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 +1,27 @@
|
|
1
|
+
#!/usr/bin/ruby -w
|
2
|
+
# Encoding: UTF-8
|
3
|
+
# frozen_string_literal: true
|
4
|
+
# =========================================================================== #
|
5
|
+
# require 'bioroebe/fasta_and_fastq/parse_fasta/parse_fasta.rb'
|
6
|
+
# Bioroebe::ParseFasta.new(ARGV)
|
7
|
+
# =========================================================================== #
|
8
|
+
require 'bioroebe/base/commandline_application/commandline_application.rb'
|
9
|
+
require 'bioroebe/fasta_and_fastq/parse_fasta/constants.rb'
|
10
|
+
require 'bioroebe/fasta_and_fastq/parse_fasta/initialize.rb'
|
11
|
+
require 'bioroebe/fasta_and_fastq/parse_fasta/misc.rb'
|
12
|
+
require 'bioroebe/fasta_and_fastq/parse_fasta/reset.rb'
|
13
|
+
require 'bioroebe/fasta_and_fastq/parse_fasta/run.rb'
|
14
|
+
|
15
|
+
if __FILE__ == $PROGRAM_NAME
|
16
|
+
Bioroebe::ParseFasta.new(ARGV) { :sizeseq }
|
17
|
+
# _ = Bioroebe::ParseFasta.new(ARGV, :dont_run_yet)
|
18
|
+
# _.we_may_exit
|
19
|
+
# _.do_sort_by_size
|
20
|
+
# _.run
|
21
|
+
# output_results
|
22
|
+
#p _.sequence
|
23
|
+
end # corefasta globins.fasta
|
24
|
+
# pfasta /GC.txt
|
25
|
+
# pfasta 013521.3_289_aa.fasta --also-show-the-sequence
|
26
|
+
# pfasta $RSRC/bioroebe/lib/bioroebe/data/GFP_mutant_3_coding_sequence.fasta --also-show-the-sequence
|
27
|
+
# corefasta $J/globins.fasta
|
@@ -0,0 +1,156 @@
|
|
1
|
+
#!/usr/bin/ruby -w
|
2
|
+
# Encoding: UTF-8
|
3
|
+
# frozen_string_literal: true
|
4
|
+
# =========================================================================== #
|
5
|
+
# require 'bioroebe/fasta_and_fastq/parse_fasta/report.rb'
|
6
|
+
# =========================================================================== #
|
7
|
+
require 'bioroebe/base/commandline_application/commandline_application.rb'
|
8
|
+
|
9
|
+
module Bioroebe
|
10
|
+
|
11
|
+
class ParseFasta < ::Bioroebe::CommandlineApplication # === Bioroebe::ParseFasta
|
12
|
+
|
13
|
+
require 'bioroebe/sequence/dna.rb'
|
14
|
+
|
15
|
+
# ========================================================================= #
|
16
|
+
# === do_report_the_sequence (report tag)
|
17
|
+
#
|
18
|
+
# This method is used to display the main sequence at hand.
|
19
|
+
# ========================================================================= #
|
20
|
+
def do_report_the_sequence
|
21
|
+
_ = main_sequence?
|
22
|
+
# ======================================================================= #
|
23
|
+
# Honour the --limit commandline flag next.
|
24
|
+
# ======================================================================= #
|
25
|
+
if @internal_hash[:limit_the_display_to_n_nucleotides]
|
26
|
+
_ = _[0 .. (@internal_hash[:limit_the_display_to_n_nucleotides] - 1)]
|
27
|
+
end
|
28
|
+
if @colourize_sequence
|
29
|
+
if is_polynucleotide?
|
30
|
+
# =================================================================== #
|
31
|
+
# Else assume this is DNA/RNA input.
|
32
|
+
# =================================================================== #
|
33
|
+
_.gsub!(/A/, teal('A')+rev)
|
34
|
+
_.gsub!(/C/, slateblue('C')+rev)
|
35
|
+
_.gsub!(/G/, royalblue('G')+rev)
|
36
|
+
_.gsub!(/T/, steelblue('T')+rev)
|
37
|
+
_.gsub!(/U/, steelblue('U')+rev)
|
38
|
+
#else
|
39
|
+
end
|
40
|
+
end
|
41
|
+
if condense_the_sequence_onto_a_single_line?
