Python MutableSeq.append方法代码示例

# 需要导入模块: from Bio.Seq import MutableSeq [as 别名]
# 或者: from Bio.Seq.MutableSeq import append [as 别名]
def generate_rolls(num_rolls):
    """Generate a bunch of rolls corresponding to the casino probabilities.

    Returns:

    - The generate roll sequence
    - The state sequence that generated the roll.

    """
    # start off in the fair state
    cur_state = 'F'
    roll_seq = MutableSeq('', DiceRollAlphabet())
    state_seq = MutableSeq('', DiceTypeAlphabet())

    # generate the sequence
    for roll in range(num_rolls):
        state_seq.append(cur_state)
        # generate a random number
        chance_num = random.random()

        # add on a new roll to the sequence
        new_roll = _loaded_dice_roll(chance_num, cur_state)
        roll_seq.append(new_roll)

        # now give us a chance to switch to a new state
        chance_num = random.random()
        if cur_state == 'F':
            if chance_num <= .05:
                cur_state = 'L'
        elif cur_state == 'L':
            if chance_num <= .1:
                cur_state = 'F'

    return roll_seq.toseq(), state_seq.toseq()

# 需要导入模块: from Bio.Seq import MutableSeq [as 别名]
# 或者: from Bio.Seq.MutableSeq import append [as 别名]
def random_population(genome_alphabet, genome_size, num_organisms,
                      fitness_calculator):
    """Generate a population of individuals with randomly set genomes.

    Arguments:

    o genome_alphabet -- An Alphabet object describing all of the
    possible letters that could potentially be in the genome of an
    organism.

    o genome_size -- The size of each organisms genome.

    o num_organism -- The number of organisms we want in the population.

    o fitness_calculator -- A function that will calculate the fitness
    of the organism when given the organisms genome.
    """
    all_orgs = []

    # a random number generator to get letters for the genome
    letter_rand = random.Random()

    # figure out what type of characters are in the alphabet
    if isinstance(genome_alphabet.letters[0], str):
        if sys.version_info[0] == 3:
            alphabet_type = "u"  # Use unicode string on Python 3
        else:
            alphabet_type = "c"  # Use byte string on Python 2
    elif isinstance(genome_alphabet.letters[0], int):
        alphabet_type = "i"
    elif isinstance(genome_alphabet.letters[0], float):
        alphabet_type = "d"
    else:
        raise ValueError(
            "Alphabet type is unsupported: %s" % genome_alphabet.letters)

    for org_num in range(num_organisms):
        new_genome = MutableSeq(array.array(alphabet_type), genome_alphabet)

        # generate the genome randomly
        for gene_num in range(genome_size):
            new_gene = letter_rand.choice(genome_alphabet.letters)
            new_genome.append(new_gene)

        # add the new organism with this genome
        all_orgs.append(Organism(new_genome, fitness_calculator))

    return all_orgs

# 需要导入模块: from Bio.Seq import MutableSeq [as 别名]
# 或者: from Bio.Seq.MutableSeq import append [as 别名]
    def viterbi(self, sequence, state_alphabet):
        """Calculate the most probable state path using the Viterbi algorithm.

        This implements the Viterbi algorithm (see pgs 55-57 in Durbin et
        al for a full explanation -- this is where I took my implementation
        ideas from), to allow decoding of the state path, given a sequence
        of emissions.

