Sequence example file

sequence.pyx

"""

Sequence
--------

String object representing biological sequences with alphabets.


"""

cdef class Sequence(object):
    '''
    The Sequence class is a general container for storing a big string (a long sequence of characters) and
    for making its manipulation easy and efficient.

    Like python standard strings, the basic sequence object is immutable. So you cannot do attribution such as
    seq[5] = 'A'.  However it allows the Sequence objects to be used as dictionary keys.

    The Sequence object provides a number of string like methods (such as count, find, split and strip), which
    are general for any biological sequences.

    For more biology-oriented purpose of storing a DNA, RNA or a sequence of amino acids, please check those
    subclasses: DNASequence, RNASequence, AASequence. They all derive directly from the Sequence class.

    The Sequence object can be used for storing any single string based on single-byte character set.


     Parameters
     ----------
     data: string
           The sequence of letters

     alphabet: Optional argument, an Alphabet object, default is None.
           The expected symbols (letters), for Sequence the alphabet is None.


    '''

    cdef public bytes data
    cdef public object alphabet

    def __init__(self, bytes data, alphabet=None):
        self.data = data
        self.alphabet = alphabet

    def __repr__(self):
        '''
        Returns a (truncated) representation of the sequence for debugging.
        '''
        return '%d-letter "%s" instance\nseq: %s' % (len(self.data), self.__class__.__name__, repr(self.data))

    def __str__(self):
        '''
        Return the full sequence as a python string, use str(sequence).
        '''
        return self.data


    def __len__(self):
        '''
        Return the length of the sequence.
        '''
        return  len(self.data)

    def __getitem__(self, index):
        '''
        Returns a subsequence of single letter.
        '''
        return Sequence(self.data[index], self.alphabet)