miga-base 0.3.0.0 → 0.3.0.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (260) hide show
  1. checksums.yaml +4 -4
  2. data/README.md +21 -4
  3. data/actions/init.rb +258 -0
  4. data/actions/run_local.rb +1 -2
  5. data/actions/test_taxonomy.rb +4 -1
  6. data/bin/miga +8 -1
  7. data/lib/miga/dataset.rb +4 -4
  8. data/lib/miga/dataset_result.rb +7 -4
  9. data/lib/miga/version.rb +2 -2
  10. data/scripts/_distances_noref_nomulti.bash +3 -1
  11. data/scripts/clade_finding.bash +1 -1
  12. data/scripts/init.bash +1 -1
  13. data/scripts/miga.bash +1 -1
  14. data/scripts/mytaxa.bash +78 -72
  15. data/scripts/mytaxa_scan.bash +67 -62
  16. data/scripts/ogs.bash +1 -1
  17. data/scripts/trimmed_fasta.bash +4 -3
  18. data/utils/enveomics/Examples/aai-matrix.bash +66 -0
  19. data/utils/enveomics/Examples/ani-matrix.bash +66 -0
  20. data/utils/enveomics/Examples/essential-phylogeny.bash +105 -0
  21. data/utils/enveomics/Examples/unus-genome-phylogeny.bash +100 -0
  22. data/utils/enveomics/LICENSE.txt +73 -0
  23. data/utils/enveomics/Makefile +52 -0
  24. data/utils/enveomics/Manifest/Tasks/aasubs.json +103 -0
  25. data/utils/enveomics/Manifest/Tasks/blasttab.json +703 -0
  26. data/utils/enveomics/Manifest/Tasks/distances.json +161 -0
  27. data/utils/enveomics/Manifest/Tasks/fasta.json +571 -0
  28. data/utils/enveomics/Manifest/Tasks/fastq.json +208 -0
  29. data/utils/enveomics/Manifest/Tasks/graphics.json +126 -0
  30. data/utils/enveomics/Manifest/Tasks/ogs.json +339 -0
  31. data/utils/enveomics/Manifest/Tasks/other.json +746 -0
  32. data/utils/enveomics/Manifest/Tasks/remote.json +355 -0
  33. data/utils/enveomics/Manifest/Tasks/sequence-identity.json +454 -0
  34. data/utils/enveomics/Manifest/Tasks/tables.json +308 -0
  35. data/utils/enveomics/Manifest/Tasks/trees.json +68 -0
  36. data/utils/enveomics/Manifest/Tasks/variants.json +111 -0
  37. data/utils/enveomics/Manifest/categories.json +132 -0
  38. data/utils/enveomics/Manifest/examples.json +154 -0
  39. data/utils/enveomics/Manifest/tasks.json +4 -0
  40. data/utils/enveomics/Pipelines/assembly.pbs/CONFIG.mock.bash +69 -0
  41. data/utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl +56 -0
  42. data/utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl +60 -0
  43. data/utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl +38 -0
  44. data/utils/enveomics/Pipelines/assembly.pbs/README.md +189 -0
  45. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-2.bash +112 -0
  46. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-3.bash +23 -0
  47. data/utils/enveomics/Pipelines/assembly.pbs/RUNME-4.bash +44 -0
  48. data/utils/enveomics/Pipelines/assembly.pbs/RUNME.bash +50 -0
  49. data/utils/enveomics/Pipelines/assembly.pbs/kSelector.R +37 -0
  50. data/utils/enveomics/Pipelines/assembly.pbs/newbler.pbs +68 -0
  51. data/utils/enveomics/Pipelines/assembly.pbs/newbler_preparator.pl +49 -0
  52. data/utils/enveomics/Pipelines/assembly.pbs/soap.pbs +80 -0
  53. data/utils/enveomics/Pipelines/assembly.pbs/stats.pbs +57 -0
  54. data/utils/enveomics/Pipelines/assembly.pbs/velvet.pbs +63 -0
  55. data/utils/enveomics/Pipelines/blast.pbs/01.pbs.bash +38 -0
  56. data/utils/enveomics/Pipelines/blast.pbs/02.pbs.bash +73 -0
  57. data/utils/enveomics/Pipelines/blast.pbs/03.pbs.bash +21 -0
  58. data/utils/enveomics/Pipelines/blast.pbs/BlastTab.recover_job.pl +72 -0
  59. data/utils/enveomics/Pipelines/blast.pbs/CONFIG.mock.bash +98 -0
  60. data/utils/enveomics/Pipelines/blast.pbs/FastA.split.pl +55 -0
  61. data/utils/enveomics/Pipelines/blast.pbs/README.md +127 -0
  62. data/utils/enveomics/Pipelines/blast.pbs/RUNME.bash +109 -0
  63. data/utils/enveomics/Pipelines/blast.pbs/TASK.check.bash +128 -0
  64. data/utils/enveomics/Pipelines/blast.pbs/TASK.dry.bash +16 -0
  65. data/utils/enveomics/Pipelines/blast.pbs/TASK.eo.bash +22 -0
  66. data/utils/enveomics/Pipelines/blast.pbs/TASK.pause.bash +26 -0
  67. data/utils/enveomics/Pipelines/blast.pbs/TASK.run.bash +89 -0
  68. data/utils/enveomics/Pipelines/blast.pbs/sentinel.pbs.bash +29 -0
  69. data/utils/enveomics/Pipelines/idba.pbs/README.md +49 -0
  70. data/utils/enveomics/Pipelines/idba.pbs/RUNME.bash +95 -0
  71. data/utils/enveomics/Pipelines/idba.pbs/run.pbs +56 -0
  72. data/utils/enveomics/Pipelines/trim.pbs/README.md +54 -0
  73. data/utils/enveomics/Pipelines/trim.pbs/RUNME.bash +70 -0
  74. data/utils/enveomics/Pipelines/trim.pbs/run.pbs +130 -0