        Arguments:

        o sequence -- A Seq object with the emission sequence that we
        want to decode.

        o state_alphabet -- The alphabet of the possible state sequences
        that can be generated.
        """

        # calculate logarithms of the initial, transition, and emission probs
        log_initial = self._log_transform(self.initial_prob)
        log_trans = self._log_transform(self.transition_prob)
        log_emission = self._log_transform(self.emission_prob)

        viterbi_probs = {}
        pred_state_seq = {}
        state_letters = state_alphabet.letters

        # --- recursion
        # loop over the training squence (i = 1 .. L)
        # NOTE: My index numbers are one less than what is given in Durbin
        # et al, since we are indexing the sequence going from 0 to
        # (Length - 1) not 1 to Length, like in Durbin et al.
        for i in range(0, len(sequence)):
            # loop over all of the possible i-th states in the state path
            for cur_state in state_letters:
                # e_{l}(x_{i})
                emission_part = log_emission[(cur_state, sequence[i])]

                max_prob = 0
                if i == 0:
                    # for the first state, use the initial probability rather
                    # than looking back to previous states
                    max_prob = log_initial[cur_state]
                else:
                    # loop over all possible (i-1)-th previous states
                    possible_state_probs = {}
                    for prev_state in self.transitions_to(cur_state):
                        # a_{kl}
                        trans_part = log_trans[(prev_state, cur_state)]

                        # v_{k}(i - 1)
                        viterbi_part = viterbi_probs[(prev_state, i - 1)]
                        cur_prob = viterbi_part + trans_part

                        possible_state_probs[prev_state] = cur_prob

                    # calculate the viterbi probability using the max
                    max_prob = max(possible_state_probs.values())

                # v_{k}(i)
                viterbi_probs[(cur_state, i)] = (emission_part + max_prob)

                if i > 0:
                    # get the most likely prev_state leading to cur_state
                    for state in possible_state_probs:
                        if possible_state_probs[state] == max_prob:
                            pred_state_seq[(i - 1, cur_state)] = state
                            break
                    
        # --- termination
        # calculate the probability of the state path
        # loop over all states
        all_probs = {}
        for state in state_letters:
            # v_{k}(L)
            all_probs[state] = viterbi_probs[(state, len(sequence) - 1)]

        state_path_prob = max(all_probs.values())

        # find the last pointer we need to trace back from
        last_state = ''
        for state in all_probs:
            if all_probs[state] == state_path_prob:
                last_state = state

        assert last_state != '', "Didn't find the last state to trace from!"
                
        # --- traceback
        traceback_seq = MutableSeq('', state_alphabet)
        
        loop_seq = range(1, len(sequence))
        loop_seq.reverse()

        # last_state is the last state in the most probable state sequence.
        # Compute that sequence by walking backwards in time. From the i-th
        # state in the sequence, find the (i-1)-th state as the most
        # probable state preceding the i-th state.
        state = last_state
        traceback_seq.append(state)
        for i in loop_seq:
            state = pred_state_seq[(i - 1, state)]
#.........这里部分代码省略.........

# 需要导入模块: from Bio.Seq import MutableSeq [as 别名]
# 或者: from Bio.Seq.MutableSeq import append [as 别名]
    def viterbi(self, sequence, state_alphabet):
        """Calculate the most probable state path using the Viterbi algorithm.

        This implements the Viterbi algorithm (see pgs 55-57 in Durbin et
        al for a full explanation -- this is where I took my implementation
        ideas from), to allow decoding of the state path, given a sequence
        of emissions.

        Arguments:

        o sequence -- A Seq object with the emission sequence that we
        want to decode.

        o state_alphabet -- The alphabet of the possible state sequences
        that can be generated.
        """
        # calculate logarithms of the transition and emission probs
        log_trans = self._log_transform(self.transition_prob)
        log_emission = self._log_transform(self.emission_prob)

        viterbi_probs = {}
        pred_state_seq = {}
        state_letters = state_alphabet.letters
        # --- initialization
        #
        # NOTE: My index numbers are one less than what is given in Durbin
        # et al, since we are indexing the sequence going from 0 to
        # (Length - 1) not 1 to Length, like in Durbin et al.
        #
        # v_{0}(0) = 1
        viterbi_probs[(state_letters[0], -1)] = 1
        # v_{k}(0) = 0 for k > 0
        for state_letter in state_letters[1:]:
            viterbi_probs[(state_letter, -1)] = 0