|
42
|
+
_ = _.delete("\n")
|
43
|
+
end
|
44
|
+
erev colourize_this_nucleotide_sequence(_)
|
45
|
+
e if condense_the_sequence_onto_a_single_line?
|
46
|
+
if show_the_translated_protein_sequence?
|
47
|
+
# ===================================================================== #
|
48
|
+
# Do show the translated protein sequence next:
|
49
|
+
# ===================================================================== #
|
50
|
+
translated_into_aa = Bioroebe.to_aa(_)
|
51
|
+
translated_into_aa_and_colourized = translated_into_aa.dup
|
52
|
+
if translated_into_aa.include? '*'
|
53
|
+
translated_into_aa_and_colourized = translated_into_aa.gsub(/\*/,tomato('*'))
|
54
|
+
end
|
55
|
+
erev 'The translated aminoacid sequence of '+
|
56
|
+
sfancy(translated_into_aa.size.to_s)+rev+
|
57
|
+
' aminoacids is:'
|
58
|
+
e
|
59
|
+
erev steelblue(" #{translated_into_aa_and_colourized}")
|
60
|
+
e
|
61
|
+
end
|
62
|
+
end; alias display do_report_the_sequence # === display
|
63
|
+
alias report do_report_the_sequence # === report
|
64
|
+
|
65
|
+
# ========================================================================= #
|
66
|
+
# === report_the_nucleotide_composition
|
67
|
+
# ========================================================================= #
|
68
|
+
def report_the_nucleotide_composition
|
69
|
+
if is_this_sequence_a_polynucleotide_sequence?
|
70
|
+
first = @hash.values.first.upcase
|
71
|
+
total_size = first.size
|
72
|
+
n_adenines = first.count('A')
|
73
|
+
n_thymidines = first.count('T')
|
74
|
+
n_cytodines = first.count('C')
|
75
|
+
n_guanines = first.count('G')
|
76
|
+
erev "The nucleotide composition is as follows:"
|
77
|
+
e " "\
|
78
|
+
"#{steelblue(n_adenines)}#{rev}x A (#{(n_adenines * 100.0 / total_size).round(2)}%), "\
|
79
|
+
"#{steelblue(n_thymidines)}#{rev}x T (#{(n_thymidines * 100.0 / total_size).round(2)}%), "\
|
80
|
+
"#{steelblue(n_cytodines)}#{rev}x C (#{(n_cytodines * 100.0 / total_size).round(2)}%), "\
|
81
|
+
"#{steelblue(n_guanines)}#{rev}x G (#{(n_guanines * 100.0 / total_size).round(2)}%)"
|
82
|
+
elsif is_a_protein?
|
83
|
+
# ===================================================================== #
|
84
|
+
# Report the composition of the protein:
|
85
|
+
# ===================================================================== #
|
86
|
+
sequence = @hash.values.first.delete("\n")
|
87
|
+
erev "The protein composition (aminoacids) is as follows:"
|
88
|
+
# e colourize_this_aminoacid_sequence_for_the_commandline(" #{sequence}")
|
89
|
+
e orchid(" #{sequence}")
|
90
|
+
end
|
91
|
+
end; alias report_the_protein_composition report_the_nucleotide_composition # === report_the_protein_composition
|
92
|
+
|
93
|
+
# ========================================================================= #
|
94
|
+
# === report_how_many_elements_we_have_found
|
95
|
+
# ========================================================================= #
|
96
|
+
def report_how_many_elements_we_have_found
|
97
|
+
if @hash
|
98
|
+
first = @hash.values.first.delete("\n")
|
99
|
+
size = first.size.to_s
|
100
|
+
if be_verbose?
|
101
|
+
n_start_codons = first.count('ATG')
|
102
|
+
# =================================================================== #
|
103
|
+
# We upcase it since as of October 2021, as some FASTA files may
|
104
|
+
# include the sequence in lowercased characters.
|
105
|
+
# =================================================================== #
|
106
|
+
n_start_codons += first.reverse.upcase.count('ATG')
|
107
|
+
result = "This sequence contains #{simp(size.to_s)}#{rev}"\
|
108
|
+
" #{nucleotides_or_aminoacids?}".dup
|
109
|
+
if is_a_nucleotide?