  75. data/utils/enveomics/README.md +40 -0
  76. data/utils/enveomics/Scripts/AAsubs.log2ratio.rb +171 -0
  77. data/utils/enveomics/Scripts/Aln.cat.rb +162 -0
  78. data/utils/enveomics/Scripts/Aln.convert.pl +35 -0
  79. data/utils/enveomics/Scripts/AlphaDiversity.pl +152 -0
  80. data/utils/enveomics/Scripts/BlastPairwise.AAsubs.pl +102 -0
  81. data/utils/enveomics/Scripts/BlastTab.addlen.rb +61 -0
  82. data/utils/enveomics/Scripts/BlastTab.advance.bash +48 -0
  83. data/utils/enveomics/Scripts/BlastTab.best_hit_sorted.pl +55 -0
  84. data/utils/enveomics/Scripts/BlastTab.catsbj.pl +106 -0
  85. data/utils/enveomics/Scripts/BlastTab.cogCat.rb +76 -0
  86. data/utils/enveomics/Scripts/BlastTab.filter.pl +47 -0
  87. data/utils/enveomics/Scripts/BlastTab.kegg_pep2path_rest.pl +194 -0
  88. data/utils/enveomics/Scripts/BlastTab.metaxaPrep.pl +104 -0
  89. data/utils/enveomics/Scripts/BlastTab.pairedHits.rb +157 -0
  90. data/utils/enveomics/Scripts/BlastTab.recplot2.R +40 -0
  91. data/utils/enveomics/Scripts/BlastTab.seqdepth.pl +86 -0
  92. data/utils/enveomics/Scripts/BlastTab.seqdepth_ZIP.pl +119 -0
  93. data/utils/enveomics/Scripts/BlastTab.seqdepth_nomedian.pl +86 -0
  94. data/utils/enveomics/Scripts/BlastTab.subsample.pl +47 -0
  95. data/utils/enveomics/Scripts/BlastTab.sumPerHit.pl +114 -0
  96. data/utils/enveomics/Scripts/BlastTab.taxid2taxrank.pl +90 -0
  97. data/utils/enveomics/Scripts/BlastTab.topHits_sorted.rb +101 -0
  98. data/utils/enveomics/Scripts/Chao1.pl +97 -0
  99. data/utils/enveomics/Scripts/CharTable.classify.rb +234 -0
  100. data/utils/enveomics/Scripts/EBIseq2tax.rb +83 -0
  101. data/utils/enveomics/Scripts/FastA.N50.pl +56 -0
  102. data/utils/enveomics/Scripts/FastA.filter.pl +52 -0
  103. data/utils/enveomics/Scripts/FastA.filterLen.pl +28 -0
  104. data/utils/enveomics/Scripts/FastA.filterN.pl +60 -0
  105. data/utils/enveomics/Scripts/FastA.fragment.rb +92 -0
  106. data/utils/enveomics/Scripts/FastA.gc.pl +42 -0
  107. data/utils/enveomics/Scripts/FastA.interpose.pl +87 -0
  108. data/utils/enveomics/Scripts/FastA.length.pl +38 -0
  109. data/utils/enveomics/Scripts/FastA.per_file.pl +36 -0
  110. data/utils/enveomics/Scripts/FastA.qlen.pl +57 -0
  111. data/utils/enveomics/Scripts/FastA.rename.pl +65 -0
  112. data/utils/enveomics/Scripts/FastA.revcom.pl +23 -0
  113. data/utils/enveomics/Scripts/FastA.slider.pl +85 -0
  114. data/utils/enveomics/Scripts/FastA.split.pl +55 -0
  115. data/utils/enveomics/Scripts/FastA.subsample.pl +131 -0
  116. data/utils/enveomics/Scripts/FastA.tag.rb +64 -0
  117. data/utils/enveomics/Scripts/FastA.wrap.rb +48 -0
  118. data/utils/enveomics/Scripts/FastQ.filter.pl +54 -0
  119. data/utils/enveomics/Scripts/FastQ.interpose.pl +90 -0
  120. data/utils/enveomics/Scripts/FastQ.offset.pl +90 -0
  121. data/utils/enveomics/Scripts/FastQ.split.pl +53 -0
  122. data/utils/enveomics/Scripts/FastQ.tag.rb +63 -0
  123. data/utils/enveomics/Scripts/FastQ.toFastA.awk +24 -0
  124. data/utils/enveomics/Scripts/GenBank.add_fields.rb +84 -0
  125. data/utils/enveomics/Scripts/HMM.essential.rb +254 -0
  126. data/utils/enveomics/Scripts/HMMsearch.extractIds.rb +83 -0
  127. data/utils/enveomics/Scripts/JPlace.distances.rb +88 -0
  128. data/utils/enveomics/Scripts/JPlace.to_iToL.rb +306 -0
  129. data/utils/enveomics/Scripts/M5nr.getSequences.rb +81 -0
  130. data/utils/enveomics/Scripts/MeTaxa.distribution.pl +198 -0
  131. data/utils/enveomics/Scripts/MyTaxa.fragsByTax.pl +35 -0
  132. data/utils/enveomics/Scripts/MyTaxa.seq-taxrank.rb +49 -0
  133. data/utils/enveomics/Scripts/NCBIacc2tax.rb +92 -0
  134. data/utils/enveomics/Scripts/Newick.autoprune.R +27 -0
  135. data/utils/enveomics/Scripts/RAxML-EPA.to_iToL.pl +228 -0
  136. data/utils/enveomics/Scripts/RefSeq.download.bash +48 -0
  137. data/utils/enveomics/Scripts/SRA.download.bash +50 -0
  138. data/utils/enveomics/Scripts/TRIBS.plot-test.R +36 -0
  139. data/utils/enveomics/Scripts/TRIBS.test.R +39 -0
  140. data/utils/enveomics/Scripts/Table.barplot.R +30 -0
  141. data/utils/enveomics/Scripts/Table.df2dist.R +30 -0
  142. data/utils/enveomics/Scripts/Table.filter.pl +61 -0
  143. data/utils/enveomics/Scripts/Table.merge.pl +77 -0
  144. data/utils/enveomics/Scripts/Table.replace.rb +69 -0
  145. data/utils/enveomics/Scripts/Table.round.rb +63 -0
  146. data/utils/enveomics/Scripts/Table.split.pl +57 -0
  147. data/utils/enveomics/Scripts/Taxonomy.silva2ncbi.rb +227 -0
