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 +1,1086 @@
|
|
1
|
+
#!/usr/bin/ruby -w
|
2
|
+
# Encoding: UTF-8
|
3
|
+
# frozen_string_literal: true
|
4
|
+
# =========================================================================== #
|
5
|
+
# === Bioroebe::ParsePdbFile
|
6
|
+
#
|
7
|
+
# This class will parse a .pdb file.
|
8
|
+
#
|
9
|
+
# The format for a .pdb file is described here:
|
10
|
+
#
|
11
|
+
# https://www.wwpdb.org/documentation/file-format
|
12
|
+
# https://www.cgl.ucsf.edu/chimera/docs/UsersGuide/tutorials/pdbintro.html
|
13
|
+
#
|
14
|
+
# The following short reference table can be used to get an overview of
|
15
|
+
# the main attributes of this format:
|
16
|
+
#
|
17
|
+
# Record Type Data Provided by Record
|
18
|
+
#
|
19
|
+
#----------------|-------------------------------------------------------------|
|
20
|
+
# ATOM | atomic coordinate record containing the X,Y,Z orthogonal Å |
|
21
|
+
# | coordinates for atoms in standard residues (amino acids and |
|
22
|
+
# | nucleic acids). Each atom in the coordinate section is |
|
23
|
+
# | identified by a sequential number in the entry file. |
|
24
|
+
# | ATOM records for proteins are listed from amino to |
|
25
|
+
# | carboxyl terminus. |
|
26
|
+
#----------------|-------------------------------------------------------------|
|
27
|
+
# HETATM | atomic coordinate record containing the X,Y,Z orthogonal Å |
|
28
|
+
# | coordinates for atoms in nonstandard residues. Nonstandard |
|
29
|
+
# | residues include inhibitors, cofactors, ions, and solvent. |
|
30
|
+
# | The only functional difference from ATOM records is that |
|
31
|
+
# | HETATM residues are by default not connected to other |
|
32
|
+
# | residues. Note that water residues should be in HETATM |
|
33
|
+
# | records. |
|
34
|
+
#----------------|-------------------------------------------------------------|
|
35
|
+
# TER | indicates the end of a chain of residues. For example, a |
|
36
|
+
# | hemoglobin molecule consists of four subunit chains that |
|
37
|
+
# | are not connected. TER indicates the end of a chain and |
|
38
|
+
# | prevents the display of a connection to the next chain. |
|
39
|
+
#----------------|-------------------------------------------------------------|
|
40
|
+
# HELIX | indicates the location and type (right-handed alpha, etc.) |
|
41
|
+
# | of helices. One record per helix. |
|
42
|
+
#----------------|-------------------------------------------------------------|
|
43
|
+
# SHEET | indicates the location, sense (anti-parallel, etc.) and |
|
44
|
+
# | registration with respect to the previous strand in the |
|
45
|
+
# | sheet (if any) of each strand in the model. One record |
|
46
|
+
# | per strand. |
|
47
|
+
# | |
|
48
|
+
# | See also: |
|
49
|
+
# | |
|
50
|
+
# | https://www.wwpdb.org/documentation/file-format-content/format23/sect5.html#SHEET
|
51
|
+
# | |
|
52
|
+
#----------------|-------------------------------------------------------------|
|
53
|
+
# SSBOND | defines disulfide bond linkages between cysteine residues. |
|
54
|
+
#----------------|-------------------------------------------------------------|
|
55
|
+
# KEYWDS | contains some extra information about the given structure |
|
56
|
+
#----------------|-------------------------------------------------------------|
|
57
|
+
#
|
58
|
+
# Format explained in more detail:
|
59
|
+
#
|
60
|
+
# COLUMNS DATA TYPE CONTENTS
|
61
|
+
# ------------------------------------------------------------------------------
|
62
|
+
# 1 - 6 Record name "ATOM "
|
63
|
+
# 7 - 11 Integer Atom serial number.
|
64
|
+
# 13 - 16 Atom Atom name.
|
65
|
+
# 17 Character Alternate location indicator.
|
66
|
+
# 18 - 20 Residue name Residue name.
|
67
|
+
# 22 Character Chain identifier.
|
68
|
+
# 23 - 26 Integer Residue sequence number.
|
69
|
+
# 27 AChar Code for insertion of residues.
|
70
|
+
# 31 - 38 Real(8.3) Orthogonal coordinates for X in Angstroms.
|
71
|
+
# 39 - 46 Real(8.3) Orthogonal coordinates for Y in Angstroms.
|
72
|
+
# 47 - 54 Real(8.3) Orthogonal coordinates for Z in Angstroms.
|
73
|
+
# 55 - 60 Real(6.2) Occupancy.
|
74
|
+
# 61 - 66 Real(6.2) Temperature factor (Default = 0.0).
|
75
|
+
# 73 - 76 LString(4) Segment identifier, left-justified.
|
76
|
+
# 77 - 78 LString(2) Element symbol, right-justified.
|
77
|
+
# 79 - 80 LString(2) Charge on the atom.
|
78
|
+
#
|
79
|
+
# Example:
|
80
|
+
#
|
81
|
+
# 1 2 3 4 5 6 7 8
|
82
|
+
# 12345678901234567890123456789012345678901234567890123456789012345678901234567890
|
83
|
+
# ATOM 145 N VAL A 25 32.433 16.336 57.540 1.00 11.92 A1 N
|
84
|
+
# ATOM 146 CA VAL A 25 31.132 16.439 58.160 1.00 11.85 A1 C
|
85
|
+
# ATOM 147 C VAL A 25 30.447 15.105 58.363 1.00 12.34 A1 C
|
86
|
+
# ATOM 148 O VAL A 25 29.520 15.059 59.174 1.00 15.65 A1 O
|
87
|
+
# ATOM 149 CB AVAL A 25 30.385 17.437 57.230 0.28 13.88 A1 C
|
88
|
+
# ATOM 150 CB BVAL A 25 30.166 17.399 57.373 0.72 15.41 A1 C
|
89
|
+
# ATOM 151 CG1AVAL A 25 28.870 17.401 57.336 0.28 12.64 A1 C
|
90
|
+
# ATOM 152 CG1BVAL A 25 30.805 18.788 57.449 0.72 15.11 A1 C
|
91
|
+
# ATOM 153 CG2AVAL A 25 30.835 18.826 57.661 0.28 13.58 A1 C
|
92
|
+
# ATOM 154 CG2BVAL A 25 29.909 16.996 55.922 0.72 13.25 A1 C
|
93
|
+
#
|
94
|
+
# Usage example:
|
95
|
+
#
|
96
|
+
# Bioroebe::ParsePdbFile.new(ARGV)
|
97
|
+
#
|
98
|
+
# =========================================================================== #
|
99
|
+
# If you need a sample .pdb file, have a look here:
|
100
|
+
#
|
101
|
+
# https://gist.github.com/cstein/6699200
|
102
|
+
#
|
103
|
+
# For more information about the ATOM entry, have a look here:
|
104
|
+
#
|
105
|
+
# https://zhanglab.ccmb.med.umich.edu/SSIPe/pdb_atom_format.html#ATOM
|
106
|
+
#
|
107
|
+
# =========================================================================== #
|
108
|
+
# require 'bioroebe/pdb/parse_pdb_file.rb'
|
109
|
+
# Bioroebe.return_aminoacid_sequence_from_this_pdb_file
|
110
|
+
# =========================================================================== #
|
111
|
+
require 'bioroebe/base/commandline_application/commandline_application.rb'
|
112
|
+
|
113
|
+
module Bioroebe
|
114
|
+
|
115
|
+
class ParsePdbFile < ::Bioroebe::CommandlineApplication # === Bioroebe::ParsePdbFile
|
116
|
+
|
117
|
+
# ========================================================================= #
|
118
|
+
# === NAMESPACE
|
119
|
+
# ========================================================================= #
|
120
|
+
NAMESPACE = inspect
|
121
|
+
|
122
|
+
# ========================================================================= #
|
