Add lysine branching

1 files changed, 56 insertions, 35 deletions

diff --git a/pepseq/amino_acid.py b/pepseq/amino_acid.py
index 5b7bb5c..05ecb07 100644
--- a/pepseq/amino_acid.py
+++ b/pepseq/amino_acid.py
@@ -6,26 +6,28 @@ class AminoAcid(object):
     """ Amino acids are molecules containing an amine group, a carboxylic acid
         group and a side chain that varies between different amino acids. """
 
-    aminoAcids = {'G': ('Glycine',       'Gly', 57.05),
-                  'A': ('Alanine',       'Ala', 71.09),
-                  'S': ('Serine',        'Ser', 87.08),
-                  'T': ('Threonine',     'Thr', 101.11),
-                  'C': ('Cysteine',      'Cys', 103.15),
-                  'V': ('Valine',        'Val', 99.14),
-                  'L': ('Leucine',       'Leu', 113.16),
-                  'I': ('Isoleucine',    'Ile', 113.16),
-                  'M': ('Methionine',    'Met', 131.19),
-                  'P': ('Proline',       'Pro', 97.12),
-                  'F': ('Phenylalanine', 'Phe', 147.18),
-                  'Y': ('Tyrosine',      'Tyr', 163.18),
-                  'W': ('Tryptophan',    'Trp', 186.21),
-                  'D': ('Aspartic Acid', 'Asp', 115.09),
-                  'E': ('Glutamic Acid', 'Glu', 129.12),
-                  'N': ('Asparagine',    'Asn', 114.11),
-                  'Q': ('Glutamine',     'Gln', 128.14),
-                  'H': ('Histidine',     'His', 137.14),
-                  'K': ('Lysine',        'Lys', 128.17),
-                  'R': ('Arginine',      'Arg', 156.19)}
+    aminoAcids = {'G': ('Glycine',                  'Gly', 57.05),
+                  'A': ('Alanine',                  'Ala', 71.09),
+                  'S': ('Serine',                   'Ser', 87.08),
+                  'T': ('Threonine',                'Thr', 101.11),
+                  'C': ('Cysteine',                 'Cys', 103.15),
+                  'V': ('Valine',                   'Val', 99.14),
+                  'L': ('Leucine',                  'Leu', 113.16),
+                  'I': ('Isoleucine',               'Ile', 113.16),
+                  'M': ('Methionine',               'Met', 131.19),
+                  'P': ('Proline',                  'Pro', 97.12),
+                  'F': ('Phenylalanine',            'Phe', 147.18),
+                  'Y': ('Tyrosine',                 'Tyr', 163.18),
+                  'W': ('Tryptophan',               'Trp', 186.21),
+                  'D': ('Aspartic Acid',            'Asp', 115.09),
+                  'E': ('Glutamic Acid',            'Glu', 129.12),
+                  'N': ('Asparagine',               'Asn', 114.11),
+                  'Q': ('Glutamine',                'Gln', 128.14),
+                  'H': ('Histidine',                'His', 137.14),
+                  'K': ('Lysine',                   'Lys', 128.17),
+                  'R': ('Arginine',                 'Arg', 156.19),
+                  'B': ('Borono Phenylalanine',     'Bpa', 309.08),
+    }
 
     def __init__(self, letter):
         self.letter = letter.upper()
@@ -41,38 +43,57 @@ class AminoAcid(object):
 class Peptide(object):
 
     def __init__(self, amino_acids):
+        self.amino_acids = amino_acids
         self.weight = 0
         self.string = ""
-        self.amino_acids = amino_acids
-        for amino_acid in self.amino_acids:
+        for amino_acid in amino_acids:
             self.weight += amino_acid.weight
-            self.string += ('%s' % (amino_acid.letter.lower()))
-            if amino_acid is not self.amino_acids[-1]:
-                self.string += ','
+            self.string += ('%s' % (amino_acid.letter))
+
+    def branch_before(self, index):
+        self.weight = 0
+        for (counter, amino_acid) in enumerate(self.amino_acids):
+            if counter < index:
+                self.weight += 2 * amino_acid.weight
+            else:
+                self.weight += amino_acid.weight
+        self.string = '(' + self.string[0:index] + ')2' + self.string[index:]
 
     def __cmp__(self, other):
         return cmp(self.weight, other.weight)
 
     def __str__(self):
-        return "%d: %s" % (self.weight, self.string)
+        return self.string
+
 
 if __name__ == '__main__':
 
     import itertools
 
-    fragment = (
-            ((AminoAcid('a'), AminoAcid('t'), AminoAcid('k'))),
-            ((AminoAcid('r'), AminoAcid('q'), AminoAcid('h'))),
-            ((AminoAcid('r'), AminoAcid('q'), AminoAcid('h'))),
-            ((AminoAcid('r'), AminoAcid('q'), AminoAcid('h'))),
-            ((AminoAcid('r'), AminoAcid('q'), AminoAcid('h'))),
+    LOW  = 2636.0
+    HIGH = 2637.0
+
+    possibilities = (
+            (AminoAcid('B'), AminoAcid('Q'), AminoAcid('T'), AminoAcid('Y')),
+            (AminoAcid('B'), AminoAcid('E'), AminoAcid('L'), AminoAcid('F')),
+            (AminoAcid('B'), AminoAcid('D'), AminoAcid('S'), AminoAcid('H')),
+            (AminoAcid('B'), AminoAcid('N'), AminoAcid('A'), AminoAcid('W')),
+            (AminoAcid('K'), AminoAcid('N')),
+            (AminoAcid('S'), AminoAcid('N'), AminoAcid('T'), AminoAcid('F')),
+            (AminoAcid('T'), AminoAcid('D'), AminoAcid('G'), AminoAcid('W')),
+            (AminoAcid('B'), AminoAcid('Q'), AminoAcid('P'), AminoAcid('H')),
+            (AminoAcid('L'), AminoAcid('E'), AminoAcid('A'), AminoAcid('Y')),
     )
 
     peptides = []
-    sequences = tuple(itertools.product(*fragment))
+    sequences = tuple(itertools.product(*possibilities))
     for sequence in sequences:
-        peptides.append(Peptide(sequence))
+        if sequence[4].letter == 'K':
+            peptide = Peptide(sequence)
+            peptide.branch_before(4)
+            peptides.append(peptide)
 
     peptides.sort()
     for peptide in peptides:
-        print peptide
+        if peptide.weight > LOW and peptide.weight < HIGH:
+            print "%.2f %s" % (peptide.weight, peptide)