bioroebe 0.10.80 → 0.11.12

data/lib/bioroebe/genbank/genbank_parser.rb

@@ -1,291 +0,0 @@
-#!/usr/bin/ruby -w
-# Encoding: UTF-8
-# frozen_string_literal: true
-# =========================================================================== #
-# === Bioroebe::GenbankParser
-#
-# This is similar to the FastaParser, but instead it will only select the
-# content between "ORIGIN" and "//" entries.
-#
-# You can pass the content of a genbank-file to this class, and it can
-# report the nucleotide sequence, e. g. the part starting after the
-# ORIGIN string.
-#
-# The reason why this class has been created was because it is sometimes
-# necessary to parse a genebank file.
-# =========================================================================== #
-# require 'bioroebe/genbank/genbank_parser.rb'
-# Bioroebe::GenbankParser.new(ARGV)
-# =========================================================================== #
-require 'bioroebe/base/commandline_application/commandline_application.rb'
-
-module Bioroebe
-
-class GenbankParser < ::Bioroebe::CommandlineApplication # === Bioroebe::GenbankParser
- 
-  # ========================================================================= #
-  # === UPCASE_SEQUENCE
-  # ========================================================================= #
-  UPCASE_SEQUENCE = true
-
-  # ========================================================================= #
-  # === TEST_STRING
-  #
-  # Our example test-string, to see how such a genbank file usually looks
-  # like.
-  # ========================================================================= #
-  TEST_STRING = '                   /note="internal transcribed spacer 2"
-ORIGIN      
-        1 cgtaacaagg tttccgtagg tgaaccttcg gaaggatcat tgttgagacc cccaaaaaaa
-       61 cgatcgagtt aatccggagg accggtgtag tttggtctcc caggggcttt ggctactgtg
-      121 gtggccgtga atttccgtcg aacctccttg ggagaattct tgatggcaat tgaacccttg
-      181 gcccggcgca gtttcgcccc aagtcaaatg agatggaacc ggcggagggc atcgtcctcc
-      241 atggaaccgg ggagggccgg cgttcttccg ttccccccat gaattttttt ttgacaactc
-      301 tcggcaacgg atatctcggc tctttgcatc cgatgaaaga acccagcgaa atgtgataag
-      361 tggtgtgaat tgcagaatcc cgtgaaccat cgagtctttg aacgcaagtt gcgcccgagg
-      421 ccatcaggct aagggcacgc ctgcctgggc gttgcgtgct gcatctctct cccattgcta
-      481 aggctgaaca ggcatactgt tcggccggcg cggatgagtg tttggcccct tgttcttcgg
-      541 tgcgatgggt ccaagacctg ggcttttgac ggccggaaat ccggcaagag gtggacggac
-      601 ggtggctgcg acgaagctgt cgtgcgaatg ccctacgctg tcgtatttga tgggccggaa
-      661 taaatccctt ttgagcccca ttggaggcac gtcaacccgt gggcggtcga cggccatttg
-      721 gatgcaaccc caggtcaggt gagga
-//
-LOCUS       Z78510                   750 bp    DNA     linear   PLN 30-NOV-2006
-DEFINITION  P.caricinum 5.8S rRNA gene and ITS1 and ITS2 DNA.
-ACCESSION   Z78510
-VERSION     Z78510.1  GI:2765635
-KEYWORDS    5.8S ribosomal RNA; 5.8S rRNA gene; internal transcribed spacer;
-            ITS1; ITS2.
-SOURCE      Phragmipedium caricinum
-  ORGANISM  Phragmipedium caricinum
-            Eukaryota; Viridiplantae; Streptophyta; Embryophyta; Tracheophyta;
-            Spermatophyta; Magnoliophyta; Liliopsida; Asparagales; Orchidaceae;
-            Cypripedioideae; Phragmipedium.
-REFERENCE   1
-  AUTHORS   Cox,A.V., Pridgeon,A.M., Albert,V.A. and Chase,M.W.
-  TITLE     Phylogenetics of the slipper orchids (Cypripedioideae:
-            Orchidaceae): nuclear rDNA ITS sequences
-  JOURNAL   Unpublished
-REFERENCE   2  (bases 1 to 750)
-  AUTHORS   Cox,A.V.
