bioroebe 0.10.80

Sign up to get free protection for your applications and to get access to all the features.
Files changed (802) hide show
  1. checksums.yaml +7 -0
  2. data/LICENSE.md +428 -0
  3. data/README.md +9280 -0
  4. data/bin/advanced_dotplot +7 -0
  5. data/bin/align_open_reading_frames +12 -0
  6. data/bin/all_positions_of_this_nucleotide +7 -0
  7. data/bin/aminoacid_composition +7 -0
  8. data/bin/aminoacid_frequencies +12 -0
  9. data/bin/aminoacid_substitution +7 -0
  10. data/bin/automatically_rename_this_fasta_file +7 -0
  11. data/bin/base_composition +7 -0
  12. data/bin/batch_create_windows_executables +7 -0
  13. data/bin/biomart_console +11 -0
  14. data/bin/bioroebe +27 -0
  15. data/bin/bioroebe_controller +10 -0
  16. data/bin/bioshell +26 -0
  17. data/bin/blosum_2D_table +12 -0
  18. data/bin/calculate_n50_value +12 -0
  19. data/bin/chunked_display +12 -0
  20. data/bin/codon_frequency +9 -0
  21. data/bin/codon_to_aminoacid +30 -0
  22. data/bin/colourize_this_fasta_sequence +14 -0
  23. data/bin/compact_fasta_file +7 -0
  24. data/bin/complement +7 -0
  25. data/bin/complementary_dna_strand +12 -0
  26. data/bin/complementary_rna_strand +12 -0
  27. data/bin/compseq +7 -0
  28. data/bin/consensus_sequence +17 -0
  29. data/bin/count_AT +12 -0
  30. data/bin/count_GC +12 -0
  31. data/bin/create_random_aminoacids +7 -0
  32. data/bin/decode_this_aminoacid_sequence +20 -0
  33. data/bin/deduce_aminoacid_sequence +13 -0
  34. data/bin/deduce_most_likely_aminoacid_sequence +7 -0
  35. data/bin/display_aminoacid_table +12 -0
  36. data/bin/display_open_reading_frames +7 -0
  37. data/bin/dna_to_aminoacid_sequence +7 -0
  38. data/bin/dna_to_rna +7 -0
  39. data/bin/downcase_chunked_display +12 -0
  40. data/bin/download_this_pdb +7 -0
  41. data/bin/fasta_index +7 -0
  42. data/bin/fetch_data_from_uniprot +12 -0
  43. data/bin/filter_away_invalid_nucleotides +12 -0
  44. data/bin/find_substring +19 -0
  45. data/bin/genbank_to_fasta +7 -0
  46. data/bin/hamming_distance +12 -0
  47. data/bin/input_as_dna +12 -0
  48. data/bin/is_palindrome +13 -0
  49. data/bin/leading_five_prime +7 -0
  50. data/bin/levensthein +7 -0
  51. data/bin/longest_ORF +14 -0
  52. data/bin/longest_substring +12 -0
  53. data/bin/n_stop_codons_in_this_sequence +15 -0
  54. data/bin/open_reading_frames +14 -0
  55. data/bin/overwrite_fasta_header +7 -0
  56. data/bin/palindrome_2D_structure +7 -0
  57. data/bin/palindrome_generator +7 -0
  58. data/bin/parse_fasta +7 -0
  59. data/bin/partner_nucleotide +9 -0
  60. data/bin/possible_codons_for_this_aminoacid +12 -0
  61. data/bin/random_dna_sequence +12 -0
  62. data/bin/random_sequence +12 -0
  63. data/bin/raw_hamming_distance +12 -0
  64. data/bin/return_longest_substring_via_LCS_algorithm +7 -0
  65. data/bin/reverse_complement +7 -0
  66. data/bin/reverse_sequence +7 -0
  67. data/bin/ruler +12 -0
  68. data/bin/scan_this_input_for_startcodons +12 -0
  69. data/bin/short_aminoacid_letter_from_long_aminoacid_name +7 -0
  70. data/bin/show_atomic_composition +7 -0
  71. data/bin/show_codon_usage +12 -0
  72. data/bin/show_fasta_header +7 -0
  73. data/bin/show_nucleotide_sequence +7 -0
  74. data/bin/show_this_codon_table +7 -0
  75. data/bin/show_this_dna_sequence +7 -0
  76. data/bin/showorf +14 -0
  77. data/bin/simplify_fasta +7 -0
  78. data/bin/sort_aminoacid_based_on_its_hydrophobicity +7 -0
  79. data/bin/split_this_fasta_file_into_chromosomes +7 -0
  80. data/bin/strict_filter_away_invalid_aminoacids +7 -0
  81. data/bin/taxonomy +63 -0
  82. data/bin/three_to_one +7 -0
  83. data/bin/to_rna +7 -0
  84. data/bin/trailing_three_prime +7 -0
  85. data/bin/trypsin_digest +7 -0
  86. data/bin/upcase_this_aminoacid_sequence_and_remove_numbers +7 -0
  87. data/bioroebe.gemspec +97 -0
  88. data/doc/IUPAC_aminoacids_code.md +36 -0
  89. data/doc/IUPAC_nucleotide_code.md +19 -0
  90. data/doc/README.gen +9237 -0
  91. data/doc/blosum.md +5 -0
  92. data/doc/compatibility/BIO_PHP.md +37 -0
  93. data/doc/compatibility/README.md +3 -0
  94. data/doc/compatibility/emboss.md +56 -0
  95. data/doc/extensive_usage_example.md +35 -0
  96. data/doc/german_names_for_the_aminoacids.md +27 -0
  97. data/doc/instructions_for_the_taxonomy_subproject.md +504 -0
  98. data/doc/legacy_paths.md +9 -0
  99. data/doc/pdb_ATOM_entry.md +33 -0
  100. data/doc/quality_control/README.md +2 -0
  101. data/doc/quality_control/commandline_applications.md +13 -0
  102. data/doc/resources.md +23 -0
  103. data/doc/setup.rb +1655 -0
  104. data/doc/statistics/statistics.md +41 -0
  105. data/doc/todo/README.md +5 -0
  106. data/doc/todo/bioroebe_GUI_todo.md +15 -0
  107. data/doc/todo/bioroebe_todo.md +2823 -0
  108. data/doc/using_biomart.md +258 -0
  109. data/html/test.html +144 -0
  110. data/lib/bioroebe/aminoacids/aminoacid_substitution.rb +118 -0
  111. data/lib/bioroebe/aminoacids/aminoacids_mass_table.rb +118 -0
  112. data/lib/bioroebe/aminoacids/codon_percentage.rb +189 -0
  113. data/lib/bioroebe/aminoacids/colourize_hydrophilic_and_hydrophobic_aminoacids.rb +110 -0
  114. data/lib/bioroebe/aminoacids/create_random_aminoacids.rb +221 -0
  115. data/lib/bioroebe/aminoacids/deduce_aminoacid_sequence.rb +460 -0
  116. data/lib/bioroebe/aminoacids/display_aminoacid_table.rb +231 -0
  117. data/lib/bioroebe/aminoacids/show_hydrophobicity.rb +184 -0
  118. data/lib/bioroebe/annotations/README.md +2 -0
  119. data/lib/bioroebe/annotations/create_annotation_format.rb +208 -0
  120. data/lib/bioroebe/autoinclude.rb +7 -0
  121. data/lib/bioroebe/base/base.rb +35 -0
  122. data/lib/bioroebe/base/colours.rb +14 -0
  123. data/lib/bioroebe/base/colours_for_base/colours_for_base.rb +275 -0
  124. data/lib/bioroebe/base/commandline_application/README.md +7 -0
  125. data/lib/bioroebe/base/commandline_application/aminoacids.rb +33 -0
  126. data/lib/bioroebe/base/commandline_application/commandline_application.rb +37 -0
  127. data/lib/bioroebe/base/commandline_application/commandline_arguments.rb +144 -0
  128. data/lib/bioroebe/base/commandline_application/directory.rb +33 -0
  129. data/lib/bioroebe/base/commandline_application/extract.rb +22 -0
  130. data/lib/bioroebe/base/commandline_application/misc.rb +485 -0
  131. data/lib/bioroebe/base/commandline_application/opn.rb +47 -0
  132. data/lib/bioroebe/base/commandline_application/reset.rb +40 -0
  133. data/lib/bioroebe/base/commandline_application/warnings.rb +36 -0
  134. data/lib/bioroebe/base/commandline_application/write_what_into.rb +29 -0
  135. data/lib/bioroebe/base/initialize.rb +18 -0
  136. data/lib/bioroebe/base/misc.rb +94 -0
  137. data/lib/bioroebe/base/namespace.rb +16 -0
  138. data/lib/bioroebe/base/prototype/README.md +12 -0
  139. data/lib/bioroebe/base/prototype/e_and_ee.rb +24 -0
  140. data/lib/bioroebe/base/prototype/misc.rb +108 -0
  141. data/lib/bioroebe/base/prototype/mkdir.rb +20 -0
  142. data/lib/bioroebe/base/prototype/prototype.rb +21 -0
  143. data/lib/bioroebe/base/prototype/reset.rb +26 -0
  144. data/lib/bioroebe/base/reset.rb +11 -0
  145. data/lib/bioroebe/biomart/LICENSE.md +27 -0
  146. data/lib/bioroebe/biomart/attribute.rb +77 -0
  147. data/lib/bioroebe/biomart/biomart.rb +227 -0
  148. data/lib/bioroebe/biomart/database.rb +128 -0
  149. data/lib/bioroebe/biomart/dataset.rb +572 -0
  150. data/lib/bioroebe/biomart/filter.rb +97 -0
  151. data/lib/bioroebe/biomart/server.rb +152 -0
  152. data/lib/bioroebe/blosum/blosum.rb +88 -0
  153. data/lib/bioroebe/calculate/calculate_blosum_score.rb +145 -0
  154. data/lib/bioroebe/calculate/calculate_gc_content.rb +301 -0
  155. data/lib/bioroebe/calculate/calculate_levensthein_distance.rb +100 -0
  156. data/lib/bioroebe/calculate/calculate_melting_temperature.rb +398 -0
  157. data/lib/bioroebe/calculate/calculate_melting_temperature_for_more_than_thirteen_nucleotides.rb +304 -0
  158. data/lib/bioroebe/calculate/calculate_the_position_specific_scoring_matrix.rb +166 -0
  159. data/lib/bioroebe/cell/README.md +1 -0
  160. data/lib/bioroebe/cell/cell.rb +63 -0
  161. data/lib/bioroebe/cleave_and_digest/README.md +2 -0
  162. data/lib/bioroebe/cleave_and_digest/cleave.rb +80 -0
  163. data/lib/bioroebe/cleave_and_digest/digestion.rb +75 -0
  164. data/lib/bioroebe/cleave_and_digest/trypsin.rb +192 -0
  165. data/lib/bioroebe/codon_tables/README.md +9 -0
  166. data/lib/bioroebe/codon_tables/frequencies/287_Pseudomonas_aeruginosa.yml +101 -0
  167. data/lib/bioroebe/codon_tables/frequencies/3702_Arabidopsis_thaliana.yml +77 -0
  168. data/lib/bioroebe/codon_tables/frequencies/4932_Saccharomyces_cerevisiae.yml +103 -0
  169. data/lib/bioroebe/codon_tables/frequencies/7227_Drosophila_melanogaster.yml +71 -0
  170. data/lib/bioroebe/codon_tables/frequencies/83333_Escherichia_coli_K12.yml +103 -0
  171. data/lib/bioroebe/codon_tables/frequencies/9606_Homo_sapiens.yml +123 -0
  172. data/lib/bioroebe/codon_tables/frequencies/9685_Felis_catus.yml +78 -0
  173. data/lib/bioroebe/codon_tables/frequencies/README.md +10 -0
  174. data/lib/bioroebe/codon_tables/frequencies/parse_frequency_table.rb +337 -0
  175. data/lib/bioroebe/codons/README.md +28 -0
  176. data/lib/bioroebe/codons/codon_table.rb +416 -0
  177. data/lib/bioroebe/codons/codon_tables.rb +123 -0
  178. data/lib/bioroebe/codons/codons.rb +517 -0
