bioroebe 0.10.80
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/LICENSE.md +428 -0
- data/README.md +9280 -0
- data/bin/advanced_dotplot +7 -0
- data/bin/align_open_reading_frames +12 -0
- data/bin/all_positions_of_this_nucleotide +7 -0
- data/bin/aminoacid_composition +7 -0
- data/bin/aminoacid_frequencies +12 -0
- data/bin/aminoacid_substitution +7 -0
- data/bin/automatically_rename_this_fasta_file +7 -0
- data/bin/base_composition +7 -0
- data/bin/batch_create_windows_executables +7 -0
- data/bin/biomart_console +11 -0
- data/bin/bioroebe +27 -0
- data/bin/bioroebe_controller +10 -0
- data/bin/bioshell +26 -0
- data/bin/blosum_2D_table +12 -0
- data/bin/calculate_n50_value +12 -0
- data/bin/chunked_display +12 -0
- data/bin/codon_frequency +9 -0
- data/bin/codon_to_aminoacid +30 -0
- data/bin/colourize_this_fasta_sequence +14 -0
- data/bin/compact_fasta_file +7 -0
- data/bin/complement +7 -0
- data/bin/complementary_dna_strand +12 -0
- data/bin/complementary_rna_strand +12 -0
- data/bin/compseq +7 -0
- data/bin/consensus_sequence +17 -0
- data/bin/count_AT +12 -0
- data/bin/count_GC +12 -0
- data/bin/create_random_aminoacids +7 -0
- data/bin/decode_this_aminoacid_sequence +20 -0
- data/bin/deduce_aminoacid_sequence +13 -0
- data/bin/deduce_most_likely_aminoacid_sequence +7 -0
- data/bin/display_aminoacid_table +12 -0
- data/bin/display_open_reading_frames +7 -0
- data/bin/dna_to_aminoacid_sequence +7 -0
- data/bin/dna_to_rna +7 -0
- data/bin/downcase_chunked_display +12 -0
- data/bin/download_this_pdb +7 -0
- data/bin/fasta_index +7 -0
- data/bin/fetch_data_from_uniprot +12 -0
- data/bin/filter_away_invalid_nucleotides +12 -0
- data/bin/find_substring +19 -0
- data/bin/genbank_to_fasta +7 -0
- data/bin/hamming_distance +12 -0
- data/bin/input_as_dna +12 -0
- data/bin/is_palindrome +13 -0
- data/bin/leading_five_prime +7 -0
- data/bin/levensthein +7 -0
- data/bin/longest_ORF +14 -0
- data/bin/longest_substring +12 -0
- data/bin/n_stop_codons_in_this_sequence +15 -0
- data/bin/open_reading_frames +14 -0
- data/bin/overwrite_fasta_header +7 -0
- data/bin/palindrome_2D_structure +7 -0
- data/bin/palindrome_generator +7 -0
- data/bin/parse_fasta +7 -0
- data/bin/partner_nucleotide +9 -0
- data/bin/possible_codons_for_this_aminoacid +12 -0
- data/bin/random_dna_sequence +12 -0
- data/bin/random_sequence +12 -0
- data/bin/raw_hamming_distance +12 -0
- data/bin/return_longest_substring_via_LCS_algorithm +7 -0
- data/bin/reverse_complement +7 -0
- data/bin/reverse_sequence +7 -0
- data/bin/ruler +12 -0
- data/bin/scan_this_input_for_startcodons +12 -0
- data/bin/short_aminoacid_letter_from_long_aminoacid_name +7 -0
- data/bin/show_atomic_composition +7 -0
- data/bin/show_codon_usage +12 -0
- data/bin/show_fasta_header +7 -0
- data/bin/show_nucleotide_sequence +7 -0
- data/bin/show_this_codon_table +7 -0
- data/bin/show_this_dna_sequence +7 -0
- data/bin/showorf +14 -0
- data/bin/simplify_fasta +7 -0
- data/bin/sort_aminoacid_based_on_its_hydrophobicity +7 -0
- data/bin/split_this_fasta_file_into_chromosomes +7 -0
- data/bin/strict_filter_away_invalid_aminoacids +7 -0
- data/bin/taxonomy +63 -0
- data/bin/three_to_one +7 -0
- data/bin/to_rna +7 -0
- data/bin/trailing_three_prime +7 -0
- data/bin/trypsin_digest +7 -0
- data/bin/upcase_this_aminoacid_sequence_and_remove_numbers +7 -0
- data/bioroebe.gemspec +97 -0
- data/doc/IUPAC_aminoacids_code.md +36 -0
- data/doc/IUPAC_nucleotide_code.md +19 -0
- data/doc/README.gen +9237 -0
- data/doc/blosum.md +5 -0
- data/doc/compatibility/BIO_PHP.md +37 -0
- data/doc/compatibility/README.md +3 -0
- data/doc/compatibility/emboss.md +56 -0
- data/doc/extensive_usage_example.md +35 -0
- data/doc/german_names_for_the_aminoacids.md +27 -0
- data/doc/instructions_for_the_taxonomy_subproject.md +504 -0
- data/doc/legacy_paths.md +9 -0
- data/doc/pdb_ATOM_entry.md +33 -0
- data/doc/quality_control/README.md +2 -0
- data/doc/quality_control/commandline_applications.md +13 -0
- data/doc/resources.md +23 -0
- data/doc/setup.rb +1655 -0
- data/doc/statistics/statistics.md +41 -0
- data/doc/todo/README.md +5 -0
- data/doc/todo/bioroebe_GUI_todo.md +15 -0
- data/doc/todo/bioroebe_todo.md +2823 -0
- data/doc/using_biomart.md +258 -0
- data/html/test.html +144 -0
- data/lib/bioroebe/aminoacids/aminoacid_substitution.rb +118 -0
- data/lib/bioroebe/aminoacids/aminoacids_mass_table.rb +118 -0
- data/lib/bioroebe/aminoacids/codon_percentage.rb +189 -0
- data/lib/bioroebe/aminoacids/colourize_hydrophilic_and_hydrophobic_aminoacids.rb +110 -0
- data/lib/bioroebe/aminoacids/create_random_aminoacids.rb +221 -0
- data/lib/bioroebe/aminoacids/deduce_aminoacid_sequence.rb +460 -0
- data/lib/bioroebe/aminoacids/display_aminoacid_table.rb +231 -0
- data/lib/bioroebe/aminoacids/show_hydrophobicity.rb +184 -0
- data/lib/bioroebe/annotations/README.md +2 -0
- data/lib/bioroebe/annotations/create_annotation_format.rb +208 -0
- data/lib/bioroebe/autoinclude.rb +7 -0
- data/lib/bioroebe/base/base.rb +35 -0
- data/lib/bioroebe/base/colours.rb +14 -0
- data/lib/bioroebe/base/colours_for_base/colours_for_base.rb +275 -0
- data/lib/bioroebe/base/commandline_application/README.md +7 -0
- data/lib/bioroebe/base/commandline_application/aminoacids.rb +33 -0
- data/lib/bioroebe/base/commandline_application/commandline_application.rb +37 -0
- data/lib/bioroebe/base/commandline_application/commandline_arguments.rb +144 -0
- data/lib/bioroebe/base/commandline_application/directory.rb +33 -0
- data/lib/bioroebe/base/commandline_application/extract.rb +22 -0
- data/lib/bioroebe/base/commandline_application/misc.rb +485 -0
- data/lib/bioroebe/base/commandline_application/opn.rb +47 -0
- data/lib/bioroebe/base/commandline_application/reset.rb +40 -0
- data/lib/bioroebe/base/commandline_application/warnings.rb +36 -0
- data/lib/bioroebe/base/commandline_application/write_what_into.rb +29 -0
- data/lib/bioroebe/base/initialize.rb +18 -0
- data/lib/bioroebe/base/misc.rb +94 -0
- data/lib/bioroebe/base/namespace.rb +16 -0
- data/lib/bioroebe/base/prototype/README.md +12 -0
- data/lib/bioroebe/base/prototype/e_and_ee.rb +24 -0
- data/lib/bioroebe/base/prototype/misc.rb +108 -0
- data/lib/bioroebe/base/prototype/mkdir.rb +20 -0
- data/lib/bioroebe/base/prototype/prototype.rb +21 -0
- data/lib/bioroebe/base/prototype/reset.rb +26 -0
- data/lib/bioroebe/base/reset.rb +11 -0
- data/lib/bioroebe/biomart/LICENSE.md +27 -0
- data/lib/bioroebe/biomart/attribute.rb +77 -0
- data/lib/bioroebe/biomart/biomart.rb +227 -0
- data/lib/bioroebe/biomart/database.rb +128 -0
- data/lib/bioroebe/biomart/dataset.rb +572 -0
- data/lib/bioroebe/biomart/filter.rb +97 -0
- data/lib/bioroebe/biomart/server.rb +152 -0
- data/lib/bioroebe/blosum/blosum.rb +88 -0
- data/lib/bioroebe/calculate/calculate_blosum_score.rb +145 -0
- data/lib/bioroebe/calculate/calculate_gc_content.rb +301 -0
- data/lib/bioroebe/calculate/calculate_levensthein_distance.rb +100 -0
- data/lib/bioroebe/calculate/calculate_melting_temperature.rb +398 -0
- data/lib/bioroebe/calculate/calculate_melting_temperature_for_more_than_thirteen_nucleotides.rb +304 -0
- data/lib/bioroebe/calculate/calculate_the_position_specific_scoring_matrix.rb +166 -0
- data/lib/bioroebe/cell/README.md +1 -0
- data/lib/bioroebe/cell/cell.rb +63 -0
- data/lib/bioroebe/cleave_and_digest/README.md +2 -0
- data/lib/bioroebe/cleave_and_digest/cleave.rb +80 -0
- data/lib/bioroebe/cleave_and_digest/digestion.rb +75 -0
- data/lib/bioroebe/cleave_and_digest/trypsin.rb +192 -0
- data/lib/bioroebe/codon_tables/README.md +9 -0
- data/lib/bioroebe/codon_tables/frequencies/287_Pseudomonas_aeruginosa.yml +101 -0
- data/lib/bioroebe/codon_tables/frequencies/3702_Arabidopsis_thaliana.yml +77 -0
- data/lib/bioroebe/codon_tables/frequencies/4932_Saccharomyces_cerevisiae.yml +103 -0
- data/lib/bioroebe/codon_tables/frequencies/7227_Drosophila_melanogaster.yml +71 -0
- data/lib/bioroebe/codon_tables/frequencies/83333_Escherichia_coli_K12.yml +103 -0
- data/lib/bioroebe/codon_tables/frequencies/9606_Homo_sapiens.yml +123 -0
- data/lib/bioroebe/codon_tables/frequencies/9685_Felis_catus.yml +78 -0
- data/lib/bioroebe/codon_tables/frequencies/README.md +10 -0
- data/lib/bioroebe/codon_tables/frequencies/parse_frequency_table.rb +337 -0
- data/lib/bioroebe/codons/README.md +28 -0
- data/lib/bioroebe/codons/codon_table.rb +416 -0
- data/lib/bioroebe/codons/codon_tables.rb +123 -0
- data/lib/bioroebe/codons/codons.rb +517 -0
- data/lib/bioroebe/codons/convert_this_codon_to_that_aminoacid.rb +102 -0
- data/lib/bioroebe/codons/detect_minimal_codon.rb +180 -0
- data/lib/bioroebe/codons/determine_optimal_codons.rb +74 -0
- data/lib/bioroebe/codons/possible_codons_for_this_aminoacid.rb +380 -0
- data/lib/bioroebe/codons/sanitize_codon_frequency.rb +144 -0
- data/lib/bioroebe/codons/show_codon_tables.rb +130 -0
- data/lib/bioroebe/codons/show_codon_usage.rb +197 -0
- data/lib/bioroebe/codons/show_this_codon_table.rb +573 -0
- data/lib/bioroebe/codons/start_codons.rb +105 -0
- data/lib/bioroebe/colours/colour_schemes/README.md +10 -0
- data/lib/bioroebe/colours/colour_schemes/array_available_colour_schemes.rb +38 -0
- data/lib/bioroebe/colours/colour_schemes/buried.rb +70 -0
- data/lib/bioroebe/colours/colour_schemes/colour_scheme.rb +101 -0
- data/lib/bioroebe/colours/colour_schemes/colour_scheme_demo.rb +262 -0
- data/lib/bioroebe/colours/colour_schemes/helix.rb +65 -0
- data/lib/bioroebe/colours/colour_schemes/hydropathy.rb +70 -0
- data/lib/bioroebe/colours/colour_schemes/nucleotide.rb +47 -0
- data/lib/bioroebe/colours/colour_schemes/score.rb +112 -0
- data/lib/bioroebe/colours/colour_schemes/simple.rb +42 -0
- data/lib/bioroebe/colours/colour_schemes/strand.rb +65 -0
- data/lib/bioroebe/colours/colour_schemes/taylor.rb +58 -0
- data/lib/bioroebe/colours/colour_schemes/turn.rb +65 -0
- data/lib/bioroebe/colours/colour_schemes/zappo.rb +59 -0
- data/lib/bioroebe/colours/colourize_sequence.rb +262 -0
- data/lib/bioroebe/colours/colours.rb +119 -0
- data/lib/bioroebe/colours/misc_colours.rb +80 -0