  148. data/utils/enveomics/Scripts/VCF.KaKs.rb +147 -0
  149. data/utils/enveomics/Scripts/VCF.SNPs.rb +88 -0
  150. data/utils/enveomics/Scripts/aai.rb +373 -0
  151. data/utils/enveomics/Scripts/ani.rb +362 -0
  152. data/utils/enveomics/Scripts/gi2tax.rb +103 -0
  153. data/utils/enveomics/Scripts/in_silico_GA_GI.pl +96 -0
  154. data/utils/enveomics/Scripts/lib/data/essential.hmm.gz +0 -0
  155. data/utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb +26 -0
  156. data/utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb +253 -0
  157. data/utils/enveomics/Scripts/lib/enveomics_rb/og.rb +182 -0
  158. data/utils/enveomics/Scripts/lib/enveomics_rb/remote_data.rb +74 -0
  159. data/utils/enveomics/Scripts/lib/enveomics_rb/seq_range.rb +237 -0
  160. data/utils/enveomics/Scripts/lib/enveomics_rb/stat.rb +30 -0
  161. data/utils/enveomics/Scripts/lib/enveomics_rb/vcf.rb +135 -0
  162. data/utils/enveomics/Scripts/ogs.annotate.rb +88 -0
  163. data/utils/enveomics/Scripts/ogs.core-pan.rb +160 -0
  164. data/utils/enveomics/Scripts/ogs.extract.rb +125 -0
  165. data/utils/enveomics/Scripts/ogs.mcl.rb +186 -0
  166. data/utils/enveomics/Scripts/ogs.rb +104 -0
  167. data/utils/enveomics/Scripts/ogs.stats.rb +131 -0
  168. data/utils/enveomics/Scripts/rbm.rb +137 -0
  169. data/utils/enveomics/Tests/Makefile +10 -0
  170. data/utils/enveomics/Tests/Mgen_M2288.faa +3189 -0
  171. data/utils/enveomics/Tests/Mgen_M2288.fna +8282 -0
  172. data/utils/enveomics/Tests/Mgen_M2321.fna +8288 -0
  173. data/utils/enveomics/Tests/Nequ_Kin4M.faa +2970 -0
  174. data/utils/enveomics/Tests/Xanthomonas_oryzae-PilA.tribs.Rdata +0 -0
  175. data/utils/enveomics/Tests/Xanthomonas_oryzae-PilA.txt +7 -0
  176. data/utils/enveomics/Tests/Xanthomonas_oryzae.aai-mat.tsv +17 -0
  177. data/utils/enveomics/Tests/Xanthomonas_oryzae.aai.tsv +137 -0
  178. data/utils/enveomics/Tests/a_mg.cds-go.blast.tsv +123 -0
  179. data/utils/enveomics/Tests/a_mg.reads-cds.blast.tsv +200 -0
  180. data/utils/enveomics/Tests/a_mg.reads-cds.counts.tsv +55 -0
  181. data/utils/enveomics/Tests/alkB.nwk +1 -0
  182. data/utils/enveomics/Tests/anthrax-cansnp-data.tsv +13 -0
  183. data/utils/enveomics/Tests/anthrax-cansnp-key.tsv +17 -0
  184. data/utils/enveomics/Tests/hiv1.faa +59 -0
  185. data/utils/enveomics/Tests/hiv1.fna +134 -0
  186. data/utils/enveomics/Tests/hiv2.faa +70 -0
  187. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv +233 -0
  188. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.lim +1 -0
  189. data/utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.rec +233 -0
  190. data/utils/enveomics/Tests/phyla_counts.tsv +10 -0
  191. data/utils/enveomics/Tests/primate_lentivirus.ogs +11 -0
  192. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv1.rbm +9 -0
  193. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv2.rbm +8 -0
  194. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-siv.rbm +6 -0
  195. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-hiv2.rbm +9 -0
  196. data/utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-siv.rbm +6 -0
  197. data/utils/enveomics/Tests/primate_lentivirus.rbm/siv-siv.rbm +6 -0
  198. data/utils/enveomics/build_enveomics_r.bash +44 -0
  199. data/utils/enveomics/enveomics.R/DESCRIPTION +31 -0
  200. data/utils/enveomics/enveomics.R/NAMESPACE +35 -0
  201. data/utils/enveomics/enveomics.R/R/autoprune.R +121 -0
  202. data/utils/enveomics/enveomics.R/R/barplot.R +165 -0
  203. data/utils/enveomics/enveomics.R/R/cliopts.R +119 -0
  204. data/utils/enveomics/enveomics.R/R/df2dist.R +117 -0
  205. data/utils/enveomics/enveomics.R/R/growthcurve.R +263 -0
  206. data/utils/enveomics/enveomics.R/R/recplot.R +320 -0
  207. data/utils/enveomics/enveomics.R/R/recplot2.R +745 -0
  208. data/utils/enveomics/enveomics.R/R/tribs.R +423 -0
  209. data/utils/enveomics/enveomics.R/R/utils.R +16 -0
  210. data/utils/enveomics/enveomics.R/README.md +52 -0
  211. data/utils/enveomics/enveomics.R/data/growth.curves.rda +0 -0
  212. data/utils/enveomics/enveomics.R/data/phyla.counts.rda +0 -0
  213. data/utils/enveomics/enveomics.R/man/enve.GrowthCurve-class.Rd +30 -0
  214. data/utils/enveomics/enveomics.R/man/enve.TRIBS-class.Rd +43 -0
  215. data/utils/enveomics/enveomics.R/man/enve.TRIBS.merge.Rd +19 -0
  216. data/utils/enveomics/enveomics.R/man/enve.TRIBStest-class.Rd +37 -0
  217. data/utils/enveomics/enveomics.R/man/enve.__prune.iter.Rd +24 -0