  179. data/lib/bioroebe/codons/convert_this_codon_to_that_aminoacid.rb +102 -0
  180. data/lib/bioroebe/codons/detect_minimal_codon.rb +180 -0
  181. data/lib/bioroebe/codons/determine_optimal_codons.rb +74 -0
  182. data/lib/bioroebe/codons/possible_codons_for_this_aminoacid.rb +380 -0
  183. data/lib/bioroebe/codons/sanitize_codon_frequency.rb +144 -0
  184. data/lib/bioroebe/codons/show_codon_tables.rb +130 -0
  185. data/lib/bioroebe/codons/show_codon_usage.rb +197 -0
  186. data/lib/bioroebe/codons/show_this_codon_table.rb +573 -0
  187. data/lib/bioroebe/codons/start_codons.rb +105 -0
  188. data/lib/bioroebe/colours/colour_schemes/README.md +10 -0
  189. data/lib/bioroebe/colours/colour_schemes/array_available_colour_schemes.rb +38 -0
  190. data/lib/bioroebe/colours/colour_schemes/buried.rb +70 -0
  191. data/lib/bioroebe/colours/colour_schemes/colour_scheme.rb +101 -0
  192. data/lib/bioroebe/colours/colour_schemes/colour_scheme_demo.rb +262 -0
  193. data/lib/bioroebe/colours/colour_schemes/helix.rb +65 -0
  194. data/lib/bioroebe/colours/colour_schemes/hydropathy.rb +70 -0
  195. data/lib/bioroebe/colours/colour_schemes/nucleotide.rb +47 -0
  196. data/lib/bioroebe/colours/colour_schemes/score.rb +112 -0
  197. data/lib/bioroebe/colours/colour_schemes/simple.rb +42 -0
  198. data/lib/bioroebe/colours/colour_schemes/strand.rb +65 -0
  199. data/lib/bioroebe/colours/colour_schemes/taylor.rb +58 -0
  200. data/lib/bioroebe/colours/colour_schemes/turn.rb +65 -0
  201. data/lib/bioroebe/colours/colour_schemes/zappo.rb +59 -0
  202. data/lib/bioroebe/colours/colourize_sequence.rb +262 -0
  203. data/lib/bioroebe/colours/colours.rb +119 -0
  204. data/lib/bioroebe/colours/misc_colours.rb +80 -0
  205. data/lib/bioroebe/colours/rev.rb +41 -0
  206. data/lib/bioroebe/colours/sdir.rb +21 -0
  207. data/lib/bioroebe/colours/sfancy.rb +21 -0
  208. data/lib/bioroebe/colours/sfile.rb +21 -0
  209. data/lib/bioroebe/colours/simp.rb +21 -0
  210. data/lib/bioroebe/colours/swarn.rb +29 -0
  211. data/lib/bioroebe/colours/use_colours.rb +27 -0
  212. data/lib/bioroebe/configuration/configuration.rb +114 -0
  213. data/lib/bioroebe/configuration/constants.rb +35 -0
  214. data/lib/bioroebe/constants/GUIs.rb +79 -0
  215. data/lib/bioroebe/constants/aminoacids_and_proteins.rb +146 -0
  216. data/lib/bioroebe/constants/base_directory.rb +120 -0
  217. data/lib/bioroebe/constants/carriage_return.rb +14 -0
  218. data/lib/bioroebe/constants/codon_tables.rb +77 -0
  219. data/lib/bioroebe/constants/database_constants.rb +107 -0
  220. data/lib/bioroebe/constants/files_and_directories.rb +579 -0
  221. data/lib/bioroebe/constants/misc.rb +189 -0
  222. data/lib/bioroebe/constants/newline.rb +14 -0
  223. data/lib/bioroebe/constants/nucleotides.rb +114 -0
  224. data/lib/bioroebe/constants/regex.rb +28 -0
  225. data/lib/bioroebe/constants/roebe.rb +38 -0
  226. data/lib/bioroebe/constants/row_terminator.rb +16 -0
  227. data/lib/bioroebe/constants/tabulator.rb +14 -0
  228. data/lib/bioroebe/constants/unicode.rb +12 -0
  229. data/lib/bioroebe/constants/urls.rb +50 -0
  230. data/lib/bioroebe/conversions/README.md +3 -0
  231. data/lib/bioroebe/conversions/convert_aminoacid_to_dna.rb +298 -0
  232. data/lib/bioroebe/conversions/dna_to_aminoacid_sequence.rb +569 -0
  233. data/lib/bioroebe/count/README.md +1 -0
  234. data/lib/bioroebe/count/count_amount_of_aminoacids.rb +352 -0
  235. data/lib/bioroebe/count/count_amount_of_nucleotides.rb +491 -0
  236. data/lib/bioroebe/count/count_at.rb +39 -0
  237. data/lib/bioroebe/count/count_gc.rb +43 -0
  238. data/lib/bioroebe/css/README.md +5 -0
  239. data/lib/bioroebe/css/project.css +121 -0
  240. data/lib/bioroebe/data/README.md +10 -0
  241. data/lib/bioroebe/data/bam/README.md +1 -0
  242. data/lib/bioroebe/data/data.txt +192 -0
  243. data/lib/bioroebe/data/fasta/GFP_mutant_3_coding_sequence.fasta +12 -0
  244. data/lib/bioroebe/data/fasta/alu_elements.fasta +42 -0
  245. data/lib/bioroebe/data/fasta/lady_slippers_orchid.fasta +1197 -0
  246. data/lib/bioroebe/data/fasta/loxP.fasta +2 -0
  247. data/lib/bioroebe/data/fasta/ls_orchid.fasta +1197 -0
  248. data/lib/bioroebe/data/fasta/pax6_in_mouse.fasta +1 -0
  249. data/lib/bioroebe/data/fasta/test.fasta +7 -0
  250. data/lib/bioroebe/data/fasta/test_DNA.fasta +1 -0
  251. data/lib/bioroebe/data/fastq/fastq_example_file.fastq +32 -0
  252. data/lib/bioroebe/data/fastq/fastq_example_file_SP1.fastq +1000 -0
  253. data/lib/bioroebe/data/fastq/one_random_fastq_entry.fastq +4 -0
  254. data/lib/bioroebe/data/genbank/sample_file.genbank +15 -0
  255. data/lib/bioroebe/data/genbank/standard.fasta +3 -0
  256. data/lib/bioroebe/data/gff/Escherichia_coli_K12_plasmid_F_DNA_NC_002483.1.gff3 +345 -0
  257. data/lib/bioroebe/data/gff/sample.gff +2 -0
  258. data/lib/bioroebe/data/gff/test_gene.gff +4 -0
  259. data/lib/bioroebe/data/gff/transcripts.gff +16 -0
  260. data/lib/bioroebe/data/gtf/README.md +1 -0
  261. data/lib/bioroebe/data/json/example_config.json +48 -0
  262. data/lib/bioroebe/data/pdb/1VII.pdb +754 -0
  263. data/lib/bioroebe/data/pdb/ala_phe_ala.pdb +228 -0
  264. data/lib/bioroebe/data/pdb/rcsb_pdb_1VII.fasta +2 -0
  265. data/lib/bioroebe/data/phylip/README.md +11 -0
  266. data/lib/bioroebe/data/phylip/example.phylip +7 -0
  267. data/lib/bioroebe/data/svg/example.svg +301 -0
  268. data/lib/bioroebe/databases/README.md +1 -0
  269. data/lib/bioroebe/databases/download_taxonomy_database.rb +102 -0
  270. data/lib/bioroebe/dotplots/README.md +5 -0
  271. data/lib/bioroebe/dotplots/advanced_dotplot.rb +256 -0
  272. data/lib/bioroebe/dotplots/dotplot.rb +184 -0
  273. data/lib/bioroebe/electron_microscopy/coordinate_analyzer.rb +191 -0
  274. data/lib/bioroebe/electron_microscopy/fix_pos_file.rb +102 -0
  275. data/lib/bioroebe/electron_microscopy/generate_em2em_file.rb +122 -0
  276. data/lib/bioroebe/electron_microscopy/parse_coordinates.rb +197 -0
  277. data/lib/bioroebe/electron_microscopy/read_file_xmd.rb +282 -0
  278. data/lib/bioroebe/electron_microscopy/simple_star_file_generator.rb +131 -0
  279. data/lib/bioroebe/encoding/README.md +2 -0
  280. data/lib/bioroebe/encoding/encoding.rb +45 -0
  281. data/lib/bioroebe/enzymes/README.md +2 -0
  282. data/lib/bioroebe/enzymes/has_this_restriction_enzyme.rb +46 -0
  283. data/lib/bioroebe/enzymes/restriction_enzyme.rb +200 -0
  284. data/lib/bioroebe/enzymes/restriction_enzymes_file.rb +72 -0
  285. data/lib/bioroebe/enzymes/return_restriction_enzyme_sequence_and_cut_position.rb +80 -0
  286. data/lib/bioroebe/enzymes/return_sequence_that_is_cut_via_restriction_enzyme.rb +65 -0
  287. data/lib/bioroebe/enzymes/show_restriction_enzymes.rb +119 -0
  288. data/lib/bioroebe/exceptions/README.md +2 -0
  289. data/lib/bioroebe/exceptions/exceptions.rb +17 -0
  290. data/lib/bioroebe/ext/LICENCE.md +5 -0
  291. data/lib/bioroebe/ext/README.md +7 -0
  292. data/lib/bioroebe/ext/main.cpp +45 -0
  293. data/lib/bioroebe/ext/nucleotide.cpp +24 -0
  294. data/lib/bioroebe/ext/nussinov_algorithm.cpp +348 -0
  295. data/lib/bioroebe/ext/sequence +0 -0
  296. data/lib/bioroebe/ext/sequence.cpp +162 -0
  297. data/lib/bioroebe/fasta_and_fastq/README.md +6 -0
  298. data/lib/bioroebe/fasta_and_fastq/autocorrect_the_name_of_this_fasta_file.rb +88 -0
  299. data/lib/bioroebe/fasta_and_fastq/compact_fasta_file/compact_fasta_file.rb +151 -0
  300. data/lib/bioroebe/fasta_and_fastq/display_how_many_fasta_entries_are_in_this_directory.rb +111 -0
  301. data/lib/bioroebe/fasta_and_fastq/download_fasta.rb +248 -0
  302. data/lib/bioroebe/fasta_and_fastq/fasta_defline/README.md +2 -0
  303. data/lib/bioroebe/fasta_and_fastq/fasta_defline/fasta_defline.rb +113 -0
  304. data/lib/bioroebe/fasta_and_fastq/fasta_parser.rb +167 -0
  305. data/lib/bioroebe/fasta_and_fastq/fastq_format_explainer.rb +131 -0
  306. data/lib/bioroebe/fasta_and_fastq/length_modifier/length_modifier.rb +87 -0
  307. data/lib/bioroebe/fasta_and_fastq/parse_fasta/constants.rb +50 -0
  308. data/lib/bioroebe/fasta_and_fastq/parse_fasta/initialize.rb +86 -0
  309. data/lib/bioroebe/fasta_and_fastq/parse_fasta/menu.rb +117 -0
  310. data/lib/bioroebe/fasta_and_fastq/parse_fasta/misc.rb +981 -0
  311. data/lib/bioroebe/fasta_and_fastq/parse_fasta/parse_fasta.rb +27 -0
  312. data/lib/bioroebe/fasta_and_fastq/parse_fasta/report.rb +156 -0
  313. data/lib/bioroebe/fasta_and_fastq/parse_fasta/reset.rb +128 -0
  314. data/lib/bioroebe/fasta_and_fastq/parse_fasta/run.rb +20 -0
  315. data/lib/bioroebe/fasta_and_fastq/parse_fastq/parse_fastq.rb +83 -0
  316. data/lib/bioroebe/fasta_and_fastq/return_fasta_subsection_of_this_file.rb +112 -0
  317. data/lib/bioroebe/fasta_and_fastq/show_fasta_headers.rb +135 -0
  318. data/lib/bioroebe/fasta_and_fastq/show_fasta_statistics.rb +188 -0
  319. data/lib/bioroebe/fasta_and_fastq/simplify_fasta_header/simplify_fasta_header.rb +111 -0
  320. data/lib/bioroebe/fasta_and_fastq/split_this_fasta_file_into_chromosomes/constants.rb +26 -0
  321. data/lib/bioroebe/fasta_and_fastq/split_this_fasta_file_into_chromosomes/menu.rb +41 -0
  322. data/lib/bioroebe/fasta_and_fastq/split_this_fasta_file_into_chromosomes/misc.rb +23 -0
  323. data/lib/bioroebe/fasta_and_fastq/split_this_fasta_file_into_chromosomes/reset.rb +68 -0