- data/lib/bioroebe/colours/rev.rb +41 -0
- data/lib/bioroebe/colours/sdir.rb +21 -0
- data/lib/bioroebe/colours/sfancy.rb +21 -0
- data/lib/bioroebe/colours/sfile.rb +21 -0
- data/lib/bioroebe/colours/simp.rb +21 -0
- data/lib/bioroebe/colours/swarn.rb +29 -0
- data/lib/bioroebe/colours/use_colours.rb +27 -0
- data/lib/bioroebe/configuration/configuration.rb +114 -0
- data/lib/bioroebe/configuration/constants.rb +35 -0
- data/lib/bioroebe/constants/GUIs.rb +79 -0
- data/lib/bioroebe/constants/aminoacids_and_proteins.rb +146 -0
- data/lib/bioroebe/constants/base_directory.rb +120 -0
- data/lib/bioroebe/constants/carriage_return.rb +14 -0
- data/lib/bioroebe/constants/codon_tables.rb +77 -0
- data/lib/bioroebe/constants/database_constants.rb +107 -0
- data/lib/bioroebe/constants/files_and_directories.rb +579 -0
- data/lib/bioroebe/constants/misc.rb +189 -0
- data/lib/bioroebe/constants/newline.rb +14 -0
- data/lib/bioroebe/constants/nucleotides.rb +114 -0
- data/lib/bioroebe/constants/regex.rb +28 -0
- data/lib/bioroebe/constants/roebe.rb +38 -0
- data/lib/bioroebe/constants/row_terminator.rb +16 -0
- data/lib/bioroebe/constants/tabulator.rb +14 -0
- data/lib/bioroebe/constants/unicode.rb +12 -0
- data/lib/bioroebe/constants/urls.rb +50 -0
- data/lib/bioroebe/conversions/README.md +3 -0
- data/lib/bioroebe/conversions/convert_aminoacid_to_dna.rb +298 -0
- data/lib/bioroebe/conversions/dna_to_aminoacid_sequence.rb +569 -0
- data/lib/bioroebe/count/README.md +1 -0
- data/lib/bioroebe/count/count_amount_of_aminoacids.rb +352 -0
- data/lib/bioroebe/count/count_amount_of_nucleotides.rb +491 -0
- data/lib/bioroebe/count/count_at.rb +39 -0
- data/lib/bioroebe/count/count_gc.rb +43 -0
- data/lib/bioroebe/css/README.md +5 -0
- data/lib/bioroebe/css/project.css +121 -0
- data/lib/bioroebe/data/README.md +10 -0
- data/lib/bioroebe/data/bam/README.md +1 -0
- data/lib/bioroebe/data/data.txt +192 -0
- data/lib/bioroebe/data/fasta/GFP_mutant_3_coding_sequence.fasta +12 -0
- data/lib/bioroebe/data/fasta/alu_elements.fasta +42 -0
- data/lib/bioroebe/data/fasta/lady_slippers_orchid.fasta +1197 -0
- data/lib/bioroebe/data/fasta/loxP.fasta +2 -0
- data/lib/bioroebe/data/fasta/ls_orchid.fasta +1197 -0
- data/lib/bioroebe/data/fasta/pax6_in_mouse.fasta +1 -0
- data/lib/bioroebe/data/fasta/test.fasta +7 -0
- data/lib/bioroebe/data/fasta/test_DNA.fasta +1 -0
- data/lib/bioroebe/data/fastq/fastq_example_file.fastq +32 -0
- data/lib/bioroebe/data/fastq/fastq_example_file_SP1.fastq +1000 -0
- data/lib/bioroebe/data/fastq/one_random_fastq_entry.fastq +4 -0
- data/lib/bioroebe/data/genbank/sample_file.genbank +15 -0
- data/lib/bioroebe/data/genbank/standard.fasta +3 -0
- data/lib/bioroebe/data/gff/Escherichia_coli_K12_plasmid_F_DNA_NC_002483.1.gff3 +345 -0
- data/lib/bioroebe/data/gff/sample.gff +2 -0
- data/lib/bioroebe/data/gff/test_gene.gff +4 -0
- data/lib/bioroebe/data/gff/transcripts.gff +16 -0
- data/lib/bioroebe/data/gtf/README.md +1 -0
- data/lib/bioroebe/data/json/example_config.json +48 -0
- data/lib/bioroebe/data/pdb/1VII.pdb +754 -0
- data/lib/bioroebe/data/pdb/ala_phe_ala.pdb +228 -0
- data/lib/bioroebe/data/pdb/rcsb_pdb_1VII.fasta +2 -0
- data/lib/bioroebe/data/phylip/README.md +11 -0
- data/lib/bioroebe/data/phylip/example.phylip +7 -0
- data/lib/bioroebe/data/svg/example.svg +301 -0
- data/lib/bioroebe/databases/README.md +1 -0
- data/lib/bioroebe/databases/download_taxonomy_database.rb +102 -0
- data/lib/bioroebe/dotplots/README.md +5 -0
- data/lib/bioroebe/dotplots/advanced_dotplot.rb +256 -0
- data/lib/bioroebe/dotplots/dotplot.rb +184 -0
- data/lib/bioroebe/electron_microscopy/coordinate_analyzer.rb +191 -0
- data/lib/bioroebe/electron_microscopy/fix_pos_file.rb +102 -0
- data/lib/bioroebe/electron_microscopy/generate_em2em_file.rb +122 -0
- data/lib/bioroebe/electron_microscopy/parse_coordinates.rb +197 -0
- data/lib/bioroebe/electron_microscopy/read_file_xmd.rb +282 -0
- data/lib/bioroebe/electron_microscopy/simple_star_file_generator.rb +131 -0
- data/lib/bioroebe/encoding/README.md +2 -0
- data/lib/bioroebe/encoding/encoding.rb +45 -0
- data/lib/bioroebe/enzymes/README.md +2 -0
- data/lib/bioroebe/enzymes/has_this_restriction_enzyme.rb +46 -0
- data/lib/bioroebe/enzymes/restriction_enzyme.rb +200 -0
- data/lib/bioroebe/enzymes/restriction_enzymes_file.rb +72 -0
- data/lib/bioroebe/enzymes/return_restriction_enzyme_sequence_and_cut_position.rb +80 -0
- data/lib/bioroebe/enzymes/return_sequence_that_is_cut_via_restriction_enzyme.rb +65 -0
- data/lib/bioroebe/enzymes/show_restriction_enzymes.rb +119 -0
- data/lib/bioroebe/exceptions/README.md +2 -0
- data/lib/bioroebe/exceptions/exceptions.rb +17 -0
- data/lib/bioroebe/ext/LICENCE.md +5 -0
- data/lib/bioroebe/ext/README.md +7 -0
- data/lib/bioroebe/ext/main.cpp +45 -0
- data/lib/bioroebe/ext/nucleotide.cpp +24 -0
- data/lib/bioroebe/ext/nussinov_algorithm.cpp +348 -0
- data/lib/bioroebe/ext/sequence +0 -0
- data/lib/bioroebe/ext/sequence.cpp +162 -0
- data/lib/bioroebe/fasta_and_fastq/README.md +6 -0
- data/lib/bioroebe/fasta_and_fastq/autocorrect_the_name_of_this_fasta_file.rb +88 -0
- data/lib/bioroebe/fasta_and_fastq/compact_fasta_file/compact_fasta_file.rb +151 -0
- data/lib/bioroebe/fasta_and_fastq/display_how_many_fasta_entries_are_in_this_directory.rb +111 -0
- data/lib/bioroebe/fasta_and_fastq/download_fasta.rb +248 -0
- data/lib/bioroebe/fasta_and_fastq/fasta_defline/README.md +2 -0
- data/lib/bioroebe/fasta_and_fastq/fasta_defline/fasta_defline.rb +113 -0
- data/lib/bioroebe/fasta_and_fastq/fasta_parser.rb +167 -0
- data/lib/bioroebe/fasta_and_fastq/fastq_format_explainer.rb +131 -0
- data/lib/bioroebe/fasta_and_fastq/length_modifier/length_modifier.rb +87 -0
- data/lib/bioroebe/fasta_and_fastq/parse_fasta/constants.rb +50 -0
- data/lib/bioroebe/fasta_and_fastq/parse_fasta/initialize.rb +86 -0
- data/lib/bioroebe/fasta_and_fastq/parse_fasta/menu.rb +117 -0
- data/lib/bioroebe/fasta_and_fastq/parse_fasta/misc.rb +981 -0
- data/lib/bioroebe/fasta_and_fastq/parse_fasta/parse_fasta.rb +27 -0
- data/lib/bioroebe/fasta_and_fastq/parse_fasta/report.rb +156 -0
- data/lib/bioroebe/fasta_and_fastq/parse_fasta/reset.rb +128 -0
- data/lib/bioroebe/fasta_and_fastq/parse_fasta/run.rb +20 -0
- data/lib/bioroebe/fasta_and_fastq/parse_fastq/parse_fastq.rb +83 -0
- data/lib/bioroebe/fasta_and_fastq/return_fasta_subsection_of_this_file.rb +112 -0
- data/lib/bioroebe/fasta_and_fastq/show_fasta_headers.rb +135 -0
- data/lib/bioroebe/fasta_and_fastq/show_fasta_statistics.rb +188 -0
- data/lib/bioroebe/fasta_and_fastq/simplify_fasta_header/simplify_fasta_header.rb +111 -0
- data/lib/bioroebe/fasta_and_fastq/split_this_fasta_file_into_chromosomes/constants.rb +26 -0
- data/lib/bioroebe/fasta_and_fastq/split_this_fasta_file_into_chromosomes/menu.rb +41 -0
- data/lib/bioroebe/fasta_and_fastq/split_this_fasta_file_into_chromosomes/misc.rb +23 -0
- data/lib/bioroebe/fasta_and_fastq/split_this_fasta_file_into_chromosomes/reset.rb +68 -0
- data/lib/bioroebe/fasta_and_fastq/split_this_fasta_file_into_chromosomes/split_this_fasta_file_into_chromosomes.rb +290 -0
- data/lib/bioroebe/genbank/README.md +1 -0
- data/lib/bioroebe/genbank/genbank_flat_file_format_generator.rb +275 -0
- data/lib/bioroebe/genbank/genbank_parser.rb +291 -0
- data/lib/bioroebe/gene/gene.rb +64 -0
- data/lib/bioroebe/genomes/genome_pattern.rb +165 -0
- data/lib/bioroebe/genomes/genome_retriever.rb +79 -0
- data/lib/bioroebe/gui/experimental/README.md +1 -0
- data/lib/bioroebe/gui/experimental/snapgene/snapgene.rb +147 -0
- data/lib/bioroebe/gui/gtk3/README.md +2 -0
- data/lib/bioroebe/gui/gtk3/alignment/alignment.rb +337 -0
- data/lib/bioroebe/gui/gtk3/aminoacid_composition/aminoacid_composition.rb +510 -0
- data/lib/bioroebe/gui/gtk3/aminoacid_composition/customized_dialog.rb +55 -0
- data/lib/bioroebe/gui/gtk3/anti_sense_strand/anti_sense_strand.config +6 -0
- data/lib/bioroebe/gui/gtk3/anti_sense_strand/anti_sense_strand.rb +29 -0
- data/lib/bioroebe/gui/gtk3/blosum_matrix_viewer/blosum_matrix_viewer.rb +196 -0
- data/lib/bioroebe/gui/gtk3/calculate_cell_numbers_of_bacteria/calculate_cell_numbers_of_bacteria.config +6 -0
- data/lib/bioroebe/gui/gtk3/calculate_cell_numbers_of_bacteria/calculate_cell_numbers_of_bacteria.rb +106 -0
- data/lib/bioroebe/gui/gtk3/controller/controller.rb +406 -0
- data/lib/bioroebe/gui/gtk3/dna_to_aminoacid_widget/dna_to_aminoacid_widget.rb +609 -0
- data/lib/bioroebe/gui/gtk3/dna_to_reverse_complement_widget/dna_to_reverse_complement_widget.config +6 -0
- data/lib/bioroebe/gui/gtk3/dna_to_reverse_complement_widget/dna_to_reverse_complement_widget.rb +189 -0
- data/lib/bioroebe/gui/gtk3/fasta_table_widget/fasta_table_widget.rb +245 -0
- data/lib/bioroebe/gui/gtk3/format_converter/format_converter.rb +346 -0
- data/lib/bioroebe/gui/gtk3/gene/gene.rb +182 -0
- data/lib/bioroebe/gui/gtk3/hamming_distance/hamming_distance.config +6 -0
- data/lib/bioroebe/gui/gtk3/hamming_distance/hamming_distance.rb +370 -0
- data/lib/bioroebe/gui/gtk3/levensthein_distance/levensthein_distance.config +6 -0
- data/lib/bioroebe/gui/gtk3/levensthein_distance/levensthein_distance.rb +175 -0
- data/lib/bioroebe/gui/gtk3/nucleotide_analyser/nucleotide_analyser.rb +428 -0
- data/lib/bioroebe/gui/gtk3/parse_pdb_file/parse_pdb_file.rb +342 -0
- data/lib/bioroebe/gui/gtk3/primer_design_widget/primer_design_widget.rb +580 -0
- data/lib/bioroebe/gui/gtk3/protein_to_DNA/protein_to_DNA.config +6 -0
- data/lib/bioroebe/gui/gtk3/protein_to_DNA/protein_to_DNA.rb +182 -0
- data/lib/bioroebe/gui/gtk3/random_sequence/random_sequence.rb +566 -0
- data/lib/bioroebe/gui/gtk3/restriction_enzymes/restriction_enzymes.config +6 -0
- data/lib/bioroebe/gui/gtk3/restriction_enzymes/restriction_enzymes.rb +329 -0
- data/lib/bioroebe/gui/gtk3/show_codon_table/misc.rb +556 -0
- data/lib/bioroebe/gui/gtk3/show_codon_table/show_codon_table.rb +171 -0
- data/lib/bioroebe/gui/gtk3/show_codon_usage/show_codon_usage.rb +146 -0
- data/lib/bioroebe/gui/gtk3/sizeseq/sizeseq.rb +207 -0
- data/lib/bioroebe/gui/gtk3/three_to_one/three_to_one.rb +279 -0