-  TITLE     Direct Submission
-  JOURNAL   Submitted (19-AUG-1996) Cox A.V., Royal Botanic Gardens, Kew,
-            Richmond, Surrey TW9 3AB, UK
-FEATURES             Location/Qualifiers
-     source          1..750
-                     /organism="Phragmipedium caricinum"
-                     /mol_type="genomic DNA"
-                     /db_xref="taxon:53127"
-     misc_feature    1..380
-                     /note="internal transcribed spacer 1"
-     gene            381..550
-                     /gene="5.8S rRNA"
-     rRNA            381..550
-                     /gene="5.8S rRNA"
-                     /product="5.8S ribosomal RNA"
-     misc_feature    551..750
-                     /note="internal transcribed spacer 2"
-ORIGIN      
-        1 ctaaccaggg ttccgaggtg accttcggga ggattccttt ttaagccccc gaaaaaacga
-       61 tcgaattaaa ccggaggacc ggtttaattt ggtctcccca ggggctttcc ccccttggtg
-      121 gccgtgaatt tccatcgaac ccccctggga gaattcttgg tggccaatgg acccttggcc
-      181 cggcgcaatt tcccccccaa tcaaatgaga taggaccggc agggggcgtc cccccccatg
-      241 gaaccgggga gggccggcat tcttccgttc ccccctcgga ttttttgaca actctcgcaa
-      301 cggatatctc gcctctttgc atcggatgga agaacgcagc gaaatgtgat aagtggtgtg
-      361 aattgcagaa tcccgtgaac catcgagtct ttgaacgcaa gttgcgcccg aggccatcag
-      421 gctaagggca cgcctgcctg ggcgttgcgt gctgcatctc tcccattgct aaggttgaac
-      481 gggcatactg ttcggccggc gcggatgaga gattggcccc ttgttcttcg gtgcgatggg
-      541 tccaagacct gggcttttga cggtccaaaa tccggcaaga ggtggacgga cggtggctgc
-      601 gacaaagctg tcgtgcgaat gccctgcgtt gtcgtttttg atgggccgga ataaatccct
-      661 tttgaacccc attggaggca cgtcaaccca tgggcggttg acggccattt ggatgcaacc
-      721 ccaggtcagg tgagccaccc gctgagttta
-//
-LOCUS       Z78509                   731 bp    DNA     linear   PLN 30-NOV-2006
-DEFINITION  P.pearcei 5.8S rRNA gene and ITS1 and ITS2 DNA.
-ACCESSION   Z78509
-VERSION     Z78509.1  GI:2765634
-KEYWORDS    5.8S ribosomal RNA; 5.8S rRNA gene; internal transcribed spacer;
-            ITS1; ITS2.
-SOURCE      Phragmipedium pearcei
-  ORGANISM  Phragmipedium pearcei
-            Eukaryota; Viridiplantae; Streptophyta; Embryophyta; Tracheophyta;
-            Spermatophyta; Magnoliophyta; Liliopsida; Asparagales; Orchidaceae;
-            Cypripedioideae; Phragmipedium.
-REFERENCE   1
-  AUTHORS   Cox,A.V., Pridgeon,A.M., Albert,V.A. and Chase,M.W.
-  TITLE     Phylogenetics of the slipper orchids (Cypripedioideae:
-            Orchidaceae): nuclear rDNA ITS sequences
-  JOURNAL   Unpublished
-REFERENCE   2  (bases 1 to 731)
-  AUTHORS   Cox,A.V.
