def question2(): human = read_protein(HUMAN_EYELESS_URL) fly = read_protein(FRUITFLY_EYELESS_URL) scoringmatrix = read_scoring_matrix(PAM50_URL) pax = read_protein(CONSENSUS_PAX_URL) alignmentmatrix = student.compute_alignment_matrix(human, fly, scoringmatrix, False) score, align_x, align_y = student.compute_local_alignment(human, fly, scoringmatrix, alignmentmatrix) align_x2 = "" for item in align_x: if not item == '-': align_x2 += item align_y2 = "" for item in align_y: if not item == '-': align_y2 += item alignmentmatrix = student.compute_alignment_matrix(align_x2, pax, scoringmatrix, True) score3, align_x3, align_y3 = student.compute_global_alignment(align_x2, pax, scoringmatrix, alignmentmatrix) print align_x3 print align_y3 print sum([align_x3[item] == align_y3[item] for item in range(len(align_x3))])/float(len(align_x3)) alignmentmatrix = student.compute_alignment_matrix(align_y2, pax, scoringmatrix, True) score3, align_x3, align_y3 = student.compute_global_alignment(align_y2, pax, scoringmatrix, alignmentmatrix) print align_x3 print align_y3 print sum([align_x3[item] == align_y3[item] for item in range(len(align_x3))])/float(len(align_x3))
def question3(): letters = "ACBEDGFIHKMLNQPSRTWVYXZ" human = [random.choice(letters) for item in range(133)] fly = [random.choice(letters) for item in range(133)] print human print fly scoringmatrix = read_scoring_matrix(PAM50_URL) pax = read_protein(CONSENSUS_PAX_URL) alignmentmatrix = student.compute_alignment_matrix(human, fly, scoringmatrix, False) score, align_x, align_y = student.compute_local_alignment(human, fly, scoringmatrix, alignmentmatrix) align_x2 = "" for item in align_x: if not item == '-': align_x2 += item align_y2 = "" for item in align_y: if not item == '-': align_y2 += item alignmentmatrix = student.compute_alignment_matrix(align_x2, pax, scoringmatrix, True) score3, align_x3, align_y3 = student.compute_global_alignment(align_x2, pax, scoringmatrix, alignmentmatrix) print align_x3 print align_y3 print sum([align_x3[item] == align_y3[item] for item in range(len(align_x3))])/float(len(align_x3)) alignmentmatrix = student.compute_alignment_matrix(align_y2, pax, scoringmatrix, True) score3, align_x3, align_y3 = student.compute_global_alignment(align_y2, pax, scoringmatrix, alignmentmatrix) print align_x3 print align_y3 print sum([align_x3[item] == align_y3[item] for item in range(len(align_x3))])/float(len(align_x3))
def question1(): human = read_protein(HUMAN_EYELESS_URL) fly = read_protein(FRUITFLY_EYELESS_URL) scoringmatrix = read_scoring_matrix(PAM50_URL) alignmentmatrix = student.compute_alignment_matrix(human, fly, scoringmatrix, False) score, align_x, align_y = student.compute_local_alignment(human, fly, scoringmatrix, alignmentmatrix) print score print align_x print align_y print len(align_x), len(align_y)
def question1():
human = read_protein(HUMAN_EYELESS_URL)
fly = read_protein(FRUITFLY_EYELESS_URL)
scoringmatrix = read_scoring_matrix(PAM50_URL)
alignmentmatrix = student.compute_alignment_matrix(human, fly,
scoringmatrix, False)
score, align_x, align_y = student.compute_local_alignment(
human, fly, scoringmatrix, alignmentmatrix)
print score
print align_x
print align_y
print len(align_x), len(align_y)
def question5(): keys = q4_dict.keys() values = q4_dict.values() nominator = sum([keys[i] * values[i] for i in range(len(keys))]) mean = float(nominator) / sum(values) nominator = sum([(keys[i] - mean)**2 * values[i] for i in range(len(keys))]) stddev = math.sqrt(float(nominator) / sum(values)) human = read_protein(HUMAN_EYELESS_URL) fly = read_protein(FRUITFLY_EYELESS_URL) scoringmatrix = read_scoring_matrix(PAM50_URL) alignmentmatrix = student.compute_alignment_matrix(human, fly, scoringmatrix, False) score, align_x, align_y = student.compute_local_alignment(human, fly, scoringmatrix, alignmentmatrix) return score, mean, stddev