        # --- recursion
        # loop over the training squence (i = 1 .. L)
        for i in range(0, len(sequence)):
            # now loop over all of the letters in the state path
            for main_state in state_letters:
                # e_{l}(x_{i})
                emission_part = log_emission[(main_state, sequence[i])]

                # loop over all possible states
                possible_state_probs = {}
                for cur_state in self.transitions_from(main_state):
                    # a_{kl}
                    trans_part = log_trans[(cur_state, main_state)]

                    # v_{k}(i - 1)
                    viterbi_part = viterbi_probs[(cur_state, i - 1)]
                    cur_prob = viterbi_part + trans_part

                    possible_state_probs[cur_state] = cur_prob

                # finally calculate the viterbi probability using the max
                max_prob = max(possible_state_probs.values())
                viterbi_probs[(main_state, i)] = (emission_part + max_prob)

                # now get the most likely state
                for state in possible_state_probs:
                    if possible_state_probs[state] == max_prob:
                        pred_state_seq[(i - 1, main_state)] = state
                        break
                    
        # --- termination
        # calculate the probability of the state path
        # loop over all letters
        all_probs = {}
        for state in state_letters:
            # v_{k}(L)
            viterbi_part = viterbi_probs[(state, len(sequence) - 1)]
            # a_{k0}
            transition_part = log_trans[(state, state_letters[0])]

            all_probs[state] = viterbi_part * transition_part

        state_path_prob = max(all_probs.values())

        # find the last pointer we need to trace back from
        last_state = ''
        for state in all_probs:
            if all_probs[state] == state_path_prob:
                last_state = state

        assert last_state != '', "Didn't find the last state to trace from!"
                
        # --- traceback
        traceback_seq = MutableSeq('', state_alphabet)
        
        loop_seq = range(0, len(sequence))
        loop_seq.reverse()

        cur_state = last_state
        for i in loop_seq:
            traceback_seq.append(cur_state)
            
            cur_state = pred_state_seq[(i - 1, cur_state)]

        # put the traceback sequence in the proper orientation
#.........这里部分代码省略.........

# 需要导入模块: from Bio.Seq import MutableSeq [as 别名]
# 或者: from Bio.Seq.MutableSeq import append [as 别名]

#.........这里部分代码省略.........

    def test_setting_slices(self):
        self.assertEqual(MutableSeq('CAAA', IUPAC.ambiguous_dna),
                         self.mutable_s[1:5], "Slice mutable seq")

        self.mutable_s[1:3] = "GAT"
        self.assertEqual(MutableSeq("TGATAAAGGATGCATCATG", IUPAC.ambiguous_dna),
                         self.mutable_s,
                         "Set slice with string and adding extra nucleotide")

        self.mutable_s[1:3] = self.mutable_s[5:7]
        self.assertEqual(MutableSeq("TAATAAAGGATGCATCATG", IUPAC.ambiguous_dna),
                         self.mutable_s, "Set slice with MutableSeq")

        self.mutable_s[1:3] = array.array(array_indicator, "GAT")
        self.assertEqual(MutableSeq("TGATTAAAGGATGCATCATG", IUPAC.ambiguous_dna),
                         self.mutable_s, "Set slice with array")

    def test_setting_item(self):
        self.mutable_s[3] = "G"
        self.assertEqual(MutableSeq("TCAGAAGGATGCATCATG", IUPAC.ambiguous_dna),
                         self.mutable_s)

    def test_deleting_slice(self):
        del self.mutable_s[4:5]
        self.assertEqual(MutableSeq("TCAAAGGATGCATCATG", IUPAC.ambiguous_dna),
                         self.mutable_s)

    def test_deleting_item(self):
        del self.mutable_s[3]
        self.assertEqual(MutableSeq("TCAAAGGATGCATCATG", IUPAC.ambiguous_dna),
                         self.mutable_s)