-  TITLE     Direct Submission
-  JOURNAL   Submitted (19-AUG-1996) Cox A.V., Royal Botanic Gardens, Kew,
-            Richmond, Surrey TW9 3AB, UK
-FEATURES             Location/Qualifiers
-     source          1..731
-                     /organism="Phragmipedium pearcei"
-                     /mol_type="genomic DNA"
-                     /db_xref="taxon:53135"
-     misc_feature    1..380
-                     /note="internal transcribed spacer 1"
-     gene            381..550
-                     /gene="5.8S rRNA"
-     rRNA            381..550
-                     /gene="5.8S rRNA"
-                     /product="5.8S ribosomal RNA"
-     misc_feature    551..731
-                     /note="internal transcribed spacer 2"
-ORIGIN      
-        1 cgtaacaagg tttccgtagg tgaacctgcg gaaggatcat tgttgagacc gccaaatata
-       61 cgatcgagtt aatccggagg accggtgtag tttggtctcc caggggcttt cgccgctgtg
-      121 gtgaccgtga tttgccatcg agcctccttg ggagatttct tgatggcaat tgaacccttg
-      181 gcccggcgca gtttcgcgcc aagtcatatg agatagaacc ggcggagggc gtcgtcctcc
-      241 atggagcggg gagggccggc atgctccgtg cccccccatg aatttttctg acaactctcg
-      301 gcaacggacg taacaaggtt taaatgtgat aagcaggtgt gaattgcaga atcccgtgaa
-      361 ccatcgagtc tttgaacgca agttgcgccc gaggccatca ggttaagggc acgcctgcct
-      421 gggcgttgcg tgctgcatct ctcccattgc taaggttgaa cgggcatact gttcggccgg
-      481 cgcggatgag agtttggccc cttgttcttc ggtgcgatgg gtccaagacc tgggcttttg
-      541 acggtccaaa atccggcaag aggtggacgg acggtggctg cgacagagct gtcgtgcgaa
-      601 tgccctacgt tgtcgttttt gatgggccag aataaatccc ttttgaaccc cattggaggc
-      661 acgtcaaccc aatggggggt gacgggcatt tggttaaccc cggcaagtta aggcacccgt
-      721 taattttagg a
-//
-LOCUS       Z78508                   741 bp    DNA     linear   PLN 30-NOV-2006'
-
-  # ========================================================================= #
-  # === initialize
-  # ========================================================================= #
-  def initialize(
-      dataset     = ARGV,
-      run_already = true
-    )
-    reset
-    determine_dataset(
-      dataset
-    )
-    if block_given?
-      yielded = yield
-      case yielded
-      # ===================================================================== #
-      # === :do_not_report_anything
-      # ===================================================================== #
-      when :do_not_report_anything
-        @report_dataset = false
-      end
-    end
-    run if run_already
-  end
-
-  # ========================================================================= #
-  # === reset
-  # ========================================================================= #
-  def reset
-    super()
-    # ======================================================================= #
-    # === @dataset
-    # ======================================================================= #
-    @dataset = nil
-    # ======================================================================= #
-    # === @report_dataset
-    # ======================================================================= #
-    @report_dataset = true
-  end
-
-  # ========================================================================= #
-  # === determine_dataset
-  # ========================================================================= #
-  def determine_dataset(i = nil)
-    if i.is_a? Array
-      i = i.first
-    end
-    if i.nil?
-      e 'Please provide some input to this class.'
-      return
-    end
-    # ======================================================================= #
-    # === Handle existing .gb files here
-    # ======================================================================= #
-    if File.exist?(i) and File.file?(i)
-      i = File.read(i)
-    end
-    case i # case tag
-    # ======================================================================= #
-    # === --test
-    #
-    # This entry point can be used to test the default TEST_STRING.
-    # ======================================================================= #
-    when nil,
-         /^-?-?test$/i,
-         /^-?-?test(-|_)?string$/i
-      i = TEST_STRING
-    end
-    # ======================================================================= #
-    # Store the results in the following array.
-    # ======================================================================= #
-    array = []
-    open = false
-    splitted = i.split(N)
-    splitted.each {|line|
-      if line.start_with? '//'
-        open = false
-      end
-      if open
-        array.last << line.strip.delete(' ').gsub(/\d/,'')
-        array.flatten!
-      end
-      if line.start_with? 'ORIGIN'
-        open = true
-        array << [] # Append a new Array.
-      end
-    }
-    string = array.first
-    string.upcase! if UPCASE_SEQUENCE
-    @dataset = string # Assign to the main @dataset here.
-  end
-
-  # ========================================================================= #
-  # === report_dataset?
-  # ========================================================================= #
-  def report_dataset?
-    @report_dataset
-  end
-
-  # ========================================================================= #
-  # === dataset?
-  # ========================================================================= #
-  def dataset?
-    @dataset
-  end; alias sequence? dataset? # === sequence?
-
-  # ========================================================================= #
-  # === report_dataset                                           (report tag)
-  #
-  # Simply output the dataset without any further processing to be done.