- data/lib/bioroebe/gui/gtk3/three_to_one/title.rb +23 -0
- data/lib/bioroebe/gui/gtk3/www_finder/www_finder.config +6 -0
- data/lib/bioroebe/gui/gtk3/www_finder/www_finder.rb +368 -0
- data/lib/bioroebe/gui/jruby/blosum_matrix_viewer/blosum_matrix_viewer.rb +82 -0
- data/lib/bioroebe/gui/libui/README.md +4 -0
- data/lib/bioroebe/gui/libui/alignment/alignment.rb +114 -0
- data/lib/bioroebe/gui/libui/blosum_matrix_viewer/blosum_matrix_viewer.rb +112 -0
- data/lib/bioroebe/gui/libui/calculate_cell_numbers_of_bacteria/calculate_cell_numbers_of_bacteria.rb +60 -0
- data/lib/bioroebe/gui/libui/dna_to_aminoacid_widget/dna_to_aminoacid_widget.rb +161 -0
- data/lib/bioroebe/gui/libui/dna_to_reverse_complement_widget/dna_to_reverse_complement_widget.rb +76 -0
- data/lib/bioroebe/gui/libui/hamming_distance/hamming_distance.rb +135 -0
- data/lib/bioroebe/gui/libui/levensthein_distance/levensthein_distance.rb +118 -0
- data/lib/bioroebe/gui/libui/protein_to_DNA/protein_to_DNA.rb +115 -0
- data/lib/bioroebe/gui/libui/random_sequence/random_sequence.rb +174 -0
- data/lib/bioroebe/gui/libui/show_codon_table/show_codon_table.rb +132 -0
- data/lib/bioroebe/gui/libui/show_codon_usage/show_codon_usage.rb +89 -0
- data/lib/bioroebe/gui/libui/three_to_one/three_to_one.rb +111 -0
- data/lib/bioroebe/gui/shared_code/blosum_matrix_viewer/blosum_matrix_viewer_module.rb +42 -0
- data/lib/bioroebe/gui/shared_code/calculate_cell_numbers_of_bacteria/calculate_cell_numbers_of_bacteria_module.rb +216 -0
- data/lib/bioroebe/gui/shared_code/dna_to_reverse_complement_widget/dna_to_reverse_complement_widget_module.rb +284 -0
- data/lib/bioroebe/gui/shared_code/levensthein_distance/levensthein_distance_module.rb +402 -0
- data/lib/bioroebe/gui/shared_code/protein_to_DNA/protein_to_DNA_module.rb +192 -0
- data/lib/bioroebe/gui/shared_code/show_codon_table/show_codon_table_module.rb +72 -0
- data/lib/bioroebe/gui/shared_code/show_codon_usage/show_codon_usage_module.rb +213 -0
- data/lib/bioroebe/gui/tk/aminoacid_composition/aminoacid_composition.rb +206 -0
- data/lib/bioroebe/gui/tk/blosum_matrix_viewer/blosum_matrix_viewer.rb +140 -0
- data/lib/bioroebe/gui/tk/hamming_distance/hamming_distance.rb +262 -0
- data/lib/bioroebe/gui/tk/levensthein_distance/levensthein_distance.rb +243 -0
- data/lib/bioroebe/gui/tk/three_to_one/three_to_one.rb +199 -0
- data/lib/bioroebe/gui/unified_widgets/anti_sense_strand/anti_sense_strand.rb +519 -0
- data/lib/bioroebe/images/BIOROEBE.png +0 -0
- data/lib/bioroebe/images/BIOROEBE_NEW_LOGO.png +0 -0
- data/lib/bioroebe/images/BlosumMatrixViewer.png +0 -0
- data/lib/bioroebe/images/DnaToAminoacidWidget.png +0 -0
- data/lib/bioroebe/images/PRINTED_AMINOACID_TABLE.png +0 -0
- data/lib/bioroebe/images/class_ConvertAminoacidToDNA.png +0 -0
- data/lib/bioroebe/images/class_SimpleStringComparer.png +0 -0
- data/lib/bioroebe/images/example_of_FASTA_coloured_output.png +0 -0
- data/lib/bioroebe/images/libui_hamming_distance_widget.png +0 -0
- data/lib/bioroebe/images/pretty_DNA_picture.png +0 -0
- data/lib/bioroebe/images/primer_design_widget.png +0 -0
- data/lib/bioroebe/images/restriction_enzyme_commandline_result.png +0 -0
- data/lib/bioroebe/images/ruby-gtk_three_to_one_widget.png +0 -0
- data/lib/bioroebe/images/small_DNA_logo.png +0 -0
- data/lib/bioroebe/images/small_drosophila_image.png +0 -0
- data/lib/bioroebe/java/README.md +6 -0
- data/lib/bioroebe/java/bioroebe/AllInOne.class +0 -0
- data/lib/bioroebe/java/bioroebe/AllInOne.java +214 -0
- data/lib/bioroebe/java/bioroebe/Base.class +0 -0
- data/lib/bioroebe/java/bioroebe/Base.java +102 -0
- data/lib/bioroebe/java/bioroebe/BisulfiteTreatment.class +0 -0
- data/lib/bioroebe/java/bioroebe/BisulfiteTreatment.java +23 -0
- data/lib/bioroebe/java/bioroebe/Cat.class +0 -0
- data/lib/bioroebe/java/bioroebe/Codons.class +0 -0
- data/lib/bioroebe/java/bioroebe/Codons.java +22 -0
- data/lib/bioroebe/java/bioroebe/Esystem.class +0 -0
- data/lib/bioroebe/java/bioroebe/Esystem.java +47 -0
- data/lib/bioroebe/java/bioroebe/GUI/BaseFrame.class +0 -0
- data/lib/bioroebe/java/bioroebe/GUI/BaseFrame.java +65 -0
- data/lib/bioroebe/java/bioroebe/GenerateRandomDnaSequence.class +0 -0
- data/lib/bioroebe/java/bioroebe/GenerateRandomDnaSequence.java +32 -0
- data/lib/bioroebe/java/bioroebe/IsPalindrome.class +0 -0
- data/lib/bioroebe/java/bioroebe/IsPalindrome.java +18 -0
- data/lib/bioroebe/java/bioroebe/PartnerNucleotide.class +0 -0
- data/lib/bioroebe/java/bioroebe/PartnerNucleotide.java +19 -0
- data/lib/bioroebe/java/bioroebe/README.md +4 -0
- data/lib/bioroebe/java/bioroebe/RemoveFile.class +0 -0
- data/lib/bioroebe/java/bioroebe/RemoveFile.java +24 -0
- data/lib/bioroebe/java/bioroebe/RemoveNumbers.class +0 -0
- data/lib/bioroebe/java/bioroebe/RemoveNumbers.java +14 -0
- data/lib/bioroebe/java/bioroebe/SanitizeNucleotideSequence.class +0 -0
- data/lib/bioroebe/java/bioroebe/SanitizeNucleotideSequence.java +20 -0
- data/lib/bioroebe/java/bioroebe/SaveFile.java +44 -0
- data/lib/bioroebe/java/bioroebe/Sequence.java +28 -0
- data/lib/bioroebe/java/bioroebe/ToCamelcase.class +0 -0
- data/lib/bioroebe/java/bioroebe/ToCamelcase.java +32 -0
- data/lib/bioroebe/java/bioroebe/ToplevelMethods.class +0 -0
- data/lib/bioroebe/java/bioroebe/ToplevelMethods.java +15 -0
- data/lib/bioroebe/java/bioroebe/enums/DNA.java +6 -0
- data/lib/bioroebe/java/bioroebe.jar +0 -0
- data/lib/bioroebe/matplotlib/matplotlib_generator.rb +104 -0
- data/lib/bioroebe/misc/quiz/README.md +6 -0
- data/lib/bioroebe/misc/quiz/three_letter_to_aminoacid.rb +163 -0
- data/lib/bioroebe/misc/ruler.rb +244 -0
- data/lib/bioroebe/misc/useful_formulas.rb +129 -0
- data/lib/bioroebe/ncbi/efetch.rb +253 -0
- data/lib/bioroebe/ncbi/ncbi.rb +93 -0
- data/lib/bioroebe/ngs/README.md +2 -0
- data/lib/bioroebe/ngs/phred_quality_score_table.rb +123 -0
- data/lib/bioroebe/nucleotides/complementary_dna_strand.rb +166 -0
- data/lib/bioroebe/nucleotides/molecular_weight_of_nucleotides.rb +135 -0
- data/lib/bioroebe/nucleotides/most_likely_nucleotide_sequence_for_this_aminoacid_sequence.rb +198 -0
- data/lib/bioroebe/nucleotides/sanitize_nucleotide_sequence.rb +133 -0
- data/lib/bioroebe/nucleotides/show_nucleotide_sequence.rb +556 -0
- data/lib/bioroebe/palindromes/palindrome_2D_structure.rb +139 -0
- data/lib/bioroebe/palindromes/palindrome_finder.rb +208 -0
- data/lib/bioroebe/palindromes/palindrome_generator.rb +272 -0
- data/lib/bioroebe/parsers/biolang_parser.rb +156 -0
- data/lib/bioroebe/parsers/blosum_parser.rb +222 -0
- data/lib/bioroebe/parsers/genbank_parser.rb +78 -0
- data/lib/bioroebe/parsers/gff.rb +346 -0
- data/lib/bioroebe/parsers/parse_embl.rb +76 -0
- data/lib/bioroebe/parsers/stride_parser.rb +117 -0
- data/lib/bioroebe/patterns/README.md +5 -0
- data/lib/bioroebe/patterns/analyse_glycosylation_pattern.rb +149 -0
- data/lib/bioroebe/patterns/is_this_sequence_a_EGF2_pattern.rb +66 -0
- data/lib/bioroebe/patterns/profile_pattern.rb +182 -0
- data/lib/bioroebe/patterns/rgg_scanner.rb +160 -0
- data/lib/bioroebe/patterns/scan_for_repeat.rb +157 -0
- data/lib/bioroebe/pdb/download_this_pdb.rb +67 -0
- data/lib/bioroebe/pdb/fetch_fasta_sequence_from_pdb.rb +164 -0
- data/lib/bioroebe/pdb/parse_mmCIF_file.rb +63 -0
- data/lib/bioroebe/pdb/parse_pdb_file.rb +1086 -0
- data/lib/bioroebe/pdb/report_secondary_structures_from_this_pdb_file.rb +225 -0
- data/lib/bioroebe/perl/README.md +7 -0
- data/lib/bioroebe/perl/local_to_global.pl +694 -0
- data/lib/bioroebe/project/project.rb +264 -0
- data/lib/bioroebe/protein_structure/alpha_helix.rb +96 -0
- data/lib/bioroebe/protein_structure/helical_wheel.rb +205 -0
- data/lib/bioroebe/raw_sequence/README.md +17 -0
- data/lib/bioroebe/raw_sequence/raw_sequence.rb +557 -0
- data/lib/bioroebe/readline/README.md +2 -0
- data/lib/bioroebe/readline/readline.rb +31 -0
- data/lib/bioroebe/regexes/README.md +2 -0
- data/lib/bioroebe/regexes/regexes.rb +34 -0
- data/lib/bioroebe/requires/commandline_application.rb +5 -0
- data/lib/bioroebe/requires/require_all_aminoacids_files.rb +28 -0
- data/lib/bioroebe/requires/require_all_calculate_files.rb +26 -0
- data/lib/bioroebe/requires/require_all_codon_files.rb +26 -0
- data/lib/bioroebe/requires/require_all_colour_scheme_files.rb +26 -0
- data/lib/bioroebe/requires/require_all_count_files.rb +26 -0
- data/lib/bioroebe/requires/require_all_dotplot_files.rb +28 -0
- data/lib/bioroebe/requires/require_all_electron_microscopy_files.rb +26 -0
- data/lib/bioroebe/requires/require_all_enzymes_files.rb +28 -0
- data/lib/bioroebe/requires/require_all_fasta_and_fastq_files.rb +32 -0
- data/lib/bioroebe/requires/require_all_nucleotides_files.rb +28 -0
- data/lib/bioroebe/requires/require_all_palindromes_files.rb +29 -0
- data/lib/bioroebe/requires/require_all_parser_files.rb +28 -0
- data/lib/bioroebe/requires/require_all_pattern_files.rb +29 -0
- data/lib/bioroebe/requires/require_all_pdb_files.rb +26 -0
- data/lib/bioroebe/requires/require_all_sequence_files.rb +26 -0
- data/lib/bioroebe/requires/require_all_string_matching_files.rb +28 -0
- data/lib/bioroebe/requires/require_all_svg_files.rb +12 -0
- data/lib/bioroebe/requires/require_all_taxonomy_files.rb +35 -0
- data/lib/bioroebe/requires/require_all_utility_scripts_files.rb +32 -0
- data/lib/bioroebe/requires/require_cleave_and_digest.rb +24 -0
- data/lib/bioroebe/requires/require_colours.rb +20 -0
- data/lib/bioroebe/requires/require_encoding.rb +7 -0
- data/lib/bioroebe/requires/require_sequence.rb +7 -0
- data/lib/bioroebe/requires/require_the_bioroebe_project.rb +162 -0
- data/lib/bioroebe/requires/require_the_bioroebe_shell.rb +7 -0
- data/lib/bioroebe/requires/require_the_bioroebe_sinatra_components.rb +7 -0
- data/lib/bioroebe/requires/require_the_constants.rb +23 -0
- data/lib/bioroebe/requires/require_the_toplevel_methods.rb +29 -0
- data/lib/bioroebe/requires/require_yaml.rb +94 -0
- data/lib/bioroebe/sequence/alignment.rb +214 -0
- data/lib/bioroebe/sequence/dna.rb +211 -0
- data/lib/bioroebe/sequence/nucleotide_module/nucleotide_module.rb +404 -0