  324. data/lib/bioroebe/fasta_and_fastq/split_this_fasta_file_into_chromosomes/split_this_fasta_file_into_chromosomes.rb +290 -0
  325. data/lib/bioroebe/genbank/README.md +1 -0
  326. data/lib/bioroebe/genbank/genbank_flat_file_format_generator.rb +275 -0
  327. data/lib/bioroebe/genbank/genbank_parser.rb +291 -0
  328. data/lib/bioroebe/gene/gene.rb +64 -0
  329. data/lib/bioroebe/genomes/genome_pattern.rb +165 -0
  330. data/lib/bioroebe/genomes/genome_retriever.rb +79 -0
  331. data/lib/bioroebe/gui/experimental/README.md +1 -0
  332. data/lib/bioroebe/gui/experimental/snapgene/snapgene.rb +147 -0
  333. data/lib/bioroebe/gui/gtk3/README.md +2 -0
  334. data/lib/bioroebe/gui/gtk3/alignment/alignment.rb +337 -0
  335. data/lib/bioroebe/gui/gtk3/aminoacid_composition/aminoacid_composition.rb +510 -0
  336. data/lib/bioroebe/gui/gtk3/aminoacid_composition/customized_dialog.rb +55 -0
  337. data/lib/bioroebe/gui/gtk3/anti_sense_strand/anti_sense_strand.config +6 -0
  338. data/lib/bioroebe/gui/gtk3/anti_sense_strand/anti_sense_strand.rb +29 -0
  339. data/lib/bioroebe/gui/gtk3/blosum_matrix_viewer/blosum_matrix_viewer.rb +196 -0
  340. data/lib/bioroebe/gui/gtk3/calculate_cell_numbers_of_bacteria/calculate_cell_numbers_of_bacteria.config +6 -0
  341. data/lib/bioroebe/gui/gtk3/calculate_cell_numbers_of_bacteria/calculate_cell_numbers_of_bacteria.rb +106 -0
  342. data/lib/bioroebe/gui/gtk3/controller/controller.rb +406 -0
  343. data/lib/bioroebe/gui/gtk3/dna_to_aminoacid_widget/dna_to_aminoacid_widget.rb +609 -0
  344. data/lib/bioroebe/gui/gtk3/dna_to_reverse_complement_widget/dna_to_reverse_complement_widget.config +6 -0
  345. data/lib/bioroebe/gui/gtk3/dna_to_reverse_complement_widget/dna_to_reverse_complement_widget.rb +189 -0
  346. data/lib/bioroebe/gui/gtk3/fasta_table_widget/fasta_table_widget.rb +245 -0
  347. data/lib/bioroebe/gui/gtk3/format_converter/format_converter.rb +346 -0
  348. data/lib/bioroebe/gui/gtk3/gene/gene.rb +182 -0
  349. data/lib/bioroebe/gui/gtk3/hamming_distance/hamming_distance.config +6 -0
  350. data/lib/bioroebe/gui/gtk3/hamming_distance/hamming_distance.rb +370 -0
  351. data/lib/bioroebe/gui/gtk3/levensthein_distance/levensthein_distance.config +6 -0
  352. data/lib/bioroebe/gui/gtk3/levensthein_distance/levensthein_distance.rb +175 -0
  353. data/lib/bioroebe/gui/gtk3/nucleotide_analyser/nucleotide_analyser.rb +428 -0
  354. data/lib/bioroebe/gui/gtk3/parse_pdb_file/parse_pdb_file.rb +342 -0
  355. data/lib/bioroebe/gui/gtk3/primer_design_widget/primer_design_widget.rb +580 -0
  356. data/lib/bioroebe/gui/gtk3/protein_to_DNA/protein_to_DNA.config +6 -0
  357. data/lib/bioroebe/gui/gtk3/protein_to_DNA/protein_to_DNA.rb +182 -0
  358. data/lib/bioroebe/gui/gtk3/random_sequence/random_sequence.rb +566 -0
  359. data/lib/bioroebe/gui/gtk3/restriction_enzymes/restriction_enzymes.config +6 -0
  360. data/lib/bioroebe/gui/gtk3/restriction_enzymes/restriction_enzymes.rb +329 -0
  361. data/lib/bioroebe/gui/gtk3/show_codon_table/misc.rb +556 -0
  362. data/lib/bioroebe/gui/gtk3/show_codon_table/show_codon_table.rb +171 -0
  363. data/lib/bioroebe/gui/gtk3/show_codon_usage/show_codon_usage.rb +146 -0
  364. data/lib/bioroebe/gui/gtk3/sizeseq/sizeseq.rb +207 -0
  365. data/lib/bioroebe/gui/gtk3/three_to_one/three_to_one.rb +279 -0
  366. data/lib/bioroebe/gui/gtk3/three_to_one/title.rb +23 -0
  367. data/lib/bioroebe/gui/gtk3/www_finder/www_finder.config +6 -0
  368. data/lib/bioroebe/gui/gtk3/www_finder/www_finder.rb +368 -0
  369. data/lib/bioroebe/gui/jruby/blosum_matrix_viewer/blosum_matrix_viewer.rb +82 -0
  370. data/lib/bioroebe/gui/libui/README.md +4 -0
  371. data/lib/bioroebe/gui/libui/alignment/alignment.rb +114 -0
  372. data/lib/bioroebe/gui/libui/blosum_matrix_viewer/blosum_matrix_viewer.rb +112 -0
  373. data/lib/bioroebe/gui/libui/calculate_cell_numbers_of_bacteria/calculate_cell_numbers_of_bacteria.rb +60 -0
  374. data/lib/bioroebe/gui/libui/dna_to_aminoacid_widget/dna_to_aminoacid_widget.rb +161 -0
  375. data/lib/bioroebe/gui/libui/dna_to_reverse_complement_widget/dna_to_reverse_complement_widget.rb +76 -0
  376. data/lib/bioroebe/gui/libui/hamming_distance/hamming_distance.rb +135 -0
  377. data/lib/bioroebe/gui/libui/levensthein_distance/levensthein_distance.rb +118 -0
  378. data/lib/bioroebe/gui/libui/protein_to_DNA/protein_to_DNA.rb +115 -0
  379. data/lib/bioroebe/gui/libui/random_sequence/random_sequence.rb +174 -0
  380. data/lib/bioroebe/gui/libui/show_codon_table/show_codon_table.rb +132 -0
  381. data/lib/bioroebe/gui/libui/show_codon_usage/show_codon_usage.rb +89 -0
  382. data/lib/bioroebe/gui/libui/three_to_one/three_to_one.rb +111 -0
  383. data/lib/bioroebe/gui/shared_code/blosum_matrix_viewer/blosum_matrix_viewer_module.rb +42 -0
  384. data/lib/bioroebe/gui/shared_code/calculate_cell_numbers_of_bacteria/calculate_cell_numbers_of_bacteria_module.rb +216 -0
  385. data/lib/bioroebe/gui/shared_code/dna_to_reverse_complement_widget/dna_to_reverse_complement_widget_module.rb +284 -0
  386. data/lib/bioroebe/gui/shared_code/levensthein_distance/levensthein_distance_module.rb +402 -0
  387. data/lib/bioroebe/gui/shared_code/protein_to_DNA/protein_to_DNA_module.rb +192 -0
  388. data/lib/bioroebe/gui/shared_code/show_codon_table/show_codon_table_module.rb +72 -0
  389. data/lib/bioroebe/gui/shared_code/show_codon_usage/show_codon_usage_module.rb +213 -0
  390. data/lib/bioroebe/gui/tk/aminoacid_composition/aminoacid_composition.rb +206 -0
  391. data/lib/bioroebe/gui/tk/blosum_matrix_viewer/blosum_matrix_viewer.rb +140 -0
  392. data/lib/bioroebe/gui/tk/hamming_distance/hamming_distance.rb +262 -0
  393. data/lib/bioroebe/gui/tk/levensthein_distance/levensthein_distance.rb +243 -0
  394. data/lib/bioroebe/gui/tk/three_to_one/three_to_one.rb +199 -0
  395. data/lib/bioroebe/gui/unified_widgets/anti_sense_strand/anti_sense_strand.rb +519 -0
  396. data/lib/bioroebe/images/BIOROEBE.png +0 -0
  397. data/lib/bioroebe/images/BIOROEBE_NEW_LOGO.png +0 -0
  398. data/lib/bioroebe/images/BlosumMatrixViewer.png +0 -0
  399. data/lib/bioroebe/images/DnaToAminoacidWidget.png +0 -0
  400. data/lib/bioroebe/images/PRINTED_AMINOACID_TABLE.png +0 -0
  401. data/lib/bioroebe/images/class_ConvertAminoacidToDNA.png +0 -0
  402. data/lib/bioroebe/images/class_SimpleStringComparer.png +0 -0
  403. data/lib/bioroebe/images/example_of_FASTA_coloured_output.png +0 -0
  404. data/lib/bioroebe/images/libui_hamming_distance_widget.png +0 -0
  405. data/lib/bioroebe/images/pretty_DNA_picture.png +0 -0
  406. data/lib/bioroebe/images/primer_design_widget.png +0 -0
  407. data/lib/bioroebe/images/restriction_enzyme_commandline_result.png +0 -0
  408. data/lib/bioroebe/images/ruby-gtk_three_to_one_widget.png +0 -0
  409. data/lib/bioroebe/images/small_DNA_logo.png +0 -0
  410. data/lib/bioroebe/images/small_drosophila_image.png +0 -0
  411. data/lib/bioroebe/java/README.md +6 -0
  412. data/lib/bioroebe/java/bioroebe/AllInOne.class +0 -0
  413. data/lib/bioroebe/java/bioroebe/AllInOne.java +214 -0
  414. data/lib/bioroebe/java/bioroebe/Base.class +0 -0
  415. data/lib/bioroebe/java/bioroebe/Base.java +102 -0
  416. data/lib/bioroebe/java/bioroebe/BisulfiteTreatment.class +0 -0
  417. data/lib/bioroebe/java/bioroebe/BisulfiteTreatment.java +23 -0
  418. data/lib/bioroebe/java/bioroebe/Cat.class +0 -0
  419. data/lib/bioroebe/java/bioroebe/Codons.class +0 -0
  420. data/lib/bioroebe/java/bioroebe/Codons.java +22 -0
  421. data/lib/bioroebe/java/bioroebe/Esystem.class +0 -0
  422. data/lib/bioroebe/java/bioroebe/Esystem.java +47 -0
  423. data/lib/bioroebe/java/bioroebe/GUI/BaseFrame.class +0 -0
  424. data/lib/bioroebe/java/bioroebe/GUI/BaseFrame.java +65 -0
  425. data/lib/bioroebe/java/bioroebe/GenerateRandomDnaSequence.class +0 -0
  426. data/lib/bioroebe/java/bioroebe/GenerateRandomDnaSequence.java +32 -0
  427. data/lib/bioroebe/java/bioroebe/IsPalindrome.class +0 -0
  428. data/lib/bioroebe/java/bioroebe/IsPalindrome.java +18 -0
  429. data/lib/bioroebe/java/bioroebe/PartnerNucleotide.class +0 -0
  430. data/lib/bioroebe/java/bioroebe/PartnerNucleotide.java +19 -0
  431. data/lib/bioroebe/java/bioroebe/README.md +4 -0
  432. data/lib/bioroebe/java/bioroebe/RemoveFile.class +0 -0
  433. data/lib/bioroebe/java/bioroebe/RemoveFile.java +24 -0
  434. data/lib/bioroebe/java/bioroebe/RemoveNumbers.class +0 -0
  435. data/lib/bioroebe/java/bioroebe/RemoveNumbers.java +14 -0
  436. data/lib/bioroebe/java/bioroebe/SanitizeNucleotideSequence.class +0 -0
  437. data/lib/bioroebe/java/bioroebe/SanitizeNucleotideSequence.java +20 -0
  438. data/lib/bioroebe/java/bioroebe/SaveFile.java +44 -0
  439. data/lib/bioroebe/java/bioroebe/Sequence.java +28 -0
  440. data/lib/bioroebe/java/bioroebe/ToCamelcase.class +0 -0
  441. data/lib/bioroebe/java/bioroebe/ToCamelcase.java +32 -0
  442. data/lib/bioroebe/java/bioroebe/ToplevelMethods.class +0 -0
  443. data/lib/bioroebe/java/bioroebe/ToplevelMethods.java +15 -0
  444. data/lib/bioroebe/java/bioroebe/enums/DNA.java +6 -0
  445. data/lib/bioroebe/java/bioroebe.jar +0 -0
  446. data/lib/bioroebe/matplotlib/matplotlib_generator.rb +104 -0
  447. data/lib/bioroebe/misc/quiz/README.md +6 -0
  448. data/lib/bioroebe/misc/quiz/three_letter_to_aminoacid.rb +163 -0
