def __init__(self, *args, **kwargs):
super(DistanceTest, self).__init__(*args, **kwargs)
utils.ModulesCommonTest.set_test_data()
self.pattern = word_pattern.create(self.dna_records.seq_list, 2)
self.counts = word_vector.Counts(self.dna_records.length_list,
self.pattern)
self.freqs = word_vector.Freqs(self.dna_records.length_list,
self.pattern)
def test_counts_pattern1(self):
counts = word_vector.Counts(self.dna_records.length_list,
self.pattern1)
exp = ["A\t8 4 6", "G\t6 6 3", "C\t6 3 4", "T\t5 5 2"]
lengths = [25, 18, 15]
self.assertEqual(counts.format(decimal_places=0), "\n".join(exp))
# Counts in a sequence should sum to sequence length.
for i in range(len(counts.data)):
self.assertEqual(sum(counts.data[i]), lengths[i])
def test_counts_pattern2(self):
counts = word_vector.Counts(self.dna_records.length_list,
self.pattern2)
exp = [
"TA\t3 3 2", "AC\t4 1 2", "GG\t1 4 2", "AG\t1 2 1", "CT\t0 3 1",
"AA\t2 0 1", "AT\t1 1 1", "CA\t1 0 2", "CC\t2 0 1", "CG\t3 0 0",
"GA\t1 1 1", "GT\t3 0 0", "TT\t1 1 0", "TC\t0 1 0", "TG\t1 0 0"
]
self.assertEqual(counts.format(decimal_places=0), "\n".join(exp))
for i in range(len(counts.data)):
self.assertEqual(sum(counts.data[i]), counts.seq_lengths[i] - 1)
def __init__(self, *args, **kwargs):
super(DistanceTest, self).__init__(*args, **kwargs)
utils.ModulesCommonTest.set_test_data()
self.patterns = []
self.counts = []
self.freqs = []
for i in range(1, 5):
p = word_pattern.create(self.pep_records.seq_list, i)
self.patterns.append(p)
c = word_vector.Counts(self.pep_records.length_list, p)
self.counts.append(c)
f = word_vector.Freqs(self.pep_records.length_list, p)
self.freqs.append(f)
elif method == "wmetric":
matrix = subsmat.get('blosum62')
dist = wmetric.Distance(seq_records, matrix)
matrix = distmatrix.create(seq_records.id_list, dist)
matrix.display()
elif method == "d2":
patterns = []
for i in range(1, 5 + 1):
p = word_pattern.create(seq_records.seq_list, i)
patterns.append(p)
counts = []
for p in patterns:
c = word_vector.Counts(seq_records.length_list, p)
counts.append(c)
countsweight = []
weights = seqcontent.get_weights('protein')
weightmodel = word_vector.WeightModel(weights)
for p in patterns:
c = word_vector.CountsWeight(seq_records, p, weightmodel)
countsweight.append(c)
dist = word_d2.Distance(countsweight)
matrix = distmatrix.create(seq_records.id_list, dist)
matrix.display()
elif method == "lempelziv":
distance = lempelziv.Distance(seq_records)
l = ['d', 'd_star', 'd1', 'd1_star', 'd1_star2']