bioroebe 0.10.80

data/lib/bioroebe/nucleotides/complementary_dna_strand.rb

@@ -0,0 +1,166 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === Bioroebe::ComplementaryDnaStrand
+#
+# Note that if the input includes "5′-TGGTACACAT-3′" or
+# "5'-TGGTACACAT-3'" then displaying header and trailer
+# will be shown automatically.
+# =========================================================================== #
+# require 'bioroebe/nucleotides/complementary_dna_strand.rb'
+# Bioroebe::ComplementaryDnaStrand.new(ARGV)
+# =========================================================================== #
+require 'bioroebe/base/commandline_application/commandline_arguments.rb'
+
+module Bioroebe
+
+class ComplementaryDnaStrand # === Bioroebe::ComplementaryDnaStrand
+
+  include Bioroebe::CommandlineArguments
+
+  require 'bioroebe/toplevel_methods/nucleotides.rb'
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      i           = ARGV,
+      run_already = true
+    )
+    reset
+    set_commandline_arguments(i)
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    # ======================================================================= #
+    # === @continue
+    # ======================================================================= #
+    @continue = true
+    # ======================================================================= #
+    # === @result
+    # ======================================================================= #
+    @result = nil
+    # ======================================================================= #
+    # === @show_leader_and_trailer
+    #
+    # If the following variable is true, then this class will show the
+    # leading 5'- and trailing -'3 part.
+    # ======================================================================= #
+    @show_leader_and_trailer = false
+  end
+
+  # ========================================================================= #
+  # === result?
+  # ========================================================================= #
+  def result?
+    @result
+  end
+
+  # ========================================================================= #
+  # === menu                                                       (menu tag)
+  # ========================================================================= #
+  def menu(
+      i = commandline_arguments?
+    )
+    if i and i.is_a?(Array)
+      i.each {|entry| menu(entry) }
+    else
+      case i
+      # ===================================================================== #
+      # === --trailer
+      # ===================================================================== #
+      when /^-?-?trailer/i,
+           /^-?-?header/i,
+           /^-?-?footer/i
+        @show_leader_and_trailer = true
+      # ===================================================================== #
+      # === --help
+      # ===================================================================== #
+      when /^-?-?help/i
+        show_help
+        @continue = false
+      else
+        @continue = true
+      end
+    end
+  end
+
+  # ========================================================================= #
+  # === show_help
+  # ========================================================================= #
+  def show_help
+    erev 'The following options are supported by this class:'
+    e
+    e
+    e
+  end
+
+  # ========================================================================= #
+  # === run
+  # ========================================================================= #
+  def run
+    menu
+    if @continue
+      _ = first_commandline_argument?
+      if _.include?("5′-") or
+         _.include?("5'-") or
+         _.include?("-3'") or
+         _.include?("5-")
+        @show_leader_and_trailer = true
+      end
+      hash = ::Bioroebe.partner_nucleotide_hash
+      if _
+        @result = _.chars.map {|entry| hash[entry] }.join
+      end
+    end
+  end
+
+  # ========================================================================= #
+  # === report
+  # ========================================================================= #
+  def report
+    if @show_leader_and_trailer
+      e "5'-#{@result}-'3"
+    else
+      e @result
+    end
+  end
+
+end
+
+# =========================================================================== #
+# === Bioroebe.show_complementary_dna_strand
+# =========================================================================== #
+def self.show_complementary_dna_strand(i = ARGV)
+  complementary_dna_strand = Bioroebe::ComplementaryDnaStrand.new(ARGV)
+  complementary_dna_strand.report
+end
+
+# =========================================================================== #
+# === Bioroebe.complementary_dna_strand
+#
+# This method will simply return the corresponding (complementary)
+# DNA strand.
+#
+# Usage example:
+#
+#   Bioroebe.complementary_dna_strand('ATCATCATC') # => "TAGTAGTAG"
+#
+# =========================================================================== #
+def self.complementary_dna_strand(i = ARGV)
+  retrn Bioroebe::ComplementaryDnaStrand.new(i).result?