-  # ========================================================================= #
-  def report_dataset
-    if @dataset
-      e @dataset if report_dataset?
-    end
-  end; alias report report_dataset # === report
-
-  # ========================================================================= #
-  # === run
-  # ========================================================================= #
-  def run
-    report_dataset
-  end
-
-  # ========================================================================= #
-  # === Bioroebe::GenbankParser[]
-  # ========================================================================= #
-  def self.[](i)
-    new(i)
-  end
-
-end; end
-
-if __FILE__ == $PROGRAM_NAME
-  Bioroebe::GenbankParser.new(ARGV) # Report the dataset as well.
-end # genbankparser
-    # genbankparser sample_file.genbank
-    # genbankparser --test

data/lib/bioroebe/shell/add.rb

@@ -1,108 +0,0 @@
-#!/usr/bin/ruby -w
-# Encoding: UTF-8
-# frozen_string_literal: true
-# =========================================================================== #
-# require 'bioroebe/shell/add.rb'
-# =========================================================================== #
-module Bioroebe
-
-class Shell < ::Bioroebe::CommandlineApplication
-
-  # ========================================================================= #
-  # === add_to_end
-  #
-  # This method will invoke append() if something has to be appended.
-  # ========================================================================= #
-  def add_to_end(i)
-    add_to_start_or_end(i, :end)
-  end; alias add add_to_end # === add (add tag)
-
-  # ========================================================================= #
-  # === add_to_start
-  # ========================================================================= #
-  def add_to_start(i)
-    add_to_start_or_end(i, :start)
-  end; alias left_add add_to_start # === left_add
-
-  # ========================================================================= #
-  # === add_to_start_or_end
-  #
-  # This method can either add to the start or to the end.
-  #
-  # The default is to append to the nucleotide sequence.
-  #
-  # We can input a number - in this case, we simply add these many
-  # nucleotides onto the main string.
-  # ========================================================================= #
-  def add_to_start_or_end(
-      i                 = '',
-      append_or_prepend = :append
-    )
-    i = i.join('') if i.is_a? Array
-    i = i.dup
-    old_length = i.size
-    case i.to_s # Easier start/stop entries.
-    # ======================================================================= #
-    # === Add a start codon.
-    # ======================================================================= #
-    when 'start',
-         'START',
-         /ORF/i,
-         ':start'
-      i = ::Bioroebe.start_codon? # Used to be hardcoded -> 'ATG'
-    # ======================================================================= #
-    # === Add a stop codon.
-    # ======================================================================= #
-    when /^stop$/i,
-         ':stop'
-      i = ::Bioroebe.stop_codons?.sample
-    end
-    i.upcase!
-    case append_or_prepend
-    # ======================================================================= #
-    # === :prepend
-    # ======================================================================= #
-    when :prepend,
-         :to_start,
-         :start
-      if i =~ /^\d+$/ # If input is only numbers.
-        erev 'Only numbers were given: Prepending '+
-              sfancy(i.to_s)+rev+
-             ' random nucleotides to the main string now.'
-        i.to_i.times { prepend(add_nucleotide) }
-      else
-        erev "Prepending #{sfancy(i)}#{rev} to the main string."
-        prepend(i)
-      end
-    # ======================================================================= #
-    # === :append
-    # ======================================================================= #
-    when :append,
-         :to_end,
-         :end
-      if i =~ /^\d+$/ # If input is only numbers.
-        erev "Only numbers were given: Adding #{sfancy(i.to_s)}#{rev}"\
-             " random nucleotides to the main string now."
-        i.to_i.times { append(return_random_nucleotide) }
-      else
-        if only_nucleotides?(i)
-          msg = "Adding #{sfancy(i)}#{rev}"
-          msg = msg.dup if msg.frozen?
-          if ::Bioroebe.is_a_stop_codon? i
-            msg << ' (a stop codon)'
-          end
-          msg << ' to the main string.'
-          erev msg
-        end
-        append(i)
-      end
-    end
-    new_length = string?.size.to_s
-    unless new_length.to_i == old_length.to_i
-      erev "The new length of the main string is now: "\
-           "#{simp(new_length)}#{rev}."
-    end
-    show_dna_sequence
-  end
-
-end; end