bioroebe 0.10.80 → 0.11.25

data/lib/bioroebe/python/protein_to_dna.py

@@ -0,0 +1,33 @@
+import sys
+import yaml
+
+USE_THIS_CODON_TABLE = \
+  '/home/x/programming/ruby/src/bioroebe/lib/bioroebe/yaml/codon_tables/1.yml'
+
+# =========================================================================== #
+# === protein_to_dna
+# =========================================================================== #
+def protein_to_dna(i):
+  output_string = ''
+  yaml_dataset = None
+  aminoacid_sequence = list(i)
+
+  with open(USE_THIS_CODON_TABLE) as file:
+    # The FullLoader parameter handles the conversion from YAML
+    # scalar values to Python the dictionary format
+    yaml_dataset = yaml.load(file, Loader=yaml.FullLoader)
+    yaml_dataset = { value: key for key, value in yaml_dataset.items() }
+
+  for this_aminoacid in aminoacid_sequence:
+    # Now we must obtain the DNA sequence.
+    # print(yaml_dataset[this_aminoacid])
+    output_string += yaml_dataset[this_aminoacid]
+    output_string += '-'
+
+  # print(yaml_dataset)
+  print(output_string[0: -1]) # Remove the last character.
+
+if __name__ == '__main__':
+  i = sys.argv[1]
+  protein_to_dna(i)
+# py protein_to_dna.py KKKLLL

data/lib/bioroebe/python/shell/shell.py

@@ -0,0 +1,19 @@
+#!/usr/bin/python 
+import sys
+
+# =========================================================================== #
+# === obtain_user_input
+# =========================================================================== #
+def obtain_user_input():
+  user_input = input("> ")
+  return user_input
+
+shall_we_continue = True
+
+while (shall_we_continue):
+  result = obtain_user_input
+  if result == "q":
+    shall_we_continue = False
+    # exit
+  else:
+    print(result)

data/lib/bioroebe/python/to_rna.py

@@ -0,0 +1,14 @@
+import sys
+    
+# =========================================================================== #
+# === to_rna
+#
+# This method will simply convert the given input, such as a 
+# nucleotide sequence, to RNA.
+# =========================================================================== #
+def to_rna(i):
+  converted = i.replace('T','U')
+  print(converted)
+
+to_rna(sys.argv[1])
+# py to_rna.py ATG

data/lib/bioroebe/python/toplevel_methods/open_in_browser.py

@@ -0,0 +1,20 @@
+#!/usr/bin/python3
+import sys
+import os
+
+class Bioroebe(object):
+
+  # =========================================================================== #
+  # === open_in_browser
+  # =========================================================================== #
+  def open_in_browser(
+      this_url,
+      use_this_browser = 'firefox'
+    ):
+    cmd = use_this_browser+" -new-tab "+this_url
+    print(cmd)
+    os.system(cmd)
+
+if __name__ == '__main__':
+  i = sys.argv[1]
+  Bioroebe.open_in_browser(i) # py open_in_browser.py "derstandard.at"

data/lib/bioroebe/python/toplevel_methods/palindromes.py

@@ -0,0 +1,42 @@
+#!/usr/bin/python3
+import sys
+
+class Bioroebe(object):
+
+  # =========================================================================== #
+  # === is_palindrome
+  # =========================================================================== #
+  def is_palindrome(i):
+    result = False
+    reverse_string = i[::-1]
+
+    hash = {
+      "A": "T",
+      "T": "A",
+      "G": "C",
+      "C": "G"
+    }
+
+    for nucleotide in i:
+      print(nucleotide)
+      if hash[nucleotide] == reverse
+      result
+# THIS IS INCOMPLETE AS OF JULY 2022.
+    return result
+
+if __name__ == '__main__':
+
+  if len(sys.argv) > 1:
+    i = sys.argv[1]
+  else:
+    i = "malayalam"
+
+  ans = Bioroebe.is_palindrome(i)
+
+  if ans:
+    print(f"Yes, {i} is a palindrome.")
+  else:
+    print(f"No, {i} is NOT a palindrome.")
+
+# py palindromes.py "OTTO"
+# py palindromes.py "GAATTC"

data/lib/bioroebe/python/toplevel_methods/rds.py

@@ -0,0 +1,13 @@
+#!/usr/bin/python3
+import re
+import sys
+
+# =========================================================================== #
+# === rds
+# =========================================================================== #
+def rds(i):
+  return re.sub('//', '/', i)
+
+if __name__ == '__main__':
+  i = sys.argv[1]
+  print(rds(i)) # py rds.py "foobar//barfoo"

data/lib/bioroebe/python/toplevel_methods/three_delimiter.py

@@ -0,0 +1,34 @@
+#!/usr/bin/python3
+# =========================================================================== #
+import sys
+import re
+
+class Bioroebe(object):
+
+  # ========================================================================= #
+  # === Bioroebe.three_delimiter
+  #
+  # This method will, applied onto a String, add the '|' token
+  # after 3 positions.
+  #
+  # Example: 
+  #
+  #    Bioroebe.three_delimiter('ATGGGGATGTAGGTA') # => "ATG|GGG|ATG|TAG|GTA"
+  #
+  # ========================================================================= #
+  def three_delimiter(i):
+
+    if isinstance(i, list):
+      i = ' '.join(str(e) for e in i)
+
+    i = re.sub(r'(...)', r'\1-', i)
+
+    if i[-1] == '-': # Chop of the last character if it is a '-' token.
+      i = i[:-1]
+
+    return i 
+
+if __name__ == '__main__':
+  i = sys.argv[1]
+  print(Bioroebe.three_delimiter(i))
+  # py three_delimiter.py ATGGGGATGTAGGTA

