wwood-bioruby 1.2.11

Sign up to get free protection for your applications and to get access to all the features.
Files changed (386) hide show
  1. data/README.rdoc +205 -0
  2. data/README_DEV.rdoc +285 -0
  3. data/VERSION.yml +4 -0
  4. data/bin/bioruby +44 -0
  5. data/bin/br_biofetch.rb +47 -0
  6. data/bin/br_bioflat.rb +293 -0
  7. data/bin/br_biogetseq.rb +45 -0
  8. data/bin/br_pmfetch.rb +421 -0
  9. data/lib/bio.rb +306 -0
  10. data/lib/bio/alignment.rb +2518 -0
  11. data/lib/bio/appl/bl2seq/report.rb +334 -0
  12. data/lib/bio/appl/blast.rb +505 -0
  13. data/lib/bio/appl/blast/ddbj.rb +142 -0
  14. data/lib/bio/appl/blast/format0.rb +1438 -0
  15. data/lib/bio/appl/blast/format8.rb +83 -0
  16. data/lib/bio/appl/blast/genomenet.rb +263 -0
  17. data/lib/bio/appl/blast/ncbioptions.rb +220 -0
  18. data/lib/bio/appl/blast/remote.rb +105 -0
  19. data/lib/bio/appl/blast/report.rb +767 -0
  20. data/lib/bio/appl/blast/rexml.rb +144 -0
  21. data/lib/bio/appl/blast/rpsblast.rb +277 -0
  22. data/lib/bio/appl/blast/wublast.rb +635 -0
  23. data/lib/bio/appl/blast/xmlparser.rb +236 -0
  24. data/lib/bio/appl/blat/report.rb +530 -0
  25. data/lib/bio/appl/clustalw.rb +219 -0
  26. data/lib/bio/appl/clustalw/report.rb +152 -0
  27. data/lib/bio/appl/emboss.rb +203 -0
  28. data/lib/bio/appl/fasta.rb +235 -0
  29. data/lib/bio/appl/fasta/format10.rb +325 -0
  30. data/lib/bio/appl/gcg/msf.rb +212 -0
  31. data/lib/bio/appl/gcg/seq.rb +195 -0
  32. data/lib/bio/appl/genscan/report.rb +552 -0
  33. data/lib/bio/appl/hmmer.rb +126 -0
  34. data/lib/bio/appl/hmmer/report.rb +683 -0
  35. data/lib/bio/appl/iprscan/report.rb +374 -0
  36. data/lib/bio/appl/mafft.rb +259 -0
  37. data/lib/bio/appl/mafft/report.rb +226 -0
  38. data/lib/bio/appl/muscle.rb +52 -0
  39. data/lib/bio/appl/paml/baseml.rb +95 -0
  40. data/lib/bio/appl/paml/baseml/report.rb +32 -0
  41. data/lib/bio/appl/paml/codeml.rb +242 -0
  42. data/lib/bio/appl/paml/codeml/rates.rb +67 -0
  43. data/lib/bio/appl/paml/codeml/report.rb +67 -0
  44. data/lib/bio/appl/paml/common.rb +348 -0
  45. data/lib/bio/appl/paml/common_report.rb +38 -0
  46. data/lib/bio/appl/paml/yn00.rb +103 -0
  47. data/lib/bio/appl/paml/yn00/report.rb +32 -0
  48. data/lib/bio/appl/phylip/alignment.rb +133 -0
  49. data/lib/bio/appl/phylip/distance_matrix.rb +96 -0
  50. data/lib/bio/appl/probcons.rb +41 -0
  51. data/lib/bio/appl/psort.rb +548 -0
  52. data/lib/bio/appl/psort/report.rb +542 -0
  53. data/lib/bio/appl/pts1.rb +263 -0
  54. data/lib/bio/appl/sim4.rb +124 -0
  55. data/lib/bio/appl/sim4/report.rb +485 -0
  56. data/lib/bio/appl/sosui/report.rb +151 -0
  57. data/lib/bio/appl/spidey/report.rb +593 -0
  58. data/lib/bio/appl/targetp/report.rb +267 -0
  59. data/lib/bio/appl/tcoffee.rb +55 -0
  60. data/lib/bio/appl/tmhmm/report.rb +231 -0
  61. data/lib/bio/command.rb +593 -0
  62. data/lib/bio/compat/features.rb +157 -0
  63. data/lib/bio/compat/references.rb +128 -0
  64. data/lib/bio/data/aa.rb +353 -0
  65. data/lib/bio/data/codontable.rb +722 -0
  66. data/lib/bio/data/na.rb +223 -0
  67. data/lib/bio/db.rb +329 -0
  68. data/lib/bio/db/aaindex.rb +357 -0
  69. data/lib/bio/db/biosql/biosql_to_biosequence.rb +67 -0
  70. data/lib/bio/db/biosql/sequence.rb +508 -0
  71. data/lib/bio/db/embl/common.rb +352 -0
  72. data/lib/bio/db/embl/embl.rb +500 -0
  73. data/lib/bio/db/embl/embl_to_biosequence.rb +85 -0
  74. data/lib/bio/db/embl/format_embl.rb +190 -0
  75. data/lib/bio/db/embl/sptr.rb +1283 -0
  76. data/lib/bio/db/embl/swissprot.rb +42 -0
  77. data/lib/bio/db/embl/trembl.rb +41 -0
  78. data/lib/bio/db/embl/uniprot.rb +42 -0
  79. data/lib/bio/db/fantom.rb +597 -0
  80. data/lib/bio/db/fasta.rb +410 -0
  81. data/lib/bio/db/fasta/defline.rb +532 -0
  82. data/lib/bio/db/fasta/fasta_to_biosequence.rb +63 -0
  83. data/lib/bio/db/fasta/format_fasta.rb +97 -0
  84. data/lib/bio/db/genbank/common.rb +307 -0
  85. data/lib/bio/db/genbank/ddbj.rb +22 -0
  86. data/lib/bio/db/genbank/format_genbank.rb +187 -0
  87. data/lib/bio/db/genbank/genbank.rb +250 -0
  88. data/lib/bio/db/genbank/genbank_to_biosequence.rb +86 -0
  89. data/lib/bio/db/genbank/genpept.rb +60 -0
  90. data/lib/bio/db/genbank/refseq.rb +18 -0
  91. data/lib/bio/db/gff.rb +1846 -0
  92. data/lib/bio/db/go.rb +481 -0
  93. data/lib/bio/db/kegg/brite.rb +41 -0
  94. data/lib/bio/db/kegg/compound.rb +131 -0
  95. data/lib/bio/db/kegg/drug.rb +98 -0
  96. data/lib/bio/db/kegg/enzyme.rb +148 -0
  97. data/lib/bio/db/kegg/expression.rb +155 -0
  98. data/lib/bio/db/kegg/genes.rb +263 -0
  99. data/lib/bio/db/kegg/genome.rb +241 -0
  100. data/lib/bio/db/kegg/glycan.rb +166 -0
  101. data/lib/bio/db/kegg/keggtab.rb +357 -0
  102. data/lib/bio/db/kegg/kgml.rb +256 -0
  103. data/lib/bio/db/kegg/orthology.rb +136 -0
  104. data/lib/bio/db/kegg/reaction.rb +82 -0
  105. data/lib/bio/db/kegg/taxonomy.rb +331 -0
  106. data/lib/bio/db/lasergene.rb +209 -0
  107. data/lib/bio/db/litdb.rb +107 -0
  108. data/lib/bio/db/medline.rb +326 -0
  109. data/lib/bio/db/nbrf.rb +191 -0
  110. data/lib/bio/db/newick.rb +658 -0
  111. data/lib/bio/db/nexus.rb +1854 -0
  112. data/lib/bio/db/pdb.rb +29 -0
  113. data/lib/bio/db/pdb/atom.rb +77 -0
  114. data/lib/bio/db/pdb/chain.rb +210 -0
  115. data/lib/bio/db/pdb/chemicalcomponent.rb +224 -0
  116. data/lib/bio/db/pdb/model.rb +148 -0
