def main():
parser = get_parser()
args = validate_args(parser)
seq_records = seqrecords.read_fasta(args.fasta)
if args.word_size:
p = word_pattern.create(seq_records.seq_list, args.word_size)
else:
p = word_pattern.read(args.word_pattern)
if args.reduce_alphabet:
p = p.reduce_alphabet(seqcontent.get_reduced_alphabet(args.molecule))
if args.merge_revcomp:
p = p.merge_revcomp()
freqs = word_vector.Freqs(seq_records.length_list, p)
dist = word_distance.Distance(freqs, args.distance)
matrix = distmatrix.create(seq_records.id_list, dist)
if args.out:
oh = open(args.out, 'w')
matrix.write_to_file(oh, args.outfmt)
oh.close()
else:
matrix.display(args.outfmt)
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_freqs_pattern1(self):
freqs = word_vector.Freqs(self.dna_records.length_list, self.pattern1)
exp = [
"A\t0.320 0.222 0.400",
"G\t0.240 0.333 0.200",
"C\t0.240 0.167 0.267",
"T\t0.200 0.278 0.133",
]
self.assertEqual(freqs.format(), "\n".join(exp))
# Freqs in a given sequence should sum to 1.
for seqrow in freqs.data:
self.assertEqual('{:.3f}'.format(sum(seqrow)), '1.000')
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)
def test_freqs_pattern2(self):
freqs = word_vector.Freqs(self.dna_records.length_list, self.pattern2)
for seqrow in freqs.data:
self.assertEqual('{:.3f}'.format(sum(seqrow)), '1.000')
exp = [
"TA\t0.125 0.176 0.143", "GG\t0.042 0.235 0.143",
"AC\t0.167 0.059 0.143", "CT\t0.000 0.176 0.071",
"AG\t0.042 0.118 0.071", "CA\t0.042 0.000 0.143",
"AT\t0.042 0.059 0.071", "GA\t0.042 0.059 0.071",
"AA\t0.083 0.000 0.071", "CC\t0.083 0.000 0.071",
"CG\t0.125 0.000 0.000", "GT\t0.125 0.000 0.000",
"TT\t0.042 0.059 0.000", "TC\t0.000 0.059 0.000",
"TG\t0.042 0.000 0.000"
]
self.assertEqual(freqs.format(), "\n".join(exp))
def test_equal_freqs_pattern2(self):
# The result of this method is identical to that from decaf+py.
p = word_pattern.create(self.dna_records.seq_list, 2, True)
freq = word_vector.Freqs(self.dna_records.length_list, p)
freqmodel = word_vector.EqualFreqs(alphabet_size=4)
freqs_std = word_vector.FreqsStd(self.dna_records.length_list, p,
freqmodel)
exp = [
"TA\t0.113 0.189 0.169", "AC\t0.150 0.063 0.169",
"GG\t0.030 0.201 0.135", "CT\t0.000 0.189 0.084",
"AG\t0.038 0.126 0.084", "CA\t0.038 0.000 0.169",
"AT\t0.038 0.063 0.084", "GA\t0.038 0.063 0.084",
"AA\t0.060 0.000 0.067", "CC\t0.060 0.000 0.067",
"CG\t0.113 0.000 0.000", "GT\t0.113 0.000 0.000",
"TT\t0.030 0.050 0.000", "TC\t0.000 0.063 0.000",
"TG\t0.038 0.000 0.000"
]
self.assertEqual(freqs_std.format(), "\n".join(exp))