+end; self.instance_eval { alias complementary_strand complementary_dna_strand } # === Bioroebe.complementary_strand
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  complementary_dna_strand = Bioroebe::ComplementaryDnaStrand.new(ARGV)
+  complementary_dna_strand.report
+end # rb complementary_dna_strand.rb TGGTACACAT
+    # rb complementary_dna_strand.rb TGGTACACAT --header
+    # rb complementary_dna_strand.rb 5'-TGGTACACAT-3'

data/lib/bioroebe/nucleotides/molecular_weight_of_nucleotides.rb

@@ -0,0 +1,135 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === Bioroebe::MolecularWeightOfNucleotides
+#
+# This tiny module just lists the molecular weight of Cytosin, Adenin
+# and so forth.
+# =========================================================================== #
+# require 'bioroebe/nucleotides/molecular_weight_of_nucleotides.rb'
+# Bioroebe::MolecularWeightOfNucleotides
+# =========================================================================== #
+module Bioroebe
+
+module MolecularWeightOfNucleotides # === Bioroebe::MolecularWeightOfNucleotides
+
+  require 'bioroebe/toplevel_methods/e.rb'
+  require 'bioroebe/colours/misc_colours.rb'
+
+  # ========================================================================= #
+  # === MolecularWeightOfNucleotides::GUANINE
+  #
+  # Molar weight of Guanine formula C5 H5 N5 O = 	151.13 g/mol
+  # ========================================================================= #
+  GUANINE  = 151.13
+
+  # ========================================================================= #
+  # === Bioroebe.MolecularWeightOfNucleotides.weight_of_guanine?
+  # ========================================================================= #
+  def self.weight_of_guanine?
+    GUANINE
+  end
+
+  # ========================================================================= #
+  # === ADENINE
+  #
+  # Adenine: Molecular formula is C5H5N5.
+  #
+  # To calculate on the commandline:
+  #
+  #   molmasse C5H5N5
+  #
+  # ========================================================================= #
+  ADENINE  = 135.13 # g/mol
+
+  # ========================================================================= #
+  # === Bioroebe::MolecularWeightOfNucleotides.weight_of_adenine?
+  # ========================================================================= #
+  def self.weight_of_adenine?
+    GUANINE
+  end
+
+  # ========================================================================= #
+  # === THYMINE
+  #
+  # Molecular formula: C5 H6 N2 O2
+  #
+  # URL: https://en.wikipedia.org/wiki/Thymine
+  #
+  # To calculate on the commandline:
+  #
+  #   molmasse C5H6N2O2
+  #
+  # ========================================================================= # 
+  THYMINE  = 126.114
+
+  # ========================================================================= #
+  # === Bioroebe::MolecularWeightOfNucleotides.weight_of_thymine?
+  # ========================================================================= #
+  def self.weight_of_thymine?
+    THYMINE
+  end
+
+  # ========================================================================= #
+  # === CYTOSINE
+  # 
+  # Molar mass of Cytosine, C4H5N3O = 111.102 g/mol (molar mass)
+  #
+  # URL: https://en.wikipedia.org/wiki/Cytosine
+  # ========================================================================= #
+  CYTOSINE = 111.102 # g / mol.
+
+  # ========================================================================= #
+  # === Bioroebe::MolecularWeightOfNucleotides.weight_of_cytosine?
+  # ========================================================================= #
+  def self.weight_of_cytosine?