- data/lib/bioroebe/sequence/protein.rb +281 -0
- data/lib/bioroebe/sequence/reverse_complement.rb +148 -0
- data/lib/bioroebe/sequence/sequence.rb +706 -0
- data/lib/bioroebe/shell/add.rb +108 -0
- data/lib/bioroebe/shell/assign.rb +360 -0
- data/lib/bioroebe/shell/chop_and_cut.rb +281 -0
- data/lib/bioroebe/shell/colours/colours.rb +235 -0
- data/lib/bioroebe/shell/configuration/additionally_set_xorg_buffer.yml +1 -0
- data/lib/bioroebe/shell/configuration/may_we_show_the_startup_information.yml +1 -0
- data/lib/bioroebe/shell/configuration/upcase_nucleotides.yml +1 -0
- data/lib/bioroebe/shell/configuration/use_silent_startup.yml +1 -0
- data/lib/bioroebe/shell/constants.rb +166 -0
- data/lib/bioroebe/shell/download.rb +335 -0
- data/lib/bioroebe/shell/enable_and_disable.rb +158 -0
- data/lib/bioroebe/shell/enzymes.rb +310 -0
- data/lib/bioroebe/shell/fasta.rb +345 -0
- data/lib/bioroebe/shell/gtk.rb +76 -0
- data/lib/bioroebe/shell/help/class.rb +443 -0
- data/lib/bioroebe/shell/help/help.rb +25 -0
- data/lib/bioroebe/shell/history.rb +132 -0
- data/lib/bioroebe/shell/initialize.rb +217 -0
- data/lib/bioroebe/shell/loop.rb +74 -0
- data/lib/bioroebe/shell/menu.rb +5320 -0
- data/lib/bioroebe/shell/misc.rb +4341 -0
- data/lib/bioroebe/shell/prompt.rb +107 -0
- data/lib/bioroebe/shell/random.rb +289 -0
- data/lib/bioroebe/shell/readline/readline.rb +91 -0
- data/lib/bioroebe/shell/reset.rb +335 -0
- data/lib/bioroebe/shell/scan_and_parse.rb +135 -0
- data/lib/bioroebe/shell/search.rb +337 -0
- data/lib/bioroebe/shell/sequences.rb +200 -0
- data/lib/bioroebe/shell/shell.rb +41 -0
- data/lib/bioroebe/shell/show_report_and_display.rb +2901 -0
- data/lib/bioroebe/shell/startup.rb +127 -0
- data/lib/bioroebe/shell/taxonomy.rb +14 -0
- data/lib/bioroebe/shell/tk.rb +23 -0
- data/lib/bioroebe/shell/user_input.rb +88 -0
- data/lib/bioroebe/shell/xorg.rb +45 -0
- data/lib/bioroebe/siRNA/README.md +2 -0
- data/lib/bioroebe/siRNA/siRNA.rb +93 -0
- data/lib/bioroebe/string_matching/README.md +13 -0
- data/lib/bioroebe/string_matching/find_longest_substring.rb +162 -0
- data/lib/bioroebe/string_matching/find_longest_substring_via_LCS_algorithm.rb +175 -0
- data/lib/bioroebe/string_matching/hamming_distance.rb +313 -0
- data/lib/bioroebe/string_matching/levensthein.rb +698 -0
- data/lib/bioroebe/string_matching/simple_string_comparer.rb +294 -0
- data/lib/bioroebe/string_matching/smith_waterman.rb +276 -0
- data/lib/bioroebe/svg/README.md +1 -0
- data/lib/bioroebe/svg/glyph.rb +719 -0
- data/lib/bioroebe/svg/mini_feature.rb +111 -0
- data/lib/bioroebe/svg/page.rb +570 -0
- data/lib/bioroebe/svg/primitive.rb +70 -0
- data/lib/bioroebe/svg/svgee.rb +326 -0
- data/lib/bioroebe/svg/track.rb +263 -0
- data/lib/bioroebe/taxonomy/README.md +1 -0
- data/lib/bioroebe/taxonomy/chart.rb +95 -0
- data/lib/bioroebe/taxonomy/class_methods.rb +181 -0
- data/lib/bioroebe/taxonomy/colours.rb +26 -0
- data/lib/bioroebe/taxonomy/constants.rb +218 -0
- data/lib/bioroebe/taxonomy/edit.rb +97 -0
- data/lib/bioroebe/taxonomy/help/help.rb +65 -0
- data/lib/bioroebe/taxonomy/help/helpline.rb +53 -0
- data/lib/bioroebe/taxonomy/info/check_available.rb +143 -0
- data/lib/bioroebe/taxonomy/info/info.rb +337 -0
- data/lib/bioroebe/taxonomy/info/is_dna.rb +150 -0
- data/lib/bioroebe/taxonomy/interactive.rb +1933 -0
- data/lib/bioroebe/taxonomy/menu.rb +905 -0
- data/lib/bioroebe/taxonomy/node.rb +118 -0
- data/lib/bioroebe/taxonomy/parse_fasta.rb +383 -0
- data/lib/bioroebe/taxonomy/shared.rb +287 -0
- data/lib/bioroebe/taxonomy/taxonomy.rb +521 -0
- data/lib/bioroebe/toplevel_methods/ad_hoc_task.rb +56 -0
- data/lib/bioroebe/toplevel_methods/aminoacids_and_proteins.rb +715 -0
- data/lib/bioroebe/toplevel_methods/atomic_composition.rb +198 -0
- data/lib/bioroebe/toplevel_methods/base_composition.rb +121 -0
- data/lib/bioroebe/toplevel_methods/blast.rb +153 -0
- data/lib/bioroebe/toplevel_methods/calculate_n50_value.rb +57 -0
- data/lib/bioroebe/toplevel_methods/cat.rb +71 -0
- data/lib/bioroebe/toplevel_methods/chunked_display.rb +92 -0
- data/lib/bioroebe/toplevel_methods/cliner.rb +81 -0
- data/lib/bioroebe/toplevel_methods/complement.rb +58 -0
- data/lib/bioroebe/toplevel_methods/convert_global_env.rb +39 -0
- data/lib/bioroebe/toplevel_methods/databases.rb +73 -0
- data/lib/bioroebe/toplevel_methods/delimiter.rb +19 -0
- data/lib/bioroebe/toplevel_methods/digest.rb +71 -0
- data/lib/bioroebe/toplevel_methods/download_and_fetch_data.rb +146 -0
- data/lib/bioroebe/toplevel_methods/e.rb +20 -0
- data/lib/bioroebe/toplevel_methods/editor.rb +21 -0
- data/lib/bioroebe/toplevel_methods/esystem.rb +22 -0
- data/lib/bioroebe/toplevel_methods/exponential_growth.rb +74 -0
- data/lib/bioroebe/toplevel_methods/extract.rb +56 -0
- data/lib/bioroebe/toplevel_methods/fasta_and_fastq.rb +353 -0
- data/lib/bioroebe/toplevel_methods/file_and_directory_related_actions.rb +257 -0
- data/lib/bioroebe/toplevel_methods/frequencies.rb +92 -0
- data/lib/bioroebe/toplevel_methods/hamming_distance.rb +60 -0
- data/lib/bioroebe/toplevel_methods/infer.rb +66 -0
- data/lib/bioroebe/toplevel_methods/is_on_roebe.rb +39 -0
- data/lib/bioroebe/toplevel_methods/leading_five_prime_and_trailing_three_prime.rb +101 -0
- data/lib/bioroebe/toplevel_methods/levensthein.rb +63 -0
- data/lib/bioroebe/toplevel_methods/log_directory.rb +109 -0
- data/lib/bioroebe/toplevel_methods/longest_common_substring.rb +55 -0
- data/lib/bioroebe/toplevel_methods/map_ncbi_entry_to_eutils_id.rb +88 -0
- data/lib/bioroebe/toplevel_methods/matches.rb +259 -0
- data/lib/bioroebe/toplevel_methods/misc.rb +432 -0
- data/lib/bioroebe/toplevel_methods/nucleotides.rb +715 -0
- data/lib/bioroebe/toplevel_methods/number_of_clones.rb +63 -0
- data/lib/bioroebe/toplevel_methods/open_in_browser.rb +77 -0
- data/lib/bioroebe/toplevel_methods/open_reading_frames.rb +236 -0
- data/lib/bioroebe/toplevel_methods/opn.rb +34 -0
- data/lib/bioroebe/toplevel_methods/palindromes.rb +127 -0
- data/lib/bioroebe/toplevel_methods/parse.rb +59 -0
- data/lib/bioroebe/toplevel_methods/phred_error_probability.rb +68 -0
- data/lib/bioroebe/toplevel_methods/rds.rb +24 -0
- data/lib/bioroebe/toplevel_methods/remove.rb +86 -0
- data/lib/bioroebe/toplevel_methods/return_source_code_of_this_method.rb +35 -0
- data/lib/bioroebe/toplevel_methods/return_subsequence_based_on_indices.rb +68 -0
- data/lib/bioroebe/toplevel_methods/rna_splicing.rb +73 -0
- data/lib/bioroebe/toplevel_methods/rnalfold.rb +69 -0
- data/lib/bioroebe/toplevel_methods/searching_and_finding.rb +116 -0
- data/lib/bioroebe/toplevel_methods/shuffleseq.rb +37 -0
- data/lib/bioroebe/toplevel_methods/statistics.rb +53 -0
- data/lib/bioroebe/toplevel_methods/sum_of_odd_integers.rb +62 -0
- data/lib/bioroebe/toplevel_methods/taxonomy.rb +187 -0
- data/lib/bioroebe/toplevel_methods/three_delimiter.rb +34 -0
- data/lib/bioroebe/toplevel_methods/time_and_date.rb +53 -0
- data/lib/bioroebe/toplevel_methods/to_camelcase.rb +26 -0
- data/lib/bioroebe/toplevel_methods/truncate.rb +48 -0
- data/lib/bioroebe/toplevel_methods/url.rb +36 -0
- data/lib/bioroebe/toplevel_methods/verbose.rb +59 -0
- data/lib/bioroebe/utility_scripts/align_open_reading_frames.rb +191 -0
- data/lib/bioroebe/utility_scripts/analyse_local_dataset.rb +119 -0
- data/lib/bioroebe/utility_scripts/check_for_mismatches/check_for_mismatches.rb +230 -0
- data/lib/bioroebe/utility_scripts/compacter.rb +131 -0
- data/lib/bioroebe/utility_scripts/compseq/compseq.rb +529 -0
- data/lib/bioroebe/utility_scripts/consensus_sequence.rb +374 -0
- data/lib/bioroebe/utility_scripts/create_batch_entrez_file.rb +130 -0
- data/lib/bioroebe/utility_scripts/determine_antigenic_areas.rb +115 -0
- data/lib/bioroebe/utility_scripts/determine_missing_nucleotides_percentage.rb +137 -0
- data/lib/bioroebe/utility_scripts/display_open_reading_frames/determine.rb +73 -0
- data/lib/bioroebe/utility_scripts/display_open_reading_frames/display_open_reading_frames.rb +31 -0
- data/lib/bioroebe/utility_scripts/display_open_reading_frames/initialize.rb +37 -0
- data/lib/bioroebe/utility_scripts/display_open_reading_frames/menu.rb +49 -0
- data/lib/bioroebe/utility_scripts/display_open_reading_frames/misc.rb +471 -0
- data/lib/bioroebe/utility_scripts/display_open_reading_frames/report.rb +113 -0
- data/lib/bioroebe/utility_scripts/display_open_reading_frames/reset.rb +56 -0
- data/lib/bioroebe/utility_scripts/dot_alignment.rb +177 -0
- data/lib/bioroebe/utility_scripts/download_files_from_rebase.rb +72 -0
- data/lib/bioroebe/utility_scripts/find_gene.rb +202 -0
- data/lib/bioroebe/utility_scripts/mirror_repeat.rb +235 -0
- data/lib/bioroebe/utility_scripts/move_file_to_its_correct_location.rb +151 -0
- data/lib/bioroebe/utility_scripts/parse_taxonomy.rb +168 -0
- data/lib/bioroebe/utility_scripts/pathways.rb +152 -0
- data/lib/bioroebe/utility_scripts/permutations.rb +145 -0
- data/lib/bioroebe/utility_scripts/punnet/punnet.rb +126 -0
- data/lib/bioroebe/utility_scripts/show_this_dna_sequence.rb +148 -0
- data/lib/bioroebe/utility_scripts/showorf/constants.rb +36 -0
- data/lib/bioroebe/utility_scripts/showorf/help.rb +33 -0
- data/lib/bioroebe/utility_scripts/showorf/initialize.rb +52 -0
- data/lib/bioroebe/utility_scripts/showorf/menu.rb +68 -0
- data/lib/bioroebe/utility_scripts/showorf/reset.rb +39 -0
- data/lib/bioroebe/utility_scripts/showorf/run.rb +152 -0
- data/lib/bioroebe/utility_scripts/showorf/show.rb +97 -0
- data/lib/bioroebe/utility_scripts/showorf/showorf.rb +488 -0
- data/lib/bioroebe/version/version.rb +44 -0
- data/lib/bioroebe/viennarna/README.md +3 -0
- data/lib/bioroebe/viennarna/rnafold_wrapper.rb +196 -0
- data/lib/bioroebe/with_gui.rb +18 -0
- data/lib/bioroebe/www/bioroebe.cgi +44 -0
- data/lib/bioroebe/www/embeddable_interface.rb +686 -0
- data/lib/bioroebe/www/sinatra/sinatra.rb +1013 -0
- data/lib/bioroebe/yaml/agarose/agarose_concentrations.yml +21 -0
- data/lib/bioroebe/yaml/aminoacids/amino_acids.yml +92 -0
- data/lib/bioroebe/yaml/aminoacids/amino_acids_abbreviations.yml +31 -0
- data/lib/bioroebe/yaml/aminoacids/amino_acids_average_mass_table.yml +33 -0