123
|
+
# === DEFAULT_PDB_FILE
|
124
|
+
# ========================================================================= #
|
125
|
+
DEFAULT_PDB_FILE = "#{::Bioroebe.log_directory?}test.pdb"
|
126
|
+
|
127
|
+
# ========================================================================= #
|
128
|
+
# === initialize
|
129
|
+
# ========================================================================= #
|
130
|
+
def initialize(
|
131
|
+
i = DEFAULT_PDB_FILE,
|
132
|
+
run_already = true
|
133
|
+
)
|
134
|
+
reset
|
135
|
+
unless i.is_a? Array
|
136
|
+
i = [i].flatten.compact
|
137
|
+
end
|
138
|
+
set_commandline_arguments(
|
139
|
+
return_entries_with_two_leading_hyphens_from(i)
|
140
|
+
)
|
141
|
+
set_pdb_files(
|
142
|
+
return_entries_without_two_leading_hyphens(i)
|
143
|
+
)
|
144
|
+
# ======================================================================= #
|
145
|
+
# === Handle blocks
|
146
|
+
# ======================================================================= #
|
147
|
+
if block_given?
|
148
|
+
yielded = yield
|
149
|
+
case yielded
|
150
|
+
# ===================================================================== #
|
151
|
+
# === :be_silent
|
152
|
+
#
|
153
|
+
# Invocation example for this entry point:
|
154
|
+
#
|
155
|
+
# Bioroebe::ParsePdbFile.new(ARGV) { :be_silent }
|
156
|
+
#
|
157
|
+
# ===================================================================== #
|
158
|
+
when :be_silent
|
159
|
+
set_be_silent
|
160
|
+
end
|
161
|
+
end
|
162
|
+
case run_already
|
163
|
+
when :do_not_run_yet
|
164
|
+
run_already = false
|
165
|
+
end
|
166
|
+
run if run_already
|
167
|
+
end
|
168
|
+
|
169
|
+
# ========================================================================= #
|
170
|
+
# === reset (reset tag)
|
171
|
+
# ========================================================================= #
|
172
|
+
def reset
|
173
|
+
super()
|
174
|
+
# ======================================================================= #
|
175
|
+
# === @namespace
|
176
|
+
# ======================================================================= #
|
177
|
+
@namespace = NAMESPACE
|
178
|
+
# ======================================================================= #
|
179
|
+
# === @do_create_a_fasta_file
|
180
|
+
#
|
181
|
+
# This variable has to exist outside of the method call
|
182
|
+
# reset_internal_variables() as it would otherwise
|
183
|
+
# ignore every commandline argument passed in by the
|
184
|
+
# user.
|
185
|
+
# ======================================================================= #
|
186
|
+
@do_create_a_fasta_file = false
|
187
|
+
# ======================================================================= #
|
188
|
+
# === @x_coordinates
|
189
|
+
# ======================================================================= #
|
190
|
+
@x_coordinates = []
|
191
|
+
# ======================================================================= #
|
192
|
+
# === @y_coordinates
|
193
|
+
# ======================================================================= #
|
194
|
+
@y_coordinates = []
|
195
|
+
# ======================================================================= #
|
196
|
+
# === @z_coordinates
|
197
|
+
# ======================================================================= #
|
198
|
+
@z_coordinates = []
|
199
|
+
# ======================================================================= #
|
200
|
+
# All internal variables can be reset through this method.
|
201
|
+
# ======================================================================= #
|
202
|
+
reset_internal_variables
|
203
|
+
end
|
204
|
+
|
205
|
+
# ========================================================================= #
|
206
|
+
# === reset_internal_variables
|
207
|
+
# ========================================================================= #
|
208
|
+
def reset_internal_variables
|
209
|
+
self.header = ''
|
210
|
+
self.title = ''
|
211
|
+
# ======================================================================= #
|
212
|
+
# === @body
|
213
|
+
# ======================================================================= #
|
214
|
+
@body = nil
|
215
|
+
# ======================================================================= #
|
216
|
+
# === @taxid
|
217
|
+
# ======================================================================= #
|
218
|
+
@taxid = nil
|
219
|
+
# ======================================================================= #
|
220
|
+
# === @n_chains_are_in_this_atom
|
221
|
+
# ======================================================================= #
|
222
|
+
@n_chains_are_in_this_atom = 0
|
223
|
+
# ======================================================================= #
|
224
|
+
# === @alpha_helices
|
225
|
+
# ======================================================================= #
|
226
|
+
@alpha_helices = []
|
227
|
+
# ======================================================================= #
|
228
|
+
# === @beta_sheets
|
229
|
+
# ======================================================================= #
|
230
|
+
@beta_sheets = []
|
231
|
+
# ======================================================================= #
|
232
|
+
# === @does_the_file_exist
|
233
|
+
# ======================================================================= #
|
234
|
+
@does_the_file_exist = false
|
235
|
+
# ======================================================================= #
|
236
|
+
# === @name_of_the_species
|
237
|
+
# ======================================================================= #
|
238
|
+
@name_of_the_species = nil
|
239
|
+
# ======================================================================= #
|
240
|
+
# === @taxid_of_the_species
|
241
|
+
# ======================================================================= #
|
242
|
+
@taxid_of_the_species = nil
|
243
|
+
# ======================================================================= #
|
244
|
+
# === @report_the_aminoacid_sequence
|
245
|
+
# ======================================================================= #
|
246
|
+
@report_the_aminoacid_sequence = true
|
247
|
+
# ======================================================================= #
|
248
|
+
# === @keywords
|
249
|
+
# ======================================================================= #
|
250
|
+
@keywords = nil
|
251
|
+
end
|
252
|
+
|
253
|
+
# ========================================================================= #
|
254
|
+
# === keywords?
|
255
|
+
# ========================================================================= #
|
256
|
+
def keywords?