data/lib/bioroebe/python/toplevel_methods/time_and_date.py

@@ -0,0 +1,43 @@
+#!/usr/bin/python3
+import sys
+from datetime import datetime
+
+class Bioroebe(object):
+
+  # ========================================================================= #
+  # === Bioroebe.return_current_day_month_year()
+  #
+  # This method will return a String such as "09.07.2022".
+  # ========================================================================= #
+  def return_current_day_month_year():
+    day   = str(datetime.now().day).rjust(2, '0')
+    month = str(datetime.now().month).rjust(2, '0')
+    year  = str(datetime.now().year)
+    return day+'.'+month+'.'+year
+
+  # ========================================================================= #
+  # === Bioroebe.return_current_hours_minutes_seconds()
+  #
+  # This method will return a String such as "20:44:20".
+  # ========================================================================= #
+  def return_current_hours_minutes_seconds():
+    hours   = str(datetime.now().hour).rjust(2, '0')
+    minutes = str(datetime.now().minute).rjust(2, '0')
+    seconds = str(datetime.now().second).rjust(2, '0')
+    return hours+':'+minutes+':'+seconds
+
+  # ========================================================================= #
+  # === Bioroebe.show_time_now
+  #
+  # This method will show the current time. It will do so only if the
+  # verbosity-variable has been set to true.
+  # ========================================================================= #
+  def show_time_now(be_verbose = True):
+    time = Bioroebe.return_current_hours_minutes_seconds()
+    if be_verbose:
+      print("Showing the current time: "+time)
+
+if __name__ == '__main__':
+  print(Bioroebe.return_current_day_month_year())
+  print(Bioroebe.return_current_hours_minutes_seconds())
+  Bioroebe.show_time_now()

data/lib/bioroebe/python/toplevel_methods/to_camelcase.py

@@ -0,0 +1,11 @@
+from re import sub
+
+# =========================================================================== #
+# === camel_case
+# =========================================================================== #
+def camel_case(i):
+  i = sub(r"(_|-)+", " ", i).title().replace(" ", "")
+  return ''.join([i[0].upper(), i[1:]])
+
+if __name__ == "__main__":
+  print(camel_case('foo_bar'))

data/lib/bioroebe/requires/require_the_bioroebe_project.rb

@@ -159,4 +159,6 @@ require 'bioroebe/requires/require_all_codon_files.rb'
 # And the sinatra-interface:
 # =========================================================================== #
 # require 'bioroebe/requires/require_the_bioroebe_sinatra_components.rb'
-require 'bioroebe/www/sinatra/sinatra.rb'
+require 'bioroebe/www/sinatra/sinatra.rb'
+
+require 'bioroebe/sequence/protein.rb'

data/lib/bioroebe/sequence/nucleotide_module/nucleotide_module.rb

@@ -72,13 +72,6 @@ module NucleotideModule # === Bioroebe::NucleotideModule
     i.tr('U','T')
   end
 
-  # ========================================================================= #
-  # === to_dna
-  # ========================================================================= #
-  def to_dna
-    seq?.tr('U','T')
-  end; alias dna to_dna # === dna
-
   # ========================================================================= #
   # === n_random_dna
   #
@@ -258,24 +251,6 @@ module NucleotideModule # === Bioroebe::NucleotideModule
     ::Bioroebe.codon_to_aminoacid(codon)
   end; alias translate_aminoacid_into_dna codon_to_aminoacid # === translate_aminoacid_into_dna
 
-  # ========================================================================= #
-  # === to_dna
-  #
-  # This method will convert a RNA sequence into a DNA sequence.
-  #
-  # It will return the translation.
-  #
-  # bio; puts Bioroebe.new.to_dna('actgggcgagagklklklklk')
-  # ========================================================================= #
-  def to_dna(
-      i = sequence?, upcase_me = true
-    )
-    if is_RNA?
-      i = sequence? if i.nil?
-      ::Bioroebe.to_dna(i, upcase_me)
-    end
-  end; alias dna to_dna # === dna
-
   # ========================================================================= #
   # === random
   #
@@ -397,6 +372,34 @@ module NucleotideModule # === Bioroebe::NucleotideModule
     end
   end; alias gc_percent gc_percentage # === gc_percent
 
+  # ========================================================================= #
+  # === to_dna
+  #
+  # This method will convert a RNA sequence into a DNA sequence.
+  #
+  # It will return the translation.
+  #
+  # Usage example:
+  #
+  #   require 'bioroebe'; puts Bioroebe::DNA.new('actgggcgagaguuuuUUUUUU').to_dna
+  #
+  # ========================================================================= #
+  def to_dna(
+      i         = sequence?,
+      upcase_me = true
+    )
+    i = sequence? if i.nil?
+    i = ::Bioroebe.to_dna(i, upcase_me)
+    return i
+  end; alias dna to_dna # === dna
+
+  # ========================================================================= #
+  # === to_dna
+  # ========================================================================= #
+  # def to_dna
+  #   seq?.tr('U','T')
+  # end; alias dna to_dna # === dna
+
 end; end
 
 if __FILE__ == $PROGRAM_NAME

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
   #