|
110
|
+
result << " and #{n_start_codons} "\
|
111
|
+
"ATG codons (on both strands) in total"
|
112
|
+
end
|
113
|
+
result << '.'
|
114
|
+
if size.to_i > 1_000_000
|
115
|
+
# ================================================================= #
|
116
|
+
# Format the number with '_' characters.
|
117
|
+
# ================================================================= #
|
118
|
+
formatted = size.to_i.to_s.reverse.split(/(.{3})/).reject(&:empty?).join('_').reverse
|
119
|
+
result = result.dup if result.frozen?
|
120
|
+
result << ' ('+simp(formatted+' bp')+rev+')'
|
121
|
+
end
|
122
|
+
erev result
|
123
|
+
end
|
124
|
+
end
|
125
|
+
end
|
126
|
+
|
127
|
+
# ========================================================================= #
|
128
|
+
# === report_on_how_many_entries_we_did_work
|
129
|
+
# ========================================================================= #
|
130
|
+
def report_on_how_many_entries_we_did_work
|
131
|
+
if be_verbose?
|
132
|
+
entry_or_entries = 'entry'
|
133
|
+
if @hash.keys.size > 1
|
134
|
+
entry_or_entries = 'entries'
|
135
|
+
end
|
136
|
+
erev "We have identified a total of #{orange(@hash.keys.size)}"\
|
137
|
+
"#{rev} #{entry_or_entries} in this fasta dataset."
|
138
|
+
e
|
139
|
+
end
|
140
|
+
end
|
141
|
+
|
142
|
+
# ========================================================================= #
|
143
|
+
# === report_the_FASTA_header
|
144
|
+
# ========================================================================= #
|
145
|
+
def report_the_FASTA_header
|
146
|
+
e "#{rev}The header is: #{steelblue(header?)}"
|
147
|
+
end
|
148
|
+
|
149
|
+
# ========================================================================= #
|
150
|
+
# === report_the_sequence?
|
151
|
+
# ========================================================================= #
|
152
|
+
def report_the_sequence?
|
153
|
+
@internal_hash[:report_the_sequence]
|
154
|
+
end
|
155
|
+
|
156
|
+
end; end
|
@@ -0,0 +1,128 @@
|
|
1
|
+
#!/usr/bin/ruby -w
|
2
|
+
# Encoding: UTF-8
|
3
|
+
# frozen_string_literal: true
|
4
|
+
# =========================================================================== #
|
5
|
+
# require 'bioroebe/fasta_and_fastq/parse_fasta/reset.rb'
|
6
|
+
# =========================================================================== #
|
7
|
+
module Bioroebe
|
8
|
+
|
9
|
+
class ParseFasta < ::Bioroebe::CommandlineApplication # === Bioroebe::ParseFasta
|
10
|
+
|
11
|
+
# ========================================================================= #
|
12
|
+
# === reset (reset tag)
|
13
|
+
# ========================================================================= #
|
14
|
+
def reset
|
15
|
+
super()