  449. data/lib/bioroebe/misc/ruler.rb +244 -0
  450. data/lib/bioroebe/misc/useful_formulas.rb +129 -0
  451. data/lib/bioroebe/ncbi/efetch.rb +253 -0
  452. data/lib/bioroebe/ncbi/ncbi.rb +93 -0
  453. data/lib/bioroebe/ngs/README.md +2 -0
  454. data/lib/bioroebe/ngs/phred_quality_score_table.rb +123 -0
  455. data/lib/bioroebe/nucleotides/complementary_dna_strand.rb +166 -0
  456. data/lib/bioroebe/nucleotides/molecular_weight_of_nucleotides.rb +135 -0
  457. data/lib/bioroebe/nucleotides/most_likely_nucleotide_sequence_for_this_aminoacid_sequence.rb +198 -0
  458. data/lib/bioroebe/nucleotides/sanitize_nucleotide_sequence.rb +133 -0
  459. data/lib/bioroebe/nucleotides/show_nucleotide_sequence.rb +556 -0
  460. data/lib/bioroebe/palindromes/palindrome_2D_structure.rb +139 -0
  461. data/lib/bioroebe/palindromes/palindrome_finder.rb +208 -0
  462. data/lib/bioroebe/palindromes/palindrome_generator.rb +272 -0
  463. data/lib/bioroebe/parsers/biolang_parser.rb +156 -0
  464. data/lib/bioroebe/parsers/blosum_parser.rb +222 -0
  465. data/lib/bioroebe/parsers/genbank_parser.rb +78 -0
  466. data/lib/bioroebe/parsers/gff.rb +346 -0
  467. data/lib/bioroebe/parsers/parse_embl.rb +76 -0
  468. data/lib/bioroebe/parsers/stride_parser.rb +117 -0
  469. data/lib/bioroebe/patterns/README.md +5 -0
  470. data/lib/bioroebe/patterns/analyse_glycosylation_pattern.rb +149 -0
  471. data/lib/bioroebe/patterns/is_this_sequence_a_EGF2_pattern.rb +66 -0
  472. data/lib/bioroebe/patterns/profile_pattern.rb +182 -0
  473. data/lib/bioroebe/patterns/rgg_scanner.rb +160 -0
  474. data/lib/bioroebe/patterns/scan_for_repeat.rb +157 -0
  475. data/lib/bioroebe/pdb/download_this_pdb.rb +67 -0
  476. data/lib/bioroebe/pdb/fetch_fasta_sequence_from_pdb.rb +164 -0
  477. data/lib/bioroebe/pdb/parse_mmCIF_file.rb +63 -0
  478. data/lib/bioroebe/pdb/parse_pdb_file.rb +1086 -0
  479. data/lib/bioroebe/pdb/report_secondary_structures_from_this_pdb_file.rb +225 -0
  480. data/lib/bioroebe/perl/README.md +7 -0
  481. data/lib/bioroebe/perl/local_to_global.pl +694 -0
  482. data/lib/bioroebe/project/project.rb +264 -0
  483. data/lib/bioroebe/protein_structure/alpha_helix.rb +96 -0
  484. data/lib/bioroebe/protein_structure/helical_wheel.rb +205 -0
  485. data/lib/bioroebe/raw_sequence/README.md +17 -0
  486. data/lib/bioroebe/raw_sequence/raw_sequence.rb +557 -0
  487. data/lib/bioroebe/readline/README.md +2 -0
  488. data/lib/bioroebe/readline/readline.rb +31 -0
  489. data/lib/bioroebe/regexes/README.md +2 -0
  490. data/lib/bioroebe/regexes/regexes.rb +34 -0
  491. data/lib/bioroebe/requires/commandline_application.rb +5 -0
  492. data/lib/bioroebe/requires/require_all_aminoacids_files.rb +28 -0
  493. data/lib/bioroebe/requires/require_all_calculate_files.rb +26 -0
  494. data/lib/bioroebe/requires/require_all_codon_files.rb +26 -0
  495. data/lib/bioroebe/requires/require_all_colour_scheme_files.rb +26 -0
  496. data/lib/bioroebe/requires/require_all_count_files.rb +26 -0
  497. data/lib/bioroebe/requires/require_all_dotplot_files.rb +28 -0
  498. data/lib/bioroebe/requires/require_all_electron_microscopy_files.rb +26 -0
  499. data/lib/bioroebe/requires/require_all_enzymes_files.rb +28 -0
  500. data/lib/bioroebe/requires/require_all_fasta_and_fastq_files.rb +32 -0
  501. data/lib/bioroebe/requires/require_all_nucleotides_files.rb +28 -0
  502. data/lib/bioroebe/requires/require_all_palindromes_files.rb +29 -0
  503. data/lib/bioroebe/requires/require_all_parser_files.rb +28 -0
  504. data/lib/bioroebe/requires/require_all_pattern_files.rb +29 -0
  505. data/lib/bioroebe/requires/require_all_pdb_files.rb +26 -0
  506. data/lib/bioroebe/requires/require_all_sequence_files.rb +26 -0
  507. data/lib/bioroebe/requires/require_all_string_matching_files.rb +28 -0
  508. data/lib/bioroebe/requires/require_all_svg_files.rb +12 -0
  509. data/lib/bioroebe/requires/require_all_taxonomy_files.rb +35 -0
  510. data/lib/bioroebe/requires/require_all_utility_scripts_files.rb +32 -0
  511. data/lib/bioroebe/requires/require_cleave_and_digest.rb +24 -0
  512. data/lib/bioroebe/requires/require_colours.rb +20 -0
  513. data/lib/bioroebe/requires/require_encoding.rb +7 -0
  514. data/lib/bioroebe/requires/require_sequence.rb +7 -0
  515. data/lib/bioroebe/requires/require_the_bioroebe_project.rb +162 -0
  516. data/lib/bioroebe/requires/require_the_bioroebe_shell.rb +7 -0
  517. data/lib/bioroebe/requires/require_the_bioroebe_sinatra_components.rb +7 -0
  518. data/lib/bioroebe/requires/require_the_constants.rb +23 -0
  519. data/lib/bioroebe/requires/require_the_toplevel_methods.rb +29 -0
  520. data/lib/bioroebe/requires/require_yaml.rb +94 -0
  521. data/lib/bioroebe/sequence/alignment.rb +214 -0
  522. data/lib/bioroebe/sequence/dna.rb +211 -0
  523. data/lib/bioroebe/sequence/nucleotide_module/nucleotide_module.rb +404 -0
  524. data/lib/bioroebe/sequence/protein.rb +281 -0
  525. data/lib/bioroebe/sequence/reverse_complement.rb +148 -0
  526. data/lib/bioroebe/sequence/sequence.rb +706 -0
  527. data/lib/bioroebe/shell/add.rb +108 -0
  528. data/lib/bioroebe/shell/assign.rb +360 -0
  529. data/lib/bioroebe/shell/chop_and_cut.rb +281 -0
  530. data/lib/bioroebe/shell/colours/colours.rb +235 -0
  531. data/lib/bioroebe/shell/configuration/additionally_set_xorg_buffer.yml +1 -0
  532. data/lib/bioroebe/shell/configuration/may_we_show_the_startup_information.yml +1 -0
  533. data/lib/bioroebe/shell/configuration/upcase_nucleotides.yml +1 -0
  534. data/lib/bioroebe/shell/configuration/use_silent_startup.yml +1 -0
  535. data/lib/bioroebe/shell/constants.rb +166 -0
  536. data/lib/bioroebe/shell/download.rb +335 -0
  537. data/lib/bioroebe/shell/enable_and_disable.rb +158 -0
  538. data/lib/bioroebe/shell/enzymes.rb +310 -0
  539. data/lib/bioroebe/shell/fasta.rb +345 -0
  540. data/lib/bioroebe/shell/gtk.rb +76 -0
  541. data/lib/bioroebe/shell/help/class.rb +443 -0
  542. data/lib/bioroebe/shell/help/help.rb +25 -0
  543. data/lib/bioroebe/shell/history.rb +132 -0
  544. data/lib/bioroebe/shell/initialize.rb +217 -0
  545. data/lib/bioroebe/shell/loop.rb +74 -0
  546. data/lib/bioroebe/shell/menu.rb +5320 -0
  547. data/lib/bioroebe/shell/misc.rb +4341 -0
  548. data/lib/bioroebe/shell/prompt.rb +107 -0
  549. data/lib/bioroebe/shell/random.rb +289 -0
  550. data/lib/bioroebe/shell/readline/readline.rb +91 -0
  551. data/lib/bioroebe/shell/reset.rb +335 -0
  552. data/lib/bioroebe/shell/scan_and_parse.rb +135 -0
  553. data/lib/bioroebe/shell/search.rb +337 -0
  554. data/lib/bioroebe/shell/sequences.rb +200 -0
  555. data/lib/bioroebe/shell/shell.rb +41 -0
  556. data/lib/bioroebe/shell/show_report_and_display.rb +2901 -0
  557. data/lib/bioroebe/shell/startup.rb +127 -0
  558. data/lib/bioroebe/shell/taxonomy.rb +14 -0
  559. data/lib/bioroebe/shell/tk.rb +23 -0
  560. data/lib/bioroebe/shell/user_input.rb +88 -0
  561. data/lib/bioroebe/shell/xorg.rb +45 -0
  562. data/lib/bioroebe/siRNA/README.md +2 -0
  563. data/lib/bioroebe/siRNA/siRNA.rb +93 -0
  564. data/lib/bioroebe/string_matching/README.md +13 -0
  565. data/lib/bioroebe/string_matching/find_longest_substring.rb +162 -0
  566. data/lib/bioroebe/string_matching/find_longest_substring_via_LCS_algorithm.rb +175 -0
  567. data/lib/bioroebe/string_matching/hamming_distance.rb +313 -0
  568. data/lib/bioroebe/string_matching/levensthein.rb +698 -0
  569. data/lib/bioroebe/string_matching/simple_string_comparer.rb +294 -0
  570. data/lib/bioroebe/string_matching/smith_waterman.rb +276 -0
  571. data/lib/bioroebe/svg/README.md +1 -0
  572. data/lib/bioroebe/svg/glyph.rb +719 -0
  573. data/lib/bioroebe/svg/mini_feature.rb +111 -0
  574. data/lib/bioroebe/svg/page.rb +570 -0
  575. data/lib/bioroebe/svg/primitive.rb +70 -0
  576. data/lib/bioroebe/svg/svgee.rb +326 -0
  577. data/lib/bioroebe/svg/track.rb +263 -0
  578. data/lib/bioroebe/taxonomy/README.md +1 -0
  579. data/lib/bioroebe/taxonomy/chart.rb +95 -0
  580. data/lib/bioroebe/taxonomy/class_methods.rb +181 -0
  581. data/lib/bioroebe/taxonomy/colours.rb +26 -0
  582. data/lib/bioroebe/taxonomy/constants.rb +218 -0
  583. data/lib/bioroebe/taxonomy/edit.rb +97 -0
  584. data/lib/bioroebe/taxonomy/help/help.rb +65 -0
  585. data/lib/bioroebe/taxonomy/help/helpline.rb +53 -0
  586. data/lib/bioroebe/taxonomy/info/check_available.rb +143 -0
  587. data/lib/bioroebe/taxonomy/info/info.rb +337 -0
  588. data/lib/bioroebe/taxonomy/info/is_dna.rb +150 -0
  589. data/lib/bioroebe/taxonomy/interactive.rb +1933 -0
  590. data/lib/bioroebe/taxonomy/menu.rb +905 -0
  591. data/lib/bioroebe/taxonomy/node.rb +118 -0
  592. data/lib/bioroebe/taxonomy/parse_fasta.rb +383 -0
  593. data/lib/bioroebe/taxonomy/shared.rb +287 -0
  594. data/lib/bioroebe/taxonomy/taxonomy.rb +521 -0
  595. data/lib/bioroebe/toplevel_methods/ad_hoc_task.rb +56 -0
  596. data/lib/bioroebe/toplevel_methods/aminoacids_and_proteins.rb +715 -0
  597. data/lib/bioroebe/toplevel_methods/atomic_composition.rb +198 -0
  598. data/lib/bioroebe/toplevel_methods/base_composition.rb +121 -0
  599. data/lib/bioroebe/toplevel_methods/blast.rb +153 -0
  600. data/lib/bioroebe/toplevel_methods/calculate_n50_value.rb +57 -0
  601. data/lib/bioroebe/toplevel_methods/cat.rb +71 -0
  602. data/lib/bioroebe/toplevel_methods/chunked_display.rb +92 -0
