def _extend_with_reads_as_single_end(self, reads1, reads2):
left_seqs, right_seqs = self._extensions_from_reads_file(reads1)
left_seqs2, right_seqs2 = self._extensions_from_reads_file(reads2)
left_kmers = kmers.Kmers(verbose=self.verbose, left=True)
right_kmers = kmers.Kmers(verbose=self.verbose, left=False)
left_kmers.extend(left_seqs)
left_kmers.extend(left_seqs2)
right_kmers.extend(right_seqs)
right_kmers.extend(right_seqs2)
left_extension = left_kmers.extension(self.ext_min_cov,
self.ext_min_ratio,
self.extend_length)
right_extension = right_kmers.extension(self.ext_min_cov,
self.ext_min_ratio,
self.extend_length)
self.seed_lengths.append(
(len(self.seq), len(left_extension), len(right_extension)))
if self.verbose >= 2:
print(' Extend seed. new length=',
len(self.seq),
'. Bases added left:',
len(left_extension),
'. Bases added right:',
len(right_extension),
sep='')
self.seq = left_extension + self.seq + right_extension
if self.verbose >= 2:
print(' new seed:', self.seq)
def extend(self, min_cov, min_ratio, extend_bases):
if self.verbose >= 2:
print(' trying to extend left end ...')
new_left_seq = self.left_kmers.extension(min_cov, min_ratio,
extend_bases)
if self.verbose >= 2:
print(' trying to extend right end ...')
new_right_seq = self.right_kmers.extension(min_cov, min_ratio,
extend_bases)
if self.verbose >= 1:
print(' new left sequence:', new_left_seq)
print(' new right sequence:', new_right_seq)
self.fa.seq = new_left_seq + self.fa.seq + new_right_seq
self.left_kmers = kmers.Kmers(left=True, verbose=self.verbose)
self.right_kmers = kmers.Kmers(verbose=self.verbose)
return len(new_left_seq), len(new_right_seq)
def test_append(self):
'''Test append'''
k = kmers.Kmers(kmer='A')
k.append('G')
self.assertListEqual(['A', 'G'], k.kmers)
k.append('N')
self.assertListEqual(['A', 'G'], k.kmers)
def test_extension(self):
'''Test extension'''
k = kmers.Kmers(kmer='AT', left=True)
self.assertEqual(k.extension(1, 2, 100), 'AT')
k.extend(['GGT'] * 5)
self.assertEqual(k.extension(5, 2, 100), 'GGT')
self.assertEqual(k.extension(5, 2, 2), 'GT')
k = kmers.Kmers()
self.assertEqual(k.extension(5, 2, 100), '')
k.extend(['ACG'] * 5)
self.assertEqual(k.extension(5, 2, 100), 'ACG')
self.assertEqual(k.extension(6, 2, 100), '')
self.assertEqual(k.extension(5, 2, 2), 'AC')
self.assertEqual(k.extension(5, 2, 1), 'A')
k.extend(['ACC'] * 2)
self.assertEqual(k.extension(5, 2, 100), 'ACG')
self.assertEqual(k.extension(5, 3, 100), 'AC')
def test_kmer_dict(self):
'''Test kmer_dict'''
k = kmers.Kmers(kmer='A')
k.extend(['A', 'C', 'GT', 'GC', 'ACT'])
expected = [{
'A': 3,
'C': 1,
'G': 2
}, {
'GT': 1,
'GC': 1,
'AC': 1
}, {
'ACT': 1
}]
for i in range(3):
d = k._kmer_dict(i + 1)
self.assertDictEqual(d, expected[i])
def test_commonest_kmers(self):
k = kmers.Kmers(kmer='AC')
k.extend(['AT'] * 4)
k.append('ATT')
commonest_kmers, counts = k._commonest_kmers(1)
self.assertEqual(commonest_kmers, (None, 'A'))
self.assertEqual(counts, (None, 6))
commonest_kmers, counts = k._commonest_kmers(2)
self.assertEqual(commonest_kmers, ('AC', 'AT'))
self.assertEqual(counts, (1, 5))
commonest_kmers, counts = k._commonest_kmers(3)
self.assertEqual(commonest_kmers, (None, 'ATT'))
self.assertEqual(counts, (None, 1))
commonest_kmers, counts = k._commonest_kmers(4)
self.assertEqual(commonest_kmers, (None, None))
self.assertEqual(counts, (None, None))
def __init__(self, fasta, verbose=0):
self.fa = fasta
self.verbose = verbose
self.left_kmers = kmers.Kmers(left=True, verbose=verbose)
self.right_kmers = kmers.Kmers(verbose=verbose)
def test_init(self):
'''Test __init__'''
k = kmers.Kmers(kmer='ACGGT')
self.assertListEqual(['ACGGT'], k.kmers)
k = kmers.Kmers(kmer='ACGGT', left=True)
self.assertListEqual(['TGGCA'], k.kmers)
def test_extend(self):
'''Test extend'''
k = kmers.Kmers(kmer='A')
k.extend(['A', 'C'])
self.assertListEqual(['A', 'A', 'C'], k.kmers)