|
16
|
+
# ======================================================================= #
|
17
|
+
# === @namespace
|
18
|
+
# ======================================================================= #
|
19
|
+
@namespace = NAMESPACE
|
20
|
+
# ======================================================================= #
|
21
|
+
# === @is_a_genbank_file
|
22
|
+
# ======================================================================= #
|
23
|
+
@is_a_genbank_file = false
|
24
|
+
# ======================================================================= #
|
25
|
+
# === @input_file
|
26
|
+
#
|
27
|
+
# This variable denotes which input file is used to read data from.
|
28
|
+
#
|
29
|
+
# It is nil initially because we may skip reading from an existing
|
30
|
+
# file and e. g. only read from a String or some other non-file
|
31
|
+
# entity.
|
32
|
+
# ======================================================================= #
|
33
|
+
@input_file = nil
|
34
|
+
# ======================================================================= #
|
35
|
+
# === @hash
|
36
|
+
#
|
37
|
+
# This is the main variable for the class. It will keep entries such
|
38
|
+
# as this one here:
|
39
|
+
#
|
40
|
+
# {
|
41
|
+
# "ENSMUSG00000020122|ENSMUST08" => "CCCTCC"
|
42
|
+
# }
|
43
|
+
#
|
44
|
+
# ======================================================================= #
|
45
|
+
@hash = {}
|
46
|
+
# ======================================================================= #
|
47
|
+
# === @internal_hash
|
48
|
+
#
|
49
|
+
# This Hash exists for internal configuration of the class.
|
50
|
+
# ======================================================================= #
|
51
|
+
@internal_hash = {}
|
52
|
+
# ======================================================================= #
|
53
|
+
# === :report_the_sequence
|
54
|
+
# ======================================================================= #
|
55
|
+
@internal_hash[:report_the_sequence] = false
|
56
|
+
# ======================================================================= #
|
57
|
+
# === :overwrite_the_original_file
|
58
|
+
# ======================================================================= #
|
59
|
+
@internal_hash[:overwrite_the_original_file] = false
|
60
|
+
# ======================================================================= #
|
61
|
+
# === :save_the_file
|
62
|
+
# ======================================================================= #
|
63
|
+
@internal_hash[:save_the_file] = false
|
64
|
+
# ======================================================================= #
|
65
|
+
# === :remove_numbers_from_input
|
66
|
+
# ======================================================================= #
|
67
|
+
@internal_hash[:remove_numbers_from_input] = false
|
68
|
+
# ======================================================================= #
|
69
|
+
# === :show_the_translated_protein_sequence
|
70
|
+
#
|
71
|
+
# This setting is false initially. If set to true via the commandline
|
72
|
+
# then report() will show the translated protein sequence as well.
|
73
|
+
# ======================================================================= #
|
74
|
+
@internal_hash[:show_the_translated_protein_sequence] = false
|
75
|
+
# ======================================================================= #
|
76
|
+
# === :condense_the_sequence_onto_a_single_line
|
77
|
+
#
|
78
|
+
# By default the output of this class will include newlines for the
|
79
|
+
# sequence. If this is not wanted by the user then the following
|
80
|
+
# variable keeps track of that behaviour. You can use the flag
|
81
|
+
# called --one-line to enable a condensed output, with newlines
|
82
|
+
# being removed.
|
83
|
+
# ======================================================================= #
|
84
|
+
@internal_hash[:condense_the_sequence_onto_a_single_line] = false
|
85
|
+
# ======================================================================= #
|
86
|
+
# === :limit_the_display_to_n_nucleotides
|
87
|
+
#
|
88
|
+
# If this variable is a number rather than nil, then it will be used
|
89
|
+
# to display only a limited number of nucleotides, e. g. "1000" if
|
90
|
+
# the user passes in 1000.
|
91
|
+
# ======================================================================= #
|
92
|
+
@internal_hash[:limit_the_display_to_n_nucleotides] = nil
|
93
|
+
# ======================================================================= #
|
94
|
+
# === @may_we_exit
|
95
|
+
# ======================================================================= #
|
96
|
+
@may_we_exit = false
|
97
|
+
# ======================================================================= #
|
98
|
+
# === @current_key
|
99
|
+
# ======================================================================= #
|
100
|
+
@current_key = nil
|
101
|
+
# ======================================================================= #
|
102
|
+
# === @use_opn
|
103
|
+
# ======================================================================= #
|
104
|
+
@use_opn = ::Bioroebe.use_opn?
