 17, 0, maxColorValue = 255),
14
+ col.equal = rgb(189, 189, 189, maxColorValue = 255),
15
+ col.below = rgb(47, 84, 150, maxColorValue = 255),
16
+ ...
17
+ )
18
+ }
19
+ \arguments{
20
+ \item{x}{Occupancy matrix (logical or numeric binary) with species as rows and samples
21
+ as columns}
22
+
23
+ \item{set}{Vector indicating samples in the test set. It can be any selection vector:
24
+ boolean (same length as the number of columns in \code{x}), or numeric or
25
+ character vector with indexes of the \code{x} columns.}
26
+
27
+ \item{ignore}{Vector indicating species to ignore. It can be any selection vector with
28
+ respect to the rows in \code{x} (see \code{set}).}
29
+
30
+ \item{signif.thr}{Absolute value of the significance threshold}
31
+
32
+ \item{plot}{Indicates if a plot should be generated}
33
+
34
+ \item{col.above}{Color for points significantly above zero}
35
+
36
+ \item{col.equal}{Color for points not significantly different from zero}
37
+
38
+ \item{col.below}{Color for points significantly below zero}
39
+
40
+ \item{...}{Any additional parameters supported by \code{plot}}
41
+ }
42
+ \value{
43
+ Returns a named vector of preference scores.
44
+ }
45
+ \description{
46
+ Estimate preference score of species based on occupancy in biased sample sets
47
+ }
48
+ \author{
49
+ Luis M. Rodriguez-R [aut, cre]
50
+ }