Represent symbols as tuple to improve performance

src/biotite/sequence/align/kmeralphabet.pyx

@@ -103,10 +103,10 @@ class KmerAlphabet(Alphabet):
 
     >>> base_alphabet = NucleotideSequence.unambiguous_alphabet()
     >>> print(base_alphabet.get_symbols())
-    ['A', 'C', 'G', 'T']
+    ('A', 'C', 'G', 'T')
     >>> kmer_alphabet = KmerAlphabet(base_alphabet, 2)
     >>> print(kmer_alphabet.get_symbols())
-    ['AA', 'AC', 'AG', 'AT', 'CA', 'CC', 'CG', 'CT', 'GA', 'GC', 'GG', 'GT', 'TA', 'TC', 'TG', 'TT']
+    ('AA', 'AC', 'AG', 'AT', 'CA', 'CC', 'CG', 'CT', 'GA', 'GC', 'GG', 'GT', 'TA', 'TC', 'TG', 'TT')
 
     Encode and decode *k-mers*:
 
@@ -210,8 +210,8 @@ class KmerAlphabet(Alphabet):
 
         Returns
         -------
-        symbols : list
-            A list of all *k-mer* symbols, i.e. all possible
+        symbols : tuple
+            A tuple of all *k-mer* symbols, i.e. all possible
             combinations of *k* symbols from its *base alphabet*.
 
         Notes
@@ -224,9 +224,9 @@ class KmerAlphabet(Alphabet):
         to be created first.
         """
         if isinstance(self._base_alph, LetterAlphabet):
-            return ["".join(self.decode(code)) for code in range(len(self))]
+            return tuple(["".join(self.decode(code)) for code in range(len(self))])
         else:
-            return [list(self.decode(code)) for code in range(len(self))]
+            return tuple([list(self.decode(code)) for code in range(len(self))])
 
 
     def extends(self, alphabet):

src/biotite/sequence/align/multiple.pyx

@@ -236,7 +236,7 @@ def align_multiple(sequences, matrix, gap_penalty=-10, terminal_penalty=True,
     # Create new matrix with neutral gap symbol
     gap_symbol = GapSymbol.instance()
     new_alphabet = Alphabet(
-        matrix.get_alphabet1().get_symbols() + [gap_symbol]
+        matrix.get_alphabet1().get_symbols() + (gap_symbol,)
     )
     new_score_matrix = np.zeros(
         (len(new_alphabet), len(new_alphabet)), dtype=np.int32

src/biotite/sequence/alphabet.py

@@ -12,7 +12,6 @@
     "common_alphabet",
 ]
 
-import copy
 import string
 from numbers import Integral
 import numpy as np
@@ -105,7 +104,7 @@ class Alphabet(object):
     def __init__(self, symbols):
         if len(symbols) == 0:
             raise ValueError("Symbol list is empty")
-        self._symbols = copy.deepcopy(list(symbols))
+        self._symbols = tuple(symbols)
         self._symbol_dict = {}
         for i, symbol in enumerate(symbols):
             self._symbol_dict[symbol] = i
@@ -120,10 +119,10 @@ def get_symbols(self):
 
         Returns
         -------
-        symbols : list
-            Copy of the internal list of symbols.
+        symbols : tuple
+            The symbols.
         """
-        return copy.deepcopy(self._symbols)
+        return self._symbols
 
     def extends(self, alphabet):
         """
@@ -244,7 +243,7 @@ def is_letter_alphabet(self):
                 return False
             if isinstance(symbol, str):
                 symbol = symbol.encode("ASCII")
-            if symbol not in LetterAlphabet.PRINATBLES:
+            if symbol not in LetterAlphabet.PRINTABLES:
                 return False
         return True
 
@@ -261,7 +260,11 @@ def __contains__(self, symbol):
         return symbol in self.get_symbols()
 
     def __hash__(self):
-        return hash(tuple(self._symbols))
+        symbols = self.get_symbols()
+        if isinstance(symbols, tuple):
+            return hash(symbols)
+        else:
+            return hash(tuple(symbols))
 
     def __eq__(self, item):
         if item is self:
@@ -293,7 +296,7 @@ class LetterAlphabet(Alphabet):
         in this list.
     """
 
-    PRINATBLES = (string.digits + string.ascii_letters + string.punctuation).encode(
+    PRINTABLES = (string.digits + string.ascii_letters + string.punctuation).encode(
         "ASCII"
     )
 
@@ -306,7 +309,7 @@ def __init__(self, symbols):
                 raise ValueError(f"Symbol '{symbol}' is not a single letter")
             if isinstance(symbol, str):
                 symbol = symbol.encode("ASCII")
-            if symbol not in LetterAlphabet.PRINATBLES:
+            if symbol not in LetterAlphabet.PRINTABLES:
                 raise ValueError(
                     f"Symbol {repr(symbol)} is not printable or whitespace"
                 )
@@ -332,15 +335,7 @@ def extends(self, alphabet):
             return super().extends(alphabet)
 
     def get_symbols(self):
-        """
-        Get the symbols in the alphabet.
-
-        Returns
-        -------
-        symbols : list
-            Copy of the internal list of symbols.
-        """
-        return [symbol.decode("ASCII") for symbol in self._symbols_as_bytes()]
+        return tuple([symbol.decode("ASCII") for symbol in self._symbols_as_bytes()])
 
     def encode(self, symbol):
         if not isinstance(symbol, (str, bytes)) or len(symbol) > 1: