bioroebe 0.10.80 → 0.11.32

data/lib/bioroebe/sequence/protein.rb

@@ -4,7 +4,12 @@
 # =========================================================================== #
 # === Bioroebe::Protein
 #
-# This is a typical sequence of aminoacids.
+# This is a typical sequence of aminoacids. It is not 100% certain whether
+# this class will be retained, but for the time being it will be. Note
+# that peptides should also use this class - while the name may not be
+# 100% accurate (smaller proteins are typically called peptides or
+# oligopeptides) I feel that this is a distinction that does not really
+# make a whole lot of sense.
 # =========================================================================== #
 # require 'bioroebe/sequence/protein.rb'
 # =========================================================================== #
@@ -94,6 +99,9 @@ class Protein < ::Bioroebe::Sequence # === Bioroebe::Protein
   # This method will return true if there are at the least two
   # cysteines in the aminoacid sequence of this protein.
   #
+  # If anyone knows of a better algorithm to determine whether
+  # a protein can REALLY create a disulfide bond let me know.
+  #
   # Usage example:
   #
   #   Bioroebe::Protein.new('MLKLKNASCCEEE').can_form_disulfide_bonds? # => true
@@ -146,7 +154,7 @@ class Protein < ::Bioroebe::Sequence # === Bioroebe::Protein
     chars.each {|this_aminoacid|
       sum += weight_of(this_aminoacid)
     }
-    sum
+    return sum
   end; alias molecular_weight? weight? # === molecular_weight?
 
   # ========================================================================= #
@@ -230,10 +238,99 @@ class Protein < ::Bioroebe::Sequence # === Bioroebe::Protein
     return result
   end
 
+  # ========================================================================= #
+  # === can_be_stained_via_coomassie?
+  #
+  # Determine whether a protein can be stained in a coomassie
+  # staining. This is just a simple, fairly dumb check and
+  # NOT guaranteed to be correct. If anyone has a better
+  # way to check for this let me know.
+  # ========================================================================= #
+  def can_be_stained_via_coomassie?
+    disallowed_aminoacids = %w( K H R W F Y)
+    sequence = sequence?
+    return sequence.chars.uniq.any? {|this_aminoacid|
+      disallowed_aminoacids.include? this_aminoacid
+    }
+  end
+
+  # ========================================================================= #
+  # === aliphatic_index
+  #
+  # This method will calculate the aliphatic acid of an aminoacid,
+  # aka a Protein.
+  #
+  # Usage example:
+  #
+  #    require 'bioroebe'; Bioroebe::Protein.new('MVKSYDRYEYEDCLGIVNSKSSNCVFLNNA').aliphatic_index # => 71.33333
+  #
+  # ========================================================================= #
+  def aliphatic_index(
+      a = 2.9,
+      b = 3.9
+    )
+   composition = {}
+   composition.default = 0
+   chars = sequence?.chars
+   chars.each { |entry| composition[entry] += 1} 
+   (
+     composition['A'] + 
+     a * composition['V'].to_f + 
+     b * (composition['I'] + composition['L'])
+   ).to_f / length.to_f * 100
+  end
+
+  # ========================================================================= #
+  # === Bioroebe::Protein.one_to_three
+  #
+  # Usage example:
+  #
+  #   Bioroebe::Protein.one_to_three('A') # => "Ala"
+  #
+  # ========================================================================= #
+  def self.one_to_three(this_aminoacid = 'A')
+    if this_aminoacid.is_a? Array
+      this_aminoacid = this_aminoacid.join(' ').strip
+    end
+    return ::Bioroebe.one_to_three(this_aminoacid)
+  end
+
+  # ========================================================================= #
+  # === Bioroebe::Protein.name
+  #
+  # Usage example:
+  #
+  #   Bioroebe::Protein.name('A') # => "alanine"
+  #
+  # ========================================================================= #
+  def self.name(this_aminoacid = 'A')
+    Bioroebe.return_long_name_of_this_aminoacid(this_aminoacid).downcase
+  end
+
+  # ========================================================================= #
+  # === Bioroebe::Protein.to_1
+  #
+  # This will convert from the long name of an aminoacid, such as 'alanine',
+  # to the short one-letter abbreviation.
+  #
+  # Usage example:
+  #
+  #   Bioroebe::Protein.to_1('alanine') # => "A"
+  #
+  # ========================================================================= #
+  def self.to_1(this_aminoacid = 'alanine')
+    if this_aminoacid.is_a? Array
+      this_aminoacid = this_aminoacid.join(' ').strip
+    end
+    this_aminoacid.downcase!
+    dataset = YAML.load_file(Bioroebe.file_amino_acids_long_name_to_one_letter)
+    return dataset[this_aminoacid]
+  end
+
 end
 