def generate_null_distribution(seq_x,seq_y, scoring_matrix, num_trials): scoring_distribution = dict() seq_x_copy = list(seq_x) for item in range(num_trials): print item rand_y = list(seq_y) random.shuffle(rand_y) alignmentmatrix = student.compute_alignment_matrix(seq_x_copy, rand_y, scoring_matrix, False) score, align_x, align_y = student.compute_local_alignment(seq_x_copy, rand_y, scoring_matrix, alignmentmatrix) if score in scoring_distribution: scoring_distribution[score]+=1 else: scoring_distribution[score] = 1 return scoring_distribution
def question5():
keys = q4_dict.keys()
values = q4_dict.values()
nominator = sum([keys[i] * values[i] for i in range(len(keys))])
mean = float(nominator) / sum(values)
nominator = sum([(keys[i] - mean)**2 * values[i]
for i in range(len(keys))])
stddev = math.sqrt(float(nominator) / sum(values))
human = read_protein(HUMAN_EYELESS_URL)
fly = read_protein(FRUITFLY_EYELESS_URL)
scoringmatrix = read_scoring_matrix(PAM50_URL)
alignmentmatrix = student.compute_alignment_matrix(human, fly,
scoringmatrix, False)
score, align_x, align_y = student.compute_local_alignment(
human, fly, scoringmatrix, alignmentmatrix)
return score, mean, stddev
def generate_null_distribution(seq_x, seq_y, scoring_matrix, num_trials):
scoring_distribution = dict()
seq_x_copy = list(seq_x)
for item in range(num_trials):
print item
rand_y = list(seq_y)
random.shuffle(rand_y)
alignmentmatrix = student.compute_alignment_matrix(
seq_x_copy, rand_y, scoring_matrix, False)
score, align_x, align_y = student.compute_local_alignment(
seq_x_copy, rand_y, scoring_matrix, alignmentmatrix)
if score in scoring_distribution:
scoring_distribution[score] += 1
else:
scoring_distribution[score] = 1
return scoring_distribution
def question3():
letters = "ACBEDGFIHKMLNQPSRTWVYXZ"
human = [random.choice(letters) for item in range(133)]
fly = [random.choice(letters) for item in range(133)]
print human
print fly
scoringmatrix = read_scoring_matrix(PAM50_URL)
pax = read_protein(CONSENSUS_PAX_URL)
alignmentmatrix = student.compute_alignment_matrix(human, fly,
scoringmatrix, False)
score, align_x, align_y = student.compute_local_alignment(
human, fly, scoringmatrix, alignmentmatrix)
align_x2 = ""
for item in align_x:
if not item == '-':
align_x2 += item
align_y2 = ""
for item in align_y:
if not item == '-':
align_y2 += item
alignmentmatrix = student.compute_alignment_matrix(align_x2, pax,
scoringmatrix, True)
score3, align_x3, align_y3 = student.compute_global_alignment(
align_x2, pax, scoringmatrix, alignmentmatrix)
print align_x3
print align_y3
print sum(
[align_x3[item] == align_y3[item]
for item in range(len(align_x3))]) / float(len(align_x3))
alignmentmatrix = student.compute_alignment_matrix(align_y2, pax,
scoringmatrix, True)
score3, align_x3, align_y3 = student.compute_global_alignment(
align_y2, pax, scoringmatrix, alignmentmatrix)
print align_x3
print align_y3
print sum(
[align_x3[item] == align_y3[item]
for item in range(len(align_x3))]) / float(len(align_x3))
def question2():
human = read_protein(HUMAN_EYELESS_URL)
fly = read_protein(FRUITFLY_EYELESS_URL)
scoringmatrix = read_scoring_matrix(PAM50_URL)
pax = read_protein(CONSENSUS_PAX_URL)
alignmentmatrix = student.compute_alignment_matrix(human, fly,
scoringmatrix, False)
score, align_x, align_y = student.compute_local_alignment(
human, fly, scoringmatrix, alignmentmatrix)
align_x2 = ""
for item in align_x:
if not item == '-':
align_x2 += item
align_y2 = ""
for item in align_y:
if not item == '-':
align_y2 += item
alignmentmatrix = student.compute_alignment_matrix(align_x2, pax,
scoringmatrix, True)
score3, align_x3, align_y3 = student.compute_global_alignment(
align_x2, pax, scoringmatrix, alignmentmatrix)
print align_x3
print align_y3
print sum(
[align_x3[item] == align_y3[item]
for item in range(len(align_x3))]) / float(len(align_x3))
alignmentmatrix = student.compute_alignment_matrix(align_y2, pax,
scoringmatrix, True)
score3, align_x3, align_y3 = student.compute_global_alignment(
align_y2, pax, scoringmatrix, alignmentmatrix)
print align_x3
print align_y3
print sum(
[align_x3[item] == align_y3[item]
for item in range(len(align_x3))]) / float(len(align_x3))