  117. data/lib/bio/db/pdb/pdb.rb +1911 -0
  118. data/lib/bio/db/pdb/residue.rb +176 -0
  119. data/lib/bio/db/pdb/utils.rb +399 -0
  120. data/lib/bio/db/prosite.rb +597 -0
  121. data/lib/bio/db/rebase.rb +456 -0
  122. data/lib/bio/db/soft.rb +404 -0
  123. data/lib/bio/db/transfac.rb +375 -0
  124. data/lib/bio/db/url.rb +42 -0
  125. data/lib/bio/feature.rb +139 -0
  126. data/lib/bio/io/biosql/biodatabase.rb +64 -0
  127. data/lib/bio/io/biosql/bioentry.rb +29 -0
  128. data/lib/bio/io/biosql/bioentry_dbxref.rb +11 -0
  129. data/lib/bio/io/biosql/bioentry_path.rb +12 -0
  130. data/lib/bio/io/biosql/bioentry_qualifier_value.rb +10 -0
  131. data/lib/bio/io/biosql/bioentry_reference.rb +10 -0
  132. data/lib/bio/io/biosql/bioentry_relationship.rb +10 -0
  133. data/lib/bio/io/biosql/biosequence.rb +11 -0
  134. data/lib/bio/io/biosql/comment.rb +7 -0
  135. data/lib/bio/io/biosql/config/database.yml +20 -0
  136. data/lib/bio/io/biosql/dbxref.rb +13 -0
  137. data/lib/bio/io/biosql/dbxref_qualifier_value.rb +12 -0
  138. data/lib/bio/io/biosql/location.rb +32 -0
  139. data/lib/bio/io/biosql/location_qualifier_value.rb +11 -0
  140. data/lib/bio/io/biosql/ontology.rb +10 -0
  141. data/lib/bio/io/biosql/reference.rb +9 -0
  142. data/lib/bio/io/biosql/seqfeature.rb +32 -0
  143. data/lib/bio/io/biosql/seqfeature_dbxref.rb +11 -0
  144. data/lib/bio/io/biosql/seqfeature_path.rb +11 -0
  145. data/lib/bio/io/biosql/seqfeature_qualifier_value.rb +20 -0
  146. data/lib/bio/io/biosql/seqfeature_relationship.rb +11 -0
  147. data/lib/bio/io/biosql/taxon.rb +12 -0
  148. data/lib/bio/io/biosql/taxon_name.rb +9 -0
  149. data/lib/bio/io/biosql/term.rb +27 -0
  150. data/lib/bio/io/biosql/term_dbxref.rb +11 -0
  151. data/lib/bio/io/biosql/term_path.rb +12 -0
  152. data/lib/bio/io/biosql/term_relationship.rb +13 -0
  153. data/lib/bio/io/biosql/term_relationship_term.rb +11 -0
  154. data/lib/bio/io/biosql/term_synonym.rb +10 -0
  155. data/lib/bio/io/das.rb +461 -0
  156. data/lib/bio/io/dbget.rb +194 -0
  157. data/lib/bio/io/ddbjxml.rb +638 -0
  158. data/lib/bio/io/ebisoap.rb +158 -0
  159. data/lib/bio/io/ensembl.rb +229 -0
  160. data/lib/bio/io/fastacmd.rb +163 -0
  161. data/lib/bio/io/fetch.rb +195 -0
  162. data/lib/bio/io/flatfile.rb +482 -0
  163. data/lib/bio/io/flatfile/autodetection.rb +545 -0
  164. data/lib/bio/io/flatfile/bdb.rb +253 -0
  165. data/lib/bio/io/flatfile/buffer.rb +237 -0
  166. data/lib/bio/io/flatfile/index.rb +1381 -0
  167. data/lib/bio/io/flatfile/indexer.rb +805 -0
  168. data/lib/bio/io/flatfile/splitter.rb +297 -0
  169. data/lib/bio/io/higet.rb +73 -0
  170. data/lib/bio/io/hinv.rb +442 -0
  171. data/lib/bio/io/keggapi.rb +805 -0
  172. data/lib/bio/io/ncbirest.rb +733 -0
  173. data/lib/bio/io/ncbisoap.rb +155 -0
  174. data/lib/bio/io/pubmed.rb +307 -0
  175. data/lib/bio/io/registry.rb +292 -0
  176. data/lib/bio/io/soapwsdl.rb +119 -0
  177. data/lib/bio/io/sql.rb +186 -0
  178. data/lib/bio/location.rb +867 -0
  179. data/lib/bio/map.rb +410 -0
  180. data/lib/bio/pathway.rb +960 -0
  181. data/lib/bio/reference.rb +602 -0
  182. data/lib/bio/sequence.rb +456 -0
  183. data/lib/bio/sequence/aa.rb +152 -0
  184. data/lib/bio/sequence/adapter.rb +108 -0
  185. data/lib/bio/sequence/common.rb +310 -0
  186. data/lib/bio/sequence/compat.rb +123 -0
  187. data/lib/bio/sequence/dblink.rb +54 -0
  188. data/lib/bio/sequence/format.rb +358 -0
  189. data/lib/bio/sequence/format_raw.rb +23 -0
  190. data/lib/bio/sequence/generic.rb +24 -0
  191. data/lib/bio/sequence/na.rb +491 -0
  192. data/lib/bio/shell.rb +44 -0
  193. data/lib/bio/shell/core.rb +578 -0
  194. data/lib/bio/shell/demo.rb +146 -0
  195. data/lib/bio/shell/interface.rb +218 -0
  196. data/lib/bio/shell/irb.rb +95 -0
  197. data/lib/bio/shell/object.rb +71 -0
  198. data/lib/bio/shell/plugin/blast.rb +42 -0
  199. data/lib/bio/shell/plugin/codon.rb +218 -0
  200. data/lib/bio/shell/plugin/das.rb +58 -0
  201. data/lib/bio/shell/plugin/emboss.rb +23 -0
  202. data/lib/bio/shell/plugin/entry.rb +105 -0
  203. data/lib/bio/shell/plugin/flatfile.rb +101 -0
  204. data/lib/bio/shell/plugin/keggapi.rb +181 -0
  205. data/lib/bio/shell/plugin/midi.rb +430 -0
  206. data/lib/bio/shell/plugin/obda.rb +45 -0
  207. data/lib/bio/shell/plugin/psort.rb +56 -0
  208. data/lib/bio/shell/plugin/seq.rb +247 -0
  209. data/lib/bio/shell/plugin/soap.rb +87 -0
  210. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/bioruby_generator.rb +29 -0
  211. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_classes.rhtml +4 -0
  212. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_log.rhtml +27 -0
  213. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_methods.rhtml +11 -0
  214. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_modules.rhtml +4 -0
  215. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_variables.rhtml +7 -0
  216. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby-bg.gif +0 -0
  217. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby-gem.png +0 -0
  218. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby-link.gif +0 -0
  219. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby.css +368 -0
  220. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby.rhtml +47 -0
  221. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby_controller.rb +144 -0
  222. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby_helper.rb +47 -0
