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 +1,694 @@
|
|
1
|
+
#!/usr/bin/perl
|
2
|
+
# =========================================================================== #
|
3
|
+
# This script will convert local coords from within a transcript into
|
4
|
+
# a global (e.g. genomic) coordinates - and vice versa.
|
5
|
+
# =========================================================================== #
|
6
|
+
|
7
|
+
use strict;
|
8
|
+
use warnings;
|
9
|
+
use Getopt::Long;
|
10
|
+
use AnnotUtil;
|
11
|
+
use Pod::Usage;
|
12
|
+
|
13
|
+
# =========================================================================== #
|
14
|
+
# Command line options:
|
15
|
+
# =========================================================================== #
|
16
|
+
my $exon_in; # exon gtf file
|
17
|
+
my $data_in; # data to be converted
|
18
|
+
|
19
|
+
my $exon_type; # annotation type of exon file
|
20
|
+
my $data_type; # annotation type of data file
|
21
|
+
|
22
|
+
my $txID_exon; # specify txID of exon file to be used
|
23
|
+
my $txID_data; # specify txID of data file to be used
|
24
|
+
|
25
|
+
my $loc2glob; # convert local to global coordinates
|
26
|
+
my $glob2loc; # convert global tp local coordinates
|
27
|
+
|
28
|
+
my $v; # verbose mode
|
29
|
+
|
30
|
+
my $show_help;
|
31
|
+
my $man;
|
32
|
+
|
33
|
+
GetOptions(
|
34
|
+
'exon|e=s' => \$exon_in,
|
35
|
+
'data|dat|d:s' => \$data_in,
|
36
|
+
'etype|et:s' => \$exon_type,
|
37
|
+
'dtype|dt:s' => \$data_type,
|
38
|
+
'exonID|eid:s' => \$txID_exon,
|
39
|
+
'dataID|did:s' => \$txID_data,
|
40
|
+
'g2l|glob2loc' => \$glob2loc,
|
41
|
+
'l2g|loc2glob' => \$loc2glob,
|
42
|
+
'verbose|v' => \$v,
|
43
|
+
'help|h' => \$show_help,
|
44
|
+
'man' => \$man
|
45
|
+
);
|
46
|
+
|
47
|
+
pod2usage(1) if $show_help;
|
48
|
+
pod2usage(-verbose => 2) if $man;
|
49
|
+
|
50
|
+
# =========================================================================== #
|
51
|
+
# Known file types.
|
52
|
+
# =========================================================================== #
|
53
|
+
my %known_types = (bed => 1,
|
54
|
+
gtf => 2,
|
55
|
+
gff3 => 3);
|
56
|
+
|
57
|
+
# =========================================================================== #
|
58
|
+
# Auto detect file types
|
59
|
+
# =========================================================================== #
|
60
|
+
unless (defined($exon_type)){
|
61
|
+
$exon_type = $1 if $exon_in =~ /\.(\w+)$/;
|
62
|
+
}
|
63
|
+
|
64
|
+
# =========================================================================== #
|
65
|
+
unless (defined($data_type)){
|
66
|
+
# =========================================================================== #
|
67
|
+
$data_type = $1 if $data_in =~ /\.(\w+)$/;
|
68
|
+
}
|
69
|
+
|
70
|
+
|
71
|
+
die "\nplease specify the exon file type: -et|-etype [bed, gtf, gff3]\n\n" unless defined($exon_type) && exists($known_types{$exon_type});
|
72
|
+
die "\nplease specify the data file type: -dt|-dtype [bed, gtf, gff3]\n\n" unless defined($data_type) && exists($known_types{$data_type});
|
73
|
+
|
74
|
+
# field that holds transcript id
|
75
|
+
my %txID_field = (bed => "name",
|
76
|
+
gtf => "transcript_id",
|
77
|
+
gff3 => "ID");
|
78
|
+
|
79
|
+
$txID_exon = $txID_field{$exon_type} unless (defined($txID_exon));
|
80
|
+
$txID_data = $txID_field{$data_type} unless (defined($txID_data));
|
81
|
+
|
82
|
+
print "txID_exon $txID_exon\n" if $v;
|
83
|
+
print "txID_data $txID_data\n" if $v;
|
84
|
+
|
85
|
+
# Read exon gtf file
|
86
|
+
# ------------------------------------------------------------
|
87
|
+
|
88
|
+
my %exons = (); # Reference to the entire %hash.