|
257
|
+
@keywords
|
258
|
+
end; alias keywords keywords? # === keywords
|
259
|
+
|
260
|
+
# ========================================================================= #
|
261
|
+
# === set_pdb_files
|
262
|
+
#
|
263
|
+
# We will keep this as an Array.
|
264
|
+
# ========================================================================= #
|
265
|
+
def set_pdb_files(
|
266
|
+
i = DEFAULT_PDB_FILE
|
267
|
+
)
|
268
|
+
i = [i] unless i.is_a? Array
|
269
|
+
i.map! {|entry|
|
270
|
+
entry = entry.to_s.dup # To avoid frozen-Strings.
|
271
|
+
case entry
|
272
|
+
# ===================================================================== #
|
273
|
+
# === :1fat
|
274
|
+
# ===================================================================== #
|
275
|
+
when ':1fat'
|
276
|
+
entry = "#{::Bioroebe.project_base_directory?}data/1fat.pdb"
|
277
|
+
end
|
278
|
+
# ===================================================================== #
|
279
|
+
# The user may input a String such as "1NR6", but may not want to
|
280
|
+
# input the longer "1NR6.pdb". In that case, if such a .pdb file
|
281
|
+
# exists, we will use that as path instead.
|
282
|
+
# ===================================================================== #
|
283
|
+
if File.exist?("#{entry}.pdb") and !File.exist?(entry)
|
284
|
+
entry << '.pdb'
|
285
|
+
end
|
286
|
+
File.absolute_path(entry) # We require the full local path to the file at hand.
|
287
|
+
}
|
288
|
+
@pdb_files = i
|
289
|
+
end
|
290
|
+
|
291
|
+
# ========================================================================= #
|
292
|
+
# === try_to_determine_the_taxid_from_this_input
|
293
|
+
#
|
294
|
+
# This method will attempt to determine the taxid entry.
|
295
|
+
# ========================================================================= #
|
296
|
+
def try_to_determine_the_taxid_from_this_input(i)
|
297
|
+
if i.is_a? Array
|
298
|
+
# ===================================================================== #
|
299
|
+
# We will try to find entries like this:
|
300
|
+
#
|
301
|
+
# SOURCE 3 ORGANISM_TAXID: 300852;
|
302
|
+
#
|
303
|
+
# ===================================================================== #
|
304
|
+
_ = i.select {|line| line.include? 'ORGANISM_TAXID:' }
|
305
|
+
unless _.empty?
|
306
|
+
@taxid = _.first.strip.delete(';').split(' ').last
|
307
|
+
end
|
308
|
+
end
|
309
|
+
end
|
310
|
+
|
311
|
+
# ========================================================================= #
|
312
|
+
# === taxid?
|
313
|
+
# ========================================================================= #
|
314
|
+
def taxid?
|
315
|
+
@taxid
|
316
|
+
end
|
317
|
+
|
318
|
+
# ========================================================================= #
|
319
|
+
# === body?
|
320
|
+
# ========================================================================= #
|
321
|
+
def body?
|
322
|
+
@body
|
323
|
+
end
|
324
|
+
|
325
|
+
# ========================================================================= #
|
326
|
+
# === input_sequence?
|
327
|
+
#
|
328
|
+
# This will return a String.
|
329
|
+
# ========================================================================= #
|
330
|
+
def input_sequence?
|
331
|
+
_ = @body
|
332
|
+
if _.is_a? Array
|
333
|
+
_ = _.join(N)
|
334
|
+
end
|
335
|
+
_
|
336
|
+
end
|
337
|
+
|
338
|
+
# ========================================================================= #
|
339
|
+
# === set_body
|
340
|
+
#
|
341
|
+
# This method keeps track of the main "body" of the .pdb file at hand.
|
342
|
+
# ========================================================================= #
|
343
|
+
def set_body(i)
|
344
|
+
@body = i
|
345
|
+
end; alias body= set_body # === body?
|
346
|
+
|
347
|
+
# ========================================================================= #
|
348
|
+
# === set_header
|
349
|
+
#
|
350
|
+
# The header may have an entry such as:
|
351
|
+
#
|
352
|
+
# HEADER RIBOSOMAL PROTEIN/RNA 16-APR-10 3IYQ
|
353
|
+
#
|
354
|
+
# ========================================================================= #
|
355
|
+
def set_header(i)
|
356
|
+
if i
|
357
|
+
if i.is_a? Array
|
358
|
+
i = i.first
|
359
|
+
return if i.nil? # Can't work with nil-entries.
|
360
|
+
end
|
361
|
+
i = i.dup if i.frozen?
|
362
|
+
# ===================================================================== #
|
363
|
+
# We do a bit sanitizing here.
|
364
|
+
# ===================================================================== #
|
365
|
+
if i.include?('HEADER')
|
366
|
+
i.sub!(/HEADER/,'')
|
367
|
+
end
|
368
|
+
i.strip!
|
369
|
+
if i.include? ' '
|
370
|
+
i = i.split(' ').map(&:strip).first
|
371
|
+
end
|
372
|
+
end
|
373
|
+
@header = i
|
374
|
+
end; alias header= set_header # === header?
|
375
|
+
|
376
|
+
# ========================================================================= #
|
377
|
+
# === string?
|
378
|
+
# ========================================================================= #
|
379
|
+
def string?
|
380
|
+
@body
|
381
|
+
end; alias data? string? # === data?
|
382
|
+
|
383
|
+
# ========================================================================= #
|
384
|
+
# === n_atoms?
|
385
|
+
#
|
386
|
+
# Returns how many ATOM entries we have in this .pdb file.
|
387
|
+
# ========================================================================= #
|
388
|
+
def n_atoms?(i = data?)
|
389
|
+
i.select {|entry| entry.start_with? 'ATOM' }.size if i
|
390
|
+
end; alias n_atom_entries? n_atoms? # === n_atom_entries?
|
391
|
+
|
392
|
+
# ========================================================================= #
|
393
|
+
# === title?
|
394
|
+
# ========================================================================= #
|
395
|
+
def title?
|
396
|
+
@title
|
397
|
+
end; alias title title? # === title
|
398
|
+
|
399
|
+
# ========================================================================= #
|
400
|
+
# === header?
|
401
|
+
# ========================================================================= #
|
402
|
+
def header?