  223. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/commands.rhtml +8 -0
  224. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/history.rhtml +10 -0
  225. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/index.rhtml +26 -0
  226. data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/spinner.gif +0 -0
  227. data/lib/bio/shell/script.rb +25 -0
  228. data/lib/bio/shell/setup.rb +109 -0
  229. data/lib/bio/shell/web.rb +102 -0
  230. data/lib/bio/tree.rb +852 -0
  231. data/lib/bio/util/color_scheme.rb +191 -0
  232. data/lib/bio/util/color_scheme/buried.rb +59 -0
  233. data/lib/bio/util/color_scheme/helix.rb +59 -0
  234. data/lib/bio/util/color_scheme/hydropathy.rb +64 -0
  235. data/lib/bio/util/color_scheme/nucleotide.rb +31 -0
  236. data/lib/bio/util/color_scheme/strand.rb +59 -0
  237. data/lib/bio/util/color_scheme/taylor.rb +50 -0
  238. data/lib/bio/util/color_scheme/turn.rb +59 -0
  239. data/lib/bio/util/color_scheme/zappo.rb +50 -0
  240. data/lib/bio/util/contingency_table.rb +370 -0
  241. data/lib/bio/util/restriction_enzyme.rb +228 -0
  242. data/lib/bio/util/restriction_enzyme/analysis.rb +249 -0
  243. data/lib/bio/util/restriction_enzyme/analysis_basic.rb +217 -0
  244. data/lib/bio/util/restriction_enzyme/cut_symbol.rb +107 -0
  245. data/lib/bio/util/restriction_enzyme/double_stranded.rb +321 -0
  246. data/lib/bio/util/restriction_enzyme/double_stranded/aligned_strands.rb +130 -0
  247. data/lib/bio/util/restriction_enzyme/double_stranded/cut_location_pair.rb +103 -0
  248. data/lib/bio/util/restriction_enzyme/double_stranded/cut_location_pair_in_enzyme_notation.rb +38 -0
  249. data/lib/bio/util/restriction_enzyme/double_stranded/cut_locations.rb +76 -0
  250. data/lib/bio/util/restriction_enzyme/double_stranded/cut_locations_in_enzyme_notation.rb +107 -0
  251. data/lib/bio/util/restriction_enzyme/enzymes.yaml +7061 -0
  252. data/lib/bio/util/restriction_enzyme/range/cut_range.rb +24 -0
  253. data/lib/bio/util/restriction_enzyme/range/cut_ranges.rb +47 -0
  254. data/lib/bio/util/restriction_enzyme/range/horizontal_cut_range.rb +67 -0
  255. data/lib/bio/util/restriction_enzyme/range/sequence_range.rb +257 -0
  256. data/lib/bio/util/restriction_enzyme/range/sequence_range/calculated_cuts.rb +242 -0
  257. data/lib/bio/util/restriction_enzyme/range/sequence_range/fragment.rb +51 -0
  258. data/lib/bio/util/restriction_enzyme/range/sequence_range/fragments.rb +41 -0
  259. data/lib/bio/util/restriction_enzyme/range/vertical_cut_range.rb +77 -0
  260. data/lib/bio/util/restriction_enzyme/single_strand.rb +200 -0
  261. data/lib/bio/util/restriction_enzyme/single_strand/cut_locations_in_enzyme_notation.rb +135 -0
  262. data/lib/bio/util/restriction_enzyme/single_strand_complement.rb +23 -0
  263. data/lib/bio/util/restriction_enzyme/string_formatting.rb +111 -0
  264. data/lib/bio/util/sirna.rb +288 -0
  265. data/test/data/HMMER/hmmpfam.out +64 -0
  266. data/test/data/HMMER/hmmsearch.out +88 -0
  267. data/test/data/SOSUI/sample.report +11 -0
  268. data/test/data/TMHMM/sample.report +21 -0
  269. data/test/data/aaindex/DAYM780301 +30 -0
  270. data/test/data/aaindex/PRAM900102 +20 -0
  271. data/test/data/bl2seq/cd8a_cd8b_blastp.bl2seq +53 -0
  272. data/test/data/bl2seq/cd8a_p53_e-5blastp.bl2seq +37 -0
  273. data/test/data/blast/2.2.15.blastp.m7 +876 -0
  274. data/test/data/blast/b0002.faa +15 -0
  275. data/test/data/blast/b0002.faa.m0 +128 -0
  276. data/test/data/blast/b0002.faa.m7 +65 -0
  277. data/test/data/blast/b0002.faa.m8 +1 -0
  278. data/test/data/blast/blastp-multi.m7 +188 -0
  279. data/test/data/command/echoarg2.bat +1 -0
  280. data/test/data/embl/AB090716.embl +65 -0
  281. data/test/data/embl/AB090716.embl.rel89 +63 -0
  282. data/test/data/fasta/example1.txt +75 -0
  283. data/test/data/fasta/example2.txt +21 -0
  284. data/test/data/genscan/sample.report +63 -0
  285. data/test/data/iprscan/merged.raw +32 -0
  286. data/test/data/iprscan/merged.txt +74 -0
  287. data/test/data/paml/codeml/control_file.txt +30 -0
  288. data/test/data/paml/codeml/output.txt +78 -0
  289. data/test/data/paml/codeml/rates +217 -0
  290. data/test/data/prosite/prosite.dat +2233 -0
  291. data/test/data/refseq/nm_126355.entret +64 -0
  292. data/test/data/rpsblast/misc.rpsblast +193 -0
  293. data/test/data/soft/GDS100_partial.soft +92 -0
  294. data/test/data/soft/GSE3457_family_partial.soft +874 -0
  295. data/test/data/uniprot/p53_human.uniprot +1456 -0
  296. data/test/functional/bio/appl/test_pts1.rb +115 -0
  297. data/test/functional/bio/io/test_ensembl.rb +229 -0
  298. data/test/functional/bio/io/test_soapwsdl.rb +52 -0
  299. data/test/functional/bio/sequence/test_output_embl.rb +51 -0
  300. data/test/functional/bio/test_command.rb +301 -0
  301. data/test/runner.rb +14 -0
  302. data/test/unit/bio/appl/bl2seq/test_report.rb +134 -0
  303. data/test/unit/bio/appl/blast/test_ncbioptions.rb +112 -0
  304. data/test/unit/bio/appl/blast/test_report.rb +1135 -0
  305. data/test/unit/bio/appl/blast/test_rpsblast.rb +398 -0
  306. data/test/unit/bio/appl/genscan/test_report.rb +182 -0
  307. data/test/unit/bio/appl/hmmer/test_report.rb +342 -0
  308. data/test/unit/bio/appl/iprscan/test_report.rb +338 -0
  309. data/test/unit/bio/appl/mafft/test_report.rb +63 -0
  310. data/test/unit/bio/appl/paml/codeml/test_rates.rb +45 -0