|
89
|
+
|
90
|
+
my $fh_exon;
|
91
|
+
|
92
|
+
if ($exon_in =~ /\.gz$/){
|
93
|
+
open($fh_exon, "zcat $exon_in |") || die "could not open gzipped exon annotation file $!\n";
|
94
|
+
}
|
95
|
+
else{
|
96
|
+
open($fh_exon, "<$exon_in") || die "could not open exon annotation file $!\n";
|
97
|
+
}
|
98
|
+
|
99
|
+
while(<$fh_exon>){
|
100
|
+
# chomp;
|
101
|
+
my $id;
|
102
|
+
|
103
|
+
if ($exon_type eq "gtf"){
|
104
|
+
my($fields, $attribs) = splitGtfLine($_);
|
105
|
+
$id = $attribs->{$txID_exon}->[0];
|
106
|
+
$id =~ s/[";]//g;
|
107
|
+
push(@{$exons{$id}},$fields);
|
108
|
+
print "exon id: $id\n" if $v;
|
109
|
+
next;
|
110
|
+
}
|
111
|
+
|
112
|
+
if ($exon_type eq "gff3"){
|
113
|
+
my($fields, $attribs) = splitGff3Line($_);
|
114
|
+
$id = $attribs->{$txID_exon}->{$txID_exon};
|
115
|
+
$id =~ s/[";]//g;
|
116
|
+
push(@{$exons{$id}},$fields);
|
117
|
+
next;
|
118
|
+
}
|
119
|
+
|
120
|
+
if ($exon_type eq "bed"){
|
121
|
+
my($fields) = splitBedLine($_);
|
122
|
+
next unless exists($fields->{strand});
|
123
|
+
$id = $fields->{$txID_exon};
|
124
|
+
push(@{$exons{$id}},$fields);
|
125
|
+
next;
|
126
|
+
}
|
127
|
+
|
128
|
+
}
|
129
|
+
close($fh_exon);
|
130
|
+
print STDERR "done reading exon table\n" if $v;
|
131
|
+
|
132
|
+
# -----------------------------------------------------------
|
133
|
+
# Calculate local coordinates
|
134
|
+
# -----------------------------------------------------------
|
135
|
+
|
136
|
+
my ($g2l) = &genomeLocalTAB(\%exons);
|
137
|
+
|
138
|
+
# Read data file
|
139
|
+
# and convert local coordinates to genomic coodinates
|
140
|
+
# --------------------------------------------------
|
141
|
+
|
142
|
+
my $fh_data;
|
143
|
+
|
144
|
+
if ($data_in =~ /\.gz$/){
|
145
|
+
open($fh_data, "zcat $data_in |") || die "could not open gzipped data gtf file $!\n";
|
146
|
+
}
|
147
|
+
else{
|
148
|
+
open($fh_data, "<$data_in") || die "could not open data annotation file $!\n";
|
149
|
+
}
|
150
|
+
|
151
|
+
while(<$fh_data>){
|
152
|
+
chomp;
|
153
|
+
my($fields, $attribs, $txID);
|
154
|
+
|
155
|
+
# the id field is the tx_id in the global data file
|
156
|
+
# when converting global2local!
|
157
|
+
|
158
|
+
if ($data_type eq "gtf"){
|
159
|
+
($fields, $attribs) = splitGtfLine($_);
|
160
|
+
$txID = $attribs->{$txID_data}->[0];
|
161
|
+
$txID =~ s/[";]//g;
|
162
|
+
}
|
163
|
+
|
164
|
+
if ($data_type eq "gff3"){
|
165
|
+
($fields, $attribs) = splitGff3Line($_);
|
166
|
+
$txID = $attribs->{$txID_data}->{$txID_data};
|
167
|
+
$txID =~ s/[";]//g;
|
168
|
+
# print "data txID $txID\n";
|
169
|
+
}
|
170
|
+
|
171
|
+
if ($data_type eq "bed"){
|
172
|
+
$fields = splitBedLine($_);
|
173
|
+
next unless exists($fields->{strand});
|
174
|
+
$txID = $fields->{$txID_data};