|
403
|
+
@header
|
404
|
+
end; alias header header? # === header
|
405
|
+
|
406
|
+
# ========================================================================= #
|
407
|
+
# === report_n_atoms
|
408
|
+
# ========================================================================= #
|
409
|
+
def report_n_atoms
|
410
|
+
if be_verbose?
|
411
|
+
e "#{sfancy(n_atoms?.to_s)}#{rev} ATOM entries were found "\
|
412
|
+
"being part of the file at"
|
413
|
+
e "`#{sfile(main_file?)}#{rev}`."
|
414
|
+
end
|
415
|
+
end
|
416
|
+
|
417
|
+
# ========================================================================= #
|
418
|
+
# === readlines_from_this_file
|
419
|
+
# ========================================================================= #
|
420
|
+
def readlines_from_this_file(file)
|
421
|
+
File.readlines(file)
|
422
|
+
end
|
423
|
+
|
424
|
+
# ========================================================================= #
|
425
|
+
# === set_header_title_and_body
|
426
|
+
#
|
427
|
+
# The input to this method should be an Array.
|
428
|
+
# ========================================================================= #
|
429
|
+
def set_header_title_and_body(dataset)
|
430
|
+
set_header(
|
431
|
+
dataset.select {|entry| entry.include? 'HEADER' }
|
432
|
+
)
|
433
|
+
self.title = dataset.select {|entry| entry.include? 'TITLE' }
|
434
|
+
set_body(dataset)
|
435
|
+
end
|
436
|
+
|
437
|
+
# ========================================================================= #
|
438
|
+
# === try_to_determine_the_alpha_helices_in_this_protein
|
439
|
+
# ========================================================================= #
|
440
|
+
def try_to_determine_the_alpha_helices_in_this_protein(i)
|
441
|
+
if i.is_a? Array
|
442
|
+
selection = i.select {|line| line.start_with? 'HELIX ' }
|
443
|
+
@alpha_helices = selection
|
444
|
+
end
|
445
|
+
end
|
446
|
+
|
447
|
+
# ========================================================================= #
|
448
|
+
# === n_alpha_helices?
|
449
|
+
# ========================================================================= #
|
450
|
+
def n_alpha_helices?
|
451
|
+
@alpha_helices.size
|
452
|
+
end
|
453
|
+
|
454
|
+
# ========================================================================= #
|
455
|
+
# === consider_reporting_alpha_helices_that_were_found
|
456
|
+
# ========================================================================= #
|
457
|
+
def consider_reporting_alpha_helices_that_were_found(
|
458
|
+
i = @alpha_helices
|
459
|
+
)
|
460
|
+
unless i.empty?
|
461
|
+
if be_verbose?
|
462
|
+
erev "This protein contains "\
|
463
|
+
"#{slateblue(i.size.to_s)}#{rev} alpha-helices."
|
464
|
+
end
|
465
|
+
end
|
466
|
+
end
|
467
|
+
|
468
|
+
# ========================================================================= #
|
469
|
+
# === consider_reporting_beta_sheet_that_were_found
|
470
|
+
# ========================================================================= #
|
471
|
+
def consider_reporting_beta_sheet_that_were_found(i = @beta_sheets)
|
472
|
+
unless i.empty?
|
473
|
+
e "This protein contains #{slateblue(i.size.to_s)}#{rev} beta-sheets."
|
474
|
+
end
|
475
|
+
end
|
476
|
+
|
477
|
+
# ========================================================================= #
|
478
|
+
# === n_aminoacids?
|
479
|
+
# ========================================================================= #
|
480
|
+
def n_aminoacids?
|
481
|
+
@aminoacid_sequence.size if @aminoacid_sequence
|
482
|
+
end
|
483
|
+
|
484
|
+
# ========================================================================= #
|
485
|
+
# === silently_determine_the_aminoacid_sequence
|
486
|
+
#
|
487
|
+
# This method is probably not quite correct, as it does not take into
|
488
|
+
# consideration that there may be a succession of aminoacids.
|
489
|
+
# ========================================================================= #
|
490
|
+
def silently_determine_the_aminoacid_sequence(i)
|
491
|
+
this_aminoacid_sequence = ''.dup
|
492
|
+
selection = i.select {|line| line.start_with?('ATOM ') }
|
493
|
+
last_number_of_aminoacid = 0
|
494
|
+
selection.each {|line, index|
|
495
|
+
line.strip!
|
496
|
+
# ===================================================================== #
|
497
|
+
# The line may look like this:
|
498
|
+
#
|
499
|
+
# ATOM 69 CG2 THR A 8 23.165 11.137 48.942 1.00 30.40 C
|
500
|
+
#
|
501
|
+
# Each atom in the coordinate section is identified by a sequential
|
502
|
+
# number in the entry file. The entry at position 5, seen below,
|
503
|
+
# identifies the aminoacid there.
|
504
|
+
# ===================================================================== #
|
505
|
+
# 0 1 2 3 4 5 6 7 8 9 10 11
|
506
|
+
# ===================================================================== #
|
507
|
+
splitted = line.split(' ').map(&:strip).map {|entry| entry.squeeze(' ') }
|
508
|
+
@x_coordinates << splitted[6].to_f
|
509
|
+
@y_coordinates << splitted[7].to_f
|
510
|
+
@z_coordinates << splitted[8].to_f
|
511
|
+
this_aminoacid = three_to_one(splitted[3])
|
512
|
+
number_of_this_aminoacid = splitted[5].to_i
|
513
|
+
# ===================================================================== #
|
514
|
+
# Entries may look like this:
|
515
|
+
#
|
516
|
+
# ATOM 490 HZ3 LYS A 70 4.674 -0.770 -3.751 1.00 2.07 H
|
517
|
+
# ATOM 491 N LYS A 71 8.012 0.034 2.745 1.00 0.74 N
|
518
|
+
#
|
519
|
+
# ===================================================================== #
|
520
|
+
if number_of_this_aminoacid > last_number_of_aminoacid
|
521
|
+
this_aminoacid_sequence << this_aminoacid
|
522
|
+
last_number_of_aminoacid = number_of_this_aminoacid
|
523
|
+
end
|
524
|
+
}
|
525
|
+
@aminoacid_sequence = this_aminoacid_sequence
|
526
|
+
end
|
527
|
+
|
528
|
+
# ========================================================================= #
|
529
|
+
# === aminoacid_sequence?
|
530
|
+
# ========================================================================= #
|
531
|
+
def aminoacid_sequence?