+    CYTOSINE
+  end
+
+  # ========================================================================= #
+  # === Bioroebe::MolecularWeightOfNucleotides.weights # A T G C
+  # ========================================================================= #
+  def self.weights
+    return [ ADENINE, THYMINE, GUANINE, CYTOSINE ] # A T G C
+  end
+
+  # ========================================================================= #
+  # === MolecularWeightOfNucleotides.hash
+  # ========================================================================= #
+  def self.hash
+    return {
+      'Adenine'  => ADENINE,
+      'Thymine'  => THYMINE,
+      'Guanine'  => GUANINE,
+      'Cytosine' => CYTOSINE,
+    }
+  end
+
+  # ========================================================================= #
+  # === MolecularWeightOfNucleotides.report_weight
+  # ========================================================================= #
+  def self.report_weight
+    e 'The molecular weight of the four main nucleotides are:'; e
+    MolecularWeightOfNucleotides.hash.each_pair {|nucleotide, weight|
+      weight = ('%.3f' % weight.to_f).to_s
+      e '  '+
+        ::Bioroebe.steelblue(
+          (nucleotide.to_s+':').ljust(10)
+        )+
+        weight.to_s.rjust(8)
+    }; e
+  end
+
+  # ========================================================================= #
+  # === Bioroebe::MolecularWeightOfNucleotides
+  # ========================================================================= #
+  def self.e(i = '')
+    ::Bioroebe.e(i)
+  end
+
+end; end
+
+if __FILE__ == $PROGRAM_NAME
+  Bioroebe::MolecularWeightOfNucleotides.report_weight
+end # molecularweightofnucleotides

data/lib/bioroebe/nucleotides/most_likely_nucleotide_sequence_for_this_aminoacid_sequence.rb

@@ -0,0 +1,198 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === Bioroebe::MostLikelyNucleotideSequenceForThisAminoacidSequence
+#
+# This class is somewhat similar to DeduceAminoacidSequence, but it
+# also takes into consideration the actual frequency values found
+# in different species (if a .yml file has been downloaded).
+#
+# That .yml file is very important for the proper function of this
+# class.
+#
+# Usage example:
+#
+#   Bioroebe::MostLikelyNucleotideSequenceForThisAminoacidSequence.new(ARGV)
+#
+# =========================================================================== #
+# require 'bioroebe/nucleotides/most_likely_nucleotide_sequence_for_this_aminoacid_sequence.rb'
+# =========================================================================== #
+require 'bioroebe/base/commandline_application/commandline_application.rb'
+
+module Bioroebe
+
+class MostLikelyNucleotideSequenceForThisAminoacidSequence < ::Bioroebe::CommandlineApplication # === Bioroebe::MostLikelyNucleotideSequenceForThisAminoacidSequence
+
+  require 'bioroebe/aminoacids/codon_percentage.rb'
+  require 'bioroebe/codons/possible_codons_for_this_aminoacid.rb'
+
+  # ========================================================================= #
+  # === NAMESPACE
+  # ========================================================================= #
+  NAMESPACE = inspect
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      commandline_arguments = nil,
+      use_this_codon_table  = :default,
+      run_already           = true
+    )
+    reset
+    set_commandline_arguments(
+      commandline_arguments
+    )
+    # ======================================================================= #
+    # === Handle blocks next
+    # ======================================================================= #
+    if block_given?
+      yielded = yield
+      case yielded
+      when :be_quiet
+        set_be_quiet
+      end
+    end
+    set_use_this_codon_table(use_this_codon_table)
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    super()
+    # ======================================================================= #
+    # === @namespace
+    # ======================================================================= #
+    @namespace = NAMESPACE
+    # ======================================================================= #
+    # === @internal_hash
+    # ======================================================================= #
+    @internal_hash = {}
+    # ======================================================================= #
+    # === :codon_percentage
+    # ======================================================================= #
+    @internal_hash[:codon_percentage] = Bioroebe::CodonPercentage.new
+  end
+
+  # ========================================================================= #
+  # === set_use_this_codon_table
+  # ========================================================================= #
+  def set_use_this_codon_table(i)
+    @internal_hash[:codon_percentage].set_use_this_codon_table(i)
+  end
+
+  # ========================================================================= #
+  # === name_of_the_codon_table?
+  # ========================================================================= #
+  def name_of_the_codon_table?
+    @internal_hash[:codon_percentage].name_of_the_codon_table?