|
175
|
+
}
|
176
|
+
|
177
|
+
# the id field is the chromosome in the local data file
|
178
|
+
# when converting local2glbal!
|
179
|
+
$txID = $fields->{chr} if $loc2glob;
|
180
|
+
|
181
|
+
next unless defined($txID) ;
|
182
|
+
$txID =~ s/[";]//g;
|
183
|
+
|
184
|
+
# check if txID exists in g2l lookup table
|
185
|
+
next unless exists($g2l->{$txID});
|
186
|
+
print STDERR "data txID exists in lookup table $txID\n" if $v;
|
187
|
+
|
188
|
+
my $data_start = $fields->{start};
|
189
|
+
my $data_end = $fields->{end};
|
190
|
+
|
191
|
+
# global2local
|
192
|
+
# --------------------------------------------------
|
193
|
+
# calculate local coordinates of global features
|
194
|
+
my $data;
|
195
|
+
|
196
|
+
$data = &global2local2(\%exons, $g2l,$txID,$data_start,$data_end) if $glob2loc;
|
197
|
+
|
198
|
+
# local2global
|
199
|
+
# --------------------------------------------------
|
200
|
+
# calculate global coordinates of local features
|
201
|
+
|
202
|
+
$data = &local2global2(\%exons, $g2l,$txID,$data_start,$data_end) if $loc2glob;
|
203
|
+
|
204
|
+
# Print results
|
205
|
+
|
206
|
+
# the chromosome field was the txID and is now the chr
|
207
|
+
$fields->{chr} = $exons{$txID}->[0]->{chr} if $loc2glob;
|
208
|
+
|
209
|
+
# get the strand right
|
210
|
+
# g2l
|
211
|
+
# if exon is on + and data is on + => stands are equal => local = +
|
212
|
+
# if exon is on - and data is on - => stands are equal => local = +
|
213
|
+
# if exon is on + and data is on - => stands are NOT equal => local = -
|
214
|
+
# if exon is on - and data is on + => stands are NOT equal => local = -
|
215
|
+
|
216
|
+
if ($glob2loc){
|
217
|
+
($exons{$txID}->[0]->{strand} eq $fields->{strand}) ? ($fields->{strand} = "+") : ($fields->{strand} = "-");
|
218
|
+
|
219
|
+
# $fields->{strand} = "+", next if $exons{$txID}->[0]->{strand} eq $fields->{strand};
|
220
|
+
# $fields->{strand} = "-", next if $exons{$txID}->[0]->{strand} ne $fields->{strand};
|
221
|
+
}
|
222
|
+
|
223
|
+
# l2g
|
224
|
+
# if exon is on + and data is on + => global stands are equal => global = +
|
225
|
+
# if exon is on - and data is on - => global stands are equal => global = -
|
226
|
+
# => strand global is strand exon
|
227
|
+
# if exon is on + and data is on - => global stands are NOT equal => global = -
|
228
|
+
# if exon is on - and data is on + => global stands are NOT equal => global = +
|
229
|
+
# => strand global is strand data => nothing to be done
|
230
|
+
|
231
|
+
if ($loc2glob){
|
232
|
+
$fields->{strand} = $exons{$txID}->[0]->{strand} if $exons{$txID}->[0]->{strand} eq $fields->{strand};
|
233
|
+
}
|
234
|
+
|
235
|
+
|
236
|
+
$fields->{strand} = $exons{$txID}->[0]->{strand} if $loc2glob;
|
237
|
+
|
238
|
+
# the chromosome field was the chr and is now the txID
|
239
|
+
$fields->{chr} = $txID if $glob2loc;
|
240
|
+
|
241
|
+
for my $i (0..$#$data){
|
242
|
+
|
243
|
+
# foreach my $k (sort keys %{$data->[$i]} ){
|
244
|
+
# print "$txID $k $data->[$i]->{$k}\n"
|
245
|
+
# }
|
246
|
+
if ($glob2loc){
|
247
|
+
$fields->{start} = $data->[$i]->{lstart};
|
248
|
+
$fields->{end} = $data->[$i]->{lend};
|
249
|
+
}
|
250
|
+
|
251
|
+
if ($loc2glob){
|
252
|
+
$fields->{start} = $data->[$i]->{gstart};
|
253
|
+
$fields->{end} = $data->[$i]->{gend};
|
254
|
+
}
|
255
|
+
|
256
|
+
|
257
|
+
printGtfFields($fields, *STDOUT) if $data_type eq "gtf" || $data_type eq "gff3";
