class SimplePeptide:
    """
        This allows comparisons between peptide sequences that are nearly identical
        except for the Isboaric Isoleucine and Leucine [IL]. MS Proteomics is based on
        identifying peptides based on their fragment mass profiles. Since [IL] have the
        same mass they can not be differentiated.

        The equals is acomplished by a simple replacement of all r'[IL]' in the sequence with
        the string [IL]. Then an exact match (No Regex matching needed) is the most efficient
        way to match two peptides.

        You could also use the complied pattern to do a RegEx pattern search against a larger sequence.

        This was really for putting the object into a Pandas DF
        pdDF['SIMPLE_PEP'] = pdDF['Sequence'].apply(lambda x: SimplePeptide(x))
    """

    def __init__(self, sequence):
        self.sequence = sequence
        self.pattern_string = re.sub(r'[IL]', '[IL]', sequence)
        self.pattern = re.compile(self.pattern_string)
        self.myhash = hash(self.pattern_string)

    def __eq__(self, other):
        if isinstance(self, other.__class__):
            return bool(self.pattern_string == other.pattern_string)
        return False

    def __hash__(self):
        return self.myhash

    def __lt__(self, other):
        return self.pattern_string < other.pattern_string

    def __str__(self):
        return self.sequence

pep1 = SimplePeptide('SDFSDFSDFLSDFISDFR')
pep2 = SimplePeptide('SDFSDFSDFLSDFISDFR')
pep3 = SimplePeptide('SDFSDFSDFISDFLSDFR')
pep4 = SimplePeptide('XZCZXCZXCIZXCLSDFR')

print('{} = {} ? {}'.format(pep1, pep2, (pep1==pep2))) # SDFSDFSDFLSDFISDFR = SDFSDFSDFLSDFISDFR ? True
print('{} = {} ? {}'.format(pep1, pep3, (pep1==pep3))) # SDFSDFSDFLSDFISDFR = SDFSDFSDFISDFLSDFR ? True
print('{} = {} ? {}'.format(pep1, pep4, (pep1==pep4))) # SDFSDFSDFLSDFISDFR = XZCZXCZXCIZXCLSDFR ? False