  218. data/utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd +24 -0
  219. data/utils/enveomics/enveomics.R/man/enve.__tribs.Rd +33 -0
  220. data/utils/enveomics/enveomics.R/man/enve.barplot.Rd +64 -0
  221. data/utils/enveomics/enveomics.R/man/enve.cliopts.Rd +37 -0
  222. data/utils/enveomics/enveomics.R/man/enve.col.alpha.Rd +19 -0
  223. data/utils/enveomics/enveomics.R/man/enve.col2alpha.Rd +18 -0
  224. data/utils/enveomics/enveomics.R/man/enve.df2dist.Rd +26 -0
  225. data/utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd +25 -0
  226. data/utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd +26 -0
  227. data/utils/enveomics/enveomics.R/man/enve.growthcurve.Rd +49 -0
  228. data/utils/enveomics/enveomics.R/man/enve.prune.dist.Rd +28 -0
  229. data/utils/enveomics/enveomics.R/man/enve.recplot.Rd +97 -0
  230. data/utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd +40 -0
  231. data/utils/enveomics/enveomics.R/man/enve.recplot2.Rd +40 -0
  232. data/utils/enveomics/enveomics.R/man/enve.recplot2.__counts.Rd +24 -0
  233. data/utils/enveomics/enveomics.R/man/enve.recplot2.__findPeak.Rd +40 -0
  234. data/utils/enveomics/enveomics.R/man/enve.recplot2.__findPeaks.Rd +18 -0
  235. data/utils/enveomics/enveomics.R/man/enve.recplot2.__peakHist.Rd +22 -0
  236. data/utils/enveomics/enveomics.R/man/enve.recplot2.__whichClosestPeak.Rd +20 -0
  237. data/utils/enveomics/enveomics.R/man/enve.recplot2.changeCutoff.Rd +18 -0
  238. data/utils/enveomics/enveomics.R/man/enve.recplot2.corePeak.Rd +18 -0
  239. data/utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd +27 -0
  240. data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd +53 -0
  241. data/utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd +44 -0
  242. data/utils/enveomics/enveomics.R/man/enve.tribs.Rd +44 -0
  243. data/utils/enveomics/enveomics.R/man/enve.tribs.test.Rd +21 -0
  244. data/utils/enveomics/enveomics.R/man/enveomics.R-package.Rd +15 -0
  245. data/utils/enveomics/enveomics.R/man/growth.curves.Rd +14 -0
  246. data/utils/enveomics/enveomics.R/man/phyla.counts.Rd +13 -0
  247. data/utils/enveomics/enveomics.R/man/plot.enve.GrowthCurve.Rd +43 -0
  248. data/utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd +29 -0
  249. data/utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd +30 -0
  250. data/utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd +71 -0
  251. data/utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd +18 -0
  252. data/utils/enveomics/enveomics.R/man/summary.enve.TRIBS.Rd +18 -0
  253. data/utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd +18 -0
  254. data/utils/enveomics/enveomics.R/man/z$-methods.Rd +27 -0
  255. data/utils/enveomics/globals.mk +8 -0
  256. data/utils/enveomics/manifest.json +9 -0
  257. data/utils/index_metadata.rb +0 -0
  258. data/utils/plot-taxdist.R +0 -0
  259. data/utils/requirements.txt +19 -19
  260. metadata +242 -2
@@ -0,0 +1,30 @@
1
+ #!/usr/bin/env Rscript
2
+ #
3
+ # @author Luis M. Rodriguez-R
4
+ # @update Jan-04-2016
5
+ # @license artistic license 2.0
6
+ #
7
+
8
+ #= Load stuff
9
+ args <- commandArgs(trailingOnly = F)
10
+ enveomics_R <- file.path(dirname(
11
+ sub("^--file=", "", args[grep("^--file=", args)])),
12
+ "lib", "enveomics.R")
13
+ source(file.path(enveomics_R, "R", "cliopts.R"))
14
+ source(file.path(enveomics_R, "R", "df2dist.R"))
15
+
16
+ #= Generate interface
17
+ opt <- enve.cliopts(enve.df2dist,
18
+ file.path(enveomics_R, "man", "enve.df2dist.Rd"),
19
+ positional_arguments=1,
20
+ usage="usage: %prog [options] output.mat",
21
+ mandatory=c("x"),
22
+ number=c("default.d", "max.sim"),
23
+ o_desc=list(x="A tab-delimited table with the distances."),
24
+ p_desc="Transform a tab-delimited list of distances into a squared matrix.")
25
+
26
+ #= Run it!
27
+ opt$options[['x']] <- read.table(opt$options[['x']],
28
+ header=TRUE, sep="\t", as.is=TRUE)
29
+ dist <- do.call("enve.df2dist", opt$options)
30
+ write.table(as.matrix(dist), opt$args[1], quote=FALSE, sep="\t", col.names=NA)
@@ -0,0 +1,61 @@
1
+ #!/usr/bin/env perl
2
+ #
3
+ # @author: Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
4
+ # @update: Mar-23-2015
5
+ # @license: artistic license 2.0
6
+ #
7
+
8
+ use warnings;
9
+ use strict;
10
+ use Getopt::Std;
11
+
12
+ my %o;
13
+ getopts('k:s:ihn', \%o);
14
+ my($list, $table) = @ARGV;
15
+
16
+ ($list and $table) or die "
17
+ .Description:
18
+ Extracts (and re-orders) a subset of rows from a raw table.