 # =========================================================================== #
-# This "alias" was added in May 2022.
+# The following "alias" was added in May 2022.
 # =========================================================================== #
 Aminoacids = Protein
 
@@ -267,6 +364,7 @@ end
 
 if __FILE__ == $PROGRAM_NAME
   require 'colours/autoinclude'
+  require 'bioroebe/toplevel_methods/verbose.rb'
   protein = Bioroebe::Protein.new(ARGV)
   e protein.weight?
   e Colours.rev+'For the aminoacid sequence:'
@@ -277,5 +375,9 @@ if __FILE__ == $PROGRAM_NAME
   e
   e "  #{Colours.royalblue(protein.to_rna)}"
   e
+  e 'Can this protein be stained via coomassie brilliant blue?:'
+  e
+  e "  #{lightblue(Bioroebe::VerboseTruth[protein.can_be_stained_via_coomassie?])}"
+  e
 end # protein MAC
     # protein MACCCCAAAAAKKKKLLLLL

data/lib/bioroebe/sequence/sequence.rb

@@ -188,6 +188,27 @@ class Sequence < ::Bioroebe::RawSequence
     @internal_hash[:type]
   end; alias type type? # === type
 
+  # ========================================================================= #
+  # === index
+  # ========================================================================= #
+  def index(i)
+    @sequence.index(i)
+  end
+
+  # ========================================================================= #
+  # === map
+  # ========================================================================= #
+  def map(&block)
+    @sequence.map(&block)
+  end
+
+  # ========================================================================= #
+  # === size?
+  # ========================================================================= #
+  def size?
+    @sequence.size
+  end
+
   # ========================================================================= #
   # === to_regexp
   #
@@ -334,7 +355,7 @@ class Sequence < ::Bioroebe::RawSequence
       # ===================================================================== #
       sequence?.tr!('T','U') if sequence?
     end
-  end
+  end; alias normalize sanitize_dataset # === normalize
 
   # ========================================================================= #
   # === set_type
@@ -484,7 +505,8 @@ class Sequence < ::Bioroebe::RawSequence
       # ===================================================================== #
       # === :do_not_downcase
       # ===================================================================== #
-      when :do_not_downcase
+      when :do_not_downcase,
+           :make_no_modification
         # Make no modification in this case.
       # ===================================================================== #
       # === :do_upcase
@@ -526,6 +548,16 @@ class Sequence < ::Bioroebe::RawSequence
   end; alias set_rna_type   set_rna # === set_rna_type
        alias convert_to_rna set_rna # === convert_to_rna
 
+  # ========================================================================= #
+  # === automatic_support_for_nucleotides
+  #
+  # This adds automatic support for RNA and DNA to this sequence object.
+  # ========================================================================= #
+  def automatic_support_for_nucleotides
+    require 'bioroebe/sequence/nucleotide_module/nucleotide_module.rb'
+    extend(Bioroebe::NucleotideModule)
+  end
+
   # ========================================================================= #
   # === set_dna
   # ========================================================================= #
@@ -544,6 +576,33 @@ class Sequence < ::Bioroebe::RawSequence
     }.join
   end
 
+  # ========================================================================= #
+  # === remove_invalid_entries_from_the_dna_sequence!
+  # ========================================================================= #
+  def remove_invalid_entries_from_the_dna_sequence!(i = sequence?)
+    result = i.chars.select {|character|
+      DNA_NUCLEOTIDES.include? character.upcase
+    }.join
+    set_sequence(result)
+  end
+
+  # ========================================================================= #
+  # === randomize
+  #
+  # Usage example:
+  #
+  #   x = Bioroebe::Sequence.new; x.randomize
+  #
+  # ========================================================================= #
+  def randomize(
+      i = { 'A'=>1,'C'=>2,'G'=>3,'T'=>4 } 
+    )
+    if i.is_a? Hash
+      i = i.map{|key, value| "#{key * value}" }.join
+    end
+    ::Bioroebe.random_dna(size?, i) # => "GGTAGGGGGGGGTAGGGGGG"
+  end
+
   # ========================================================================= #
   # === Bioroebe::Sequence.sequence_from_file
   #