|
532
|
+
@aminoacid_sequence
|
533
|
+
end
|
534
|
+
|
535
|
+
# ========================================================================= #
|
536
|
+
# === calculate_the_distance_between_two_points
|
537
|
+
#
|
538
|
+
# Pass in two arrays to this method.
|
539
|
+
# ========================================================================= #
|
540
|
+
def calculate_the_distance_between_two_points(p1, p2)
|
541
|
+
a = (p2[0] - p1[0]) ** 2
|
542
|
+
b = (p2[1] - p1[1]) ** 2
|
543
|
+
c = (p2[2] - p1[2]) ** 2
|
544
|
+
return Math.sqrt(a+b+c)
|
545
|
+
end
|
546
|
+
|
547
|
+
# ========================================================================= #
|
548
|
+
# === check_whether_this_pdb_sequence_contains_dna
|
549
|
+
# ========================================================================= #
|
550
|
+
def check_whether_this_pdb_sequence_contains_dna
|
551
|
+
_ = input_sequence?
|
552
|
+
if _.include? 'MOLECULE: DNA'
|
553
|
+
erev 'This protein sequence contains at the least one DNA strand.'
|
554
|
+
sequence = _.scan(/ MOLECULE: DNA(.+)$/).flatten
|
555
|
+
if sequence
|
556
|
+
sequence = sequence.first.to_s.strip if sequence.respond_to? :first
|
557
|
+
# =================================================================== #
|
558
|
+
# This may look like this:
|
559
|
+
#
|
560
|
+
# "(5'-D(*CP*GP*CP*GP*AP*AP*TP*TP*CP*GP*CP*G)-3');"
|
561
|
+
#
|
562
|
+
# =================================================================== #
|
563
|
+
sequence = sequence.tr('-','').delete("'D(P*);53")
|
564
|
+
result = ('This DNA sequence is '+colourize_dna(sequence)+rev+'.').dup
|
565
|
+
# =================================================================== #
|
566
|
+
# Check whether it is a palindrome.
|
567
|
+
# =================================================================== #
|
568
|
+
if is_this_sequence_a_palindrome? sequence
|
569
|
+
result << rev+' It is a palindrome.'
|
570
|
+
else
|
571
|
+
result << rev+' It is NOT a palindrome.'
|
572
|
+
end
|
573
|
+
erev result
|
574
|
+
end
|
575
|
+
end
|
576
|
+
end
|
577
|
+
|
578
|
+
# ========================================================================= #
|
579
|
+
# === try_to_determine_the_beta_sheets_in_this_protein
|
580
|
+
#
|
581
|
+
# Beta-sheets begin with the word 'SHEET '.
|
582
|
+
# ========================================================================= #
|
583
|
+
def try_to_determine_the_beta_sheets_in_this_protein(i)
|
584
|
+
if i.is_a? Array
|
585
|
+
selection = i.select {|line| line.start_with? 'SHEET ' }
|
586
|
+
@beta_sheets = selection
|
587
|
+
end
|
588
|
+
end
|
589
|
+
|
590
|
+
# ========================================================================= #
|
591
|
+
# === return_all_ATOM_entries
|
592
|
+
# ========================================================================= #
|
593
|
+
def return_all_ATOM_entries
|
594
|
+
@body.select {|entry| entry.start_with? 'ATOM ' }
|
595
|
+
end
|
596
|
+
|
597
|
+
# ========================================================================= #
|
598
|
+
# === consider_reporting_how_many_chains_are_in_this_structure
|
599
|
+
#
|
600
|
+
# A better way to report how many chains are in a structure
|
601
|
+
# is via:
|
602
|
+
#
|
603
|
+
# COMPND 3 CHAIN: A, B;
|
604
|
+
#
|
605
|
+
# ========================================================================= #
|
606
|
+
def consider_reporting_how_many_chains_are_in_this_structure
|
607
|
+
# _ = return_all_ATOM_entries.max {|line|
|
608
|
+
# line.split(' ')[1].to_i
|
609
|
+
# }
|
610
|
+
# # ===================================================================== #
|
611
|
+
# # The entry may look like this:
|
612
|
+
# #
|
613
|
+
# # "ATOM 52643 N LYS N 393 27.402 -53.192 44.13"
|
614
|
+
# #
|
615
|
+
# # ===================================================================== #
|
616
|
+
# _ = convert_this_alphabet_character_to_number(
|
617
|
+
# _.split(' ')[2]
|
618
|
+
# )
|
619
|
+
selection = @body.select {|entry|
|
620
|
+
entry.include? 'COMPND ' and entry.include? 'CHAIN: '
|
621
|
+
}
|
622
|
+
# ======================================================================= #
|
623
|
+
# Examples:
|
624
|
+
#
|
625
|
+
# ["COMPND 3 CHAIN: A, B, C, D, E, F, G, H, I, J, K, L, M, N; \n",
|
626
|
+
# "COMPND 8 CHAIN: O, P, Q, R, S, T, U; \n"]
|
627
|
+
#
|
628
|
+
# ======================================================================= #
|
629
|
+
_ = selection.join(' ')
|
630
|
+
use_this_regex = /([A-Z])(,|;)/
|
631
|
+
scanned = _.scan(use_this_regex).map {|inner_array| inner_array[0].ord }
|
632
|
+
unless scanned.empty?
|
633
|
+
max = scanned.max - 64 # -64 because A is 65 and it is the start.
|
634
|
+
if be_verbose?
|
635
|
+
erev "There are #{steelblue(max)}#{rev} chains in this molecule."
|
636
|
+
end
|
637
|
+
end
|
638
|
+
end
|
639
|
+
|
640
|
+
# ========================================================================= #
|
641
|
+
# === convert_this_alphabet_character_to_number
|
642
|
+
#
|
643
|
+
# The input of "A" would mean "1".
|
644
|
+
# ========================================================================= #
|
645
|
+
def convert_this_alphabet_character_to_number(i)
|
646
|
+
(i.ord - 64)
|
647
|
+
end
|
648
|
+
|
649
|
+
# ========================================================================= #
|
650
|
+
# === try_to_report_the_organism_at_hand
|
651
|
+
#
|
652
|
+
# This method will try to extract the organism's name.
|
653
|
+
#
|
654
|
+
# This entry may look like this:
|
655
|
+
#
|
656
|
+
# SOURCE 2 ORGANISM_SCIENTIFIC: SQUALUS ACANTHIAS;
|
657
|
+
#
|
658
|
+
# ========================================================================= #
|
659
|
+
def try_to_report_the_organism_at_hand(i = @body)
|
660
|
+
if i.is_a?(Array) and !i.empty?
|
661
|
+
# ===================================================================== #
|
662
|
+
# === ORGANISM_SCIENTIFIC
|
663
|
+
# ===================================================================== #
|
664
|
+
_ = i.select {|line| line.include? 'ORGANISM_SCIENTIFIC:' }
|
665
|
+
if _
|
666
|
+
first_element = _.first
|
667
|
+
if first_element
|
668
|
+
first_element.strip!