19
+
20
+ .Usage: $0 [options] list.txt table.txt > subset.txt
21
+
22
+ Options:
23
+ -k <int> Column of the table to use as key to filter. By default, 1.
24
+ -s <str> String to use as separation between rows. By default, tabulation.
25
+ -i If set, reports the inverse of the list (i.e., reports only rows
26
+ absent in the list). Implies -n.
27
+ -h Keep first row of the table (header) untouched.
28
+ -n No re-order. The output has the same order of the table. By
29
+ default, it prints in the order of the list.
30
+
31
+ list.txt List of IDs to extract.
32
+ table.txt Table file containing the superset.
33
+ subset.txt Table file to be created.
34
+
35
+ ";
36
+
37
+ $o{k} ||= 1;
38
+ $o{s} ||= "\t";
39
+ $o{n}=1 if $o{i};
40
+ my $HEADER = "";
41
+
42
+ my $tbl2 = $o{n} ? $list : $table;
43
+ open TBL, "<", $tbl2 or die "Cannot read file: $tbl2: $!\n";
44
+ $HEADER = <TBL> if $o{h} and not $o{n};
45
+ my %tbl2 = map { my $l=$_; chomp $l; my @r=split $o{s}, $l; $r[ $o{n} ? 0 : $o{k}-1] => $l } <TBL>;
46
+ close TBL;
47
+
48
+ my $tbl1 = $o{n} ? $table : $list;
49
+ open TBL, "<", $tbl1 or die "Cannot read file: $tbl1: $!\n";
50
+ $HEADER = <TBL> if $o{h} and $o{n};
51
+ print $HEADER;
52
+ while(my $ln = <TBL>){
53
+ chomp $ln;
54
+ next unless $ln;
55
+ my @ln = split $o{s}, $ln;
56
+ my $good = exists $tbl2{ $ln[$o{n} ? $o{k}-1 : 0] };
57
+ $good = not $good if $o{i};
58
+ print "".($o{n} ? $ln : $tbl2{$ln[0]})."\n" if $good;
59
+ }
60
+ close TBL;
61
+
@@ -0,0 +1,77 @@
1
+ #!/usr/bin/env perl
2
+ #
3
+ # @author: Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
4
+ # @update: Sep-20-2015
5
+ # @license: artistic license 2.0
6
+ #
7
+
8
+ use warnings;
9
+ use strict;
10
+ use Getopt::Std;
11
+
12
+ my %o;
13
+ getopts('si:o:ne:h:H:r:', \%o);
14
+ my @files = @ARGV;
15
+
16
+ $#files>0 or die "
17
+ .Description:
18
+ Merges multiple (two-column) lists into one table.
19
+
20
+ .Usage:
21
+ $0 [options] files... > output.txt
22
+
23
+ Options:
24
+ -s Values are read as Strings. By default, values are read as numbers.
25
+ -i <str> Input field-delimiter. By default: tabulation (\"\\t\").
26
+ -o <str> Output field-delimiter. By default: tabulation (\"\\t\").
27
+ -n No-header. By default, the header is determined by the file names.
28
+ -e <str> Default string when no value is found. By default, the \"empty\" value
29
+ is 0 if values are numeric (i.e., unless -s is set) or an empty string
30
+ otherwise.
31
+ -h <str> Header of the first column, containing the IDs. By default: \"Tag\".
32
+ -H <str> Format of filenames capturing the column header in the first capturing
33
+ parenthesis. Non-capturing paretheses can be defined as (?:...). By
34
+ default: \"(?:.*/)?([^\\.]+)\", which captures the part of the basename
35
+ of the file before the first dot (if any).
36
+ -r <int> Number of leading rows to ignore in the input files. Zero by default.
37
+
38
+ ";
39
+ $o{i} ||= "\t";
40
+ $o{o} ||= "\t";
41
+ $o{e} ||= ($o{s} ? "" : 0);
42
+ $o{h} ||= "Tag";
43
+ $o{H} ||= "(?:.*/)?([^\\.]+)";
44
+ $o{r} += 0;
45
+
46
+ my $notes = {};
47
+
48
+ print $o{h} unless $o{n};
49
+ my $i = 0;
50
+ for my $file (@files){
51
+ unless($o{n}){
52
+ $file =~ m/$o{H}/ or die "Filename '$file' doesn't match format '$o{H}'.";
53
+ my $tag=$1;
54
+ print $o{o}.$tag;
55
+ }
56
+ open IN, "<", $file or die "Cannot read file: $file: $!\n";
57
+ while(<IN>){
58
+ next if $. <= $o{r};
59
+ chomp;
60
+ my @l = split $o{i};
61
+ $l[1]+=0 unless $o{s};
62
+ $notes->{$l[0]} ||= [];
63
+ $notes->{$l[0]}->[$i] = $l[1];
64
+ }
65
+ close IN;
66
+ $i++;
67
+ }
68
+ print "\n" unless $o{n};
69
+
70
+ for my $id (keys %$notes){
71
+ print $id;
72
+ for my $i (0 .. $#files){
73
+ print $o{o}.(( defined $notes->{$id}->[$i] ? $notes->{$id}->[$i] : $o{e} ));
74
+ }
75
+ print "\n";
76
+ }
77
+
@@ -0,0 +1,69 @@
1
+ #!/usr/bin/env ruby
2
+
3
+ #
4
+ # @author Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
5
+ # @update Feb 01 2016
6
+ # @license artistic license 2.0
7
+ #
8
+
9
+ require "optparse"
10
+
11
+ o = {delimiter: "\t", key: 1, default: ""}
12
+ ARGV << "-h" if ARGV.size==0
13
+ OptionParser.new do |opts|
14
+ opts.banner = "\nReplaces a field in a table using a mapping file."