|
258
|
+
printBedLine($fields) if $data_type eq "bed";
|
259
|
+
}
|
260
|
+
|
261
|
+
# print "main l2g $txID " if $loc2glob;
|
262
|
+
# print "main g2l $txID " if $glob2loc;
|
263
|
+
# print "main global: ",$data->[0]->{gstart}," ",$data->[0]->{gend}," ";
|
264
|
+
# print "main local $data->[0]->{lstart} $data->[0]->{lend}\n";
|
265
|
+
}
|
266
|
+
close($fh_data);
|
267
|
+
|
268
|
+
# --------------------------------------------------
|
269
|
+
# Subfunctions
|
270
|
+
# --------------------------------------------------
|
271
|
+
sub genomeLocalTAB {
|
272
|
+
my ($exons) = @_;
|
273
|
+
|
274
|
+
my %g2l = ();
|
275
|
+
|
276
|
+
foreach my $txID (sort keys %$exons ){
|
277
|
+
|
278
|
+
# sort exons if plus strand
|
279
|
+
if ($exons->{$txID}->[0]->{strand} eq "+"){
|
280
|
+
@{$exons->{$txID}} = sort(MySort2 @{$exons->{$txID}});
|
281
|
+
}
|
282
|
+
|
283
|
+
# reverse sort exons if minus strand
|
284
|
+
if ($exons->{$txID}->[0]->{strand} eq "-"){
|
285
|
+
@{$exons->{$txID}} = sort(RevMySort2 @{$exons->{$txID}});
|
286
|
+
}
|
287
|
+
|
288
|
+
# for the first exon it's simple :)
|
289
|
+
my $firstex_start = $exons->{$txID}->[0]->{start};
|
290
|
+
my $firstex_end = $exons->{$txID}->[0]->{end};
|
291
|
+
|
292
|
+
$g2l{$txID}->[0]->{lstart} = 1;
|
293
|
+
$g2l{$txID}->[0]->{lend} = 1+ ($firstex_end - $firstex_start +1) -1;
|
294
|
+
$g2l{$txID}->[0]->{gstart} = $exons->{$txID}->[0]->{start};
|
295
|
+
$g2l{$txID}->[0]->{gend} = $exons->{$txID}->[0]->{end};
|
296
|
+
|
297
|
+
# convert coordinates for exons 1-n
|
298
|
+
for my $i (1..$#{$exons->{$txID}}){
|
299
|
+
my $tmp_start = $exons->{$txID}->[$i]->{start};
|
300
|
+
my $tmp_end = $exons->{$txID}->[$i]->{end};
|
301
|
+
|
302
|
+
my $tmp_length = $tmp_end - $tmp_start +1;
|
303
|
+
$g2l{$txID}->[$i]->{lstart} = $g2l{$txID}->[$i-1]->{lend}+1;
|
304
|
+
$g2l{$txID}->[$i]->{lend} = $g2l{$txID}->[$i]->{lstart} + $tmp_length -1;
|
305
|
+
$g2l{$txID}->[$i]->{gstart} = $exons->{$txID}->[$i]->{start};
|
306
|
+
$g2l{$txID}->[$i]->{gend} = $exons->{$txID}->[$i]->{end};
|
307
|
+
}
|
308
|
+
}
|
309
|
+
return(\%g2l);
|
310
|
+
}
|
311
|
+
|
312
|
+
# --------------------------------------------------
|
313
|
+
|
314
|
+
# Convert Global coordinates to local coordinates
|
315
|
+
# example: cds exons within transcript exons
|
316
|
+
|
317
|
+
sub global2local2{
|
318
|
+
my ($exons,$g2l,$ID,$data_gstart,$data_gend) = @_;
|
319
|
+
|
320
|
+
my $data_length = $data_gend - $data_gstart + 1;
|
321
|
+
|
322
|
+
# exons on plus strand and local feature on plus strand
|
323
|
+
if ($exons->{$ID}->[0]->{strand} eq "+"){
|
324
|
+
@{$g2l->{$ID}} = sort(MySortGlobal @{$g2l->{$ID}});
|
325
|
+
|
326
|
+
my @data = ();
|
327
|
+
|
328
|
+
for my $i (0..$#{$g2l->{$ID}}){
|
329
|
+
my $ex_gstart = $g2l->{$ID}->[$i]->{gstart};
|
330
|
+
my $ex_gend = $g2l->{$ID}->[$i]->{gend};
|
331
|
+
my $ex_lstart = $g2l->{$ID}->[$i]->{lstart};
|
332
|
+
my $ex_lend = $g2l->{$ID}->[$i]->{lend};
|
333
|
+
|
334
|
+
# feature starts in exon and must end in exon!
|
335
|
+
next unless (($data_gstart >= $ex_gstart) && ($data_gend <= $ex_gend));
|
336
|
+
|
337
|
+
my %tmp = ();
|
338
|
+
|
339
|
+
# calculate local start coordinate
|
340
|
+
my $start_shift = $data_gstart - $ex_gstart +1;
|
341
|
+
$tmp{lstart} = $ex_lstart + $start_shift -1;
|
342
|
+
$tmp{gstart} = $data_gstart;