|
105
|
+
# ======================================================================= #
|
106
|
+
# === @colourize_sequence
|
107
|
+
# ======================================================================= #
|
108
|
+
@colourize_sequence = false
|
109
|
+
# ======================================================================= #
|
110
|
+
# === @sort_by_size
|
111
|
+
#
|
112
|
+
# If the following variable is set to true, then this class will
|
113
|
+
# run a sizeseq-comparison, that is, it will compare all sequences
|
114
|
+
# and output them in a size-sorted manner, similar to the EMBOSS
|
115
|
+
# sizeseq action.
|
116
|
+
# ======================================================================= #
|
117
|
+
@sort_by_size = false
|
118
|
+
# ======================================================================= #
|
119
|
+
# === @show_the_header
|
120
|
+
#
|
121
|
+
# If this variable is true then the header will be shown.
|
122
|
+
# ======================================================================= #
|
123
|
+
@show_the_header = false
|
124
|
+
set_round_to :default
|
125
|
+
set_be_verbose
|
126
|
+
end
|
127
|
+
|
128
|
+
end; end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
#!/usr/bin/ruby -w
|
2
|
+
# Encoding: UTF-8
|
3
|
+
# frozen_string_literal: true
|
4
|
+
# =========================================================================== #
|
5
|
+
# require 'bioroebe/fasta_and_fastq/parse_fasta/run.rb'
|
6
|
+
# =========================================================================== #
|
7
|
+
module Bioroebe
|
8
|
+
|
9
|
+
class ParseFasta < ::Bioroebe::CommandlineApplication # === Bioroebe::ParseFasta
|
10
|
+
|
11
|
+
# ========================================================================= #
|
12
|
+
# === run (run tag)
|
13
|
+
# ========================================================================= #
|
14
|
+
def run
|
15
|
+
menu
|
16
|
+
do_process_the_commandline_arguments_that_are_files
|
17
|
+
do_save_the_file if save_the_file?
|
18
|
+
end
|
19
|
+
|
20
|
+
end; end
|
@@ -0,0 +1,83 @@
|
|
1
|
+
#!/usr/bin/ruby -w
|
2
|
+
# Encoding: UTF-8
|
3
|
+
# frozen_string_literal: true
|
4
|
+
# =========================================================================== #
|
5
|
+
# === Bioroebe::ParseFastq
|
6
|
+
#
|
7
|
+
# The purpose of this class is to parse FASTQ files.
|
8
|
+
#
|
9
|
+
# Usage example:
|
10
|
+
#
|
11
|
+
# Bioroebe::ParseFastq.new
|
12
|
+
#
|
13
|
+
# =========================================================================== #
|
14
|
+
# require 'biroebe/fastq/parse_fastq.rb'
|
15
|
+
# =========================================================================== #
|
16
|
+
require 'bioroebe/base/commandline_application/commandline_application.rb'
|
17
|
+
|
18
|
+
module Bioroebe
|
19
|
+
|
20
|
+
class ParseFastq < ::Bioroebe::CommandlineApplication # === Bioroebe::ParseFastq
|
21
|
+
|
22
|
+
# ========================================================================= #
|
23
|
+
# === initialize
|
24
|
+
# ========================================================================= #
|
25
|
+
def initialize(
|
26
|
+
commandline_arguments = nil,
|
27
|
+
run_already = true
|
28
|
+
)
|
29
|
+
reset
|
30
|
+
set_commandline_arguments(
|
31
|
+
commandline_arguments
|
32
|
+
)
|
33
|
+
run if run_already
|
34
|
+
end
|
35
|
+
|
36
|
+
# ========================================================================= #
|
37
|
+
# === reset (reset tag)
|
38
|
+
# ========================================================================= #
|
39
|
+
def reset
|
40
|
+
super()
|
41
|
+
end
|
42
|
+
|
43
|
+
# ========================================================================= #
|
44
|
+
# === check_whether_the_fastq_format_is_valid
|
45
|
+
#
|
46
|
+
# This method will try to determine whether the FASTQ format at hand
|
47
|
+
# is valid or whether it is not.
|
48
|
+
# ========================================================================= #
|
49
|
+
def check_whether_the_fastq_format_is_valid(i)
|
50
|
+
unless i =~ /^\@(\S*)\s?(.*)$/
|
51
|
+
raise InvalidFastqFormat,
|
52
|
+
"Invalid FASTQ format: a '@' must be at the beginning of the line"
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
56
|
+
# ========================================================================= #
|
57
|
+
# === run (run tag)
|
58
|
+
# ========================================================================= #
|
59
|
+
def run
|
60
|
+
_ = first_argument?
|
61
|
+
if File.exist? _
|
62
|
+
dataset = File.read(_)
|
63
|
+
check_whether_the_fastq_format_is_valid(dataset)
|
64
|
+
e 'DEBUG'
|
65
|
+
pp dataset
|
66
|
+
e 'The .fastq file is valid.'
|
67
|
+
else
|
68
|
+
e 'No file could be found at '+sfile(_.to_s)+'.'