|
669
|
+
@name_of_the_species = first_element.split(':').last.delete(';').strip
|
670
|
+
end
|
671
|
+
end
|
672
|
+
# ===================================================================== #
|
673
|
+
# === ORGANISM_TAXID
|
674
|
+
#
|
675
|
+
# Next try to find out the taxid number of the organism at hand.
|
676
|
+
# ===================================================================== #
|
677
|
+
_ = i.select {|line| line.include? ' ORGANISM_TAXID: ' }
|
678
|
+
if _
|
679
|
+
first_element = _.first
|
680
|
+
if first_element
|
681
|
+
first_element.strip!
|
682
|
+
@taxid_of_the_species = first_element.split(':').last.delete(';').strip
|
683
|
+
end
|
684
|
+
end
|
685
|
+
if be_verbose? and @name_of_the_species
|
686
|
+
report_extra_information_about_the_species_at_hand
|
687
|
+
end
|
688
|
+
end
|
689
|
+
end
|
690
|
+
|
691
|
+
# ========================================================================= #
|
692
|
+
# === name_of_the_species?
|
693
|
+
# ========================================================================= #
|
694
|
+
def name_of_the_species?
|
695
|
+
@name_of_the_species
|
696
|
+
end
|
697
|
+
|
698
|
+
# ========================================================================= #
|
699
|
+
# === report_extra_information_about_the_species_at_hand
|
700
|
+
# ========================================================================= #
|
701
|
+
def report_extra_information_about_the_species_at_hand
|
702
|
+
result = ''.dup
|
703
|
+
result << 'The name of the organism (Entry: '+
|
704
|
+
steelblue('ORGANISM_SCIENTIFIC')+
|
705
|
+
rev+
|
706
|
+
') is'+N
|
707
|
+
result << '`'+orange(name_of_the_species?)+rev+'`.'
|
708
|
+
if @taxid_of_the_species
|
709
|
+
organism_common = organism_common?.to_s
|
710
|
+
if organism_common and !organism_common.empty?
|
711
|
+
result << rev+' (Taxid: '+
|
712
|
+
steelblue(@taxid_of_the_species.to_s)+
|
713
|
+
rev+'; '+
|
714
|
+
seagreen(
|
715
|
+
organism_common
|
716
|
+
)+rev+')'
|
717
|
+
end
|
718
|
+
end
|
719
|
+
erev result
|
720
|
+
end
|
721
|
+
|
722
|
+
# ========================================================================= #
|
723
|
+
# === organism_common?
|
724
|
+
# ========================================================================= #
|
725
|
+
def organism_common?
|
726
|
+
if @body
|
727
|
+
_ = @body.join(N).scan(/ORGANISM_COMMON: (.+);/).flatten.uniq
|
728
|
+
if _ and _.is_a?(Array)
|
729
|
+
_ = _.first.to_s
|
730
|
+
end
|
731
|
+
return _
|
732
|
+
end
|
733
|
+
end
|
734
|
+
|
735
|
+
# ========================================================================= #
|
736
|
+
# === process_each_pdb_file
|
737
|
+
#
|
738
|
+
# This method is the main powerhorse method of this class.
|
739
|
+
# ========================================================================= #
|
740
|
+
def process_each_pdb_file
|
741
|
+
@pdb_files.each {|file|
|
742
|
+
if File.exist?(file) and File.file?(file)
|
743
|
+
reset_internal_variables # Reset the internal variables here.
|
744
|
+
@does_the_file_exist = true
|
745
|
+
set_this_file(file)
|
746
|
+
dataset = readlines_from_this_file(file)
|
747
|
+
if dataset.any? {|line| line.include? 'KEYWDS' }
|
748
|
+
set_keywords(dataset)
|
749
|
+
end
|
750
|
+
set_header_title_and_body(dataset)
|
751
|
+
analyze_the_dataset
|
752
|
+
consider_creating_a_fasta_file
|
753
|
+
else
|
754
|
+
opnn; erev "No file at `#{sfile(file)}#{rev}` could be found."
|
755
|
+
@does_the_file_exist = false
|
756
|
+
end
|
757
|
+
}
|
758
|
+
end
|
759
|
+
|
760
|
+
# ========================================================================= #
|
761
|
+
# === taxid_of_the_species?
|
762
|
+
# ========================================================================= #
|
763
|
+
def taxid_of_the_species?
|
764
|
+
@taxid_of_the_species
|
765
|
+
end
|
766
|
+
|
767
|
+
# ========================================================================= #
|
768
|
+
# === menu (menu tag)
|
769
|
+
# ========================================================================= #
|
770
|
+
def menu(
|
771
|
+
i = @commandline_arguments
|
772
|
+
)
|
773
|
+
if i.is_a? Array
|
774
|
+
i.each {|entry| menu(entry) }
|
775
|
+
else
|
776
|
+
case i
|
777
|
+
# ===================================================================== #
|
778
|
+
# === parsedb 2HI4.pdb --no-colours
|
779
|
+
# ===================================================================== #
|
780
|
+
when /^-?-?no(-|_)?colou?rs$/i
|
781
|
+
disable_colours
|
782
|
+
# ===================================================================== #
|
783
|
+
# === parsedb 2HI4.pdb --create-fasta-file
|
784
|
+
# ===================================================================== #
|
785
|
+
when /^-?-?create(-|_)?fasta(-|_)?file$/i
|
786
|
+
@do_create_a_fasta_file = true
|
787
|
+
end
|
788
|
+
end
|
789
|
+
end
|
790
|
+
|
791
|
+
# ========================================================================= #
|
792
|
+
# === return_short_filename
|
793
|
+
# ========================================================================= #
|
794
|
+
def return_short_filename
|
795
|
+
File.basename(@this_file)
|
796
|
+
end
|
797
|
+
|
798
|
+
# ========================================================================= #
|
799
|
+
# === consider_creating_a_fasta_file
|
800
|
+
# ========================================================================= #
|
801
|
+
def consider_creating_a_fasta_file
|
802
|
+
if @do_create_a_fasta_file
|
803
|
+
what = aminoacid_sequence?
|
804
|
+
into = return_short_filename.sub(/\.pdb$/,'')+'.fasta'
|
805
|
+
into = File.absolute_path(into)
|
806
|
+
erev 'Storing into the file `'+sfile(into)+rev+'`.'
|
807
|
+
write_what_into(what, into)
|
808
|
+
end
|
809
|
+
end
|
810
|
+
|
811
|
+
# ========================================================================= #
|
812
|
+
# === set_this_file
|
813
|
+
# ========================================================================= #
|
814
|
+
def set_this_file(i)
|
815
|
+
@this_file = i
|
816
|
+
end
|
817
|
+
|
818
|
+
# ========================================================================= #
|
819
|
+
# === main_file?
|
820
|
+
# ========================================================================= #
|
821
|
+
def main_file?