|
343
|
+
|
344
|
+
# calculate local end coordinate
|
345
|
+
# feature must be included in exon!
|
346
|
+
$tmp{lend} = $tmp{lstart} + $data_length -1;
|
347
|
+
$tmp{gend} = $data_gend;
|
348
|
+
push(@data,\%tmp);
|
349
|
+
last;
|
350
|
+
}
|
351
|
+
return(\@data);
|
352
|
+
}
|
353
|
+
|
354
|
+
# exons on minus strand
|
355
|
+
if ($exons->{$ID}->[0]->{strand} eq "-"){
|
356
|
+
@{$g2l->{$ID}} = sort(MySortGlobal @{$g2l->{$ID}});
|
357
|
+
|
358
|
+
my @data = ();
|
359
|
+
|
360
|
+
for my $i (0..$#{$g2l->{$ID}}){
|
361
|
+
my $ex_gstart = $g2l->{$ID}->[$i]->{gstart};
|
362
|
+
my $ex_gend = $g2l->{$ID}->[$i]->{gend};
|
363
|
+
my $ex_lstart = $g2l->{$ID}->[$i]->{lstart};
|
364
|
+
my $ex_lend = $g2l->{$ID}->[$i]->{lend};
|
365
|
+
|
366
|
+
# feature starts in exon and must end in exon!
|
367
|
+
next unless (($data_gstart >= $ex_gstart) && ($data_gend <= $ex_gend));
|
368
|
+
|
369
|
+
# print "$data_gstart $data_gend $i\n";
|
370
|
+
my %tmp = ();
|
371
|
+
|
372
|
+
# feature is included in exon
|
373
|
+
# exon_global s<<<<<<<<<<<<e
|
374
|
+
# data_global s<<<<<<<<<e
|
375
|
+
# local e<<<<<<<<<s
|
376
|
+
# shift --
|
377
|
+
|
378
|
+
# calculate local end coordinate
|
379
|
+
my $start_shift = $data_gstart - $ex_gstart +1;
|
380
|
+
$tmp{lend} = $ex_lend - $start_shift +1;
|
381
|
+
$tmp{gstart} = $data_gstart;
|
382
|
+
|
383
|
+
# calculate local start coordinate
|
384
|
+
# feature must be included in exon!
|
385
|
+
$tmp{lstart} = $tmp{lend} - $data_length +1;
|
386
|
+
$tmp{gend} = $data_gend;
|
387
|
+
push(@data,\%tmp);
|
388
|
+
last;
|
389
|
+
}
|
390
|
+
return(\@data);
|
391
|
+
}
|
392
|
+
}
|
393
|
+
|
394
|
+
# =========================================================================== #
|
395
|
+
# === local2global2
|
396
|
+
#
|
397
|
+
# Convert local coordinates to global coordinates
|
398
|
+
# example: RNA secondary structure element in transcript
|
399
|
+
# where RNALfold was run on transcript sequences.
|
400
|
+
# here, the feature need not be included in an exon
|
401
|
+
# and may cross exon junctions
|
402
|
+
# =========================================================================== #
|
403
|
+
sub local2global2 {
|
404
|
+
my ($exons,$g2l,$ID,$data_lstart,$data_lend) = @_;
|
405
|
+
|
406
|
+
my $data_length = $data_lend - $data_lstart + 1;
|
407
|
+
# print "data coords: ls $data_lstart le $data_lend length $data_length\n";
|
408
|
+
|
409
|
+
# exons on plus strand
|
410
|
+
if ($exons->{$ID}->[0]->{strand} eq "+"){
|
411
|
+
@{$g2l->{$ID}} = sort(MySortLocal @{$g2l->{$ID}});
|
412
|
+
|
413
|
+
my @data = ();
|
414
|
+
|
415
|
+
for my $i (0..$#{$g2l->{$ID}}){
|
416
|
+
my $ex_gstart = $g2l->{$ID}->[$i]->{gstart};
|
417
|
+
my $ex_gend = $g2l->{$ID}->[$i]->{gend};
|
418
|
+
my $ex_lstart = $g2l->{$ID}->[$i]->{lstart};
|
419
|
+
my $ex_lend = $g2l->{$ID}->[$i]->{lend};
|
420
|
+
|
421
|
+
# feature starts in exon
|
422
|
+
next unless ($data_lstart >= $ex_lstart) && ($data_lstart <= $ex_lend);
|
423
|
+
|
424
|
+
my %tmp = ();
|
425
|
+
# calculate global start coordinate
|
426
|
+
my $start_shift = $data_lstart - $ex_lstart +1;
|
427
|
+