  603. data/lib/bioroebe/toplevel_methods/cliner.rb +81 -0
  604. data/lib/bioroebe/toplevel_methods/complement.rb +58 -0
  605. data/lib/bioroebe/toplevel_methods/convert_global_env.rb +39 -0
  606. data/lib/bioroebe/toplevel_methods/databases.rb +73 -0
  607. data/lib/bioroebe/toplevel_methods/delimiter.rb +19 -0
  608. data/lib/bioroebe/toplevel_methods/digest.rb +71 -0
  609. data/lib/bioroebe/toplevel_methods/download_and_fetch_data.rb +146 -0
  610. data/lib/bioroebe/toplevel_methods/e.rb +20 -0
  611. data/lib/bioroebe/toplevel_methods/editor.rb +21 -0
  612. data/lib/bioroebe/toplevel_methods/esystem.rb +22 -0
  613. data/lib/bioroebe/toplevel_methods/exponential_growth.rb +74 -0
  614. data/lib/bioroebe/toplevel_methods/extract.rb +56 -0
  615. data/lib/bioroebe/toplevel_methods/fasta_and_fastq.rb +353 -0
  616. data/lib/bioroebe/toplevel_methods/file_and_directory_related_actions.rb +257 -0
  617. data/lib/bioroebe/toplevel_methods/frequencies.rb +92 -0
  618. data/lib/bioroebe/toplevel_methods/hamming_distance.rb +60 -0
  619. data/lib/bioroebe/toplevel_methods/infer.rb +66 -0
  620. data/lib/bioroebe/toplevel_methods/is_on_roebe.rb +39 -0
  621. data/lib/bioroebe/toplevel_methods/leading_five_prime_and_trailing_three_prime.rb +101 -0
  622. data/lib/bioroebe/toplevel_methods/levensthein.rb +63 -0
  623. data/lib/bioroebe/toplevel_methods/log_directory.rb +109 -0
  624. data/lib/bioroebe/toplevel_methods/longest_common_substring.rb +55 -0
  625. data/lib/bioroebe/toplevel_methods/map_ncbi_entry_to_eutils_id.rb +88 -0
  626. data/lib/bioroebe/toplevel_methods/matches.rb +259 -0
  627. data/lib/bioroebe/toplevel_methods/misc.rb +432 -0
  628. data/lib/bioroebe/toplevel_methods/nucleotides.rb +715 -0
  629. data/lib/bioroebe/toplevel_methods/number_of_clones.rb +63 -0
  630. data/lib/bioroebe/toplevel_methods/open_in_browser.rb +77 -0
  631. data/lib/bioroebe/toplevel_methods/open_reading_frames.rb +236 -0
  632. data/lib/bioroebe/toplevel_methods/opn.rb +34 -0
  633. data/lib/bioroebe/toplevel_methods/palindromes.rb +127 -0
  634. data/lib/bioroebe/toplevel_methods/parse.rb +59 -0
  635. data/lib/bioroebe/toplevel_methods/phred_error_probability.rb +68 -0
  636. data/lib/bioroebe/toplevel_methods/rds.rb +24 -0
  637. data/lib/bioroebe/toplevel_methods/remove.rb +86 -0
  638. data/lib/bioroebe/toplevel_methods/return_source_code_of_this_method.rb +35 -0
  639. data/lib/bioroebe/toplevel_methods/return_subsequence_based_on_indices.rb +68 -0
  640. data/lib/bioroebe/toplevel_methods/rna_splicing.rb +73 -0
  641. data/lib/bioroebe/toplevel_methods/rnalfold.rb +69 -0
  642. data/lib/bioroebe/toplevel_methods/searching_and_finding.rb +116 -0
  643. data/lib/bioroebe/toplevel_methods/shuffleseq.rb +37 -0
  644. data/lib/bioroebe/toplevel_methods/statistics.rb +53 -0
  645. data/lib/bioroebe/toplevel_methods/sum_of_odd_integers.rb +62 -0
  646. data/lib/bioroebe/toplevel_methods/taxonomy.rb +187 -0
  647. data/lib/bioroebe/toplevel_methods/three_delimiter.rb +34 -0
  648. data/lib/bioroebe/toplevel_methods/time_and_date.rb +53 -0
  649. data/lib/bioroebe/toplevel_methods/to_camelcase.rb +26 -0
  650. data/lib/bioroebe/toplevel_methods/truncate.rb +48 -0
  651. data/lib/bioroebe/toplevel_methods/url.rb +36 -0
  652. data/lib/bioroebe/toplevel_methods/verbose.rb +59 -0
  653. data/lib/bioroebe/utility_scripts/align_open_reading_frames.rb +191 -0
  654. data/lib/bioroebe/utility_scripts/analyse_local_dataset.rb +119 -0
  655. data/lib/bioroebe/utility_scripts/check_for_mismatches/check_for_mismatches.rb +230 -0
  656. data/lib/bioroebe/utility_scripts/compacter.rb +131 -0
  657. data/lib/bioroebe/utility_scripts/compseq/compseq.rb +529 -0
  658. data/lib/bioroebe/utility_scripts/consensus_sequence.rb +374 -0
  659. data/lib/bioroebe/utility_scripts/create_batch_entrez_file.rb +130 -0
  660. data/lib/bioroebe/utility_scripts/determine_antigenic_areas.rb +115 -0
  661. data/lib/bioroebe/utility_scripts/determine_missing_nucleotides_percentage.rb +137 -0
  662. data/lib/bioroebe/utility_scripts/display_open_reading_frames/determine.rb +73 -0
  663. data/lib/bioroebe/utility_scripts/display_open_reading_frames/display_open_reading_frames.rb +31 -0
  664. data/lib/bioroebe/utility_scripts/display_open_reading_frames/initialize.rb +37 -0
  665. data/lib/bioroebe/utility_scripts/display_open_reading_frames/menu.rb +49 -0
  666. data/lib/bioroebe/utility_scripts/display_open_reading_frames/misc.rb +471 -0
  667. data/lib/bioroebe/utility_scripts/display_open_reading_frames/report.rb +113 -0
  668. data/lib/bioroebe/utility_scripts/display_open_reading_frames/reset.rb +56 -0
  669. data/lib/bioroebe/utility_scripts/dot_alignment.rb +177 -0
  670. data/lib/bioroebe/utility_scripts/download_files_from_rebase.rb +72 -0
  671. data/lib/bioroebe/utility_scripts/find_gene.rb +202 -0
  672. data/lib/bioroebe/utility_scripts/mirror_repeat.rb +235 -0
  673. data/lib/bioroebe/utility_scripts/move_file_to_its_correct_location.rb +151 -0
  674. data/lib/bioroebe/utility_scripts/parse_taxonomy.rb +168 -0
  675. data/lib/bioroebe/utility_scripts/pathways.rb +152 -0
  676. data/lib/bioroebe/utility_scripts/permutations.rb +145 -0
  677. data/lib/bioroebe/utility_scripts/punnet/punnet.rb +126 -0
  678. data/lib/bioroebe/utility_scripts/show_this_dna_sequence.rb +148 -0
  679. data/lib/bioroebe/utility_scripts/showorf/constants.rb +36 -0
  680. data/lib/bioroebe/utility_scripts/showorf/help.rb +33 -0
  681. data/lib/bioroebe/utility_scripts/showorf/initialize.rb +52 -0
  682. data/lib/bioroebe/utility_scripts/showorf/menu.rb +68 -0
  683. data/lib/bioroebe/utility_scripts/showorf/reset.rb +39 -0
  684. data/lib/bioroebe/utility_scripts/showorf/run.rb +152 -0
  685. data/lib/bioroebe/utility_scripts/showorf/show.rb +97 -0
  686. data/lib/bioroebe/utility_scripts/showorf/showorf.rb +488 -0
  687. data/lib/bioroebe/version/version.rb +44 -0
  688. data/lib/bioroebe/viennarna/README.md +3 -0
  689. data/lib/bioroebe/viennarna/rnafold_wrapper.rb +196 -0
  690. data/lib/bioroebe/with_gui.rb +18 -0
  691. data/lib/bioroebe/www/bioroebe.cgi +44 -0
  692. data/lib/bioroebe/www/embeddable_interface.rb +686 -0
  693. data/lib/bioroebe/www/sinatra/sinatra.rb +1013 -0
  694. data/lib/bioroebe/yaml/agarose/agarose_concentrations.yml +21 -0
  695. data/lib/bioroebe/yaml/aminoacids/amino_acids.yml +92 -0
  696. data/lib/bioroebe/yaml/aminoacids/amino_acids_abbreviations.yml +31 -0
  697. data/lib/bioroebe/yaml/aminoacids/amino_acids_average_mass_table.yml +33 -0
  698. data/lib/bioroebe/yaml/aminoacids/amino_acids_classification.yml +18 -0
  699. data/lib/bioroebe/yaml/aminoacids/amino_acids_english.yml +26 -0
  700. data/lib/bioroebe/yaml/aminoacids/amino_acids_frequency.yml +44 -0
  701. data/lib/bioroebe/yaml/aminoacids/amino_acids_long_name_to_one_letter.yml +61 -0
  702. data/lib/bioroebe/yaml/aminoacids/amino_acids_molecular_formula.yml +32 -0
  703. data/lib/bioroebe/yaml/aminoacids/amino_acids_monoisotopic_mass_table.yml +38 -0
  704. data/lib/bioroebe/yaml/aminoacids/amino_acids_reste.yml +35 -0
  705. data/lib/bioroebe/yaml/aminoacids/amino_acids_three_to_one.yml +34 -0
  706. data/lib/bioroebe/yaml/aminoacids/hydropathy_table.yml +44 -0
  707. data/lib/bioroebe/yaml/aminoacids/molecular_weight.yml +29 -0
  708. data/lib/bioroebe/yaml/aminoacids/simple_aminoacids.yml +66 -0
  709. data/lib/bioroebe/yaml/aminoacids/weight_of_common_proteins.yml +33 -0
  710. data/lib/bioroebe/yaml/antisense/antisense.yml +9 -0
  711. data/lib/bioroebe/yaml/base_composition_of_dna.yml +37 -0
  712. data/lib/bioroebe/yaml/blosum/blosum45.yml +36 -0
  713. data/lib/bioroebe/yaml/blosum/blosum50.yml +34 -0
  714. data/lib/bioroebe/yaml/blosum/blosum62.yml +35 -0
  715. data/lib/bioroebe/yaml/blosum/blosum80.yml +37 -0
  716. data/lib/bioroebe/yaml/blosum/blosum90.yml +36 -0
  717. data/lib/bioroebe/yaml/blosum/blosum_matrix.yml +200 -0
  718. data/lib/bioroebe/yaml/chromosomes/chromosome_numbers.yml +30 -0
  719. data/lib/bioroebe/yaml/codon_tables/1.yml +113 -0
  720. data/lib/bioroebe/yaml/codon_tables/10.yml +89 -0
  721. data/lib/bioroebe/yaml/codon_tables/11.yml +91 -0
  722. data/lib/bioroebe/yaml/codon_tables/12.yml +89 -0
  723. data/lib/bioroebe/yaml/codon_tables/13.yml +89 -0
  724. data/lib/bioroebe/yaml/codon_tables/14.yml +89 -0
  725. data/lib/bioroebe/yaml/codon_tables/15.yml +94 -0
  726. data/lib/bioroebe/yaml/codon_tables/16.yml +89 -0
  727. data/lib/bioroebe/yaml/codon_tables/2.yml +86 -0
  728. data/lib/bioroebe/yaml/codon_tables/21.yml +89 -0
  729. data/lib/bioroebe/yaml/codon_tables/22.yml +89 -0
  730. data/lib/bioroebe/yaml/codon_tables/23.yml +91 -0
  731. data/lib/bioroebe/yaml/codon_tables/24.yml +89 -0
  732. data/lib/bioroebe/yaml/codon_tables/25.yml +89 -0
  733. data/lib/bioroebe/yaml/codon_tables/26.yml +96 -0
  734. data/lib/bioroebe/yaml/codon_tables/27.yml +104 -0
  735. data/lib/bioroebe/yaml/codon_tables/28.yml +97 -0
  736. data/lib/bioroebe/yaml/codon_tables/29.yml +93 -0
  737. data/lib/bioroebe/yaml/codon_tables/3.yml +98 -0
  738. data/lib/bioroebe/yaml/codon_tables/30.yml +91 -0
  739. data/lib/bioroebe/yaml/codon_tables/31.yml +94 -0
  740. data/lib/bioroebe/yaml/codon_tables/33.yml +101 -0
  741. data/lib/bioroebe/yaml/codon_tables/4.yml +96 -0