  311. data/test/unit/bio/appl/paml/codeml/test_report.rb +45 -0
  312. data/test/unit/bio/appl/paml/test_codeml.rb +174 -0
  313. data/test/unit/bio/appl/sosui/test_report.rb +81 -0
  314. data/test/unit/bio/appl/targetp/test_report.rb +146 -0
  315. data/test/unit/bio/appl/test_blast.rb +277 -0
  316. data/test/unit/bio/appl/test_fasta.rb +130 -0
  317. data/test/unit/bio/appl/test_psort.rb +57 -0
  318. data/test/unit/bio/appl/test_pts1.rb +77 -0
  319. data/test/unit/bio/appl/tmhmm/test_report.rb +126 -0
  320. data/test/unit/bio/data/test_aa.rb +90 -0
  321. data/test/unit/bio/data/test_codontable.rb +107 -0
  322. data/test/unit/bio/data/test_na.rb +80 -0
  323. data/test/unit/bio/db/embl/test_common.rb +117 -0
  324. data/test/unit/bio/db/embl/test_embl.rb +214 -0
  325. data/test/unit/bio/db/embl/test_embl_rel89.rb +219 -0
  326. data/test/unit/bio/db/embl/test_embl_to_bioseq.rb +203 -0
  327. data/test/unit/bio/db/embl/test_sptr.rb +1812 -0
  328. data/test/unit/bio/db/embl/test_uniprot.rb +31 -0
  329. data/test/unit/bio/db/kegg/test_genes.rb +45 -0
  330. data/test/unit/bio/db/pdb/test_pdb.rb +152 -0
  331. data/test/unit/bio/db/test_aaindex.rb +197 -0
  332. data/test/unit/bio/db/test_fasta.rb +250 -0
  333. data/test/unit/bio/db/test_gff.rb +1190 -0
  334. data/test/unit/bio/db/test_lasergene.rb +95 -0
  335. data/test/unit/bio/db/test_medline.rb +127 -0
  336. data/test/unit/bio/db/test_newick.rb +293 -0
  337. data/test/unit/bio/db/test_nexus.rb +364 -0
  338. data/test/unit/bio/db/test_prosite.rb +1437 -0
  339. data/test/unit/bio/db/test_rebase.rb +101 -0
  340. data/test/unit/bio/db/test_soft.rb +138 -0
  341. data/test/unit/bio/db/test_url.rb +36 -0
  342. data/test/unit/bio/io/flatfile/test_autodetection.rb +375 -0
  343. data/test/unit/bio/io/flatfile/test_buffer.rb +251 -0
  344. data/test/unit/bio/io/flatfile/test_splitter.rb +369 -0
  345. data/test/unit/bio/io/test_ddbjxml.rb +80 -0
  346. data/test/unit/bio/io/test_ensembl.rb +109 -0
  347. data/test/unit/bio/io/test_fastacmd.rb +42 -0
  348. data/test/unit/bio/io/test_flatfile.rb +505 -0
  349. data/test/unit/bio/io/test_soapwsdl.rb +32 -0
  350. data/test/unit/bio/sequence/test_aa.rb +115 -0
  351. data/test/unit/bio/sequence/test_common.rb +373 -0
  352. data/test/unit/bio/sequence/test_compat.rb +69 -0
  353. data/test/unit/bio/sequence/test_dblink.rb +58 -0
  354. data/test/unit/bio/sequence/test_na.rb +330 -0
  355. data/test/unit/bio/shell/plugin/test_seq.rb +185 -0
  356. data/test/unit/bio/test_alignment.rb +1025 -0
  357. data/test/unit/bio/test_command.rb +349 -0
  358. data/test/unit/bio/test_db.rb +96 -0
  359. data/test/unit/bio/test_feature.rb +144 -0
  360. data/test/unit/bio/test_location.rb +599 -0
  361. data/test/unit/bio/test_map.rb +230 -0
  362. data/test/unit/bio/test_pathway.rb +499 -0
  363. data/test/unit/bio/test_reference.rb +252 -0
  364. data/test/unit/bio/test_sequence.rb +329 -0
  365. data/test/unit/bio/test_shell.rb +18 -0
  366. data/test/unit/bio/test_tree.rb +593 -0
  367. data/test/unit/bio/util/restriction_enzyme/analysis/test_calculated_cuts.rb +299 -0
  368. data/test/unit/bio/util/restriction_enzyme/analysis/test_cut_ranges.rb +103 -0
  369. data/test/unit/bio/util/restriction_enzyme/analysis/test_sequence_range.rb +240 -0
  370. data/test/unit/bio/util/restriction_enzyme/double_stranded/test_aligned_strands.rb +101 -0
  371. data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_location_pair.rb +75 -0
  372. data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_location_pair_in_enzyme_notation.rb +73 -0
  373. data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_locations.rb +53 -0
  374. data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_locations_in_enzyme_notation.rb +104 -0
  375. data/test/unit/bio/util/restriction_enzyme/single_strand/test_cut_locations_in_enzyme_notation.rb +83 -0
  376. data/test/unit/bio/util/restriction_enzyme/test_analysis.rb +246 -0
  377. data/test/unit/bio/util/restriction_enzyme/test_cut_symbol.rb +44 -0
  378. data/test/unit/bio/util/restriction_enzyme/test_double_stranded.rb +115 -0
  379. data/test/unit/bio/util/restriction_enzyme/test_single_strand.rb +147 -0
  380. data/test/unit/bio/util/restriction_enzyme/test_single_strand_complement.rb +147 -0
  381. data/test/unit/bio/util/restriction_enzyme/test_string_formatting.rb +60 -0
  382. data/test/unit/bio/util/test_color_scheme.rb +33 -0
  383. data/test/unit/bio/util/test_contingency_table.rb +94 -0
  384. data/test/unit/bio/util/test_restriction_enzyme.rb +42 -0
  385. data/test/unit/bio/util/test_sirna.rb +245 -0
  386. metadata +543 -0
@@ -0,0 +1,852 @@
1
+ #
2
+ # = bio/tree.rb - phylogenetic tree data structure class
3
+ #
4
+ # Copyright:: Copyright (C) 2006
5
+ # Naohisa Goto <ng@bioruby.org>
6
+ # License:: The Ruby License
7
+ #
8
+ # $Id:$
9
+ #
10
+
11
+ require 'matrix'
12
+ require 'bio/pathway'
13
+
14
+ module Bio
15
+
16
+ # This is the class for phylogenetic tree.
17
+ # It stores a phylogenetic tree.
18
+ #
19
+ # Internally, it is based on Bio::Pathway class.
20
+ # However, users cannot handle Bio::Pathway object directly.
21
+ #
22
+ # This is alpha version. Incompatible changes may be made frequently.
23
+ class Tree
24
+
25
+ # Error when there are no path between specified nodes
26
+ class NoPathError < RuntimeError; end
27
+
28
+ # Edge object of each node.