$tmp{gstart} = $ex_gstart + $start_shift -1;
|
428
|
+
$tmp{lstart} = $data_lstart;
|
429
|
+
|
430
|
+
# print "exon $i\n exon coords: gs $ex_gstart ge $ex_gend ls $ex_lstart le $ex_lend length ",($ex_lend-$ex_lstart+1),"\n";
|
431
|
+
|
432
|
+
# calculate global end coordinate
|
433
|
+
# feature is included in exon -> we are done here
|
434
|
+
if ($data_lend <= $ex_lend){
|
435
|
+
# $tmp{gend} = $tmp{gstart} + $data_length -1 ;
|
436
|
+
$tmp{gend} = $tmp{gstart} + ($data_lend-$tmp{lstart}+1 ) -1 ;
|
437
|
+
$tmp{lend} = $data_lend;
|
438
|
+
|
439
|
+
# print("data $i included\n data coords: gs $tmp{gstart} ge $tmp{gend} ls $tmp{lstart} le $tmp{lend} glength ",($tmp{gend}-$tmp{gstart}+1)," llength ",($tmp{lend}-$tmp{lstart}+1),"\n\n");
|
440
|
+
|
441
|
+
push(@data,\%tmp);
|
442
|
+
last;
|
443
|
+
}
|
444
|
+
|
445
|
+
# feature goes beyond exon and reaches into following exons
|
446
|
+
if ($data_lend > $ex_lend){
|
447
|
+
$tmp{gend} = $ex_gend;
|
448
|
+
$tmp{lend} = $ex_lend;
|
449
|
+
# print("data $i part\n data coords: gs $tmp{gstart} ge $tmp{gend} ls $tmp{lstart} le $tmp{lend} glength ",($tmp{gend}-$tmp{gstart}+1)," llength ",($tmp{lend}-$tmp{lstart}+1),"\n\n");
|
450
|
+
push(@data,\%tmp);
|
451
|
+
# new start coordinate for next loop
|
452
|
+
$data_lstart = $ex_lend + 1;
|
453
|
+
next;
|
454
|
+
}
|
455
|
+
}
|
456
|
+
return(\@data);
|
457
|
+
}
|
458
|
+
|
459
|
+
# exons on minus strand
|
460
|
+
if ($exons->{$ID}->[0]->{strand} eq "-"){
|
461
|
+
@{$g2l->{$ID}} = sort(MySortLocal @{$g2l->{$ID}});
|
462
|
+
|
463
|
+
my @data = ();
|
464
|
+
|
465
|
+
for my $i (0..$#{$g2l->{$ID}}){
|
466
|
+
my $ex_gstart = $g2l->{$ID}->[$i]->{gstart};
|
467
|
+
my $ex_gend = $g2l->{$ID}->[$i]->{gend};
|
468
|
+
my $ex_lstart = $g2l->{$ID}->[$i]->{lstart};
|
469
|
+
my $ex_lend = $g2l->{$ID}->[$i]->{lend};
|
470
|
+
|
471
|
+
# feature starts in exon
|
472
|
+
next unless ($data_lstart >= $ex_lstart) && ($data_lstart <= $ex_lend);
|
473
|
+
|
474
|
+
my %tmp = ();
|
475
|
+
|
476
|
+
# calculate GLOBAL END coordinate = local start
|
477
|
+
# --------------------------------------------------
|
478
|
+
|
479
|
+
my $start_shift = $data_lstart - $ex_lstart +1;
|
480
|
+
$tmp{gend} = $ex_gend - $start_shift +1;
|
481
|
+
$tmp{lstart} = $data_lstart;
|
482
|
+
|
483
|
+
# calculate GLOBAL START coordinate = local end
|
484
|
+
# --------------------------------------------------
|
485
|
+
# feature is included in exon -> we are done here
|
486
|
+
# global s>>>>>>>>>>>>e
|
487
|
+
# local e<<<<<<s
|
488
|
+
# shift ----
|
489
|
+
if ($data_lend <= $ex_lend){
|
490
|
+
$tmp{gstart} = $tmp{gend} - ($data_lend-$tmp{lstart}+1 ) +1 ;
|
491
|
+
$tmp{lend} = $data_lend;
|
492
|
+
push(@data,\%tmp);
|
493
|
+
last;
|
494
|
+
}
|
495
|
+
|
496
|
+
# feature goes beyond exon and reaches into following exons
|
497
|
+
# global s>>>>>e s>>>>>>>>>>>>e
|
498
|
+
# local e<<<......<<<<s
|
499
|
+
# shift --------
|
500
|
+
if ($data_lend > $ex_lend){
|
501
|
+
$tmp{gstart} = $ex_gstart;
|
502
|
+
$tmp{lend} = $ex_lend;
|
503
|
+
push(@data,\%tmp);
|
504
|
+
|
505
|
+
# new start coordinate for next loop
|
506
|
+