+  end
+
+  # ========================================================================= #
+  # === codon_percentage?
+  # ========================================================================= #
+  def codon_percenage?
+    @internal_hash[:codon_percentage]
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    _ = first?.delete('-').split(//)
+    erev 'The aminoacid sequence '+steelblue(_.join)+rev+
+         ' is best represented by:' if be_verbose?
+    codon_percentage = codon_percenage?
+    all_codons = ::Bioroebe.possible_codons_for_these_aminoacids(_)
+    final_sequence = ''.dup
+    all_codons.each {|array_codons|
+      max_value = array_codons.map {|this_codon|
+        codon_percentage[this_codon]
+      }
+      # ===================================================================== #
+      # Next we build a sorted Hash representing these frequencies:
+      # ===================================================================== #
+      max_element = array_codons.zip(max_value).
+                    max_by {|key, value| value }.first # This will give us: "ATC" from ["ATC", 20.8]
+      final_sequence << max_element
+    }
+    @internal_hash[:final_sequence] = final_sequence
+    if be_verbose?
+      e
+      e "  5'-#{colourize_nucleotide_sequence(final_sequence)}-3'"
+      e
+      erev 'This assumes the codon table '+
+           steelblue(name_of_the_codon_table?)+
+           rev+'.'
+    end
+  end
+
+  # ========================================================================= #
+  # === final_sequence?
+  # ========================================================================= #
+  def final_sequence?
+    @internal_hash[:final_sequence]
+  end; alias sequence? final_sequence? # === sequence?
+
+  # ========================================================================= #
+  # === Bioroebe::MostLikelyNucleotideSequenceForThisAminoacidSequence[]
+  # ========================================================================= #
+  def self.[](i = '')
+    new(i)
+  end
+
+end
+
+# =========================================================================== #
+# === Bioroebe.deduce_most_likely_aminoacid_sequence
+# =========================================================================== #
+def self.deduce_most_likely_aminoacid_sequence(from_this_sequence = :default)
+  Bioroebe::MostLikelyNucleotideSequenceForThisAminoacidSequence.new(from_this_sequence)
+end
+
+# =========================================================================== #
+# ==== Bioroebe.return_the_most_likely_codon_sequence_for_this_aminoacid_sequence
+#
+# This method will (quietly) return the most likely codon sequence (in DNA)
+# from a particular aminoacid sequence.
+#
+# Presently this method will use the Homo sapiens codon table as default
+# input (the second parameter).
+#
+# Numeric values such as 1 or 2 can also be provided as first argument
+# to this method.
+#
+# A String will be returned by this method.
+#
+# Invocation examples:
+#
+#   Bioroebe.return_the_most_likely_codon_sequence_for_this_aminoacid_sequence 'KKKA'              # => "AAGAAGAAGGCC"
+#   Bioroebe.return_the_most_likely_codon_sequence_for_this_aminoacid_sequence 'KKKA', :yeast      # => "AAAAAAAAAGCU"
+#   Bioroebe.return_the_most_likely_codon_sequence_for_this_aminoacid_sequence 'AWKT', :drosophila # => "GCCUGGAAGACC"
+#
+# =========================================================================== #
+def self.return_the_most_likely_codon_sequence_for_this_aminoacid_sequence(
+    i                                 = 'KKKA',
+    use_this_codon_tables_frequencies = :homo_sapiens
+  )
+  if i.is_a? Array
+    i = i.reject {|entry| entry.start_with?('--') }.join.strip
+  end
+  return Bioroebe::MostLikelyNucleotideSequenceForThisAminoacidSequence.new(i, use_this_codon_tables_frequencies) { :be_quiet }.sequence?