  742. data/lib/bioroebe/yaml/codon_tables/5.yml +100 -0
  743. data/lib/bioroebe/yaml/codon_tables/6.yml +96 -0
  744. data/lib/bioroebe/yaml/codon_tables/9.yml +97 -0
  745. data/lib/bioroebe/yaml/codon_tables/overview.yml +42 -0
  746. data/lib/bioroebe/yaml/configuration/README.md +12 -0
  747. data/lib/bioroebe/yaml/configuration/browser.yml +1 -0
  748. data/lib/bioroebe/yaml/configuration/colourize_fasta_sequences.yml +14 -0
  749. data/lib/bioroebe/yaml/configuration/default_colours_for_the_aminoacids.yml +28 -0
  750. data/lib/bioroebe/yaml/configuration/temp_dir.yml +1 -0
  751. data/lib/bioroebe/yaml/configuration/try_to_use_matplotlib.yml +1 -0
  752. data/lib/bioroebe/yaml/configuration/use_opn.yml +1 -0
  753. data/lib/bioroebe/yaml/configuration/use_this_database.yml +1 -0
  754. data/lib/bioroebe/yaml/create_these_directories_on_startup/create_these_directories_on_startup.yml +9 -0
  755. data/lib/bioroebe/yaml/default_dna_input.yml +3 -0
  756. data/lib/bioroebe/yaml/enzymes/enzyme_classes.yml +15 -0
  757. data/lib/bioroebe/yaml/enzymes/pH-Optima.yml +11 -0
  758. data/lib/bioroebe/yaml/fasta_and_fastq/fastq_quality_schemes.yml +44 -0
  759. data/lib/bioroebe/yaml/genomes/README.md +16 -0
  760. data/lib/bioroebe/yaml/humans/README.md +2 -0
  761. data/lib/bioroebe/yaml/humans/human_chromosomes.yml +53 -0
  762. data/lib/bioroebe/yaml/laboratory/README.md +1 -0
  763. data/lib/bioroebe/yaml/laboratory/pipettes.yml +8 -0
  764. data/lib/bioroebe/yaml/mRNA/mRNA.yml +16 -0
  765. data/lib/bioroebe/yaml/nuclear_localization_sequences.yml +15 -0
  766. data/lib/bioroebe/yaml/nucleotides/abbreviations_for_nucleotides.yml +29 -0
  767. data/lib/bioroebe/yaml/nucleotides/nucleotide_density.yml +10 -0
  768. data/lib/bioroebe/yaml/nucleotides/nucleotides.yml +34 -0
  769. data/lib/bioroebe/yaml/nucleotides/nucleotides_weight.yml +12 -0
  770. data/lib/bioroebe/yaml/pathways/README.md +2 -0
  771. data/lib/bioroebe/yaml/pathways/citric_acid_cycle.yml +16 -0
  772. data/lib/bioroebe/yaml/pathways/glycolysis.yml +20 -0
  773. data/lib/bioroebe/yaml/pathways/shikimate_pathway.yml +23 -0
  774. data/lib/bioroebe/yaml/pathways/urea_cycle.yml +11 -0
  775. data/lib/bioroebe/yaml/primers/README.md +4 -0
  776. data/lib/bioroebe/yaml/primers/primers.yml +3 -0
  777. data/lib/bioroebe/yaml/promoters/35S.yml +15 -0
  778. data/lib/bioroebe/yaml/promoters/strong_promoters.yml +24 -0
  779. data/lib/bioroebe/yaml/proteases/proteases.yml +3 -0
  780. data/lib/bioroebe/yaml/proteins/ubiquitin.yml +4 -0
  781. data/lib/bioroebe/yaml/remote_urls/README.md +4 -0
  782. data/lib/bioroebe/yaml/remote_urls/remote_urls.yml +3 -0
  783. data/lib/bioroebe/yaml/restriction_enzymes/restriction_enzymes.yml +630 -0
  784. data/lib/bioroebe/yaml/sequences/JX472995_Green_fluorescent_protein_from_Aequorea_victoria.fasta +14 -0
  785. data/lib/bioroebe/yaml/sequences/README.md +2 -0
  786. data/lib/bioroebe/yaml/talens.yml +22 -0
  787. data/lib/bioroebe/yaml/viruses/ecoli_phages.yml +63 -0
  788. data/lib/bioroebe/yaml/viruses/viruses.yml +6 -0
  789. data/lib/bioroebe.rb +5 -0
  790. data/spec/testing_toplevel_method_editor.rb +20 -0
  791. data/spec/testing_toplevel_method_url.rb +15 -0
  792. data/spec/testing_toplevel_method_verbose.rb +13 -0
  793. data/test/advanced_svg_example.rb +307 -0
  794. data/test/testing_bioroebe.rb +25 -0
  795. data/test/testing_codons.rb +45 -0
  796. data/test/testing_dna_to_rna_conversion.rb +15 -0
  797. data/test/testing_parse_pdb_file.rb +23 -0
  798. data/test/testing_reverse_complement.rb +32 -0
  799. data/test/testing_svg_component_of_bioroebe.rb +311 -0
  800. data/test/testing_svg_component_of_bioroebe_from_json_dataset.rb +34 -0
  801. data/test/testing_taxonomy.rb +22 -0
  802. metadata +1059 -0
@@ -0,0 +1,715 @@
1
+ #!/usr/bin/ruby -w
2
+ # Encoding: UTF-8
3
+ # frozen_string_literal: true
4
+ # =========================================================================== #
5
+ # require 'bioroebe/toplevel_methods/aminoacids_and_proteins.rb'
6
+ # puts Bioroebe.colourize_this_aminoacid_sequence_for_the_commandline('NLKRSPTHY')
7
+ # Bioroebe.upcase_this_aminoacid_sequence_and_remove_numbers
8
+ # Bioroebe.parse_this_prosite_pattern
9
+ # Bioroebe.weight_of_this_aminoacid?
10
+ # Bioroebe.strict_filter_away_invalid_aminoacids(ARGV)
11
+ # Bioroebe.three_to_one(ARGV)
12
+ # Bioroebe.return_short_aminoacid_letter_from_long_aminoacid_name('lysine') # => "K"
13
+ # Bioroebe.return_the_most_likely_codon_sequence_for_this_aminoacid_sequence
14
+ # Bioroebe.sort_aminoacid_based_on_its_hydrophobicity(ARGV)
15
+ # =========================================================================== #
16
+ module Bioroebe
17
+
18
+ require 'bioroebe/toplevel_methods/e.rb'
19
+ require 'bioroebe/constants/files_and_directories.rb'
20
+ require 'bioroebe/colours/colours.rb'
21
+ require 'bioroebe/requires/require_yaml.rb'
22
+
23
+ # ========================================================================= #
24
+ # === @array_colourize_this_aminoacid
25
+ #
26
+ # These aminoacids must be colourized in red.
27
+ # ========================================================================= #
28
+ @array_colourize_this_aminoacid = []
29
+
30
+ # ========================================================================= #
31
+ # === Bioroebe.clear_array_colourize_this_aminoacid
32
+ # ========================================================================= #
33
+ def self.clear_array_colourize_this_aminoacid
34
+ @array_colourize_this_aminoacid = []
35
+ end
36
+
37
+ # ========================================================================= #
38
+ # === Bioroebe.array_colourize_this_aminoacid
39
+ #
40
+ # Query as to which aminoacid we will colourize, if any at all.
41
+ # ========================================================================= #
42
+ def self.array_colourize_this_aminoacid
43
+ @array_colourize_this_aminoacid
44
+ end; self.instance_eval { alias array_colourize_this_aminoacid? array_colourize_this_aminoacid } # === Bioroebe.array_colourize_this_aminoacid?
45
+
46
+ # ========================================================================= #
47
+ # === Bioroebe.three_to_one
48
+ #
49
+ # This method will convert from e. g. "THR" to "T" - aka the one-letter
50
+ # abbreviation for the aminoacid threonine.
51
+ #
52
+ # That way this method acts as the sister method to the other method
53
+ # that gives us three letters from ONE letter, sort of. Taken together,
54
+ # these two methods form a corresponding dual-pair there, yin/yang,
55
+ # from 3-to-1 and from 1-to-3.
56
+ #
57
+ # Behaviour of this method:
58
+ #
59
+ # This method will translate "Lys" into "L", and the other
60
+ # corresponding aminoacids into their one-letter abbreviation.
61
+ #
62
+ # The input to this method should be a String.
63
+ #
64
+ # The output will not contain any '-' character by default, even if
65
+ # the input came with '-' characters. The reason why this is the
66
+ # default is because the most common use cases may wish to continue
67
+ # to work with the one-letter abbreviation instead, which is much
68
+ # more common than the three-letter abbreviation.
69
+ # ========================================================================= #
70
+ def self.three_to_one(i)
71
+ _ = ''.dup
72
+ if i
73
+ if i.is_a? Array
74
+ i = i.join
75
+ end
76
+ if i =~ /gui/i
77
+ require 'bioroebe/gui/gtk3/three_to_one/three_to_one.rb'
78
+ Bioroebe::GUI::Gtk::ThreeToOne.run # three_to_one --gui
79
+ return
80
+ end
81
+ if i.include? '-'
82
+ i = i.dup if i.frozen?
83
+ i.delete!('-')
84
+ end
85
+ dataset = AMINO_ACIDS_THREE_TO_ONE
86
+ # ===================================================================== #
87
+ # The table keeps the members in a downcase variant, hence why we
88
+ # also apply .downcase next. The above dataset will keep the hash
89
+ # keys in a downcased variant as-is.
90
+ # ===================================================================== #
91
+ scanned = i.scan(/.../).map(&:downcase)
92
+ scanned.each {|key|
93
+ if dataset.has_key? key
94
+ match = dataset[key]
95
+ _ << match
96
+ end
97
+ }
98
+ end
99
+ return _
100
+ end; self.instance_eval { alias three_letters_to_one_letter three_to_one } # === Bioroebe.three_letters_to_one_letter
101
+
102
+ # ========================================================================= #
103
+ # === Bioroebe.colourize_this_aminoacid_sequence_for_the_commandline
104
+ #
105
+ # This method uses some hardcoded colour assignments to the 20
106
+ # different aminoacids.
107
+ #
108
+ # Usage example:
109
+ #
110
+ # puts Bioroebe.colourize_this_aminoacid_sequence_for_the_commandline('NLKRSPTHY')
111
+ #
112
+ # ========================================================================= #
113
+ def self.colourize_this_aminoacid_sequence_for_the_commandline(i)
114
+ if i.is_a? Array
115
+ i = i.join
116
+ end
117
+ dataset = YAML.load_file(FILE_DEFAULT_COLOURS_FOR_THE_AMINOACIDS)
118
+ array_of_allowed_aminoacids = %w( A R N D B C E Q Z G H I L K M F P S T W Y V )
119
+ _ = ''.dup
120
+ splitted = i.chars
121
+ splitted.each {|this_aminoacid|
122
+ case this_aminoacid
123
+ when *array_of_allowed_aminoacids
124
+ this_aminoacid = send(dataset[this_aminoacid.to_s], this_aminoacid)
125
+ # else # else it will not be colourized.