$data_lstart = $ex_lend + 1;
|
507
|
+
next;
|
508
|
+
}
|
509
|
+
}
|
510
|
+
return(\@data);
|
511
|
+
}
|
512
|
+
}
|
513
|
+
|
514
|
+
# --------------------------------------------------
|
515
|
+
|
516
|
+
sub MySort2 {
|
517
|
+
if(${$a}{start} < ${$b}{start})
|
518
|
+
{ return -1; }
|
519
|
+
elsif(${$a}{start} == ${$b}{start})
|
520
|
+
{ return 0; }
|
521
|
+
else
|
522
|
+
{ return 1; }
|
523
|
+
}
|
524
|
+
|
525
|
+
sub RevMySort2 {
|
526
|
+
if(${$a}{end} > ${$b}{end})
|
527
|
+
{ return -1; }
|
528
|
+
elsif(${$a}{end} == ${$b}{end})
|
529
|
+
{ return 0; }
|
530
|
+
else
|
531
|
+
{ return 1; }
|
532
|
+
}
|
533
|
+
|
534
|
+
sub MySortGlobal {
|
535
|
+
if(${$a}{gstart} < ${$b}{gstart})
|
536
|
+
{ return -1; }
|
537
|
+
elsif(${$a}{gstart} == ${$b}{gstart})
|
538
|
+
{ return 0; }
|
539
|
+
else
|
540
|
+
{ return 1; }
|
541
|
+
}
|
542
|
+
|
543
|
+
sub RevMySortGlobal {
|
544
|
+
if(${$a}{gend} > ${$b}{gend})
|
545
|
+
{ return -1; }
|
546
|
+
elsif(${$a}{gend} == ${$b}{gend})
|
547
|
+
{ return 0; }
|
548
|
+
else
|
549
|
+
{ return 1; }
|
550
|
+
}
|
551
|
+
|
552
|
+
sub MySortLocal {
|
553
|
+
if(${$a}{lstart} < ${$b}{lstart})
|
554
|
+
{ return -1; }
|
555
|
+
elsif(${$a}{lstart} == ${$b}{lstart})
|
556
|
+
{ return 0; }
|
557
|
+
else
|
558
|
+
{ return 1; }
|
559
|
+
}
|
560
|
+
|
561
|
+
sub RevMySortLocal{
|
562
|
+
if(${$a}{lend} > ${$b}{lend})
|
563
|
+
{ return -1; }
|
564
|
+
elsif(${$a}{lend} == ${$b}{lend})
|
565
|
+
{ return 0; }
|
566
|
+
else
|
567
|
+
{ return 1; }
|
568
|
+
}
|
569
|
+
|
570
|
+
__END__
|
571
|
+
=head1 NAME
|
572
|
+
|
573
|
+
local2global.pl
|
574
|
+
|
575
|
+
=head1 SYNOPSIS
|
576
|
+
|
577
|
+
local2global.pl [options] [file]
|
578
|
+
|
579
|
+
=head1 OPTIONS
|
580
|
+
|
581
|
+
=over 8
|
582
|
+
|
583
|
+
=item B<-exon, -e>
|
584
|
+
|
585
|
+
name of exon annotation file
|
586
|
+
|
587
|
+
=item B<-etype, -et>
|
588
|
+
|
589
|
+
type of exon annotation file; possible types: gtf, gff3, bed; default: autodetect via suffix of input file
|
590
|
+
|
591
|
+
=item B<-exonID, -eid>
|
592
|
+
|
593
|
+
field to use as transcript ID;
|
594
|
+
|
595
|
+
defaults
|
596
|
+
|
597
|
+
for gtf: attribute "transcript_id"
|
598
|
+
|
599
|
+
for gff3: attribute "ID"
|
600
|
+
|
601
|
+
for bed: ID (=field 4)
|
602
|
+
|
603
|
+
=item B<-data, -d>
|
604
|
+
|
605
|
+
name of data annotation file
|
606
|
+
|
607
|
+
=item B<-dtype, -dt>
|
608
|
+
|
609
|
+
type of data annotation file; possible types: gtf, gff3, bed; default: autodetect via suffix of input file
|
610
|
+
|
611
|
+
=item B<-dataID, -did>
|
612
|
+
|
613
|
+
field to use as transcript ID;
|
614
|
+
|
615
|
+
defaults
|
616
|
+
|
617
|
+
for gtf: attribute "transcript_id"
|
618
|
+
|
619
|
+
for gff3: attribute "ID"
|
620
|
+
|
621
|
+
for bed: ID (=field 4)
|
622
|
+
|
623
|
+
=item B<-g2l>
|
624
|
+
|
625
|
+
covert global coordinates (e.g. genomic coordinates) of features
|
626
|
+
in data file to local coordinates relative to the respective
|
627
|
+
features in the exon annotation file
|
628
|
+
|
629
|
+
=item B<-l2g>
|
630
|
+
|
631
|
+
covert local coordinates (e.g. within a spliced transcript) of