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
72
|
+
# ========================================================================= #
|
73
|
+
# === Bioroebe::ParseFastq[]
|
74
|
+
# ========================================================================= #
|
75
|
+
def self.[](i = '')
|
76
|
+
new(i)
|
77
|
+
end
|
78
|
+
|
79
|
+
end; end
|
80
|
+
|
81
|
+
if __FILE__ == $PROGRAM_NAME
|
82
|
+
Bioroebe::ParseFastq.new(ARGV)
|
83
|
+
end # parse_fastq fastq_example_file.fastq
|
@@ -0,0 +1,112 @@
|
|
1
|
+
#!/usr/bin/ruby -w
|
2
|
+
# Encoding: UTF-8
|
3
|
+
# frozen_string_literal: true
|
4
|
+
# =========================================================================== #
|
5
|
+
# require 'bioroebe/toplevel_methods/return_fasta_subsection_of_this_file.rb'
|
6
|
+
# Bioroebe.return_fasta_subsection_of_this_file("foobar.fa", :keep_it_flat)
|
7
|
+
# =========================================================================== #
|
8
|
+
module Bioroebe
|
9
|
+
|
10
|
+
require 'bioroebe/toplevel_methods/e.rb'
|
11
|
+
|
12
|
+
# ========================================================================= #
|
13
|
+
# === Bioroebe.return_fasta_subsection_of_this_file
|
14
|
+
#
|
15
|
+
# This method will parse an existing fasta file into its constituent header
|
16
|
+
# and body parts, stored as an Array in an Array.
|
17
|
+
#
|
18
|
+
# The second argument to this method can be used to flatten the inner
|
19
|
+
# Array keeping track of the FASTA content; or to keep it separate.
|
20
|
+
# Keeping it separate is the default behaviour.
|
21
|
+
#
|
22
|
+
# Invocation examples:
|
23
|
+
#
|
24
|
+
# Bioroebe.return_fasta_subsection_of_this_file("foobar.fa")
|
25
|
+
# Bioroebe.return_fasta_subsection_of_this_file("foobar.fa", :keep_it_flat)
|
26
|
+
#
|
27
|
+
# ========================================================================= #
|
28
|
+
def self.return_fasta_subsection_of_this_file(
|
29
|
+
i = nil,
|
30
|
+
extra_options = :default # The two values can be :keep_it_flat or :keep_body_together
|
31
|
+
)
|
32
|
+
case extra_options
|
33
|
+
when :default
|
34
|
+
extra_options = :keep_it_flat
|
35
|
+
end
|
36
|
+
array = []
|
37
|
+
i = i.first if i.is_a? Array
|
38
|
+
if i.nil?
|
39
|
+
e 'Please provide the file path to a locally '\
|
40
|
+
'existing fasta file, as argument.'
|
41
|
+
return
|
42
|
+
end
|
43
|
+
if File.exist? i
|
44
|
+
dataset = File.readlines(i)
|
45
|
+
inner_array = []
|
46
|
+
size = dataset.size
|
47
|
+
dataset.each_with_index {|line, index|
|
48
|
+
if line.start_with? '>'
|
49
|
+
# ================================================================= #
|
50
|
+
# Store it in that case - this will be a fasta header section.
|
51
|
+
# ================================================================= #
|
52
|
+
unless inner_array.empty?
|
53
|
+
array << inner_array
|
54
|
+
inner_array = [] # And reset it here as well.
|
55
|
+
end
|
56
|
+
inner_array.prepend(line)
|
57
|
+
else
|
58
|
+
# This will be a FASTA body section.
|
59
|
+
case extra_options
|
60
|
+
when :keep_body_together # the default
|
61
|
+
inner_array << line
|
62
|
+
else
|
63
|
+
# =============================================================== #
|
64
|
+
# Else we have to append it.
|
65
|
+
# =============================================================== #
|
66
|
+
previous_line = inner_array.last
|
67
|
+
if previous_line.start_with? '>'
|
68
|
+
inner_array << line
|
69
|
+
else
|
70
|
+
inner_array.last.strip!