29
+ # By default, the object doesn't contain any node information.
30
+ class Edge
31
+
32
+ # creates a new edge.
33
+ def initialize(distance = nil)
34
+ if distance.kind_of?(Numeric)
35
+ self.distance = distance
36
+ elsif distance
37
+ self.distance_string = distance
38
+ end
39
+ end
40
+
41
+ # evolutionary distance
42
+ attr_reader :distance
43
+
44
+ # evolutionary distance represented as a string
45
+ attr_reader :distance_string
46
+
47
+ # set evolutionary distance value
48
+ def distance=(num)
49
+ @distance = num
50
+ @distance_string = (num ? num.to_s : num)
51
+ end
52
+
53
+ # set evolutionary distance value from a string
54
+ def distance_string=(str)
55
+ if str.to_s.strip.empty?
56
+ @distance = nil
57
+ @distance_string = str
58
+ else
59
+ @distance = str.to_f
60
+ @distance_string = str
61
+ end
62
+ end
63
+
64
+ # visualization of this object
65
+ def inspect
66
+ "<Edge distance=#{@distance.inspect}>"
67
+ end
68
+
69
+ # string representation of this object
70
+ def to_s
71
+ @distance_string.to_s
72
+ end
73
+
74
+ #---
75
+ # methods for NHX (New Hampshire eXtended) and/or PhyloXML
76
+ #+++
77
+
78
+ # log likelihood value (:L in NHX)
79
+ attr_accessor :log_likelihood
80
+
81
+ # width of the edge
82
+ # (<branch width="w"> of PhyloXML, or :W="w" in NHX)
83
+ attr_accessor :width
84
+
85
+ # Other NHX parameters. Returns a Hash.
86
+ # Note that :L and :W
87
+ # are not stored here but stored in the proper attributes in this class.
88
+ # However, if you force to set these parameters in this hash,
89
+ # the parameters in this hash are preferred when generating NHX.
90
+ # In addition, If the same parameters are defined at Node object,
91
+ # the parameters in the node are preferred.
92
+ def nhx_parameters
93
+ @nhx_parameters ||= {}
94
+ @nhx_parameters
95
+ end
96
+
97
+ end #class Edge
98
+
99
+ # Gets distance value from the given edge.
100
+ # Returns float or any other numeric value or nil.
101
+ def get_edge_distance(edge)
102
+ begin
103
+ dist = edge.distance
104
+ rescue NoMethodError
105
+ dist = edge
106
+ end
107
+ dist
108
+ end
109
+
110
+ # Gets distance string from the given edge.
111
+ # Returns a string or nil.
112
+ def get_edge_distance_string(edge)
113
+ begin
114
+ dist = edge.distance_string
115
+ rescue NoMethodError
116
+ dist = (edge ? edge.to_s : nil)
117
+ end
118
+ dist
119
+ end
120
+
121
+ # Returns edge1 + edge2
122
+ def get_edge_merged(edge1, edge2)
123
+ dist1 = get_edge_distance(edge1)
124
+ dist2 = get_edge_distance(edge2)
125
+ if dist1 and dist2 then
126
+ Edge.new(dist1 + dist2)
127
+ elsif dist1 then
128
+ Edge.new(dist1)
129
+ elsif dist2 then
130
+ Edge.new(dist2)
131
+ else
132
+ Edge.new
133
+ end
134
+ end
135
+
136
+ # Node object.
137
+ class Node
138
+
139
+ # Creates a new node.
140
+ def initialize(name = nil)
141
+ @name = name if name
142
+ end
143
+
144
+ # name of the node
145
+ attr_accessor :name
146
+
147
+ # bootstrap value
148
+ attr_reader :bootstrap
149
+
150
+ # bootstrap value as a string
151
+ attr_reader :bootstrap_string
152
+
153
+ # sets a bootstrap value
154
+ def bootstrap=(num)
155
+ @bootstrap_string = (num ? num.to_s : num)
156
+ @bootstrap = num
157
+ end
158
+
159
+ # sets a bootstrap value from a string
160
+ def bootstrap_string=(str)
161
+ if str.to_s.strip.empty?
162
+ @bootstrap = nil
163
+ @bootstrap_string = str
164
+ else
165
+ i = str.to_i
166
+ f = str.to_f
167
+ @bootstrap = (i == f ? i : f)
168
+ @bootstrap_string = str
169
+ end
170
+ end
171
+
172
+ # visualization of this object
173
+ def inspect
174
+ if @name and !@name.empty? then
175
+ str = "(Node:#{@name.inspect}"
176
+ else
177
+ str = sprintf('(Node:%x', (self.__id__ << 1) & 0xffffffff)
178
+ end
179
+ if defined?(@bootstrap) and @bootstrap then
180
+ str += " bootstrap=#{@bootstrap.inspect}"
181
+ end
182
+ str += ")"
183
+ str
184
+ end
185
+
186
+ # string representation of this object
187
+ def to_s
188
+ @name.to_s
189
+ end
190
+
191
+ # the order of the node
192
+ # (lower value, high priority)
193
+ attr_accessor :order_number
194
+
195
+ #---
196
+ # methods for NHX (New Hampshire eXtended) and/or PhyloXML
197
+ #+++
198
+
199
+ # Phylogenetic events.
200
+ # Returns an Array of one (or more?) of the following symbols
201
+ # :gene_duplication
202
+ # :speciation
203
+ def events
204
+ @events ||= []
205
+ @events
206
+ end
207
+
208
+ # EC number (EC_number in PhyloXML, or :E in NHX)
209
+ attr_accessor :ec_number
210
+
211
+ # scientific name (scientific_name in PhyloXML, or :S in NHX)
212
+ attr_accessor :scientific_name
213
+
214
+ # taxonomy identifier (taxonomy_identifier in PhyloXML, or :T in NHX)
215
+ attr_accessor :taxonomy_id
216
+
217
+ # Other NHX parameters. Returns a Hash.
218
+ # Note that :D, :E, :S, and :T
219
+ # are not stored here but stored in the proper attributes in this class.
220
+ # However, if you force to set these parameters in this hash,
221
+ # the parameters in this hash are preferred when generating NHX.
222
+ def nhx_parameters
223
+ @nhx_parameters ||= {}
224
+ @nhx_parameters
225
+ end
226
+
227
+ end #class Node
228
+
229
+ # Gets node name
230
+ def get_node_name(node)
231
+ begin
232
+ node.name
233
+ rescue NoMethodError
234
+ node.to_s
235
+ end
236
+ end
237
+
238
+ def get_node_bootstrap(node)
239
+ begin
240
+ node.bootstrap
241
+ rescue NoMethodError
242
+ nil
243
+ end
244
+ end
245
+
246
+ def get_node_bootstrap_string(node)
247
+ begin
248
+ node.bootstrap_string
249
+ rescue NoMethodError
250
+ nil
251
+ end
252
+ end
253
+
254
+ # Creates a new phylogenetic tree.
255
+ # When no arguments are given, it creates a new empty tree.
256
+ # When a Tree object is given, it copies the tree.
257
+ # Note that the new tree shares Node and Edge objects
258
+ # with the given tree.