126
+ end
127
+ _ << this_aminoacid
128
+ }
129
+ return _
130
+ end
131
+
132
+ # ========================================================================= #
133
+ # === Bioroebe.remove_invalid_aminoacids
134
+ #
135
+ # This method will filter away invalid aminoacids such as "U".
136
+ # "U" is not a valid aminoacid.
137
+ #
138
+ # Usage example:
139
+ #
140
+ # Bioroebe.remove_invalid_aminoacids('LKLSUSURZZZ')
141
+ #
142
+ # ========================================================================= #
143
+ def self.remove_invalid_aminoacids(from_this_string)
144
+ if from_this_string.is_a? Array
145
+ from_this_string = from_this_string.first
146
+ end
147
+ all_valid_aminoacids = YAML.load_file(Bioroebe.file_amino_acids).keys
148
+ new_result = ''.dup
149
+ from_this_string.chars.each {|entry|
150
+ new_result << entry if all_valid_aminoacids.include?(entry)
151
+ }
152
+ return new_result
153
+ end
154
+
155
+ # ========================================================================= #
156
+ # === Bioroebe.colourize_aa
157
+ #
158
+ # Use this method if you wish to colourize an aminoacid, in a red colour.
159
+ #
160
+ # The input should be the specific aminoacid sequence in question
161
+ # that you wish to see being colourized here.
162
+ #
163
+ # This currently only works for aminoacids, and only in red. Perhaps
164
+ # at a later time it will become more flexible, but for now, it will
165
+ # be exclusive for aminoacids alone.
166
+ #
167
+ # Usage example:
168
+ #
169
+ # puts Bioroebe.colourize_aa 'STGYGGCTR', 'S T Y'
170
+ #
171
+ # ========================================================================= #
172
+ def self.colourize_aa(
173
+ i,
174
+ array_colourize_these_aminoacids = array_colourize_this_aminoacid?
175
+ )
176
+ if array_colourize_these_aminoacids.is_a? String
177
+ array_colourize_these_aminoacids = array_colourize_these_aminoacids.split(' ') # Split it into an Array.
178
+ end
179
+ unless array_colourize_these_aminoacids.empty?
180
+ if i.nil?
181
+ puts 'You first have to assign a sequence.'
182
+ else
183
+ if i.chars.any? {|entry| array_colourize_these_aminoacids.include? entry }
184
+ # =================================================================== #
185
+ # Ok, we have established a need to colourize the result.
186
+ # =================================================================== #
187
+ array_colourize_these_aminoacids.each {|colour|
188
+ i.gsub!(/(#{colour})/, swarn('\\1')+rev)
189
+ }
190
+ end
191
+ end
192
+ end if use_colours? # But only if we use colours.
193
+ return i
194
+ end
195
+
196
+ # ========================================================================= #
197
+ # === Bioroebe.upcase_this_aminoacid_sequence_and_remove_numbers
198
+ #
199
+ # This method can be used to remove numbers, upcase all entries
200
+ # and delete all ' ' characters and newlines. It is mostly a
201
+ # "sanitize" method.
202
+ #
203
+ # Invocation example:
204
+ #
205
+ # Bioroebe.upcase_this_aminoacid_sequence_and_remove_numbers # => "MSASASA" (etc..)
206
+ #
207
+ # ========================================================================= #
208
+ def self.upcase_this_aminoacid_sequence_and_remove_numbers(
209
+ i = '1 msasasacdc lvgvptgptl astcggsafm lfmgllevfi rsqcdledpc grassrfrse
210
+ 61 pdyeydfivi gggsagsvva srlsevpqwk vllieaggde pvgaqipsmf lnfigsdidy'
211
+ )
212
+ if i.is_a? Array
213
+ i = i.join(' ').strip
214
+ end
215
+ i = i.dup if i.frozen?
216
+ i = i.delete(' ').delete("\n").gsub(/\d+/,'').strip.upcase
217
+ e i
218
+ end
219
+
220
+ # ========================================================================= #
221
+ # === Bioroebe.convert_one_letter_to_full
222
+ #
223
+ # Convert one aminoacid to the real name.
224
+ #
225
+ # Usage example:
226
+ #
227
+ # Bioroebe.convert_one_letter_to_full('T') # => "threonine"
228
+ #
229
+ # ========================================================================= #
230
+ def self.convert_one_letter_to_full(i)
231
+ if i.is_a? Array
232
+ i.each {|entry| convert_one_letter_to_full(entry) }
233
+ else
234
+ i = i.to_s.downcase # need it to be downcased.
235
+ three_letters = convert_one_letter_to_three(i)
236
+ i = AMINO_ACIDS_ABBREVIATIONS[three_letters]
237
+ return i
238
+ end
239
+ end
240
+
241
+ # ========================================================================= #
242
+ # === Bioroebe.amino_acid_average_mass
243
+ #
244
+ # The input to this method should be in the form of the one-letter
245
+ # code for aminoacids. Several aminoacids can be input, of course,
246
+ # such as 'AGL'.
247
+ #
248
+ # Do note that since as of March 2020 a float will be returned by
249
+ # this method, if the input was found to be a valid aminoacid.
250
+ #
251
+ # Usage example:
252
+ #
253
+ # Bioroebe.amino_acid_average_mass('F') # => "147.17660"
254
+ #
255
+ # ========================================================================= #
256
+ def self.amino_acid_average_mass(i)
257
+ use_this_table = AMINO_ACIDS_AVERAGE_MASS_TABLE
258
+ i = i.split(//) if i.is_a? String
259
+ i = [i] unless i.is_a? Array
260
+ result = i.map {|entry|
261
+ entry = use_this_table[entry].to_f
262
+ }
263
+ return ('%.5f' % result.sum).to_f # ← This is our properly formatted result.
264
+ end
265
+
266
+ # ========================================================================= #
267
+ # === Bioroebe.amino_acid_monoisotopic_mass
268
+ #
269
+ # We require the monoisotopic table for this method, and return the
270
+ # corresponding match to the given aminoacid.
271
+ #
272
+ # The input format should be in the one-letter aminoacid abbreviation.
273
+ #
274
+ # Invocation example:
275
+ #
276
+ # Bioroebe.amino_acid_monoisotopic_mass 'L' # => 113.08406
277
+ # Bioroebe.amino_acid_monoisotopic_mass 'K' # => 128.09496
278
+ #
279
+ # ========================================================================= #
280
+ def self.amino_acid_monoisotopic_mass(this_aminoacid)
281
+ use_this_table = AMINO_ACIDS_AVERAGE_MONOISOTOPIC_TABLE
282
+ # '%.5f' % use_this_table[this_aminoacid].to_f
283
+ use_this_table[this_aminoacid].to_f
284
+ end
285
+
286
+ # ========================================================================= #
287
+ # === Bioroebe.return_long_aminoacid_name
288
+ #
289
+ # Use this method to translate a one-letter aminoacid to the long name
290
+ # of the given aminoacid.
291
+ #
292
+ # We also have to consider Stop-Codons as input.
293
+ #
294
+ # Usage examples:
295
+ #
296
+ # Bioroebe.return_long_aminoacid_name 'M' # => "Methionin"
297
+ # Bioroebe.return_long_aminoacid_name 'T' # => "Threonine"
298
+ #
299
+ # ========================================================================= #
300
+ def self.return_long_aminoacid_name(
301
+ short_name_of_the_aminoacid
302
+ )
303
+ aminoacid = AMINO_ACIDS_ENGLISH[short_name_of_the_aminoacid].dup
304
+ if aminoacid
305
+ aminoacid = aminoacid.select {|key,value|
306
+ key.size == 3
307
+ }.flatten[1]
308
+ else
309
+ aminoacid = short_name_of_the_aminoacid
310
+ aminoacid = 'Translation Stop' if aminoacid == '*'
311
+ end unless aminoacid.is_a? String
312
+ return aminoacid
313
+ end; self.instance_eval {
314
+ alias return_long_name_of_this_aminoacid return_long_aminoacid_name
315
+ } # === Bioroebe.return_long_name_of_this_aminoacid
316
+
317
+ # ========================================================================= #
318
+ # === Bioroebe.sort_aminoacid_based_on_its_hydrophobicity
319
+ #
320
+ # This method can sort aminoacids based on their hydrophobicity.
321
+ #
322
+ # The input to this method MUST happen in the form of the one-aminoacid
323
+ # letter code, as the input will be upcased, as-is.
324
+ #
325
+ # The preferred input "type" should be a String.
326
+ #
327
+ # The output of this method will be a String, such as 'D < F < P'
328
+ # or something similar. This output is then already sorted by
329
+ # hydrophobicity, e. g. D being not as hydrophobic as F, and
330
+ # so forth.
331
+ #
332
+ # This method was created primarily because of a Rosalind challenge,
333
+ # but the functionality seems sufficiently useful to retain in
334
+ # general, as it may be useful for other code elements.
335
+ #
336
+ # Usage example:
337
+ #
338
+ # Bioroebe.sort_aminoacid_based_on_its_hydrophobicity('TAMS')
339
+ # Bioroebe.sort_aminoacid_based_on_its_hydrophobicity('TAMS') # => T < G < A
340
+ #
341
+ # ========================================================================= #
342
+ def self.sort_aminoacid_based_on_its_hydrophobicity(
343
+ i = 'FDMS'
344
+ )
345
+ dataset_from_the_hydropathy_table_file = YAML.load_file(
346
+ FILE_HYDROPATHY_TABLE
347
+ )
348
+ i = i.first if i.is_a? Array
349
+ i = 'FDMS' if i.nil?
350
+ i = i.chars.uniq # Obtain the characters.
351
+ hash = {}
352
+ i.each {|entry|
353
+ # ===================================================================== #
354
+ # Find the entry in our main dataset next.
355
+ # ===================================================================== #
356
+ hash[entry] = dataset_from_the_hydropathy_table_file[entry]
357
+ }
358
+ sorted_hash = hash.sort_by {|key, hydrophobicity_value|
359
+ hydrophobicity_value
360
+ }
361
+ # ======================================================================= #
362
+ # We will return a String as a result.
363
+ # ======================================================================= #
364
+ result = ''.dup
365
+ sorted_hash.each {|a,b|
366
+ result << "#{a} < "
367
+ }
368
+ result.strip!
369
+ result.chop! if result.end_with? '<'
370
+ result.strip!
371
+ return result
372
+ end
373
+
374
+ # ========================================================================= #
375
+ # === Bioroebe.is_an_aminoacid?
376
+ #
377
+ # This method will return either true or false, depending on whether the
378
+ # given input is an Aminoacid or whether it is not.
379
+ #
380
+ # Currently this requires the long letter, but it should be no problem
381
+ # to also check or one-letter key codes.
382
+ #
383
+ # Usage examples:
384
+ #
385
+ # Bioroebe.is_aminoacid? 'Tryptophane' # => true
386
+ # Bioroebe.is_aminoacid? 'Glycine'
387
+ # Bioroebe.is_aminoacid? 'lysine' # => true
388
+ # Bioroebe.is_aminoacid? 'GB'
389
+ #
390
+ # ========================================================================= #
391
+ def self.is_an_aminoacid?(i)
392
+ i = i.first if i.is_a? Array
393
+ i = i.dup if i.frozen?
394
+ if i
395
+ i.downcase!
396
+ return_value = false
397
+ keys = AMINO_ACIDS_RESTE.keys
398
+ return_value = true if keys.include? i
399
+ return return_value
400
+ else
401
+ e 'Something went wrong in the method Bioroebe.is_an_aminoacid?() - '\
402
+ 'nil was passed.'
403
+ e 'caller() was:'
404
+ e
405
+ pp caller
406
+ e
407
+ end
408
+ end; self.instance_eval { alias is_aminoacid? is_an_aminoacid? } # === Bioroebe.is_aminoacid?
409
+
410
+ # ========================================================================= #
411
+ # === Bioroebe.parse_this_prosite_pattern
412
+ #
413
+ # Usage example:
414
+ #
415
+ # Bioroebe.parse_this_prosite_pattern('[GSTNE]-[GSTQCR]-[FYW]-{ANW}-x(2)-P') # => "EGFIWQP"
416
+ #
417
+ # ========================================================================= #
418
+ def self.parse_this_prosite_pattern(
419
+ i = '[GSTNE]-[GSTQCR]-[FYW]-{ANW}-x(2)-P'
420
+ )
421
+ i = i.first if i.is_a? Array
422
+ if i.include? '-'
423
+ splitted = i.split('-')
424
+ return splitted.map {|entry|
425
+ return_random_aminoacid_from_this_prosite_pattern(entry)
426
+ }.join
427
+ end
428
+ end
429
+
430
+ # ========================================================================= #
431
+ # === Bioroebe.return_random_aminoacid_from_this_prosite_pattern
432
+ #
433
+ # If no match was found, the original input will be returned.