|
822
|
+
@this_file
|
823
|
+
end; alias return_filename main_file? # === return_filename
|
824
|
+
|
825
|
+
# ========================================================================= #
|
826
|
+
# === try_to_determine_the_max_distance_between_the_atoms_in_this_protein?
|
827
|
+
# ========================================================================= #
|
828
|
+
def try_to_determine_the_max_distance_between_the_atoms_in_this_protein?(
|
829
|
+
array = @body
|
830
|
+
)
|
831
|
+
max_value = max_distance?(array)
|
832
|
+
if be_verbose?
|
833
|
+
erev 'The maximum difference between the atoms is '+
|
834
|
+
sfancy(max_value.to_s)+rev
|
835
|
+
end
|
836
|
+
end; alias try_to_determine_the_max_distance_between_the_atoms_in_this_protein try_to_determine_the_max_distance_between_the_atoms_in_this_protein? # === try_to_determine_the_max_distance_between_the_atoms_in_this_protein
|
837
|
+
|
838
|
+
# ========================================================================= #
|
839
|
+
# === max_distance?
|
840
|
+
# ========================================================================= #
|
841
|
+
def max_distance?(
|
842
|
+
array = @body
|
843
|
+
)
|
844
|
+
return if array.nil? or array.empty?
|
845
|
+
# ======================================================================= #
|
846
|
+
# ["ATOM 1 N MET A 41 1.177 -10.035 -3.493 1.00 2.04 N",
|
847
|
+
# "ATOM 2 CA MET A 41 0.292 -8.839 -3.377 1.00 1.55 C"]
|
848
|
+
# ======================================================================= #
|
849
|
+
max_value = 0
|
850
|
+
modified_array = array.map {|line|
|
851
|
+
splitted = line.split(' ')
|
852
|
+
x = splitted[6].to_f
|
853
|
+
y = splitted[7].to_f
|
854
|
+
z = splitted[8].to_f
|
855
|
+
[x,y,z]
|
856
|
+
}
|
857
|
+
# ======================================================================= #
|
858
|
+
# [1.177, -10.035, -3.493]
|
859
|
+
# [0.292, -8.839, -3.377]
|
860
|
+
# ======================================================================= #
|
861
|
+
modified_array.each_with_index {|entry, index| index += 1
|
862
|
+
if index == modified_array.size
|
863
|
+
index = 0
|
864
|
+
end
|
865
|
+
array1 = entry
|
866
|
+
array2 = modified_array[index]
|
867
|
+
result = calculate_the_distance_between_two_points(array1, array2)
|
868
|
+
if result > max_value
|
869
|
+
max_value = result
|
870
|
+
end
|
871
|
+
}
|
872
|
+
return max_value
|
873
|
+
end
|
874
|
+
|
875
|
+
# ========================================================================= #
|
876
|
+
# === title?
|
877
|
+
# ========================================================================= #
|
878
|
+
def title=(i)
|
879
|
+
if i.is_a? Array
|
880
|
+
i.map!(&:chomp)
|
881
|
+
i.map!(&:strip)
|
882
|
+
end
|
883
|
+
@title = i
|
884
|
+
end; alias set_title title= # === set_title
|
885
|
+
|
886
|
+
# ========================================================================= #
|
887
|
+
# === calculate_the_centroid_position
|
888
|
+
#
|
889
|
+
# This method will calculate the centroid aka the "average position
|
890
|
+
# of the atoms" in that .pdb file. Currently this will only
|
891
|
+
# assume that each atom is the same, but in reality we should also
|
892
|
+
# include the weight of the atom at hand - this is currently not
|
893
|
+
# implemented via this method, though.
|
894
|
+
#
|
895
|
+
# If this is ever improved, we need to include the weight of the
|
896
|
+
# corresponding atom as well.
|
897
|
+
# ========================================================================= #
|
898
|
+
def calculate_the_centroid_position
|
899
|
+
n_atoms = n_atoms?.to_i
|
900
|
+
if n_atoms > 0
|
901
|
+
x_average = @x_coordinates.sum / n_atoms.to_f
|
902
|
+
y_average = @y_coordinates.sum / n_atoms.to_f
|
903
|
+
z_average = @z_coordinates.sum / n_atoms.to_f
|
904
|
+
else
|
905
|
+
x_average = y_average = z_average = 0
|
906
|
+
end
|
907
|
+
array = [x_average, y_average, z_average]
|
908
|
+
return array
|
909
|
+
end; alias calculate_centroid calculate_the_centroid_position # === calculate_centroid
|
910
|
+
|
911
|
+
# ========================================================================= #
|
912
|
+
# === report_header
|
913
|
+
#
|
914
|
+
# This will also report the filename.
|
915
|
+
# ========================================================================= #
|
916
|
+
def report_header(
|
917
|
+
of_this_file = @this_file
|
918
|
+
)
|
919
|
+
if be_verbose?
|
920
|
+
_ = return_short_filename
|
921
|
+
e orange(header?)+rev+
|
922
|
+
' (File: '+
|
923
|
+
steelblue(_)+
|
924
|
+
rev+'; Filesize: '+
|
925
|
+
(File.size(of_this_file) / 1024).to_s+
|
926
|
+
'kb'+')'+rev
|
927
|
+
end
|
928
|
+
end
|
929
|
+
|
930
|
+
# ========================================================================= #
|
931
|
+
# === analyze_the_dataset
|
932
|
+
#
|
933
|
+
# This method is the "powerhorse" of this class.
|
934
|
+
# ========================================================================= #
|
935
|
+
def analyze_the_dataset(
|
936
|
+
body = @body
|
937
|
+
)
|
938
|
+
if @does_the_file_exist
|
939
|
+
report_header
|
940
|
+
try_to_report_the_organism_at_hand(body)
|
941
|
+
report_n_atoms
|
942
|
+
check_whether_this_pdb_sequence_contains_dna
|
943
|
+
silently_determine_the_aminoacid_sequence(body)
|
944
|
+
consider_reporting_the_aminoacid_sequence
|
945
|
+
consider_reporting_the_number_of_individual_aminoacids
|
946
|
+
consider_reporting_the_number_of_residues
|
947
|
+
# ===================================================================== #
|
948
|
+
# Try to obtain the taxid.
|
949
|
+
# ===================================================================== #
|
950
|
+
try_to_determine_the_taxid_from_this_input(body)
|
951
|
+
try_to_determine_the_alpha_helices_in_this_protein(body)
|
952
|
+
consider_reporting_alpha_helices_that_were_found
|
953
|
+
try_to_determine_the_beta_sheets_in_this_protein(body)
|
954
|
+
try_to_determine_the_max_distance_between_the_atoms_in_this_protein(body)
|
955
|
+
consider_reporting_beta_sheet_that_were_found
|
956
|
+
consider_reporting_how_many_chains_are_in_this_structure
|
957
|
+
consider_reporting_the_keywords
|
958
|
+
end
|
959
|
+
end
|
960
|
+
|
961
|
+
# ========================================================================= #
|
962
|
+
# === consider_reporting_the_keywords
|
963
|
+
#
|
964
|
+
# This method will report the discovered keyword entries in the given
|
965
|
+
# .pdb file at hand (if this .pdb file contains these keywords entries
|
966
|
+
# that is).
|
967
|
+
# ========================================================================= #
|
968
|
+
def consider_reporting_the_keywords(
|
969
|
+
keywords = keywords?