259
+ def initialize(tree = nil)
260
+ # creates an undirected adjacency list graph
261
+ @pathway = Bio::Pathway.new([], true)
262
+ @root = nil
263
+ @options = {}
264
+ self.concat(tree) if tree
265
+ end
266
+
267
+ # root node of this tree
268
+ # (even if unrooted tree, it is used by some methods)
269
+ attr_accessor :root
270
+
271
+ # tree options; mainly used for tree output
272
+ attr_accessor :options
273
+
274
+ # Clears all nodes and edges.
275
+ # Returns self.
276
+ # Note that options and root are also cleared.
277
+ def clear
278
+ initialize
279
+ self
280
+ end
281
+
282
+ # Returns all nodes as an array.
283
+ def nodes
284
+ @pathway.graph.keys
285
+ end
286
+
287
+ # Number of nodes.
288
+ def number_of_nodes
289
+ @pathway.nodes
290
+ end
291
+
292
+ # Iterates over each node of this tree.
293
+ def each_node(&x) #:yields: node
294
+ @pathway.graph.each_key(&x)
295
+ self
296
+ end
297
+
298
+ # Iterates over each edges of this tree.
299
+ def each_edge #:yields: source, target, edge
300
+ @pathway.relations.each do |rel|
301
+ yield rel.node[0], rel.node[1], rel.relation
302
+ end
303
+ self
304
+ end
305
+
306
+ # Returns all edges an array of [ node0, node1, edge ]
307
+ def edges
308
+ @pathway.relations.collect do |rel|
309
+ [ rel.node[0], rel.node[1], rel.relation ]
310
+ end
311
+ end
312
+
313
+ # Returns number of edges in the tree.
314
+ def number_of_edges
315
+ @pathway.relations.size
316
+ end
317
+
318
+ # Returns an array of adjacent nodes of the given node.
319
+ def adjacent_nodes(node)
320
+ h = @pathway.graph[node]
321
+ h ? h.keys : []
322
+ end
323
+
324
+ # Returns all connected edges with adjacent nodes.
325
+ # Returns an array of the array [ source, target, edge ].
326
+ #
327
+ # The reason why the method name is "out_edges" is that
328
+ # it comes from the Boost Graph Library.
329
+ def out_edges(source)
330
+ h = @pathway.graph[source]
331
+ if h
332
+ h.collect { |key, val| [ source, key, val ] }
333
+ else
334
+ []
335
+ end
336
+ end
337
+
338
+ # Iterates over each connected edges of the given node.
339
+ # Returns self.
340
+ #
341
+ # The reason why the method name is "each_out_edge" is that
342
+ # it comes from the Boost Graph Library.
343
+ def each_out_edge(source) #:yields: source, target, edge
344
+ h = @pathway.graph[source]
345
+ h.each { |key, val| yield source, key, val } if h
346
+ self
347
+ end
348
+
349
+ # Returns number of edges in the given node.
350
+ #
351
+ # The reason why the method name is "out_degree" is that
352
+ # it comes from the Boost Graph Library.
353
+ def out_degree(source)
354
+ h = @pathway.graph[source]
355
+ h ? h.size : 0
356
+ end
357
+
358
+ # Returns an edge from source to target.
359
+ # If source and target are not adjacent nodes, returns nil.
360
+ def get_edge(source, target)
361
+ h = @pathway.graph[source]
362
+ h ? h[target] : nil
363
+ end
364
+
365
+ # Adds a new edge to the tree.
366
+ # Returns the newly added edge.
367
+ # If the edge already exists, it is overwritten with new one.
368
+ def add_edge(source, target, edge = Edge.new)
369
+ @pathway.append(Bio::Relation.new(source, target, edge))
370
+ edge
371
+ end
372
+
373
+ # Finds a node in the tree by given name and returns the node.
374
+ # If the node does not found, returns nil.
375
+ # If multiple nodes with the same name exist,
376
+ # the result would be one of those (unspecified).
377
+ def get_node_by_name(str)
378
+ self.each_node do |node|
379
+ if get_node_name(node) == str
380
+ return node
381
+ end
382
+ end
383
+ nil
384
+ end
385
+
386
+ # Adds a node to the tree.
387
+ # Returns self.
388
+ # If the node already exists, it does nothing.
389
+ def add_node(node)
390
+ @pathway.graph[node] ||= {}
391
+ self
392
+ end
393
+
394
+ # If the node exists, returns true.
395
+ # Otherwise, returns false.
396
+ def include?(node)
397
+ @pathway.graph[node] ? true : false
398
+ end
399
+
400
+ # Removes all edges connected with the node.
401
+ # Returns self.
402
+ # If the node does not exist, raises IndexError.
403
+ def clear_node(node)
404
+ unless self.include?(node)
405
+ raise IndexError, 'the node does not exist'
406
+ end
407
+ @pathway.relations.delete_if do |rel|
408
+ rel.node.include?(node)
409
+ end
410
+ @pathway.graph[node].each_key do |k|
411
+ @pathway.graph[k].delete(node)
412
+ end
413
+ @pathway.graph[node].clear
414
+ self
415
+ end
416
+
417
+ # Removes the given node from the tree.
418
+ # All edges connected with the node are also removed.
419
+ # Returns self.
420
+ # If the node does not exist, raises IndexError.
421
+ def remove_node(node)
422
+ self.clear_node(node)
423
+ @pathway.graph.delete(node)
424
+ self
425
+ end
426
+
427
+ # Removes each node if the block returns not nil.
428
+ # All edges connected with the removed nodes are also removed.
429
+ # Returns self.
430
+ def remove_node_if
431
+ all = self.nodes
432
+ all.each do |node|
433
+ if yield node then
434
+ self.clear_node(node)
435
+ @pathway.graph.delete(node)
436
+ end
437
+ end
438
+ self
439
+ end
440
+
441
+ # Removes an edge between source and target.
442
+ # Returns self.
443
+ # If the edge does not exist, raises IndexError.
444
+ #---
445
+ # If two or more edges exists between source and target,
446
+ # all of them are removed.
447
+ #+++
448
+ def remove_edge(source, target)
449
+ unless self.get_edge(source, target) then
450
+ raise IndexError, 'edge not found'
451
+ end
452
+ fwd = [ source, target ]
453
+ rev = [ target, source ]
454
+ @pathway.relations.delete_if do |rel|
455
+ rel.node == fwd or rel.node == rev
456
+ end
457
+ h = @pathway.graph[source]
458
+ h.delete(target) if h
459
+ h = @pathway.graph[target]
460
+ h.delete(source) if h
461
+ self
462
+ end
463
+
464
+ # Removes each edge if the block returns not nil.
465
+ # Returns self.
466
+ def remove_edge_if #:yields: source, target, edge
467
+ removed_rel = []
468
+ @pathway.relations.delete_if do |rel|
469
+ if yield rel.node[0], rel.node[1], edge then
470
+ removed_rel << rel
471
+ true
472
+ end
473
+ end
474
+ removed_rel.each do |rel|
475
+ source = rel[0]
476
+ target = rel[1]
477
+ h = @pathway.graph[source]
478
+ h.delete(target) if h
479
+ h = @pathway.graph[target]
480
+ h.delete(source) if h
481
+ end
482
+ self
483
+ end
484
+
485
+ # Replaces each node by each block's return value.