- data/lib/bioroebe/yaml/aminoacids/amino_acids_classification.yml +18 -0
- data/lib/bioroebe/yaml/aminoacids/amino_acids_english.yml +26 -0
- data/lib/bioroebe/yaml/aminoacids/amino_acids_frequency.yml +44 -0
- data/lib/bioroebe/yaml/aminoacids/amino_acids_long_name_to_one_letter.yml +61 -0
- data/lib/bioroebe/yaml/aminoacids/amino_acids_molecular_formula.yml +32 -0
- data/lib/bioroebe/yaml/aminoacids/amino_acids_monoisotopic_mass_table.yml +38 -0
- data/lib/bioroebe/yaml/aminoacids/amino_acids_reste.yml +35 -0
- data/lib/bioroebe/yaml/aminoacids/amino_acids_three_to_one.yml +34 -0
- data/lib/bioroebe/yaml/aminoacids/hydropathy_table.yml +44 -0
- data/lib/bioroebe/yaml/aminoacids/molecular_weight.yml +29 -0
- data/lib/bioroebe/yaml/aminoacids/simple_aminoacids.yml +66 -0
- data/lib/bioroebe/yaml/aminoacids/weight_of_common_proteins.yml +33 -0
- data/lib/bioroebe/yaml/antisense/antisense.yml +9 -0
- data/lib/bioroebe/yaml/base_composition_of_dna.yml +37 -0
- data/lib/bioroebe/yaml/blosum/blosum45.yml +36 -0
- data/lib/bioroebe/yaml/blosum/blosum50.yml +34 -0
- data/lib/bioroebe/yaml/blosum/blosum62.yml +35 -0
- data/lib/bioroebe/yaml/blosum/blosum80.yml +37 -0
- data/lib/bioroebe/yaml/blosum/blosum90.yml +36 -0
- data/lib/bioroebe/yaml/blosum/blosum_matrix.yml +200 -0
- data/lib/bioroebe/yaml/chromosomes/chromosome_numbers.yml +30 -0
- data/lib/bioroebe/yaml/codon_tables/1.yml +113 -0
- data/lib/bioroebe/yaml/codon_tables/10.yml +89 -0
- data/lib/bioroebe/yaml/codon_tables/11.yml +91 -0
- data/lib/bioroebe/yaml/codon_tables/12.yml +89 -0
- data/lib/bioroebe/yaml/codon_tables/13.yml +89 -0
- data/lib/bioroebe/yaml/codon_tables/14.yml +89 -0
- data/lib/bioroebe/yaml/codon_tables/15.yml +94 -0
- data/lib/bioroebe/yaml/codon_tables/16.yml +89 -0
- data/lib/bioroebe/yaml/codon_tables/2.yml +86 -0
- data/lib/bioroebe/yaml/codon_tables/21.yml +89 -0
- data/lib/bioroebe/yaml/codon_tables/22.yml +89 -0
- data/lib/bioroebe/yaml/codon_tables/23.yml +91 -0
- data/lib/bioroebe/yaml/codon_tables/24.yml +89 -0
- data/lib/bioroebe/yaml/codon_tables/25.yml +89 -0
- data/lib/bioroebe/yaml/codon_tables/26.yml +96 -0
- data/lib/bioroebe/yaml/codon_tables/27.yml +104 -0
- data/lib/bioroebe/yaml/codon_tables/28.yml +97 -0
- data/lib/bioroebe/yaml/codon_tables/29.yml +93 -0
- data/lib/bioroebe/yaml/codon_tables/3.yml +98 -0
- data/lib/bioroebe/yaml/codon_tables/30.yml +91 -0
- data/lib/bioroebe/yaml/codon_tables/31.yml +94 -0
- data/lib/bioroebe/yaml/codon_tables/33.yml +101 -0
- data/lib/bioroebe/yaml/codon_tables/4.yml +96 -0
- data/lib/bioroebe/yaml/codon_tables/5.yml +100 -0
- data/lib/bioroebe/yaml/codon_tables/6.yml +96 -0
- data/lib/bioroebe/yaml/codon_tables/9.yml +97 -0
- data/lib/bioroebe/yaml/codon_tables/overview.yml +42 -0
- data/lib/bioroebe/yaml/configuration/README.md +12 -0
- data/lib/bioroebe/yaml/configuration/browser.yml +1 -0
- data/lib/bioroebe/yaml/configuration/colourize_fasta_sequences.yml +14 -0
- data/lib/bioroebe/yaml/configuration/default_colours_for_the_aminoacids.yml +28 -0
- data/lib/bioroebe/yaml/configuration/temp_dir.yml +1 -0
- data/lib/bioroebe/yaml/configuration/try_to_use_matplotlib.yml +1 -0
- data/lib/bioroebe/yaml/configuration/use_opn.yml +1 -0
- data/lib/bioroebe/yaml/configuration/use_this_database.yml +1 -0
- data/lib/bioroebe/yaml/create_these_directories_on_startup/create_these_directories_on_startup.yml +9 -0
- data/lib/bioroebe/yaml/default_dna_input.yml +3 -0
- data/lib/bioroebe/yaml/enzymes/enzyme_classes.yml +15 -0
- data/lib/bioroebe/yaml/enzymes/pH-Optima.yml +11 -0
- data/lib/bioroebe/yaml/fasta_and_fastq/fastq_quality_schemes.yml +44 -0
- data/lib/bioroebe/yaml/genomes/README.md +16 -0
- data/lib/bioroebe/yaml/humans/README.md +2 -0
- data/lib/bioroebe/yaml/humans/human_chromosomes.yml +53 -0
- data/lib/bioroebe/yaml/laboratory/README.md +1 -0
- data/lib/bioroebe/yaml/laboratory/pipettes.yml +8 -0
- data/lib/bioroebe/yaml/mRNA/mRNA.yml +16 -0
- data/lib/bioroebe/yaml/nuclear_localization_sequences.yml +15 -0
- data/lib/bioroebe/yaml/nucleotides/abbreviations_for_nucleotides.yml +29 -0
- data/lib/bioroebe/yaml/nucleotides/nucleotide_density.yml +10 -0
- data/lib/bioroebe/yaml/nucleotides/nucleotides.yml +34 -0
- data/lib/bioroebe/yaml/nucleotides/nucleotides_weight.yml +12 -0
- data/lib/bioroebe/yaml/pathways/README.md +2 -0
- data/lib/bioroebe/yaml/pathways/citric_acid_cycle.yml +16 -0
- data/lib/bioroebe/yaml/pathways/glycolysis.yml +20 -0
- data/lib/bioroebe/yaml/pathways/shikimate_pathway.yml +23 -0
- data/lib/bioroebe/yaml/pathways/urea_cycle.yml +11 -0
- data/lib/bioroebe/yaml/primers/README.md +4 -0
- data/lib/bioroebe/yaml/primers/primers.yml +3 -0
- data/lib/bioroebe/yaml/promoters/35S.yml +15 -0
- data/lib/bioroebe/yaml/promoters/strong_promoters.yml +24 -0
- data/lib/bioroebe/yaml/proteases/proteases.yml +3 -0
- data/lib/bioroebe/yaml/proteins/ubiquitin.yml +4 -0
- data/lib/bioroebe/yaml/remote_urls/README.md +4 -0
- data/lib/bioroebe/yaml/remote_urls/remote_urls.yml +3 -0
- data/lib/bioroebe/yaml/restriction_enzymes/restriction_enzymes.yml +630 -0
- data/lib/bioroebe/yaml/sequences/JX472995_Green_fluorescent_protein_from_Aequorea_victoria.fasta +14 -0
- data/lib/bioroebe/yaml/sequences/README.md +2 -0
- data/lib/bioroebe/yaml/talens.yml +22 -0
- data/lib/bioroebe/yaml/viruses/ecoli_phages.yml +63 -0
- data/lib/bioroebe/yaml/viruses/viruses.yml +6 -0
- data/lib/bioroebe.rb +5 -0
- data/spec/testing_toplevel_method_editor.rb +20 -0
- data/spec/testing_toplevel_method_url.rb +15 -0
- data/spec/testing_toplevel_method_verbose.rb +13 -0
- data/test/advanced_svg_example.rb +307 -0
- data/test/testing_bioroebe.rb +25 -0
- data/test/testing_codons.rb +45 -0
- data/test/testing_dna_to_rna_conversion.rb +15 -0
- data/test/testing_parse_pdb_file.rb +23 -0
- data/test/testing_reverse_complement.rb +32 -0
- data/test/testing_svg_component_of_bioroebe.rb +311 -0
- data/test/testing_svg_component_of_bioroebe_from_json_dataset.rb +34 -0
- data/test/testing_taxonomy.rb +22 -0
- metadata +1059 -0
@@ -0,0 +1,981 @@
|
|
1
|
+
#!/usr/bin/ruby -w
|
2
|
+
# Encoding: UTF-8
|
3
|
+
# frozen_string_literal: true
|
4
|
+
# =========================================================================== #
|
5
|
+
# === Bioroebe::ParseFasta
|
6
|
+
#
|
7
|
+
# This class will parse through a local FASTA file and find the
|
8
|
+
# proper entries.
|
9
|
+
#
|
10
|
+
# A FASTA file may have nucleotides or an aminoacid-sequence, so
|
11
|
+
# we have to keep this in mind when parsing it.
|
12
|
+
#
|
13
|
+
# Usage examples:
|
14
|
+
#
|
15
|
+
# Bioroebe::ParseFasta.new(ARGV)
|
16
|
+
# Bioroebe.parse_fasta(ARGV)
|
17
|
+
#
|
18
|
+
# =========================================================================== #
|
19
|
+
# require 'bioroebe/fasta_and_fastq/parse_fasta/misc.rb'
|
20
|
+
# Bioroebe.parse_fasta
|
21
|
+
# Bioroebe.sizeseq
|
22
|
+
# =========================================================================== #
|
23
|
+
require 'bioroebe/base/commandline_application/commandline_application.rb'
|
24
|
+
require 'bioroebe/fasta_and_fastq/parse_fasta/menu.rb'
|
25
|
+
require 'bioroebe/fasta_and_fastq/parse_fasta/report.rb'
|
26
|
+
|
27
|
+
module Bioroebe
|
28
|
+
|
29
|
+
class ParseFasta < ::Bioroebe::CommandlineApplication # === Bioroebe::ParseFasta
|
30
|
+
|
31
|
+
require 'bioroebe/calculate/calculate_gc_content.rb'
|
32
|
+
|
33
|
+
# ========================================================================= #
|
34
|
+
# === show_help (help tag)
|
35
|
+
#
|
36
|
+
# This method will inform the user how this class may be used from the
|
37
|
+
# commandline.
|
38
|
+
#
|
39
|
+
# Invocation example:
|
40
|
+
#
|
41
|
+
# pfasta --help
|
42
|
+
#
|
43
|
+
# ========================================================================= #
|
44
|
+
def show_help
|
45
|
+
e
|
46
|
+
eparse ' --size'
|
47
|
+
eparse ' --also-show-the-sequence'
|
48
|
+
eparse ' --header # show the header as well (normally the '\
|
49
|
+
'header is not shown)'
|
50
|
+
eparse ' --limit=1000 # limit to show only the first 1000 '\
|
51
|
+
'nucleotides; use'
|
52
|
+
eparse ' # any number that you need here'
|
53
|
+
eparse ' --one-line # show the sequence on one line only, '\
|
54
|
+
'e. g. all newlines'
|
55
|
+
eparse ' # were removed'
|
56
|
+
eparse ' --toprotein # show the protein sequence as well '\
|
57
|
+
'(assumes DNA or RNA'
|
58
|
+
eparse ' # .fasta file)'
|
59
|
+
e
|
60
|
+
end
|
61
|
+
|
62
|
+
# ========================================================================= #
|
63
|
+
# === show_the_translated_protein_sequence?
|
64
|
+
# ========================================================================= #
|
65
|
+
def show_the_translated_protein_sequence?
|
66
|
+
@internal_hash[:show_the_translated_protein_sequence]
|
67
|
+
end
|
68
|
+
|
69
|
+
# ========================================================================= #
|
70
|
+
# === set_round_to
|
71
|
+
#
|
72
|
+
# This will set to how many decimal numbers we will round to. This is
|
73
|
+
# mostly done for display-purposes, hence why the default is a fairly
|
74
|
+
# low value.
|
75
|
+
# ========================================================================= #
|
76
|
+
def set_round_to(
|
77
|
+
i = :default
|
78
|
+
)
|
79
|
+
case i
|
80
|
+
# ======================================================================= #
|
81
|
+
# === :default
|
82
|
+
#
|
83
|
+
# Since as of April 2021, the new default is 2, for rounding.
|
84
|
+
# ======================================================================= #
|
85
|
+
when :default
|
86
|
+
i = DEFAULT_ROUND_TO
|
87
|
+
end
|
88
|
+
@round_to = i.to_i
|
89
|
+
end
|
90
|
+
|
91
|
+
# ========================================================================= #
|
92
|
+
# === do_process_the_commandline_arguments_that_are_files
|
93
|
+
# ========================================================================= #
|
94
|
+
def do_process_the_commandline_arguments_that_are_files(
|
95
|
+
these_files = commandline_arguments_that_are_files?