|
71
|
+
inner_array.last << line
|
72
|
+
end
|
73
|
+
end
|
74
|
+
end
|
75
|
+
if (index + 1) == size
|
76
|
+
# Store the last entry as well.
|
77
|
+
array << inner_array
|
78
|
+
inner_array = [] # And reset it here as well.
|
79
|
+
end
|
80
|
+
}
|
81
|
+
array
|
82
|
+
else
|
83
|
+
e "No file exists at `#{i}`."
|
84
|
+
end
|
85
|
+
end; self.instance_eval { alias return_fasta_subsection return_fasta_subsection_of_this_file } # === Bioroebe.return_fasta_subsection
|
86
|
+
self.instance_eval { alias fasta_subsection return_fasta_subsection_of_this_file } # === Bioroebe.fasta_subsection
|
87
|
+
|
88
|
+
end
|
89
|
+
|
90
|
+
if __FILE__ == $PROGRAM_NAME
|
91
|
+
require 'colours/autoinclude'
|
92
|
+
array = Bioroebe.return_fasta_subsection_of_this_file(ARGV, :default)
|
93
|
+
if array.is_a? Array
|
94
|
+
e Colours.rev+
|
95
|
+
'This dataset contains a total of '+
|
96
|
+
Colours.slateblue(array.size.to_s)+
|
97
|
+
' individual FASTA subsections.'
|
98
|
+
end
|
99
|
+
if array
|
100
|
+
e 'The body (FASTA) content of that last element is:'
|
101
|
+
e
|
102
|
+
e ' '+slateblue(array.last.last.chomp)
|
103
|
+
e
|
104
|
+
e "The #{gold('last element')} is:"
|
105
|
+
e
|
106
|
+
e steelblue(" #{array.last.last.strip}")
|
107
|
+
e
|
108
|
+
end
|
109
|
+
end # returnfastasubsectionofthisfile
|
110
|
+
# returnfastasubsectionofthisfile /public/indium4/scratch/bioinf4/Mouse2/ncrna/TEST/Mus_musculus.GRCm38.ncrna.fa
|
111
|
+
# returnfastasubsectionofthisfile /Depot/Bioroebe/Mouse/ncrna/ncrna.4.fa
|
112
|
+
# returnfasta /root/Bioroebe/fasta/1fat.fasta
|
@@ -0,0 +1,135 @@
|
|
1
|
+
#!/usr/bin/ruby -w
|
2
|
+
# Encoding: UTF-8
|
3
|
+
# frozen_string_literal: true
|
4
|
+
# =========================================================================== #
|
5
|
+
# === Bioroebe::ShowFastaHeaders
|
6
|
+
#
|
7
|
+
# This class will show all FASTA headers of all fasta files.
|
8
|
+
#
|
9
|
+
# Usage example:
|
10
|
+
#
|
11
|
+
# Bioroebe::ShowFastaHeaders(ARGV)
|
12
|
+
#
|
13
|
+
# =========================================================================== #
|
14
|
+
# require 'bioroebe/fasta_and_fastq/show_fasta_headers.rb'
|
15
|
+
# =========================================================================== #
|
16
|
+
require 'bioroebe/base/commandline_application/commandline_application.rb'
|
17
|
+
|
18
|
+
module Bioroebe
|
19
|
+
|
20
|
+
class ShowFastaHeaders < Bioroebe::CommandlineApplication # === Biroebe::ShowFastaHeaders