486
+ # Returns self.
487
+ def collect_node! #:yields: node
488
+ tr = {}
489
+ self.each_node do |node|
490
+ tr[node] = yield node
491
+ end
492
+ # replaces nodes in @pathway.relations
493
+ @pathway.relations.each do |rel|
494
+ rel.node.collect! { |node| tr[node] }
495
+ end
496
+ # re-generates @pathway from relations
497
+ @pathway.to_list
498
+ # adds orphan nodes
499
+ tr.each_value do |newnode|
500
+ @pathway.graph[newnode] ||= {}
501
+ end
502
+ self
503
+ end
504
+
505
+ # Replaces each edge by each block's return value.
506
+ # Returns self.
507
+ def collect_edge! #:yields: source, target, edge
508
+ @pathway.relations.each do |rel|
509
+ newedge = yield rel.node[0], rel.node[1], rel.relation
510
+ rel.relation = newedge
511
+ @pathway.append(rel, false)
512
+ end
513
+ self
514
+ end
515
+
516
+ # Gets the sub-tree consisted of given nodes.
517
+ # _nodes_ must be an array of nodes.
518
+ # Nodes that do not exist in the original tree are ignored.
519
+ # Returns a Tree object.
520
+ # Note that the sub-tree shares Node and Edge objects
521
+ # with the original tree.
522
+ def subtree(nodes)
523
+ nodes = nodes.find_all do |x|
524
+ @pathway.graph[x]
525
+ end
526
+ return self.class.new if nodes.empty?
527
+ # creates subtree
528
+ new_tree = self.class.new
529
+ nodes.each do |x|
530
+ new_tree.add_node(x)
531
+ end
532
+ self.each_edge do |node1, node2, edge|
533
+ if new_tree.include?(node1) and new_tree.include?(node2) then
534
+ new_tree.add_edge(node1, node2, edge)
535
+ end
536
+ end
537
+ return new_tree
538
+ end
539
+
540
+ # Gets the sub-tree consisted of given nodes and
541
+ # all internal nodes connected between given nodes.
542
+ # _nodes_ must be an array of nodes.
543
+ # Nodes that do not exist in the original tree are ignored.
544
+ # Returns a Tree object.
545
+ # The result is unspecified for cyclic trees.
546
+ # Note that the sub-tree shares Node and Edge objects
547
+ # with the original tree.
548
+ def subtree_with_all_paths(nodes)
549
+ hash = {}
550
+ nodes.each { |x| hash[x] = true }
551
+ nodes.each_index do |i|
552
+ node1 = nodes[i]
553
+ (0...i).each do |j|
554
+ node2 = nodes[j]
555
+ unless node1 == node2 then
556
+ begin
557
+ path = self.path(node1, node2)
558
+ rescue IndexError, NoPathError
559
+ path = []
560
+ end
561
+ path.each { |x| hash[x] = true }
562
+ end
563
+ end
564
+ end
565
+ self.subtree(hash.keys)
566
+ end
567
+
568
+ # Concatenates the other tree.
569
+ # If the same edge exists, the edge in _other_ is used.
570
+ # Returns self.
571
+ # The result is unspecified if _other_ isn't a Tree object.
572
+ # Note that the Node and Edge objects in the _other_ tree are
573
+ # shared in the concatinated tree.
574
+ def concat(other)
575
+ #raise TypeError unless other.kind_of?(self.class)
576
+ other.each_node do |node|
577
+ self.add_node(node)
578
+ end
579
+ other.each_edge do |node1, node2, edge|
580
+ self.add_edge(node1, node2, edge)
581
+ end
582
+ self
583
+ end
584
+
585
+ # Gets path from node1 to node2.
586
+ # Retruns an array of nodes, including node1 and node2.
587
+ # If node1 and/or node2 do not exist, IndexError is raised.
588
+ # If node1 and node2 are not connected, NoPathError is raised.
589
+ # The result is unspecified for cyclic trees.
590
+ def path(node1, node2)
591
+ raise IndexError, 'node1 not found' unless @pathway.graph[node1]
592
+ raise IndexError, 'node2 not found' unless @pathway.graph[node2]
593
+ return [ node1 ] if node1 == node2
594
+ step, path = @pathway.bfs_shortest_path(node1, node2)
595
+ unless path[0] == node1 and path[-1] == node2 then
596
+ raise NoPathError, 'node1 and node2 are not connected'
597
+ end
598
+ path
599
+ end
600
+
601
+ # Iterates over each edge from node1 to node2.
602
+ # The result is unspecified for cyclic trees.
603
+ def each_edge_in_path(node1, node2)
604
+ path = self.path(node1, node2)
605
+ source = path.shift
606
+ path.each do |target|
607
+ edge = self.get_edge(source, target)
608
+ yield source, target, edge
609
+ source = target
610
+ end
611
+ self
612
+ end
613
+
614
+ # Returns distance between node1 and node2.
615
+ # It would raise error if the edges didn't contain distance values.
616
+ # The result is unspecified for cyclic trees.
617
+ def distance(node1, node2)
618
+ distance = 0
619
+ self.each_edge_in_path(node1, node2) do |source, target, edge|
620
+ distance += get_edge_distance(edge)
621
+ end
622
+ distance
623
+ end
624
+
625
+ # Gets the parent node of the _node_.
626
+ # If _root_ isn't specified or _root_ is <code>nil</code>, @root is used.
627
+ # Returns an <code>Node</code> object or nil.
628
+ # The result is unspecified for cyclic trees.
629
+ def parent(node, root = nil)
630
+ root ||= @root
631
+ self.path(root, node)[-2]
632
+ end
633
+
634
+ # Gets the adjacent children nodes of the _node_.
635
+ # If _root_ isn't specified or _root_ is <code>nil</code>, @root is used.
636
+ # Returns an array of <code>Node</code>s.
637
+ # The result is unspecified for cyclic trees.
638
+ def children(node, root = nil)
639
+ root ||= @root
640
+ path = self.path(root, node)
641
+ result = self.adjacent_nodes(node)
642
+ result -= path
643
+ result
644
+ end
645
+
646
+ # Gets all descendent nodes of the _node_.
647
+ # If _root_ isn't specified or _root_ is <code>nil</code>, @root is used.
648
+ # Returns an array of <code>Node</code>s.
649
+ # The result is unspecified for cyclic trees.
650
+ def descendents(node, root = nil)
651
+ root ||= @root
652
+ distance, route = @pathway.breadth_first_search(root)
653
+ d = distance[node]
654
+ result = []
655
+ distance.each do |key, val|
656
+ if val > d then
657
+ x = key
658
+ while x = route[x]
659
+ if x == node then
660
+ result << key
661
+ break
662
+ end
663
+ break if distance[x] <= d
664
+ end
665
+ end
666
+ end
667
+ result
668
+ end
669
+
670
+ # If _node_ is nil, returns an array of
671
+ # all leaves (nodes connected with one edge).
672
+ # Otherwise, gets all descendent leaf nodes of the _node_.
673
+ # If _root_ isn't specified or _root_ is <code>nil</code>, @root is used.
674
+ # Returns an array of <code>Node</code>s.