|
96
|
+
)
|
97
|
+
unless these_files.is_a? Array
|
98
|
+
these_files = [these_files].flatten.compact
|
99
|
+
end
|
100
|
+
these_files.each {|this_file|
|
101
|
+
set_input_file(this_file)
|
102
|
+
set_data # This will use the default file.
|
103
|
+
split_into_proper_sections
|
104
|
+
report_the_FASTA_header if @show_the_header
|
105
|
+
if @sort_by_size
|
106
|
+
run_sizeseq_comparison
|
107
|
+
else
|
108
|
+
# =================================================================== #
|
109
|
+
# === Handle cases where the input is a protein
|
110
|
+
# =================================================================== #
|
111
|
+
if is_the_sequence_a_polypeptide?
|
112
|
+
if be_verbose?
|
113
|
+
erev "This sequence is assumed to be a #{royalblue('protein')}#{rev}."
|
114
|
+
report_how_many_elements_we_have_found
|
115
|
+
end
|
116
|
+
else # Must be a protein.
|
117
|
+
# =================================================================== #
|
118
|
+
# === Else it must be RNA or DNA
|
119
|
+
# =================================================================== #
|
120
|
+
if be_verbose?
|
121
|
+
erev "This sequence is assumed to "\
|
122
|
+
"be #{royalblue('DNA')}#{rev} or #{royalblue('RNA')}#{rev}."
|
123
|
+
end
|
124
|
+
calculate_gc_content # GC content makes only sense for nucleotides.
|
125
|
+
report_how_many_elements_we_have_found if be_verbose?
|
126
|
+
end
|
127
|
+
if be_verbose?
|
128
|
+
report_the_nucleotide_composition
|
129
|
+
report_on_how_many_entries_we_did_work
|
130
|
+
if report_the_sequence?
|
131
|
+
do_report_the_sequence
|
132
|
+
end
|
133
|
+
end
|
134
|
+
end
|
135
|
+
}
|
136
|
+
end
|
137
|
+
|
138
|
+
# ========================================================================= #
|
139
|
+
# === sanitize_the_description
|
140
|
+
#
|
141
|
+
# This method will iterate over the description entry and sanitize
|
142
|
+
# it. In this context sanitizing means to add the "length" entry,
|
143
|
+
# and the "type" entry, such as in:
|
144
|
+
#
|
145
|
+
# " # length=231; type=dna"
|
146
|
+
#
|
147
|
+
# ========================================================================= #
|
148
|
+
def sanitize_the_description
|
149
|
+
@data.map! {|line|
|
150
|
+
if line.start_with?('>') and !line.include?('length=')
|
151
|
+
length = 0
|
152
|
+
if @hash.has_key? line.delete('>')
|
153
|
+
length = @hash[line.delete('>')].size
|
154
|
+
end
|
155
|
+
line << " # length=#{length}; type=dna" # Currently hardcoded to DNA.
|
156
|
+
end
|
157
|
+
line
|
158
|
+
}
|
159
|
+
end
|
160
|
+
|
161
|
+
# ========================================================================= #
|
162
|
+
# === entries?
|
163
|
+
# ========================================================================= #
|
164
|
+
def entries?
|
165
|
+
@data
|
166
|
+
end
|
167
|
+
|
168
|
+
# ========================================================================= #
|
169
|
+
# === we_may_exit
|
170
|
+
# ========================================================================= #
|
171
|
+
def we_may_exit
|
172
|
+
@may_we_exit = true
|
173
|
+
end
|
174
|
+
|
175
|
+
# ========================================================================= #
|
176
|
+
# === output_results
|
177
|
+
# ========================================================================= #
|
178
|
+
def output_results
|
179
|
+
pp @hash
|
180
|
+
end
|
181
|
+
|
182
|
+
# ========================================================================= #
|
183
|
+
# === sanitize_data
|
184
|
+
# ========================================================================= #
|
185
|
+
def sanitize_data(i)
|
186
|
+
if i.is_a? Array
|
187
|
+
i.flatten!
|
188
|
+
i.reject! {|entry| entry.start_with? '#' }
|
189
|
+
i.reject! {|entry| entry.strip.empty? }
|
190
|
+
if i.first and i.first.include? "\r"
|
191
|
+
# =================================================================== #
|
192
|
+
# Some FASTA files include "\r" line endings. We will check first
|
193
|
+
# for the first entry to contain a \r, and if so, we assume the
|
194
|
+
# whole FASTA file may have \r, which then will be removed.
|
195
|
+
# =================================================================== #
|
196
|
+
i.map! {|entry| entry.delete("\r") }
|
197
|
+
end
|
198
|
+
end
|
199
|
+
# ========================================================================= #
|
200
|
+
# === Run through SanitizeNucleotideSequence
|
201
|
+
# ========================================================================= #
|
202
|
+
if @internal_hash[:remove_numbers_from_input]
|
203
|
+
i = Bioroebe::SanitizeNucleotideSequence[i]
|
204
|
+
end
|
205
|
+
i
|
206
|
+
end
|
207
|
+
|
208
|
+
# ========================================================================= #
|
209
|
+
# === current_key?
|
210
|
+
# ========================================================================= #
|
211
|
+
def current_key?
|
212
|
+
@current_key
|
213
|
+
end; alias id? current_key? # === id?
|
214
|
+
alias sequence_id? current_key? # === sequence_id?
|
215
|
+
alias title current_key? # === title
|
216
|
+
alias title? current_key? # === title?
|
217
|
+
|
218
|
+
# ========================================================================= #
|
219
|
+
# === opnn
|
220
|
+
# ========================================================================= #
|
221
|
+
def opnn
|
222
|
+
super(NAMESPACE) if use_opn?
|
223
|
+
end
|
224
|
+
|
225
|
+
# ========================================================================= #
|
226
|
+
# === use_opn?
|
227
|
+
# ========================================================================= #
|
228
|
+
def use_opn?
|
229
|
+
@use_opn
|
230
|
+
end
|
231
|
+
|
232
|
+
# ========================================================================= #
|
233
|
+
# === calculate_gc_content
|
234
|
+
#
|
235
|
+
# Calculate the gc content through this method, which is called from
|
236
|
+
# within the method run().
|
237
|
+
# ========================================================================= #
|
238
|
+
def calculate_gc_content
|
239
|
+
_ = @hash.values.join.delete(N)
|
240
|
+
if is_polynucleotide? _
|
241
|
+
@hash.each_pair {|key, content|
|
242
|
+
# =================================================================== #
|
243
|
+
# Delegate towards the method Bioroebe.gc_content next, including
|
244
|
+
# to round towards 5 positions:
|
245
|
+
# =================================================================== #
|
246
|
+
gc_content = ::Bioroebe.gc_content(content.upcase, @round_to)
|
247
|
+
gc_content = gc_content.first if gc_content.is_a? Array
|
248
|
+
gc_content = gc_content.to_s
|
249
|
+
minimal_key = key.to_s
|
250
|
+
if minimal_key.include? '|'
|
251
|
+
minimal_key = minimal_key.split('|').last.strip
|
252
|
+
end
|
253
|
+
if be_verbose?
|
254
|
+
_ = minimal_key.strip
|
255
|
+
if _.size > 40 # Shorten the content a bit if it is too long.
|
256
|
+
_ = _[0 .. 40]+' [...]'
|
257
|
+
end
|
258
|
+
erev 'GC content of "'+simp(_)+rev+'" is: '+
|
259
|
+
"#{sfancy(gc_content)}#{rev} %"
|
260
|
+
end
|
261
|
+
}
|
262
|
+
else
|
263
|
+
erev '`'+simp(_)+rev+'` is not a polynucleotide.' if be_verbose?
|
264
|
+
end
|
265
|
+
end
|
266
|
+
|
267
|
+
# ========================================================================= #
|
268
|
+
# === first_value
|
269
|
+
#
|
270
|
+
# This will return the first entry of the Fasta files.
|
271
|
+
# ========================================================================= #
|
272
|
+
def first_value
|
273
|
+
sequences?.first
|
274
|
+
end
|
275
|
+
|
276
|
+
# ========================================================================= #
|
277
|
+
# === nucleotides_or_aminoacids?
|
278
|
+
# ========================================================================= #
|
279
|
+
def nucleotides_or_aminoacids?
|
280
|
+
if is_polynucleotide?
|
281
|
+
'nucleotides'
|
282
|
+
else
|
283
|
+
'aminoacids'
|
284
|
+
end
|
285
|
+
end
|
286
|
+
|
287
|
+
# ========================================================================= #
|
288
|
+
# === is_polynucleotide?
|
289
|
+
# ========================================================================= #
|
290
|
+
def is_polynucleotide?(i = main_sequence?)
|
291
|
+
!is_protein?(i)
|
292
|
+
end; alias is_a_nucleotide? is_polynucleotide? # === is_a_nucleotide?
|
293
|
+
|
294
|
+
# ========================================================================= #
|
295
|
+
# === is_this_sequence_a_polynucleotide_sequence?
|
296
|
+
# ========================================================================= #
|
297
|
+
def is_this_sequence_a_polynucleotide_sequence?
|
298
|
+
!is_protein?
|
299
|
+
end
|
300
|
+
|
301
|
+
# ========================================================================= #
|
302
|
+
# === data?
|
303
|
+
#
|
304
|
+
# This will contain the full content of the (whole) .fasta file, including
|
305
|
+
# the header.
|
306
|
+
# ========================================================================= #
|
307
|
+
def data?
|
308
|
+
@data
|
309
|
+
end; alias input? data? # === input?
|
310
|
+
alias dataset? data? # === dataset?
|
311
|
+
|
312
|
+
# ========================================================================= #
|
313
|
+
# === hash?
|
314
|
+
# ========================================================================= #
|
315
|
+
def hash?
|
316
|
+
@hash
|
317
|
+
end
|
318
|
+
|
319
|
+
# ========================================================================= #
|
320
|
+
# === sequences?
|
321
|
+
#
|
322
|
+
# This method will obtain all found sequences.
|
323
|
+
# ========================================================================= #
|
324
|
+
def sequences?
|
325
|
+
@hash.values
|
326
|
+
end; alias sequences sequences? # === sequences
|
327
|
+
alias values sequences? # === values
|
328
|
+
|
329
|
+
# ========================================================================= #
|
330
|
+
# === short_headers?
|
331
|
+
#
|
332
|
+
# The short-headers are like the headers, but if a ' ' token is found
|
333
|
+
# then the line will be truncated towards that first ' '.
|
334
|
+
#
|
335
|
+
# An example is:
|
336
|
+
#
|
337
|
+
# sp|Q91FT8|234R_IIV6 Uncharacterized protein 234R OS=Invertebrate iridescent virus 6 OX=176652 GN=IIV6-234R PE=4 SV=1
|
338
|
+
#
|
339
|
+
# This will be truncated towards
|
340
|
+
#
|
341
|
+
# sp|Q91FT8|234R_IIV6
|
342
|
+
#
|
343
|
+
# This could then be used to automatically rename FASTA files, for
|
344
|
+
# instance.
|
345
|
+
# ========================================================================= #
|
346
|
+
def short_headers?
|
347
|
+
headers?.map {|entry|
|
348
|
+
if entry.include? ' '
|
349
|
+
entry = entry.split(' ').first
|
350
|
+
end
|
351
|
+
entry
|
352
|
+
}
|
353
|
+
end
|
354
|
+
|
355
|
+
# ========================================================================= #
|
356
|
+
# === set_data
|
357
|
+
#
|
358
|
+
# This is the setter-method towards @data. It is no longer allowed to
|
359
|
+
# invoke set_input_file() since as of 12.06.2020. This means that
|
360
|
+
# you have to invoke that method prior to calling this method.
|
361
|
+
# ========================================================================= #
|
362
|
+
def set_data(i = @input_file)
|
363
|
+
# ======================================================================= #
|
364
|
+
# The next line attempts to ensure that even an Array can be used
|
365
|
+
# as input to that method.
|
366
|
+
# ======================================================================= #
|
367
|
+
i = [i].flatten.compact.first.to_s.dup
|
368
|
+
if File.exist? i.to_s # First try to read in from a file.
|
369
|
+
if be_verbose?
|
370
|
+
opnn; erev "Will read from the file `#{sfile(i)}#{rev}`."
|
371
|
+
end
|
372
|
+
i = File.readlines(i)
|
373
|
+
if @is_a_genbank_file
|
374
|
+
selected = i.select {|line|
|
375
|
+
line.start_with?(' ') and # such as: " 61 atggggcctg caatggggcc tgcaatgggg cctgca\n"
|
376
|
+
(line.strip =~ /\d+/)
|
377
|
+
}.map {|inner_line|
|
378
|
+
inner_line.strip.delete(' 0123456789').strip.upcase
|
379
|
+
}
|
380
|
+
i = ["> genbank file"]+selected
|
381
|
+
end
|
382
|
+
end
|
383
|
+
if i.nil? or i.empty?
|
384
|
+
i = DEFAULT_FASTA
|
385
|
+
opnn; erev 'No input was provided. Thus a default FASTA '\
|
386
|
+
'sequence will be used instead.'