15
+ opts.on("-m", "--map FILE",
16
+ "Mapping file with two columns (key and replacement)."){ |v| o[:map] = v }
17
+ opts.on("-i", "--in FILE", "Input table."){ |v| o[:in] = v }
18
+ opts.on("-o", "--out FILE", "Output table."){ |v| o[:out] = v }
19
+ opts.on("-k", "--key INT",
20
+ "Column to replace in --in. By deafult: 1."){ |v| o[:key] = v.to_i }
21
+ opts.on("-u", "--unknown STR",
22
+ "String to use whenever the key is not found in --map."
23
+ ){ |v| o[:default] = v }
24
+ opts.on("-d", "--delimiter STR",
25
+ "String delimiting columns. By default, tabulation."
26
+ ){ |v| o[:delimiter] = v }
27
+ opts.on("-h", "--help", "Display this screen") do
28
+ puts opts
29
+ exit
30
+ end
31
+ opts.separator ""
32
+ end.parse!
33
+ abort "-m is mandatory" if o[:map].nil?
34
+ abort "-i is mandatory" if o[:in].nil?
35
+ abort "-o is mandatory" if o[:out].nil?
36
+
37
+ class String
38
+ def is_number?
39
+ true if Float(self) rescue false
40
+ end
41
+ end
42
+
43
+ begin
44
+ # Read mapping file
45
+ ifh = File.open(o[:map], "r")
46
+ map = {}
47
+ while(ln = ifh.gets)
48
+ row = ln.chomp.split(o[:delimiter])
49
+ map[ row[0] ] = row[1]
50
+ end
51
+ ifh.close
52
+ # Process table
53
+ ifh = File.open(o[:in], "r")
54
+ ofh = File.open(o[:out], "w")
55
+ while(ln = ifh.gets)
56
+ row = ln.chomp.split(o[:delimiter])
57
+ k = row[ o[:key]-1 ]
58
+ v = map[ k ]
59
+ v = o[:default] if v.nil?
60
+ row[ o[:key]-1 ] = v
61
+ ofh.puts(row.join(o[:delimiter]))
62
+ end
63
+ ifh.close
64
+ ofh.close
65
+ rescue => err
66
+ $stderr.puts "Exception: #{err}\n\n"
67
+ err.backtrace.each { |l| $stderr.puts " - " + l + "\n" }
68
+ err
69
+ end
@@ -0,0 +1,63 @@
1
+ #!/usr/bin/env ruby
2
+
3
+ #
4
+ # @author: Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
5
+ # @update: Feb 04 2015
6
+ # @license: artistic license 2.0
7
+ #
8
+
9
+ require 'optparse'
10
+
11
+ o = {:ndigits=>0, :action=>:round, :delimiter=>"\t"}
12
+ ARGV << '-h' if ARGV.size==0
13
+ OptionParser.new do |opts|
14
+ opts.banner = "\nRounds numbers in a table."
15
+ opts.on("-i", "--in FILE", "Input table."){ |v| o[:in] = v}
16
+ opts.on("-o", "--out FILE", "Output table."){ |v| o[:out] = v }
17
+ opts.on("-n", "--ndigits INT", "Number of decimal digits. By default: #{o[:ndigits]}"){ |v| o[:ndigits] = v.to_i }
18
+ opts.on("-f", "--floor", "Floors the values instead of rounding them. Ignores -n."){ o[:action] = :floor }
19
+ opts.on("-c", "--ceil", "Ceils the values instead of rounding them. Ignores -n."){ o[:action] = :ceil }
20
+ opts.on("-d", "--delimiter STR", "String delimiting columns. By default, tabulation."){ |v| o[:delimiter] = v }
21
+ opts.on("-h", "--help", "Display this screen") do
22
+ puts opts
23
+ exit
24
+ end
25
+ opts.separator ""
26
+ end.parse!
27
+ abort "-i is mandatory" if o[:in].nil?
28
+ abort "-o is mandatory" if o[:out].nil?
29
+
30
+ class String
31
+ def is_number?
32
+ true if Float(self) rescue false
33
+ end
34
+ end
35
+
36
+ begin
37
+ ifh = File.open(o[:in], "r")
38
+ ofh = File.open(o[:out], "w")
39
+ while(ln = ifh.gets)
40
+ ln.chomp!
41
+ row = []
42
+ ln.split(o[:delimiter]).each do |value|
43
+ if value.is_number?
44
+ case o[:action]
45
+ when :round
46
+ value = value.to_f.round(o[:ndigits])
47
+ when :floor
48
+ value = value.to_f.floor
49
+ when :ceil
50
+ value = value.to_f.ceil
51
+ end
52
+ end
53
+ row.push value.to_s
54
+ end
55
+ ofh.puts(row.join(o[:delimiter]))
56
+ end
57
+ ifh.close
58
+ ofh.close
59
+ rescue => err
60
+ $stderr.puts "Exception: #{err}\n\n"
61
+ err.backtrace.each { |l| $stderr.puts " - " + l + "\n" }
62
+ err
63
+ end
@@ -0,0 +1,57 @@
1
+ #!/usr/bin/env perl
2
+ #
3
+ # @author Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
4
+ # @update Feb-01-2016
5
+ # @license artistic license 2.0
6
+ #
7
+
8
+ use warnings;
9
+ use strict;
10
+ use Getopt::Std;
11
+ use Symbol;
12
+
13
+ my %o;
14
+ getopts('i:o:d:e:h', \%o);
15
+ my $file = shift @ARGV;
16
+
17
+ ($file and not $o{h}) or die "
18
+ .Description:
19
+ Split a file with multiple columns into multiple two-columns lists.