|
970
|
+
)
|
971
|
+
if keywords
|
972
|
+
erev "The keywords are: #{steelblue(keywords)}"
|
973
|
+
end
|
974
|
+
end
|
975
|
+
|
976
|
+
# ========================================================================= #
|
977
|
+
# === consider_reporting_the_number_of_residues
|
978
|
+
# ========================================================================= #
|
979
|
+
def consider_reporting_the_number_of_residues
|
980
|
+
if @report_the_aminoacid_sequence and be_verbose?
|
981
|
+
erev 'Total no:of residues - '+steelblue(@aminoacid_sequence.size.to_s)
|
982
|
+
end
|
983
|
+
end
|
984
|
+
|
985
|
+
# ========================================================================= #
|
986
|
+
# === consider_reporting_the_number_of_individual_aminoacids
|
987
|
+
# ========================================================================= #
|
988
|
+
def consider_reporting_the_number_of_individual_aminoacids
|
989
|
+
if @report_the_aminoacid_sequence and be_verbose?
|
990
|
+
hash = @aminoacid_sequence.each_char.tally
|
991
|
+
hash.each_pair {|aminoacid_one_letter, n_occurrences|
|
992
|
+
erev 'Total no:of '+
|
993
|
+
rev+
|
994
|
+
lightgreen(::Bioroebe.one_to_three(aminoacid_one_letter).upcase)+
|
995
|
+
rev+
|
996
|
+
' - '+
|
997
|
+
steelblue(n_occurrences.to_s)
|
998
|
+
}
|
999
|
+
end
|
1000
|
+
end
|
1001
|
+
|
1002
|
+
# ========================================================================= #
|
1003
|
+
# === set_keywords
|
1004
|
+
# ========================================================================= #
|
1005
|
+
def set_keywords(i)
|
1006
|
+
if i.is_a? Array
|
1007
|
+
i.flatten!
|
1008
|
+
selection = i.select {|entry| entry.include? 'KEYWDS' }
|
1009
|
+
i = selection.first
|
1010
|
+
end
|
1011
|
+
@keywords = i.to_s.strip
|
1012
|
+
end; alias keywords= set_keywords # === keywords=
|
1013
|
+
|
1014
|
+
# ========================================================================= #
|
1015
|
+
# === consider_reporting_the_aminoacid_sequence
|
1016
|
+
#
|
1017
|
+
# This method will typically display the aminoacid sequence at hand.
|
1018
|
+
# ========================================================================= #
|
1019
|
+
def consider_reporting_the_aminoacid_sequence
|
1020
|
+
if @report_the_aminoacid_sequence and be_verbose?
|
1021
|
+
_ = @aminoacid_sequence
|
1022
|
+
erev 'The aminoacid sequence ('+
|
1023
|
+
steelblue(_.size.to_s)+rev+
|
1024
|
+
' aminoacids) is:'
|
1025
|
+
# erev ' '+colourize_this_aminoacid_sequence(_) # <- We could colourize it.
|
1026
|
+
erev " #{steelblue(_)}"
|
1027
|
+
end
|
1028
|
+
end
|
1029
|
+
|
1030
|
+
# ========================================================================= #
|
1031
|
+
# === run (run tag)
|
1032
|
+
# ========================================================================= #
|
1033
|
+
def run
|
1034
|
+
menu
|
1035
|
+
process_each_pdb_file
|
1036
|
+
if be_verbose?
|
1037
|
+
erev 'The centered position is at: '+
|
1038
|
+
steelblue(
|
1039
|
+
calculate_the_centroid_position.join(', ')
|
1040
|
+
)
|
1041
|
+
end
|
1042
|
+
end
|
1043
|
+
|
1044
|
+
end
|
1045
|
+
|
1046
|
+
# =========================================================================== #
|
1047
|
+
# === Bioroebe.parse_pdb_file
|
1048
|
+
# =========================================================================== #
|
1049
|
+
def self.parse_pdb_file(i = ARGV)
|
1050
|
+
Bioroebe::ParsePdbFile.new(i)
|
1051
|
+
end
|
1052
|
+
|
1053
|
+
# =========================================================================== #
|
1054
|
+
# === Bioroebe.return_aminoacid_sequence_from_this_pdb_file
|
1055
|
+
#
|
1056
|
+
# This variant will (silently) return the aminoacid sequence. The
|
1057
|
+
# input must be a file that exists locally; if you already have
|
1058
|
+
# a String that you wish to just parse, use the method defined
|
1059
|
+
# below instead.
|
1060
|
+
#
|
1061
|
+
# Invocation example:
|
1062
|
+
#
|
1063
|
+
# Bioroebe.return_aminoacid_sequence_from_this_pdb_file "1VII.pdb" # => "MLSDEDFKAVFGMTRSAFANLPLWKQQNLKKEKGLF"
|
1064
|
+
#
|
1065
|
+
# =========================================================================== #
|
1066
|
+
def self.return_aminoacid_sequence_from_this_pdb_file(i = ARGV)
|
1067
|
+
Bioroebe::ParsePdbFile.new(i) { :be_silent }.aminoacid_sequence?
|
1068
|
+
end
|
1069
|
+
|
1070
|
+
# =========================================================================== #
|
1071
|
+
# === Bioroebe.return_aminoacid_sequence_from_this_string
|
1072
|
+
# =========================================================================== #
|
1073
|
+
def self.return_aminoacid_sequence_from_this_string(i = ARGV)
|
1074
|
+
_ = Bioroebe::ParsePdbFile.new(i, :do_not_run_yet) { :be_silent }
|
1075
|
+
dataset = i.split("\n")
|
1076
|
+
_.set_header_title_and_body(dataset)
|
1077
|
+
_.aminoacid_sequence?
|
1078
|
+
end
|
1079
|
+
|
1080
|
+
end
|
1081
|
+
|
1082
|
+
if __FILE__ == $PROGRAM_NAME
|
1083
|
+
require 'colours/autoinclude'
|
1084
|
+
_ = Bioroebe::ParsePdbFile.new(ARGV)
|
1085
|
+
end # pdbfile test.pdb
|
1086
|
+
# pdbfile :1fat
|