|
387
|
+
end
|
388
|
+
i = sanitize_data(i)
|
389
|
+
i = i.split(N) if i.is_a? String
|
390
|
+
@data = i
|
391
|
+
end; alias set_sequence set_data # === set_Sequence
|
392
|
+
|
393
|
+
# ========================================================================= #
|
394
|
+
# === set_be_verbose_and_report_the_sequence
|
395
|
+
# ========================================================================= #
|
396
|
+
def set_be_verbose_and_report_the_sequence
|
397
|
+
set_be_verbose
|
398
|
+
@internal_hash[:report_the_sequence] = true
|
399
|
+
end
|
400
|
+
|
401
|
+
# ========================================================================= #
|
402
|
+
# === condense_the_sequence_onto_a_single_line?
|
403
|
+
# ========================================================================= #
|
404
|
+
def condense_the_sequence_onto_a_single_line?
|
405
|
+
@internal_hash[:condense_the_sequence_onto_a_single_line]
|
406
|
+
end
|
407
|
+
|
408
|
+
# ========================================================================= #
|
409
|
+
# === return_size_sorted_hash
|
410
|
+
# ========================================================================= #
|
411
|
+
def return_size_sorted_hash(i = @hash)
|
412
|
+
_ = i.sort_by {|key, value| value.size }
|
413
|
+
i = Hash[_]
|
414
|
+
return i
|
415
|
+
end
|
416
|
+
|
417
|
+
# ========================================================================= #
|
418
|
+
# === do_sort_by_size
|
419
|
+
#
|
420
|
+
# This method will sort the hash by size of the sequence. It has been
|
421
|
+
# inspired by the EMBOSS sizeq functionality.
|
422
|
+
#
|
423
|
+
# The output that should be generated might look like this:
|
424
|
+
#
|
425
|
+
# https://www.bioinformatics.nl/cgi-bin/emboss/help/sizeseq#input.1
|
426
|
+
#
|
427
|
+
# Invocation example:
|
428
|
+
#
|
429
|
+
# x = Bioroebe::ParseFasta.new('/Depot/j/globins.fasta'); x.do_sort_by_size
|
430
|
+
#
|
431
|
+
# ========================================================================= #
|
432
|
+
def do_sort_by_size
|
433
|
+
# ======================================================================= #
|
434
|
+
# Sort it here first, by the size of the "value", aka the sequence body.
|
435
|
+
# ======================================================================= #
|
436
|
+
@hash = return_size_sorted_hash(@hash)
|
437
|
+
_ = ''.dup
|
438
|
+
@hash.each_pair {|key, sequence|
|
439
|
+
_ << '> ID '+sequence.size.to_s+' AA.; DE: '+key.to_s+
|
440
|
+
' SQ '+sequence.size.to_s+' AA'+N # ; unknown MW as of yet; '\
|
441
|
+
#'unknown CRC64 as of yet'+N
|
442
|
+
_ << sequence+N+N
|
443
|
+
}
|
444
|
+
e _
|
445
|
+
end; alias run_sizeseq_comparison do_sort_by_size # === run_sizeseq_comparison
|
446
|
+
|
447
|
+
# ========================================================================= #
|
448
|
+
# === n_nucleotides?
|
449
|
+
# ========================================================================= #
|
450
|
+
def n_nucleotides?
|
451
|
+
@hash.values.first.delete("\n").size
|
452
|
+
end; alias return_n_aminoacids n_nucleotides? # === return_n_aminoacids
|
453
|
+
alias size? n_nucleotides? # === size?
|
454
|
+
alias sequence_size? n_nucleotides? # === sequence_size?
|
455
|
+
|
456
|
+
# ========================================================================= #
|
457
|
+
# === headers?
|
458
|
+
# ========================================================================= #
|
459
|
+
def headers?
|
460
|
+
@hash.keys
|
461
|
+
end
|
462
|
+
|
463
|
+
# ========================================================================= #
|
464
|
+
# === first_key?
|
465
|
+
#
|
466
|
+
# Obtain the very first entry.
|
467
|
+
# ========================================================================= #
|
468
|
+
def first_key?
|
469
|
+
headers?.first
|
470
|
+
end
|
471
|
+
|
472
|
+
# ========================================================================= #
|
473
|
+
# === header?
|
474
|
+
#
|
475
|
+
# This variant will always return the first entry.
|
476
|
+
# ========================================================================= #
|
477
|
+
def header?
|
478
|
+
headers?.first.to_s
|
479
|
+
end
|
480
|
+
|
481
|
+
# ========================================================================= #
|
482
|
+
# === raw_body?
|
483
|
+
# ========================================================================= #
|
484
|
+
def raw_body?
|
485
|
+
@hash.values.first
|
486
|
+
end
|
487
|
+
|
488
|
+
# ========================================================================= #
|
489
|
+
# === do_show_the_header
|
490
|
+
# ========================================================================= #
|
491
|
+
def do_show_the_header
|
492
|
+
@show_the_header = true
|
493
|
+
end
|
494
|
+
|
495
|
+
# ========================================================================= #
|
496
|
+
# === set_input_file
|
497
|
+
#
|
498
|
+
# This method will be used to keep track of the input-file, from
|
499
|
+
# which we will read the dataset.
|
500
|
+
# ========================================================================= #
|
501
|
+
def set_input_file(i = nil)
|
502
|
+
if i.nil?
|
503
|
+
# ===================================================================== #
|
504
|
+
# First, we try to find a .fasta or .fa file in the current
|
505
|
+
# directory. If we can find it, we will use that instead.
|
506
|
+
# ===================================================================== #
|
507
|
+
unless Dir['*.{fa,fasta}'].empty?
|
508
|
+
file = Dir['*.{fa,fasta}'].first
|
509
|
+
if be_verbose?
|
510
|
+
result = 'A '
|
511
|
+
if file.end_with? '.fasta'
|
512
|
+
result < 'FASTA '
|
513
|
+
end
|
514
|
+
result << 'file was found in this directory ('+sfile(file)+').'
|
515
|
+
opnn; erev result
|
516
|
+
opnn; erev 'We will use it.'
|
517
|
+
end
|
518
|
+
i = file
|
519
|
+
end
|
520
|
+
unless Dir['*.{fa,fasta}'].empty?
|
521
|
+
file = Dir['*.{fa,fasta}'].first
|
522
|
+
if be_verbose?
|
523
|
+
opnn; erev "We have found a file in this "\
|
524
|
+
"directory (#{sfile(file)}#{rev})."
|
525
|
+
opnn; erev 'We will use it.'
|
526
|
+
end
|
527
|
+
i = file
|
528
|
+
end
|
529
|
+
end
|
530
|
+
if i and File.exist?(i)
|
531
|
+
dataset = File.read(i)
|
532
|
+
if dataset[0 .. ('LOCUS'.size - 1)] == 'LOCUS'
|
533
|
+
@is_a_genbank_file = true
|
534
|
+
end
|
535
|
+
end
|
536
|
+
@input_file = i
|
537
|
+
end; alias set_input_files set_input_file # === set_input_files
|
538
|
+
|
539
|
+
# ========================================================================= #
|
540
|
+
# === save_the_file?
|
541
|
+
# ========================================================================= #
|
542
|
+
def save_the_file?
|
543
|
+
@internal_hash[:save_the_file]
|
544
|
+
end
|
545
|
+
|
546
|
+
# ========================================================================= #
|
547
|
+
# === overwrite_the_original_file?
|
548
|
+
# ========================================================================= #
|
549
|
+
def overwrite_the_original_file?
|
550
|
+
@internal_hash[:overwrite_the_original_file]
|
551
|
+
end
|
552
|
+
|
553
|
+
# ========================================================================= #
|
554
|
+
# === split_into_proper_sections
|
555
|
+
#
|
556
|
+
# Split up into the fasta identifier, and the content.
|
557
|
+
# ========================================================================= #
|
558
|
+
def split_into_proper_sections
|
559
|
+
unless @data.to_s.include? '>'
|
560
|
+
erev 'No ">" character was found in this dataset.'
|
561
|
+
erev 'It is recommended to always have a > identifier '\
|
562
|
+
'for the'
|
563
|
+
erev 'FASTA format (such as in a .fasta or a .fa file).'
|
564
|
+
end if be_verbose? # Ok, the input data includes >. We can proceed.
|
565
|
+
@data.each { |line|
|
566
|
+
# ===================================================================== #
|
567
|
+
# === Handle the leading > FASTA identifier first
|
568
|
+
# ===================================================================== #
|
569
|
+
if line.start_with? '>' # leading identifier.
|
570
|
+
@current_key = line[1..-1].chomp # Select all but the first character.
|
571
|
+
@hash[@current_key] = ''.dup
|
572
|
+
else
|
573
|
+
line.delete!('_')
|
574
|
+
unless @current_key
|
575
|
+
@current_key = 'standard'
|
576
|
+
@hash[@current_key] = ''.dup
|
577
|
+
end
|
578
|
+
# =================================================================== #
|
579
|
+
# === Retain the newlines
|
580
|
+
#
|
581
|
+
# Here we may decide to get rid of newlines, but it is better to
|
582
|
+
# NOT remove the newlines - that way we can simply save the
|
583
|
+
# dataset again.
|
584
|
+
# @hash[@current_key] << no_newlines(line)
|
585
|
+
# =================================================================== #
|
586
|
+
@hash[@current_key] << line
|
587
|
+
end
|
588
|
+
}
|
589
|
+
end
|
590
|
+
|
591
|
+
# ========================================================================= #
|
592
|
+
# === save_into_a_fasta_file
|
593
|
+
# ========================================================================= #
|
594
|
+
def save_into_a_fasta_file(
|
595
|
+
be_verbose = be_verbose?
|
596
|
+
)
|
597
|
+
case be_verbose
|
598
|
+
when :be_verbose
|
599
|
+
be_verbose = true
|
600
|
+
end
|
601
|
+
if @data
|
602
|
+
what = @data.join("\n")
|
603
|
+
into = 'standard.fasta'
|
604
|
+
erev 'Saving into '+sfile(into)+rev+'.' if be_verbose
|
605
|
+
write_what_into(what, into)
|
606
|
+
return File.absolute_path(into) # And return the file we saved into.
|
607
|
+
else
|
608
|
+
opnn; erev 'No @data variable exists.'
|
609
|
+
end
|
610
|
+
end; alias do_save_the_file save_into_a_fasta_file # === do_save_the_file
|
611
|
+
|
612
|
+
# ========================================================================= #
|
613
|
+
# === add_length_information_to_the_header
|
614
|
+
# ========================================================================= #
|
615
|
+
def add_length_information_to_the_header
|
616
|
+
_ = header?.strip
|
617
|
+
_ << ' length='+sequence_size?.to_s+';'
|
618
|
+
# ======================================================================= #
|
619
|
+
# Next, designate where to store this file.
|
620
|
+
# ======================================================================= #
|
621
|
+
into = 'new_fasta_file.fasta'
|
622
|
+
if overwrite_the_original_file?
|
623
|
+
into = @input_file
|
624
|
+
end
|
625
|
+
what = ''.dup
|
626
|
+
what << "> "+_+"\n"
|
627
|
+
what << raw_body?
|
628
|
+
if what and into
|
629
|
+
erev 'Storing into `'+sfile(into)+rev+'`.'
|
630
|
+
write_what_into(what, into)
|
631
|
+
end
|
632
|
+
end
|
633
|
+
|
634
|
+
# ========================================================================= #
|
635
|
+
# === simplify_header
|
636
|
+
#
|
637
|
+
# This method can be called to simplify the header. It will save into
|
638
|
+
# a .fasta file at once.
|
639
|
+
# ========================================================================= #
|
640
|
+
def simplify_header
|
641
|
+
_ = header?
|
642
|
+
# ======================================================================= #
|
643
|
+
# Next, simplify the header. We must start with checking for [] first,
|
644
|
+
# because if there are any [] in the FASTA header then we can simplify
|
645
|
+
# stuff at once.
|
646
|
+
# ======================================================================= #
|
647
|
+
if _.include?('[') and _.include?(']')
|
648
|
+
_ = '> '+_.strip.scan(/\[.+\]/).flatten.first.delete('[]')+"\n"
|
649
|
+
elsif _.include? ','
|
650
|
+
_ = _[0 .. (_.index(',') - 1) ].strip
|
651
|
+
end
|
652
|
+
what = nil
|
653
|
+
# ======================================================================= #
|
654
|
+
# Next, designate where to store this file.
|
655
|
+
# ======================================================================= #
|
656
|
+
into = 'new_fasta_file.fasta'
|
657
|
+
if overwrite_the_original_file?
|
658
|
+
into = @input_file
|
659
|
+
end
|
660
|
+
if _.start_with? '>'
|
661
|
+
what = _
|
662
|
+
elsif _.include?('[') and _.include?(']') # For example: [Pan troglodytes]
|
663
|
+
# ===================================================================== #
|
664
|
+
# See rubular at:
|
665
|
+
#
|
666
|
+
# https://rubular.com/r/aDjI0JwMOUlZzP
|
667
|
+
#
|
668
|
+
# ===================================================================== #
|
669
|
+
what = "> "+_.scan(/\[(.+)\]/).flatten.first.to_s+"\n".dup
|
670
|
+
elsif _.include? 'Human'
|
671
|
+
_scanned_result = _.scan(/(Human)/)
|
672
|
+
what = "> "+$1.to_s.dup+"\n".dup
|
673
|
+
else
|
674
|
+
erev "Unsure what to do: #{steelblue(_)}"
|
675
|
+
end
|
676
|
+
if what and into
|
677
|
+
what << raw_body?
|
678
|
+
erev 'Storing into `'+sfile(into)+rev+'`.'