|
21
|
+
|
22
|
+
# ========================================================================= #
|
23
|
+
# === NAMESPACE
|
24
|
+
# ========================================================================= #
|
25
|
+
NAMESPACE = inspect
|
26
|
+
|
27
|
+
# ========================================================================= #
|
28
|
+
# === BASE_DIR
|
29
|
+
#
|
30
|
+
# This base-directory will only work on my home setup, by default.
|
31
|
+
# ========================================================================= #
|
32
|
+
BASE_DIR =
|
33
|
+
'/home/x/data/science/bioinformatics/data/fasta/'
|
34
|
+
|
35
|
+
# ========================================================================= #
|
36
|
+
# === initialize
|
37
|
+
# ========================================================================= #
|
38
|
+
def initialize(
|
39
|
+
i = BASE_DIR,
|
40
|
+
run_already = true
|
41
|
+
)
|
42
|
+
reset
|
43
|
+
set_input(i)
|
44
|
+
run if run_already
|
45
|
+
end
|
46
|
+
|
47
|
+
# ========================================================================= #
|
48
|
+
# === reset (reset tag)
|
49
|
+
# ========================================================================= #
|
50
|
+
def reset
|
51
|
+
super()
|
52
|
+
# ======================================================================= #
|
53
|
+
# === @be_verbose
|
54
|
+
# ======================================================================= #
|
55
|
+
@be_verbose = true
|
56
|
+
# ======================================================================= #
|
57
|
+
# === @namespace
|
58
|
+
# ======================================================================= #
|
59
|
+
@namespace = NAMESPACE
|
60
|
+
end
|
61
|
+
|
62
|
+
# ========================================================================= #
|
63
|
+
# === set_input
|
64
|
+
# ========================================================================= #
|
65
|
+
def set_input(i = '')
|
66
|
+
i = i.first if i.is_a? Array
|
67
|
+
i = i.to_s.dup
|
68
|
+
if i.empty?
|
69
|
+
i = BASE_DIR
|
70
|
+
end
|
71
|
+
i = i.dup if i.frozen?
|
72
|
+
if i.end_with?('/') and !File.directory?(i) # Reject invalid directories here.
|
73
|
+
i.chop!
|
74
|
+
end
|
75
|
+
if File.directory? i
|
76
|
+
i << '/*.ffn'
|
77
|
+
end
|
78
|
+
i.squeeze!('/')
|
79
|
+
@input = i
|
80
|
+
end
|
81
|
+
|
82
|
+
# ========================================================================= #
|
83
|
+
# === input?
|
84
|
+
# ========================================================================= #
|
85
|
+
def input?
|
86
|
+
@input
|
87
|
+
end
|
88
|
+
|
89
|
+
# ========================================================================= #
|
90
|
+
# === report_this_header_from_that_file
|
91
|
+
# ========================================================================= #
|
92
|
+
def report_this_header_from_that_file(header, file)
|
93
|
+
if @be_verbose
|
94
|
+
erev "The file at #{sfile(file)}#{rev} has the following FASTA header:"
|
95
|
+
e
|
96
|
+
end
|
97
|
+
e " #{simp(header)}"
|
98
|
+
end
|
99
|
+
|
100
|
+
# ========================================================================= #
|
101
|
+
# === input_without_extension
|
102
|
+
# ========================================================================= #
|
103
|
+
def input_without_extension
|
104
|
+
input?.sub(/\*\.ffn$/,'')
|
105
|
+
end
|
106
|
+
|
107
|
+
# ========================================================================= #
|
108
|
+
# === report_these_files
|
109
|
+
# ========================================================================= #
|
110
|
+
def report_these_files(files)
|
111
|
+
files.each {|this_file|
|
112
|
+
dataset = File.readlines(this_file)
|
113
|
+
dataset.reject! {|line| line.strip.start_with? '#' }
|
114
|
+
header = dataset.first
|
115
|
+
report_this_header_from_that_file(header, this_file)
|
116
|
+
}
|
117
|
+
end
|
118
|
+
|
119
|
+
# ========================================================================= #
|
120
|
+
# === run (run tag)
|
121
|
+
# ========================================================================= #
|
122
|
+
def run
|
123
|
+
files = Dir[input?]
|
124
|
+
if files.empty?
|
125
|
+
opnn; e 'No files could be found for '+input?+'.'
|
126
|
+
else
|
127
|
+
report_these_files(files)
|
128
|
+
end
|
129
|
+
end
|
130
|
+
|
131
|
+
end; end
|
132
|
+
|
133
|
+
if __FILE__ == $PROGRAM_NAME
|
134
|
+
Bioroebe::ShowFastaHeaders.new(ARGV)
|
135
|
+
end # sfasta test.fasta
|