+end; self.instance_eval {
+       alias aa_to_dna return_the_most_likely_codon_sequence_for_this_aminoacid_sequence
+     } # === Bioroebe.aa_to_dna
+     self.instance_eval {
+       alias aminoacid_to_codon return_the_most_likely_codon_sequence_for_this_aminoacid_sequence
+     } # === Bioroebe.aminoacid_to_codon
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  Bioroebe::MostLikelyNucleotideSequenceForThisAminoacidSequence.new(ARGV)
+end # mostlikelynucleotides HLI
+    # mostlikelynucleotides MTTAGP
+    # mostlikelynucleotides M-T-T-A-G-P

data/lib/bioroebe/nucleotides/sanitize_nucleotide_sequence.rb

@@ -0,0 +1,133 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === Bioroebe::SanitizeNucleotideSequence
+#
+# This class can do these things:
+#
+#   - It can sanitize input that contains numbers - it will simply remove
+#     these numbers.
+#   - Additionally it will chomp away all newlines and ' ' characters too.
+#
+# So for example, the String "1 ATCCG\n30 TTA" will become "ATCCGTTA".
+#
+# Although the name refers to nucleotides, this class can also be applied
+# to the formatting of protein sequences (aminoacids).
+#
+# Usage example:
+#
+#   Bioroebe::SanitizeNucleotideSequence.new
+#
+# =========================================================================== #
+# require 'bioroebe/nucleotides/sanitize_nucleotide_sequence.rb'
+# =========================================================================== #
+require 'bioroebe/base/base.rb'
+
+module Bioroebe
+
+class SanitizeNucleotideSequence < Base # === Bioroebe::SanitizeNucleotideSequence
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      i           = nil,
+      run_already = true
+    )
+    reset
+    set_input(i)
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    super()
+  end
+
+  # ========================================================================= #
+  # === set_input
+  # ========================================================================= #
+  def set_input(
+      i = ''
+    )
+    if i.is_a? Array
+      if i.first.start_with?('>') and i.first.include?(N) # Assume gi number, which we will chop off.
+        i[0] = i[0][i[0].index(N) .. -1] # Get all from the start, to the first newline.
+      end 
+      i = i.join(' ').strip
+    end
+    i = i.to_s.dup
+    @input = i
+    sanitize_input
+  end
+
+  # ========================================================================= #
+  # === sanitize_input
+  # ========================================================================= #
+  def sanitize_input
+    @input.delete!("\n")
+    @input.delete!("\\\\n")
+    # ======================================================================= #
+    # Next remove all numbers.
+    # ======================================================================= #
+    chars = input?.chars
+    chars.reject! {|entry| entry =~ /\d+/ } # Reject numbers.
+    @input = chars.join(' ')
+    @input.delete!(' ')
+    if @input.include? '/'
+      @input.delete!('/')
+    end
+  end
+
+  # ========================================================================= #
+  # === input?
+  # ========================================================================= #
+  def input?
+    @input
+  end; alias result? input? # === result?
+
+  # ========================================================================= #
+  # === report_result
+  #
+  # This will report the result, but it has to be invoked manually.
+  # ========================================================================= #
+  def report_result
+    e result?
+  end; alias report report_result # === report
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+  end
+
+  # ========================================================================= #
+  # === Bioroebe::SanitizeNucleotideSequence[]
+  # ========================================================================= #
+  def self.[](i = "1 ATCCG\n30 TTA") # This will become a consecutive nucleotide String.
+    new(i).result?
+  end
+
+end
+
+# =========================================================================== #
+# === Bioroebe.sanitize_nucleotide_sequence
+#
+# Usage example:
+#
+#   Bioroebe.sanitize_nucleotide_sequence  "1 ATCCG\n30 TTACG\n50 AAATTTG" # => "ATCCGTTACGAAATTTG"
+#
+# =========================================================================== #
+def self.sanitize_nucleotide_sequence(i)
+  SanitizeNucleotideSequence.new(i).result?
+end
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  _ = Bioroebe::SanitizeNucleotideSequence.new(ARGV)
+  _.report_result # Manual invocation here. Usage example below.
+end # snucleotidesequence "1 ATCCG\n30 TTACG\n50 AAATTTG"