|
679
|
+
write_what_into(what, into)
|
680
|
+
end
|
681
|
+
end
|
682
|
+
|
683
|
+
# ========================================================================= #
|
684
|
+
# === sequence
|
685
|
+
#
|
686
|
+
# This method will return the sequence, without any newlines. It is also
|
687
|
+
# called the "body" of a FASTA file.
|
688
|
+
# ========================================================================= #
|
689
|
+
def sequence
|
690
|
+
_ = @hash.values.first
|
691
|
+
_.chomp! if _ and _.end_with?(N)
|
692
|
+
return no_newlines(_)
|
693
|
+
end; alias fasta_sequence sequence # === fasta_sequence
|
694
|
+
alias sequence? sequence # === sequence?
|
695
|
+
alias body? sequence # === body?
|
696
|
+
alias body sequence # === body?
|
697
|
+
alias naseq sequence # === naseq
|
698
|
+
alias nucleotide_sequence sequence # === nucleotide_sequence
|
699
|
+
alias return_sequence sequence # === return_sequence
|
700
|
+
alias content? sequence # === content?
|
701
|
+
|
702
|
+
# ========================================================================= #
|
703
|
+
# === save
|
704
|
+
#
|
705
|
+
# This method will save our FASTA file.
|
706
|
+
# ========================================================================= #
|
707
|
+
def save
|
708
|
+
if @input_file.nil?
|
709
|
+
erev "The generic file #{sfile('foobar.fasta')}#{rev} "\
|
710
|
+
"will be used."
|
711
|
+
set_input_file('foobar.fasta')
|
712
|
+
end
|
713
|
+
into = @input_file
|
714
|
+
what = @data.join("\n")
|
715
|
+
erev 'Storing into '+sfile(into)+rev+'.'
|
716
|
+
write_what_into(what, into)
|
717
|
+
return into
|
718
|
+
end
|
719
|
+
|
720
|
+
# ========================================================================= #
|
721
|
+
# === []
|
722
|
+
#
|
723
|
+
# This is a simpler query-interface for obtaining the DNA/RNA sequence
|
724
|
+
# of the FASTA file (or aminoacid sequence, if we have a protein at
|
725
|
+
# hand here).
|
726
|
+
#
|
727
|
+
# Using the method sequences? here, which in turn works on @hash, is
|
728
|
+
# ok because Hashes are kept in a sorted manner in ruby since some
|
729
|
+
# time.
|
730
|
+
# ========================================================================= #
|
731
|
+
def [](i)
|
732
|
+
sequences?[i]
|
733
|
+
end
|
734
|
+
|
735
|
+
# ========================================================================= #
|
736
|
+
# === Bioroebe::ParseFasta[]
|
737
|
+
# ========================================================================= #
|
738
|
+
def self.[](i)
|
739
|
+
_ = new(i)
|
740
|
+
_.sequences?
|
741
|
+
end
|
742
|
+
|
743
|
+
# ========================================================================= #
|
744
|
+
# === type?
|
745
|
+
# ========================================================================= #
|
746
|
+
def type?
|
747
|
+
if is_the_sequence_a_polypeptide?
|
748
|
+
:protein
|
749
|
+
elsif is_this_sequence_a_polynucleotide_sequence?
|
750
|
+
:dna_or_rna
|
751
|
+
else
|
752
|
+
:unknown
|
753
|
+
end
|
754
|
+
end
|
755
|
+
|
756
|
+
# ========================================================================= #
|
757
|
+
# === is_the_sequence_a_polypeptide?
|
758
|
+
#
|
759
|
+
# This method can be used to determine whether a given input sequence
|
760
|
+
# is a polypeptide (aka a protein) or whether it is not.
|
761
|
+
#
|
762
|
+
# If this sequence is a polypeptide then this method will return true.
|
763
|
+
# Otherwise false will be returned.
|
764
|
+
# ========================================================================= #
|
765
|
+
def is_the_sequence_a_polypeptide?(
|
766
|
+
i = main_sequence?
|
767
|
+
)
|
768
|
+
return_value = false # Set the default return value here.
|
769
|
+
# ======================================================================= #
|
770
|
+
# Look at the first 120 positions to determine whether this is a protein
|
771
|
+
# or a nucleotide sequence.
|
772
|
+
# ======================================================================= #
|
773
|
+
subsequence = i[0 .. 119] # Must deduct 1 at the end since Arrays in ruby start at 0.
|
774
|
+
# ======================================================================= #
|
775
|
+
# Build a frequency of the characters there.
|
776
|
+
# ======================================================================= #
|
777
|
+
hash = {}
|
778
|
+
hash.default = 0
|
779
|
+
subsequence.chars.each {|character|
|
780
|
+
hash[character] += 1
|
781
|
+
}
|
782
|
+
keys_to_check_for = %w(
|
783
|
+
B D E F H I J K L M O P Q R S V W X Y Z
|
784
|
+
)
|
785
|
+
|
786
|
+
values = hash.select {|key, value|
|
787
|
+
if keys_to_check_for.include? key
|
788
|
+
true
|
789
|
+
else
|
790
|
+
false
|
791
|
+
end
|
792
|
+
}.values.sum
|
793
|
+
if values > 0
|
794
|
+
return_value = true
|
795
|
+
end
|
796
|
+
return return_value
|
797
|
+
end; alias is_protein? is_the_sequence_a_polypeptide? # === is_protein?
|
798
|
+
alias is_a_protein? is_the_sequence_a_polypeptide? # === is_a_protein?
|
799
|
+
|
800
|
+
# ========================================================================= #
|
801
|
+
# === main_sequence?
|
802
|
+
#
|
803
|
+
# This will always return the first entry.
|
804
|
+
# ========================================================================= #
|
805
|
+
def main_sequence?
|
806
|
+
@hash.values.first
|
807
|
+
end
|
808
|
+
|
809
|
+
# ========================================================================= #
|
810
|
+
# === gc_content?
|
811
|
+
# ========================================================================= #
|
812
|
+
def gc_content?
|
813
|
+
return ::Bioroebe.gc_content(main_sequence?).to_f # Must be a float.
|
814
|
+
end; alias gc_content gc_content? # === gc_content
|
815
|
+
|
816
|
+
# ========================================================================= #
|
817
|
+
# === sequence_object
|
818
|
+
#
|
819
|
+
# This method will return a Sequence object.
|
820
|
+
#
|
821
|
+
# Usage example:
|
822
|
+
#
|
823
|
+
# x = Bioroebe.parse_fasta 'ls_orchid.fasta'
|
824
|
+
# y = x.sequence_object # y is now an instance of Bioroebe::Sequence
|
825
|
+
#
|
826
|
+
# ========================================================================= #
|
827
|
+
def sequence_object
|
828
|
+
::Bioroebe::Sequence.new(main_sequence?)
|
829
|
+
end
|
830
|
+
|
831
|
+
end
|
832
|
+
|
833
|
+
Fasta = ParseFasta # Add an "alias" constant to class ParseFasta.
|
834
|
+
|
835
|
+
# =========================================================================== #
|
836
|
+
# === Bioroebe.parse_fasta_quietly
|
837
|
+
#
|
838
|
+
# As the variant above, but will work quietly.
|
839
|
+
# =========================================================================== #
|
840
|
+
def self.parse_fasta_quietly(
|
841
|
+
i, use_colours = true
|
842
|
+
)
|
843
|
+
::Bioroebe.parse_fasta(i, use_colours) { :be_quiet }
|
844
|
+
end
|
845
|
+
|
846
|
+
# =========================================================================== #
|
847
|
+
# === Bioroebe.return_fasta_entry_with_the_highest_gc_content
|
848
|
+
#
|
849
|
+
# The first argument should be a locally existing FASTA file that
|
850
|
+
# contains different sequences.
|
851
|
+
#
|
852
|
+
# Usage example:
|
853
|
+
#
|
854
|
+
# x = Bioroebe.return_fasta_entry_with_the_highest_gc_content('/rosalind_gc.txt')
|
855
|
+
#
|
856
|
+
# =========================================================================== #
|
857
|
+
def self.return_fasta_entry_with_the_highest_gc_content(this_fasta_file)
|
858
|
+
if File.exist? this_fasta_file
|
859
|
+
dataset = File.read(this_fasta_file)
|
860
|
+
dataset = parse_fasta(dataset) { :be_quiet }
|
861
|
+
hash = dataset.hash?
|
862
|
+
hash.transform_values! {|this_value|
|
863
|
+
::Bioroebe.gc_content(this_value).to_f
|
864
|
+
}
|
865
|
+
return hash.max_by {|key, value| value }
|
866
|
+
else
|
867
|
+
erev "No file exists at #{sfile(this_fasta_file)}#{rev}."
|
868
|
+
end
|
869
|
+
end
|
870
|
+
|
871
|
+
# =========================================================================== #
|
872
|
+
# === Bioroebe.sizeseq
|
873
|
+
#
|
874
|
+
# This method will "size-sequence compare", typically on a .fasta file.
|
875
|
+
# =========================================================================== #
|
876
|
+
def self.sizeseq(i)
|
877
|
+
if i.is_a? Array
|
878
|
+
i = i.first
|
879
|
+
end
|
880
|
+
_ = Bioroebe.parse_fasta(i) { :be_quiet }
|
881
|
+
_.do_sort_by_size
|
882
|
+
end
|
883
|
+
|
884
|
+
# =========================================================================== #
|
885
|
+
# === Bioroebe.return_sizeseq
|
886
|
+
#
|
887
|
+
# This is as Bioroebe.sizeseq(), but it will just return the result,
|
888
|
+
# rather than output it.
|
889
|
+
# =========================================================================== #
|
890
|
+
def self.return_sizeseq(i)
|
891
|
+
if i.is_a? Array
|
892
|
+
i = i.first
|
893
|
+
end
|
894
|
+
_ = Bioroebe.parse_fasta(i) { :be_quiet }
|
895
|
+
hash = _.return_size_sorted_hash
|
896
|
+
result = ''.dup
|
897
|
+
hash.each_pair {|key, sequence|
|
898
|
+
result << '> ID '+sequence.size.to_s+' AA.; DE: '+key.to_s+
|
899
|
+
' SQ '+sequence.size.to_s+' AA'+N
|
900
|
+
result << sequence+N+N
|
901
|
+
}
|
902
|
+
return result
|
903
|
+
end
|
904
|
+
|
905
|
+
# =========================================================================== #
|
906
|
+
# === Bioroebe.genbank_to_fasta
|
907
|
+
#
|
908
|
+
# This method will convert from a genbank file, to a .fasta file.
|
909
|
+
#
|
910
|
+
# Invocation example:
|
911
|
+
#
|
912
|
+
# Bioroebe.genbank_to_fasta('/home/x/DATA/PROGRAMMING_LANGUAGES/RUBY/src/bioroebe/lib/bioroebe/data/genbank/sample_file.genbank')
|
913
|
+
#
|
914
|
+
# =========================================================================== #
|
915
|
+
def self.genbank_to_fasta(
|
916
|
+
this_file,
|
917
|
+
be_verbose = :be_verbose
|
918
|
+
)
|
919
|
+
case be_verbose
|
920
|
+
when :be_quiet
|
921
|
+
be_verbose = false
|
922
|
+
end
|
923
|
+
if this_file.is_a? Array
|
924
|
+
this_file = this_file.first
|
925
|
+
end
|
926
|
+
if File.exist? this_file
|
927
|
+
_ = Bioroebe::ParseFasta.new(this_file) { :be_quiet }
|
928
|
+
else
|
929
|
+
_ = Bioroebe::ParseFasta.new(:do_not_run_yet) { :be_quiet }
|
930
|
+
_.set_data # This will use the default file.
|
931
|
+
_.split_into_proper_sections
|
932
|
+
end
|
933
|
+
file_path = _.save_into_a_fasta_file(be_verbose)
|
934
|
+
return file_path
|
935
|
+
end
|
936
|
+
|
937
|
+
# =========================================================================== #
|
938
|
+
# === Bioroebe.parse_fasta_file
|
939
|
+
# =========================================================================== #
|
940
|
+
def self.parse_fasta_file(
|
941
|
+
i, use_colours = true
|
942
|
+
)
|
943
|
+
use_this_hash = {
|
944
|
+
use_colours: use_colours,
|
945
|
+
be_verbose: false
|
946
|
+
}
|
947
|
+
ParseFasta.new(i) { use_this_hash }
|
948
|
+
end; self.instance_eval { alias fasta_file parse_fasta_file } # === Bioroebe.fasta_file
|
949
|
+
|
950
|
+
# =========================================================================== #
|
951
|
+
# === Bioroebe.parse_fasta
|
952
|
+
#
|
953
|
+
# Easier reader-method for .fasta files.
|
954
|
+
#
|
955
|
+
# The second argument determines whether we will use colours or whether
|
956
|
+
# we will not. For now, the default is to not use colours when we use
|
957
|
+
# this particular class method.
|
958
|
+
#
|
959
|
+
# Invocation examples:
|
960
|
+
#
|
961
|
+
# x = Bioroebe.parse_fasta('/rosalind_gc.txt')
|
962
|
+
# hash = Bioroebe.parse_fasta('/rosalind_gc.txt').hash?
|
963
|
+
#
|
964
|
+
# =========================================================================== #
|
965
|
+
def self.parse_fasta(
|
966
|
+
i,
|
967
|
+
use_colours = true
|
968
|
+
)
|
969
|
+
use_this_hash = {
|
970
|
+
use_colours: use_colours
|
971
|
+
}
|
972
|
+
if block_given?
|
973
|
+
use_this_hash = {
|
974
|
+
use_colours: use_colours,
|
975
|
+
be_verbose: yield
|
976
|
+
}
|
977
|
+
end
|
978
|
+
::Bioroebe::ParseFasta.new(i) { use_this_hash }
|
979
|
+
end; self.instance_eval { alias fasta parse_fasta } # === Bioroebe.fasta
|
980
|
+
|
981
|
+
end
|