|
632
|
+
features in the data file to global coordinates (e.g. genomic
|
633
|
+
coordinates) relative to the respective features in the exon
|
634
|
+
annotation file
|
635
|
+
|
636
|
+
=item B<-help>
|
637
|
+
|
638
|
+
Print a brief help message and exit
|
639
|
+
|
640
|
+
=item B<-man>
|
641
|
+
|
642
|
+
Print full man page and exit
|
643
|
+
|
644
|
+
=head1 DESCRIPTION
|
645
|
+
|
646
|
+
local2global.pl converts coordinates of a sub-feature within a
|
647
|
+
feature to genomic coordinates and vice versa. It requires two
|
648
|
+
annotation files: the features are listed in the "exon" file
|
649
|
+
and the sub-features contained in these features are in the
|
650
|
+
"data" file. Annotation formats are "gtf", "gff3" and "bed".
|
651
|
+
|
652
|
+
The identifier, based on which subfeatures are assigned to
|
653
|
+
features, can be specified.
|
654
|
+
|
655
|
+
B<Example 1: conversion local to global>
|
656
|
+
|
657
|
+
You analysed structural motifs in spliced transcript sequences and
|
658
|
+
want to know the genomic position of these structures. The "data"
|
659
|
+
file contains the positions of your RNA structures within a
|
660
|
+
transcript, the "exon" file is the exon annotation of your
|
661
|
+
transcripts. Let us assume you are using gtf files.
|
662
|
+
|
663
|
+
In this case, you would create gtf annotation files for all
|
664
|
+
your RNA structures, use the "gene_id" attribute to reference
|
665
|
+
the transcripts these structures belong to and assign each
|
666
|
+
structure a unique "transcript_id". In the chromosome fields
|
667
|
+
put the same id as in the "gene_id" attribute, since the
|
668
|
+
coordinates are relative to the transcript. The exon file
|
669
|
+
is the annotation file you retreived from some gene annotation
|
670
|
+
repository, e.g. ensembl. The output would then be genomic
|
671
|
+
coordinates of your structures, in the chromosome filed you
|
672
|
+
will find the chromosome the transcript resides on.
|
673
|
+
Structures spanning exon-exon junctions are split into
|
674
|
+
multiple intervals (i.e. "exons").
|
675
|
+
|
676
|
+
local2global.pl -e exon.gtf -et gtf -eid transcript_id -d structure.gtf -dt gtf -did gene_id -l2g > structure.global.gtf
|
677
|
+
|
678
|
+
B<Example 2: conversion global to local>
|
679
|
+
|
680
|
+
Say that you wish to know the position of the coding exons
|
681
|
+
within a spliced transcript. In this case, your "data"
|
682
|
+
file is the CDS annotation file with genomic coordinates
|
683
|
+
of the CDS exons, the "exon" file is again the "exon"
|
684
|
+
annotation file. Both were downloaded from a database,
|
685
|
+
e.g. ensembl. Note, that here the identifyer of the
|
686
|
+
CDS exons is the "transcript_id". The output in this
|
687
|
+
case are coordinates of the CDS exons realtive to
|
688
|
+
the spliced transcript, i.e. local coordinates,
|
689
|
+
and thus you will find the transcript_id the in
|
690
|
+
the chromosome field.
|
691
|
+
|
692
|
+
local2global.pl -e exon.gtf -et gtf -eid transcript_id -d CDS.gtf -dt gtf -did transcript_id -g2l > CDS.local.gtf
|
693
|
+
|
694
|
+
=cut
|