20
+
21
+ .Usage:
22
+ $0 [options] file
23
+
24
+ Options:
25
+ -i <str> Input field-delimiter. By default: tabulation (\"\\t\").
26
+ -o <str> Prefix of the output files. By default: no prefix (\"\").
27
+ -d <str> Output directory. By default: current directory (\"\").
28
+
29
+ ";
30
+ $o{i} ||= "\t";
31
+ $o{o} ||= "";
32
+ $o{o} = $o{d}."/".$o{o} if $o{d};
33
+
34
+ my $open=0;
35
+ my @fhs=();
36
+ open IN, "<", $file or die "Cannot read file: $file: $!\n";
37
+ while(<IN>){
38
+ chomp;
39
+ my @row = split $o{i};
40
+ my $h = shift @row;
41
+ if($open){
42
+ for my $i (0 .. $#row){
43
+ print { qualify_to_ref $fhs[$i] } $h.$o{i}.$row[$i]."\n" if $row[$i];
44
+ }
45
+ }else{
46
+ $open++;
47
+ for my $l (@row){
48
+ $l =~ s/[\.\/:]/_/g;
49
+ my $gs = gensym;
50
+ open($gs, '>', $o{o}.$l.".txt") or die "Cannot create file: $o{o}$l.txt: $!\n";
51
+ push @fhs, $gs;
52
+ }
53
+ }
54
+ }
55
+ close IN;
56
+ close $_ for @fhs;
57
+
@@ -0,0 +1,227 @@
1
+ #!/usr/bin/env ruby
2
+
3
+ #
4
+ # @author Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
5
+ # @update: Feb-06-2015
6
+ # @license artistic license 2.0
7
+ #
8
+
9
+ require 'optparse'
10
+
11
+ $opts = {:warns=>false}
12
+ ARGV << '-h' if ARGV.size==0
13
+ OptionParser.new do |opt|
14
+ opt.separator "Re-formats Silva taxonomy into NCBI-like taxonomy dump files."
15
+ opt.separator ""
16
+ opt.separator "Mandatory arguments"
17
+ opt.on("-k", "--silvaranks FILE", "Input Silva ranks file (e.g., tax_ranks_ssu_115.txt)."){ |v| $opts[:silvaranks]=v }
18
+ opt.on("-f", "--silvaref FILE", "Input Silva ref alignment file (e.g., SSURef_NR99_115_tax_silva_full_align_trunc.fasta)."){ |v| $opts[:silvaref]=v }
19
+ opt.separator ""
20
+ opt.separator "Additional options"
21
+ opt.on("-p", "--patch FILE", "If passed, it replaces the paths specified in the patch."){ |v| $opts[:patch]=v }
22
+ opt.on("-s", "--seqinfo FILE", "If passed, it creates a CSV seq-info file compatible with taxtastic."){ |v| $opts[:seqinfo]=v }
23
+ opt.on("-t", "--taxfile FILE", "If passed, it creates a simple TSV taxonomy file."){ |v| $opts[:taxfile]=v }
24
+ opt.on("-n", "--ncbi FILE", "If passed, output folder for the NCBI dump files (e.g., taxdmp)."){ |v| $opts[:ncbi]=v }
25
+ opt.on("-w", "--warns", "Verbously display warnings."){ $opts[:warns]=true }
26
+ opt.on("-h", "--help","Display this screen") do
27
+ puts opt
28
+ exit
29
+ end
30
+ opt.separator ""
31
+ end.parse!
32
+ abort "-k/--silvaranks is mandatory." if $opts[:silvaranks].nil?
33
+ abort "-k/--silvaranks must exist." unless File.exists? $opts[:silvaranks]
34
+ abort "-f/--silvaref is mandatory." if $opts[:silvaref].nil?
35
+ abort "-f/--silvaref must exist." unless File.exists? $opts[:silvaref]
36
+
37
+ class Node
38
+ attr_accessor :id, :tax, :leaf, :name_type
39
+ attr_reader :name, :rank, :parent, :children
40
+ def initialize(name, rank=nil)
41
+ @name = name
42
+ @rank = rank.nil? ? "no rank" : rank
43
+ @children = []
44
+ @leaf = false
45
+ @name_type = "scientific name";
46
+ end
47
+ def parent=(node)
48
+ @parent=node
49
+ node.add_child(self)
50
+ end
51
+ def add_child(node)
52
+ @children << node
53
+ end
54
+ def ncbirank
55
+ ncbirank =
56
+ self.rank == "superkingdom" ? "no rank" :
57
+ self.rank == "domain" ? "superkingdom" :
58
+ self.rank == "major_clade" ? "no rank" : self.rank
59
+ return ncbirank
60
+ end
61
+ def path
62
+ if self.parent.nil?
63
+ self.name
64
+ else
65
+ "#{self.parent.path};#{self.name}"
66
+ end
67
+ end
68
+ def each_desc internals, leaves, &blk
69
+ blk[self] if (leaves and self.leaf) or (internals and not self.leaf)
70
+ self.children.each {|child| child.each_desc internals, leaves, &blk}
71
+ end
72
+ def to_s
73
+ "#{self.name} (#{self.rank})"
74
+ end
75
+ end
76
+
77
+ class Taxonomy
78
+ attr_reader :root, :next_id
79
+ def initialize
80
+ @root = Node.new('root')
81
+ @root.id = 1
82
+ @next_id = 2
83
+ end
84
+ def register(node)
85
+ node.id = self.next_id
86
+ node.parent = self.root if node.parent.nil?