434
+ #
435
+ # Usage examples:
436
+ #
437
+ # Bioroebe.return_random_aminoacid_from_this_prosite_pattern()
438
+ # Bioroebe.return_random_aminoacid_from_this_prosite_pattern('[GSTNE]')
439
+ # Bioroebe.return_random_aminoacid_from_this_prosite_pattern('{ANW}')
440
+ # Bioroebe.return_random_aminoacid_from_this_prosite_pattern('x(2)')
441
+ #
442
+ # ========================================================================= #
443
+ def self.return_random_aminoacid_from_this_prosite_pattern(i)
444
+ if i.include?('(') and i.include?(')') and i.include?('x')
445
+ n_aminoacids = i.scan(REGEX_PROSITE_FOR_ANY_AMINOACID).flatten.first.to_i
446
+ result = n_aminoacids.times.map { return_random_aminoacid }.join
447
+ return result
448
+ end
449
+ if i.include?('[') and i.include?(']')
450
+ splitted = i.delete('[]').split(//)
451
+ return splitted.sample
452
+ end
453
+ if i.include?('{') and i.include?('}')
454
+ # ===================================================================== #
455
+ # In this case we will return a random aminoacid
456
+ # without any of the specified aminoacids.
457
+ # ===================================================================== #
458
+ forbidden_aminoacids = i.delete('{}').split(//)
459
+ all_aminoacids = Bioroebe.aminoacids?.keys
460
+ filtered_aminoacids = all_aminoacids.reject {|this_aminoacid|
461
+ forbidden_aminoacids.include? this_aminoacid
462
+ }
463
+ return filtered_aminoacids.sample
464
+ end
465
+ return i # Return the original input in this case.
466
+ end
467
+
468
+ # ========================================================================= #
469
+ # === Bioroebe.strict_filter_away_invalid_aminoacids
470
+ #
471
+ # This method, named `Bioroebe.strict_filter_away_invalid_aminoacids()`,
472
+ # is a strict filter for aminoacids. That is, if an invalid aminoacid
473
+ # is passed to this method, that aminoacid will simply be discarded.
474
+ #
475
+ # Only 20 aminoacids are valid, in regards to this filter here - the
476
+ # canonical aminoacids.
477
+ #
478
+ # The following behaviour is valid for this method:
479
+ #
480
+ # - Any String passed into this method will be converted to an Array.
481
+ #
482
+ # - Any Array passed into this method will be turned into an Array"
483
+ # of Strings" if it contains at the least one String.
484
+ #
485
+ # Note that this method will return an Array as a result. This
486
+ # Array will retain only valid aminoacids (e. g. from the 20
487
+ # that are possible).
488
+ #
489
+ # Usage example:
490
+ #
491
+ # Bioroebe.strict_filter_away_invalid_aminoacids('ABCDEFGHIJKLMNOPQRSTUVWXYZ') # => 'ACDEFGHIKLMNOPQRSTUVWY'
492
+ #
493
+ # ========================================================================= #
494
+ def self.strict_filter_away_invalid_aminoacids(
495
+ i = :default
496
+ )
497
+ case i
498
+ when :default
499
+ # Assign a default in this case.
500
+ i = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
501
+ # In the past, the above entry also handled nil, '',
502
+ # but I realized that this makes no sense, so it was
503
+ # disabled as of 06.12.2020.
504
+ end
505
+ if i.is_a? String
506
+ i = i.chars
507
+ elsif i.is_a?(Array) and i.first.is_a?(String)
508
+ i = i.first.chars
509
+ end
510
+ # ======================================================================= #
511
+ # We should now have an Array, hopefully. Next we can apply a filter on
512
+ # that Array.
513
+ # ======================================================================= #
514
+ valid_aminoacids = AMINO_ACIDS.keys
515
+ i.select! {|this_aminoacid|
516
+ valid_aminoacids.include? this_aminoacid
517
+ }
518
+ if i.is_a? Array
519
+ i = i.join
520
+ end
521
+ i
522
+ end
523
+
524
+ # ========================================================================= #
525
+ # === Bioroebe.convert_one_letter_to_three
526
+ #
527
+ # Convert a one-letter-code for an aminoacid into the slightly longer
528
+ # three-letter-code variant for that particular aminoacid.
529
+ #
530
+ # Note that this method will return the result in a downcased variant,
531
+ # such as "gly" for "glycine".
532
+ #
533
+ # Returns:
534
+ #
535
+ # A string of three characters, if it is a valid one-letter aminoacid.
536
+ #
537
+ # Usage example for an aminoacid such as Glycine:
538
+ #
539
+ # Bioroebe.convert_one_letter_to_three('G') # => "gly"
540
+ #
541
+ # ========================================================================= #
542
+ def self.convert_one_letter_to_three(i)
543
+ AMINO_ACIDS_THREE_TO_ONE.invert[i.upcase]
544
+ end
545
+
546
+ # ========================================================================= #
547
+ # === Bioroebe.return_short_aminoacid_letter_from_long_aminoacid_name
548
+ #
549
+ # This will turn input such as "lysine" into "K".
550
+ #
551
+ # Invocation example:
552
+ #
553
+ # Bioroebe.return_short_aminoacid_letter_from_long_aminoacid_name('lysine') # => "K"
554
+ #
555
+ # Commandline invocation example:
556
+ #
557
+ # short_aminoacid_letter_from_long_aminoacid_name lysine
558
+ #
559
+ # ========================================================================= #
560
+ def self.return_short_aminoacid_letter_from_long_aminoacid_name(
561
+ i
562
+ )
563
+ if i.nil?
564
+ e "Please provide some input to the method #{__method__.to_s}."
565
+ return nil
566
+ end
567
+ aminoacids = AMINO_ACIDS_ENGLISH
568
+ inverted_table = aminoacids.invert
569
+ i = [i].flatten.compact.map(&:capitalize)
570
+ if i.first.include? '-'
571
+ i = i.join.strip.split('-').map {|entry|
572
+ entry.capitalize!
573
+ if inverted_table.has_key? entry
574
+ entry = inverted_table[entry]
575
+ else
576
+ e "The given input `#{entry}` does not appear to be "\
577
+ "a valid long-letter aminoacid."
578
+ end
579
+ entry
580
+ }
581
+ end
582
+ end
583
+
584
+ # ========================================================================= #
585
+ # === Bioroebe.is_in_the_three_letter_code?
586
+ #
587
+ # This method can be used to check whether the given input is in the
588
+ # three letter code.
589
+ #
590
+ # Usage examples:
591
+ #
592
+ # Bioroebe.is_in_the_three_letter_code? 'Lys-Asp-Glu-Leu' # => true
593
+ # Bioroebe.is_in_the_three_letter_code? 'Lys-Asp-Glu-Leu-Lun' # => false
594
+ #
595
+ # ========================================================================= #
596
+ def self.is_in_the_three_letter_code?(
597
+ i = 'Lys-Asp-Glu-Leu'
598
+ )
599
+ result = true
600
+ dataset = AMINO_ACIDS_THREE_TO_ONE
601
+ if i.is_a? Array
602
+ i = i.join('-').strip
603
+ end
604
+ i = i.to_s.dup
605
+ i.strip!
606
+ i.delete!(' ') if i.include? ' '
607
+ i.delete!('-') if i.include? '-'
608
+ scanned = i.scan(/.../).map(&:downcase)
609
+ scanned.each {|key|
610
+ if dataset.has_key? key
611
+ else
612
+ result = false
613
+ end
614
+ }
615
+ return result
616
+ end
617
+
618
+ # ========================================================================= #
619
+ # === Bioroebe.one_to_three
620
+ #
621
+ # This method will convert from the one-aminoacid letter to the
622
+ # three-letter code.
623
+ #
624
+ # Usage example:
625
+ #
626
+ # Bioroebe.one_to_three('HIM') # => "His-Ile-Met"
627
+ #
628
+ # ========================================================================= #
629
+ def self.one_to_three(i)
630
+ if i.is_a? Array
631
+ i = i.join
632
+ end
633
+ inverted_hash = AMINO_ACIDS_THREE_TO_ONE.invert
634
+ chars = i.chars
635
+ result = chars.map {|one_aminoacid_letter|
636
+ inverted_hash[one_aminoacid_letter].capitalize+'-'
637
+ }.join
638
+ return result.chop
639
+ end
640
+
641
+ # ========================================================================= #
642
+ # === Bioroebe.weight_of_this_aminoacid?
643
+ #
644
+ # This method will return the weight of an aminoacid (that is bound
645
+ # in a protein, thus having a H2O group less than normally in total).
646
+ # ========================================================================= #
647
+ def self.weight_of_this_aminoacid?(
648
+ i, use_this_dataset = nil
649
+ )
650
+ if use_this_dataset.nil?
651
+ use_this_dataset = YAML.load_file(FILE_AMINO_ACIDS_MASS_TABLE)
652
+ end
653
+ if i.is_a? Array
654
+ i.map {|entry|
655
+ result = weight_of_this_aminoacid?(entry, use_this_dataset)
656
+ if result.nil?
657
+ erev 'A nil value happened for '+steelblue(entry)+rev+
658
+ '. Check file '+sfile(FILE_AMINO_ACIDS_MASS_TABLE)
659
+ end
660
+ result
661
+ }.compact.sum
662
+ else
663
+ use_this_dataset[i]
664
+ end
665
+ end
666
+
667
+ end
668
+
669
+ if __FILE__ == $PROGRAM_NAME
670
+
671
+ alias e puts
672
+
673
+ Bioroebe.upcase_this_aminoacid_sequence_and_remove_numbers(
674
+ '1 msasasacdc lvgvptgptl astcggsafm lfmgllevfi rsqcdledpc grassrfrse
675
+ 61 pdyeydfivi gggsagsvva srlsevpqwk vllieaggde pvgaqipsmf lnfigsdidy')
676
+
677
+ e Bioroebe.three_to_one('THR')
678
+
679
+ if ARGV.empty?
680
+ input = 'thr-Arg-His'
681
+ else
682
+ input = ARGV.join(' ').strip
683
+ end
684
+
685
+ puts 'From '+input+' to: '+Bioroebe.three_to_one(input) # => "TRH"
686
+ # And more tests:
687
+ # p Bioroebe.is_aminoacid? 'Tryptophan' # => true
688
+ # p Bioroebe.is_aminoacid? 'Glycine' # => true
689
+ # p Bioroebe.is_aminoacid? 'lysine' # => true
690
+ # p Bioroebe.is_aminoacid? 'GB' # => false
691
+ # p Bioroebe.is_aminoacid? 'G' # => false
692
+ #
693
+ # puts Bioroebe.return_long_aminoacid_name 'M' # => "Methionine"
694
+ # puts Bioroebe.return_long_aminoacid_name ARGV.first
695
+ #
696
+ # puts Bioroebe.sort_aminoacid_based_on_its_hydrophobicity(ARGV)
697
+ #
698
+ # if ARGV.empty?
699
+ # puts Bioroebe.return_short_aminoacid_letter_from_long_aminoacid_name 'M' # => "Methionine"
700
+ # else
701
+ # puts Bioroebe.return_short_aminoacid_letter_from_long_aminoacid_name ARGV.first
702
+ # end
703
+ #
704
+ # if ARGV.empty?
705
+ # puts 'This test-code will show 1,2,3 aminoacids in build-up (Alanin, Glycine, Leucine):'
706
+ # puts
707
+ # puts ' '+Bioroebe.amino_acid_average_mass('A').to_s # Alanin
708
+ # puts ' '+Bioroebe.amino_acid_average_mass('AG').to_s # Alanin, Glycine
709
+ # puts ' '+Bioroebe.amino_acid_average_mass('AGL').to_s # Alanin, Glycine, Leucine.
710
+ # puts
711
+ # else
712
+ # puts ' '+Bioroebe.amino_acid_average_mass(ARGV).to_s # Alanin, Glycine, Leucine.
713
+ # end
714
+ #
715
+ end # three_to_one His