    def test_appending(self):
        self.mutable_s.append("C")
        self.assertEqual(MutableSeq("TCAAAAGGATGCATCATGC", IUPAC.ambiguous_dna),
                         self.mutable_s)

    def test_inserting(self):
        self.mutable_s.insert(4, "G")
        self.assertEqual(MutableSeq("TCAAGAAGGATGCATCATG", IUPAC.ambiguous_dna),
                         self.mutable_s)

    def test_popping_last_item(self):
        self.assertEqual("G", self.mutable_s.pop())

    def test_remove_items(self):
        self.mutable_s.remove("G")
        self.assertEqual(MutableSeq("TCAAAAGATGCATCATG", IUPAC.ambiguous_dna),
                         self.mutable_s, "Remove first G")

        self.assertRaises(ValueError, self.mutable_s.remove, 'Z')

    def test_count(self):
        self.assertEqual(7, self.mutable_s.count("A"))
        self.assertEqual(2, self.mutable_s.count("AA"))

    def test_index(self):
        self.assertEqual(2, self.mutable_s.index("A"))
        self.assertRaises(ValueError, self.mutable_s.index, "8888")

    def test_reverse(self):
        """Test using reverse method"""
        self.mutable_s.reverse()
        self.assertEqual(MutableSeq("GTACTACGTAGGAAAACT", IUPAC.ambiguous_dna),
                         self.mutable_s)

# 需要导入模块: from Bio.Seq import MutableSeq [as 别名]
# 或者: from Bio.Seq.MutableSeq import append [as 别名]
 def get_optimal_alignment(self):
     """Follow the traceback to get the optimal alignment."""
     # intialize the two sequences which will return the alignment
     align_seq1 = MutableSeq(array.array("c"), 
       Alphabet.Gapped(IUPAC.protein, GAP_CHAR))
     align_seq2 = MutableSeq(array.array("c"), 
       Alphabet.Gapped(IUPAC.protein, GAP_CHAR))
       
     # take care of the initial case with the bottom corner matrix
     # item
     current_cell = self.dpmatrix[(len(self.seq1), len(self.seq2))]
     align_seq1.append(current_cell.seq1item)
     align_seq2.append(current_cell.seq2item)
     
     next_cell = current_cell.get_parent()
     current_cell = next_cell
     next_cell = current_cell.get_parent()
     
     # keeping adding sequence until we reach (0, 0)
     while next_cell:
         # add the new sequence--three cases:
         # 1. Move up diaganolly, add a new seq1 and seq2 to the 
         # aligned sequences
         if ((next_cell.col_pos == current_cell.col_pos - 1) and
           (next_cell.row_pos == current_cell.row_pos - 1)):
             # print "case 1 -> seq1 %s, seq2 %s" % (
             # current_cell.seq1item, current_cell.seq2item)
             align_seq1.append(current_cell.seq1item)
             align_seq2.append(current_cell.seq2item)
         # 2. Move upwards, add a new seq2 and a gap in seq1
         elif ((next_cell.col_pos  == current_cell.col_pos) and
           (next_cell.row_pos == current_cell.row_pos - 1)):
             #print "case 2 -> seq2 %s" % current_cell.seq2item
             align_seq1.append(GAP_CHAR)
             align_seq2.append(current_cell.seq2item)
         # 3. Move to the right, add a new seq1 and a gap in seq2
         elif ((next_cell.col_pos == current_cell.col_pos - 1) and
           (next_cell.row_pos == current_cell.row_pos)):
             #print "case 3 -> seq1 % s" % current_cell.seq1item
             align_seq1.append(current_cell.seq1item)
             align_seq2.append(GAP_CHAR)
         
         # now move on to the next sequence
         current_cell = next_cell
         next_cell = current_cell.get_parent()
     
     # reverse the returned alignments since we are reading them in
     # backwards
     align_seq1.reverse()
     align_seq2.reverse()
     return align_seq1.toseq(), align_seq2.toseq()