87
+ @next_id += 1
88
+ end
89
+ def node(path)
90
+ node = self.root
91
+ path.each do |level|
92
+ node.children.each do |child|
93
+ if child.name == level
94
+ node = child
95
+ break
96
+ end
97
+ end
98
+ unless node.name == level
99
+ $stderr.puts "Warning: Impossible to find #{level} at #{node.to_s}, making it up." if $opts[:warns]
100
+ child = Node.new(level)
101
+ child.parent = node
102
+ self.register(child)
103
+ node = child
104
+ end
105
+ end
106
+ node
107
+ end
108
+ def each_node &blk
109
+ self.root.each_desc true, true, &blk
110
+ end
111
+ def each_leaf &blk
112
+ self.root.each_desc false, true, &blk
113
+ end
114
+ def each_internal &blk
115
+ self.root.each_desc true, false, &blk
116
+ end
117
+ end
118
+
119
+ begin
120
+ taxo = Taxonomy.new()
121
+
122
+ ## Read patch
123
+ patch = {}
124
+ unless $opts[:patch].nil?
125
+ $stderr.puts "Reading patch: #{$opts[:patch]}"
126
+ f = File.open($opts[:patch], "r")
127
+ while(ln = f.gets)
128
+ m = ln.chomp.split(/\t/)
129
+ patch[ m[0] ] = m[1]
130
+ end
131
+ end
132
+
133
+ ## Read the Silva ranks
134
+ $stderr.puts "Reading Silva ranks: #{$opts[:silvaranks]}"
135
+ f = File.open($opts[:silvaranks], "r")
136
+ f.gets # header
137
+ while(ln = f.gets)
138
+ m = ln.chomp.split(/\t/)
139
+ m[0] = patch[ m[0] ] unless patch[ m[0] ].nil?
140
+ p = m[0].split(/;/)
141
+ raise "Inconsistent path and node name at line #{$.}: #{ln}." unless m[1] == p.pop
142
+ if m[3] != "w"
143
+ node = Node.new(m[1], m[2])
144
+ node.name_type = "common name" if m[3] == "a"
145
+ node.parent = taxo.node(p)
146
+ taxo.register(node)
147
+ end
148
+ end
149
+ f.close
150
+
151
+ $stderr.puts " Top taxa:"
152
+ taxo.root.children.each do |top|
153
+ $stderr.puts " o #{top.to_s} has #{top.children.length} children."
154
+ end
155
+
156
+ ## Read the Silva ref alignment
157
+ $stderr.puts "Reading Silva ref alignment: #{$opts[:silvaref]}"
158
+ i = 0
159
+ f = File.open($opts[:silvaref], "r")
160
+ while(ln = f.gets)
161
+ m = />([^\s]+)\s(.*)/.match(ln)
162
+ next unless m
163
+ # Patch
164
+ pm = /(.+);([^;]+)/.match(m[2])
165
+ path = "#{patch[ pm[1] ].nil? ? pm[1] : patch[ pm[1] ]};#{pm[2]}".split(/;/)
166
+ # Register
167
+ node = taxo.node(path)
168
+ taxo.register(node)
169
+ refseq = Node.new(m[1], 'refseq')
170
+ refseq.parent = node
171
+ refseq.leaf = true
172
+ taxo.register(refseq)
173
+ i += 1
174
+ end
175
+ f.close
176
+ $stderr.puts " Saved #{i} leaves."
177
+
178
+ ### NCBI
179
+ unless $opts[:ncbi].nil?
180
+ ## Create taxonomy .dmp files
181
+ $stderr.puts "Creating NCBI-like files: #{$opts[:ncbi]}"
182
+ Dir.mkdir($opts[:ncbi]) unless Dir.exists?($opts[:ncbi]);
183
+ # merged.dmp
184
+ $stderr.puts " o Creating merged.dmp"
185
+ File.open(File.join($opts[:ncbi], 'merged.dmp'), 'w'){}
186
+ # names.dmp
187
+ $stderr.puts " o Creating names.dmp"
188
+ f = File.open(File.join($opts[:ncbi], 'names.dmp'), 'w')
189
+ taxo.each_internal do |n|
190
+ f.puts [n.id, n.name, "", n.name_type].join("\t|\t")+"\t|"
191
+ end
192
+ f.close
193
+ # nodes.dmp
194
+ $stderr.puts " o Creating nodes.dmp"
195
+ f = File.open(File.join($opts[:ncbi], 'nodes.dmp'), 'w')
196
+ taxo.each_internal do |n|
197
+ f.puts ([n.id, n.parent.nil? ? n.id : n.parent.id, n.ncbirank, ""] << Array.new(8,0) << "").join("\t|\t")+"\t|"
198
+ end
199
+ f.close
200
+ end
201
+
202
+ ## Taxtastic
203
+ unless $opts[:seqinfo].nil?
204
+ $stderr.puts "Creating seq-info file: #{$opts[:seqinfo]}"
205
+ f = File.open($opts[:seqinfo], 'w')
206
+ f.puts "\"seqname\",\"tax_id\",\"group_name\""
207
+ taxo.each_leaf { |n| f.puts "\"#{n.name}\",\"#{n.parent.id}\",\"#{n.parent.name}\"" }
208
+ f.close
209
+ end
210
+
211
+ ## Misc
212
+ unless $opts[:taxfile].nil?
213
+ $stderr.puts "Creating taxonomy file: #{$opts[:taxfile]}"
214
+ f = File.open($opts[:taxfile], 'w')
215
+ f.puts "tax_id\tparent_id\trank\ttax_name"
216
+ taxo.each_internal do |n|
217
+ f.puts [n.id, n.parent.nil? ? n.id : n.parent.id, n.rank, n.name].join("\t")
218
+ end
219
+ f.close
220
+ end
221
+ rescue => err
222
+ $stderr.puts "Exception: #{err}\n\n"
223
+ err.backtrace.each { |l| $stderr.puts l + "\n" }
224
+ err
225
+ end
226
+
227
+