print(path)
print(matrix)
product = 0.5 # probability of the first letter being A or B
for i, k in zip(path[0::1], path[1::1]):
if i == 'A' and k == 'A':
product *= matrix.item(0)
elif i == 'A' and k == 'B':
product *= matrix.item(1)
elif i == 'B' and k == 'A':
product *= matrix.item(2)
elif i == 'B' and k == 'B':
product *= matrix.item(3)
return product
if __name__ == '__main__':
path = 'AABBBAABABAAAABBBBAABBABABBBAABBAAAABABAABBABABBAB'
transition_matrix = np.matrix([[0.194, 0.806], [0.273, 0.727]])
# read the dataset file in and construct the numpy matrix and path
if len(sys.argv) >= 2:
file_lines = utils.read_file_lines(sys.argv[1])
path = file_lines[0]
last_line = np.array(file_lines[len(file_lines) - 1].split()[1:])
second_to_last = np.array(file_lines[len(file_lines) - 2].split()[1:])
transition_matrix = np.column_stack(
(second_to_last.astype(float), last_line.astype(float)))
print(format(path_probability(path, transition_matrix), '.11e'))
"""get_uniprot_fasta(uniprot_id) - makes a network GET request to the uniprot server using an id which returns a fasta file. This data is decoded into a 'utf-8' string."""
data = ''
with urllib.request.urlopen('http://www.uniprot.org/uniprot/{}.fasta'.format(uniprot_id)) as response:
data = response.read().decode('utf-8')
return data
def find_locations(id):
"""find_locations(id) - fetches the fasta of a protein id, then parses the fasta and looks for the locations of the protein motifs. returns an array of indcies, could be empty"""
fasta = utils.parse_fasta(get_uniprot_fasta(id))
pattern = r'(?=(N[^P][ST][^P]))'
locations = []
for match in re.finditer(pattern, str(fasta[0])):
locations.append(match.start(0) + 1)
return locations
if __name__ == '__main__':
dataset = ['A2Z669', 'B5ZC00', 'P07204_TRBM_HUMAN', 'P20840_SAG1_YEAST']
if len(sys.argv) >= 2:
dataset = utils.read_file_lines(sys.argv[1])
# for each id, in the dataset, we figure out the locations from the remote fasta
# and print out the id followed by the locations if they exist
for access_id in dataset:
if access_id.strip() is not '':
locations = find_locations(access_id.strip())
if len(locations):
print(access_id.strip())
print(' '.join(map(str, locations)))
import sys
import dna.utils as utils
def suffix_array(text):
return [
str(j[1]) for j in sorted([((s[i:], i)) for i in range(len(text))])
]
if __name__ == '__main__':
s = 'AACGATAGCGGTAGA$'
if len(sys.argv) >= 2:
s = utils.read_file_lines(sys.argv[1])[0].strip()
print(', '.join(suffix_array(s)))
with open('output/answer_21.txt', 'w') as out:
print(', '.join(map(str, suffix_array(s))), file=out)
print('Written to {}'.format(out.name))
expected = utils.read_file('output/expected_suff_arr.txt')
actual = utils.read_file('output/answer_21.txt')
print(actual == expected)
import sys
import dna.utils as utils
def remaining_rabbits(n, m):
sequence = [1, 1]
for i in range(n - 2):
tmp = 0
if i + 2 < m:
tmp = sequence[i] + sequence[i + 1]
else:
tmp = sum(sequence[i - (m - 2):i + 1])
sequence.append(tmp)
return sequence[-1]
if __name__ == '__main__':
n = 6
m = 3
if len(sys.argv) >= 2:
n, m = utils.read_file_lines(sys.argv[1])[0].split()
n = int(n)
m = int(m)
print(remaining_rabbits(n, m))
given an integer 'n', calculates all the possible permutations from
1 to 'n' without repeating signs"""
permutations = list(it.permutations(range(1, n + 1)))
prefixes = list(it.product('-+', repeat=n))
results = list(it.product(permutations, prefixes))
enumerations = []
for product in results:
numbers, signs = product
for i, number in enumerate(numbers):
sign = signs[i]
number = int(sign + str(number))
enumerations.append(number)
return enumerations
if __name__ == '__main__':
d = 5
if len(sys.argv) >= 2:
d = int(utils.read_file_lines(sys.argv)[0])
gene_orders = enumerate_oriented_gene_orders(d)
print(int(len(gene_orders) / d))
iterator = iter(gene_orders)
for x in iterator:
result = []
result.append(x)
for i in range(d - 1):
result.append(next(iterator))
print(' '.join(map(str, result)))