Exemplo n.º 1
0
 def test_hamming_distance_same_length(self):
     """hamming_distance: should return # of chars different"""
     self.assertEqual(hamming_distance(array('ABC'),array('ABB')),1)
     self.assertEqual(hamming_distance(array('ABC'),array('ABC')),0)
     self.assertEqual(hamming_distance(array('ABC'),array('DDD')),3)
Exemplo n.º 2
0
 def test_hamming_distance_diff_length(self):
     """hamming_distance: truncates at shortest sequence"""
     self.assertEqual(hamming_distance(array('ABC'),array('ABBDDD')),1)
     self.assertEqual(hamming_distance(array('ABC'),array('ABCDDD')),0)
     self.assertEqual(hamming_distance(array('ABC'),array('DDDDDD')),3)
Exemplo n.º 3
0
def VOR(alignment,n=1000,force_monte_carlo=False,mc_threshold=1000):
    """Returns sequence weights according to the Voronoi weighting method.

    alignment: Alignment object
    n: sampling size (in case monte carlo is used)
    force_monte_carlo: generate pseudo seqs with monte carlo always (even
        if there's only a small number of possible unique pseudo seqs
    mc_threshold: threshold of when to use the monte carlo sampling method
        if the number of possible pseudo seqs exceeds this threshold monte
        carlo is used.

    VOR differs from VA in the set of sequences against which it's comparing
    all the sequences in the alignment. In addition to the sequences in the 
    alignment itself, it uses a set of pseudo sequences.
    
    Generating discrete random sequences: 
    A discrete random sequence is generated by choosing with equal
    likelihood at each position one of the residues observed at that position 
    in the alighment. An occurrence of once in the alignment column is 
    sufficient to make the residue type an option. Note: you're choosing 
    with equal likelihood from each of the observed residues (independent 
    of their frequency at that position). In earlier versions of the algorithm 
    the characters were chosen either at the frequency with which they occur 
    at a position or at the frequency with which they occur in the database. 
    Both trials were unsuccesful, because they deviate from random sampling 
    (see Sibbald & Argos 1990).

    Depending on the number of possible pseudo sequences, all of them are 
    used or a random sample is taken (monte carlo).

    Example:
    Alignment: AA, AA, BB
        AA      AA      BB
    AA  0 (.5)  0 (.5)  2
    AB  1 (1/3) 1 (1/3) 1 (1/3)
    BA  1 (1/3) 1 (1/3) 1 (1/3)
    BB  2       2       0 (1)
    -----------------------------
    total 7/6     7/6     10/6
    norm  .291    .291    .418

    For a bigger example with more pseudo sequences, see Henikoff 1994

    I tried the described optimization (pre-calculate the distance to the
    closest sequence). I doesn't have an advantage over the original method.
    """
    
    MC_THRESHOLD = mc_threshold
    
    #decide on sampling method
    if force_monte_carlo or number_of_pseudo_seqs(alignment) > MC_THRESHOLD:
        sampling_method = pseudo_seqs_monte_carlo
    else:
        sampling_method = pseudo_seqs_exact
   
    #change sequences into arrays
    aln_array = Alignment([(k,array(alignment[k])) for k in\
        alignment.RowOrder],RowOrder=alignment.RowOrder)

    weights = zeros(len(aln_array),Float64)
    #calc distances for each pseudo seq
    for seq in sampling_method(aln_array,n=n):
        temp = [hamming_distance(row, seq) for row in aln_array.Rows]
        votes = row_to_vote(array(temp)) #change distances to votes
        weights += votes #add to previous weights
    weight_dict = Weights(dict(zip(aln_array.RowOrder,weights)))
    weight_dict.normalize() #normalize
    return weight_dict