675
+ # The result is unspecified for cyclic trees.
676
+ def leaves(node = nil, root = nil)
677
+ unless node then
678
+ nodes = []
679
+ self.each_node do |x|
680
+ nodes << x if self.out_degree(x) == 1
681
+ end
682
+ return nodes
683
+ else
684
+ root ||= @root
685
+ self.descendents(node, root).find_all do |x|
686
+ self.adjacent_nodes(x).size == 1
687
+ end
688
+ end
689
+ end
690
+
691
+ # Gets all ancestral nodes of the _node_.
692
+ # If _root_ isn't specified or _root_ is <code>nil</code>, @root is used.
693
+ # Returns an array of <code>Node</code>s.
694
+ # The result is unspecified for cyclic trees.
695
+ def ancestors(node, root = nil)
696
+ root ||= @root
697
+ (self.path(root, node) - [ node ]).reverse
698
+ end
699
+
700
+ # Gets the lowest common ancestor of the two nodes.
701
+ # If _root_ isn't specified or _root_ is <code>nil</code>, @root is used.
702
+ # Returns a <code>Node</code> object or nil.
703
+ # The result is unspecified for cyclic trees.
704
+ def lowest_common_ancestor(node1, node2, root = nil)
705
+ root ||= @root
706
+ distance, route = @pathway.breadth_first_search(root)
707
+ x = node1; r1 = []
708
+ begin; r1 << x; end while x = route[x]
709
+ x = node2; r2 = []
710
+ begin; r2 << x; end while x = route[x]
711
+ return (r1 & r2).first
712
+ end
713
+
714
+ # Returns total distance of all edges.
715
+ # It would raise error if some edges didn't contain distance values.
716
+ def total_distance
717
+ distance = 0
718
+ self.each_edge do |source, target, edge|
719
+ distance += get_edge_distance(edge)
720
+ end
721
+ distance
722
+ end
723
+
724
+ # Calculates distance matrix of given nodes.
725
+ # If _nodes_ is nil, or is ommited, it acts the same as
726
+ # tree.distance_matrix(tree.leaves).
727
+ # Returns a matrix object.
728
+ # The result is unspecified for cyclic trees.
729
+ # Note 1: The diagonal values of the matrix are 0.
730
+ # Note 2: If the distance cannot be calculated, nil will be set.
731
+ def distance_matrix(nodes = nil)
732
+ nodes ||= self.leaves
733
+ matrix = []
734
+ nodes.each_index do |i|
735
+ row = []
736
+ nodes.each_index do |j|
737
+ if i == j then
738
+ distance = 0
739
+ elsif r = matrix[j] and val = r[i] then
740
+ distance = val
741
+ else
742
+ distance = (self.distance(nodes[i], nodes[j]) rescue nil)
743
+ end
744
+ row << distance
745
+ end
746
+ matrix << row
747
+ end
748
+ Matrix.rows(matrix, false)
749
+ end
750
+
751
+ # Shows the adjacency matrix representation of the tree.
752
+ # It shows matrix only for given nodes.
753
+ # If _nodes_ is nil or is ommitted,
754
+ # it acts the same as tree.adjacency_matrix(tree.nodes).
755
+ # If a block is given, for each edge,
756
+ # it yields _source_, _target_, and _edge_, and
757
+ # uses the returned value of the block.
758
+ # Without blocks, it uses edge.
759
+ # Returns a matrix object.
760
+ def adjacency_matrix(nodes = nil,
761
+ default_value = nil,
762
+ diagonal_value = nil) #:yields: source, target, edge
763
+ nodes ||= self.nodes
764
+ size = nodes.size
765
+ hash = {}
766
+ nodes.each_with_index { |x, i| hash[x] = i }
767
+ # prepares an matrix
768
+ matrix = Array.new(size, nil)
769
+ matrix.collect! { |x| Array.new(size, default_value) }
770
+ (0...size).each { |i| matrix[i][i] = diagonal_value }
771
+ # fills the matrix from each edge
772
+ self.each_edge do |source, target, edge|
773
+ i_source = hash[source]
774
+ i_target = hash[target]
775
+ if i_source and i_target then
776
+ val = block_given? ? (yield source, target, edge) : edge
777
+ matrix[i_source][i_target] = val
778
+ matrix[i_target][i_source] = val
779
+ end
780
+ end
781
+ Matrix.rows(matrix, false)
782
+ end
783
+
784
+ # Removes all nodes that are not branches nor leaves.
785
+ # That is, removes nodes connected with exactly two edges.
786
+ # For each removed node, two adjacent edges are merged and
787
+ # a new edge are created.
788
+ # Returns removed nodes.
789
+ # Note that orphan nodes are still kept unchanged.
790
+ def remove_nonsense_nodes
791
+ hash = {}
792
+ self.each_node do |node|
793
+ hash[node] = true if @pathway.graph[node].size == 2
794
+ end
795
+ hash.each_key do |node|
796
+ adjs = @pathway.graph[node].keys
797
+ edges = @pathway.graph[node].values
798
+ new_edge = get_edge_merged(edges[0], edges[1])
799
+ @pathway.graph[adjs[0]].delete(node)
800
+ @pathway.graph[adjs[1]].delete(node)
801
+ @pathway.graph.delete(node)
802
+ @pathway.append(Bio::Relation.new(adjs[0], adjs[1], new_edge))
803
+ end
804
+ #@pathway.to_relations
805
+ @pathway.relations.reject! do |rel|
806
+ hash[rel.node[0]] or hash[rel.node[1]]
807
+ end
808
+ return hash.keys
809
+ end
810
+
811
+ # Insert a new node between adjacent nodes node1 and node2.
812
+ # The old edge between node1 and node2 are changed to the edge
813
+ # between new_node and node2.
814
+ # The edge between node1 and new_node is newly created.
815
+ #
816
+ # If new_distance is specified, the distance between
817
+ # node1 and new_node is set to new_distance, and
818
+ # distance between new_node and node2 is set to
819
+ # <code>tree.get_edge(node1, node2).distance - new_distance</code>.
820
+ #
821
+ # Returns self.
822
+ # If node1 and node2 are not adjacent, raises IndexError.
823
+ #
824
+ # If new_node already exists in the tree, the tree would become
825
+ # circular. In addition, if the edge between new_node and
826
+ # node1 (or node2) already exists, it will be erased.
827
+ def insert_node(node1, node2, new_node, new_distance = nil)
828
+ unless edge = self.get_edge(node1, node2) then
829
+ raise IndexError, 'nodes not found or two nodes are not adjacent'
830
+ end
831
+ new_edge = Edge.new(new_distance)
832
+ self.remove_edge(node1, node2)
833
+ self.add_edge(node1, new_node, new_edge)
834
+ if new_distance and old_distance = get_edge_distance(edge) then
835
+ old_distance -= new_distance
836
+ begin
837
+ edge.distance = old_distance
838
+ rescue NoMethodError
839
+ edge = old_distance
840
+ end
841
+ end
842
+ self.add_edge(new_node, node2, edge)
843
+ self
844
+ end
845
+ end #class Tree
846
+ end #module Bio
847
+
848
+ #---
849
+ # temporary added
850
+ #+++
851
+ require 'bio/db/newick'
852
+