def test_global_pairwise_align_nucleotide(self):
obs_msa, obs_score, obs_start_end = global_pairwise_align_nucleotide(
DNA("GACCTTGACCAGGTACC"),
DNA("GAACTTTGACGTAAC"),
gap_open_penalty=5.,
gap_extend_penalty=0.5,
match_score=5,
mismatch_score=-4)
self.assertEqual(
obs_msa,
TabularMSA([DNA("G-ACCTTGACCAGGTACC"),
DNA("GAACTTTGAC---GTAAC")]))
self.assertEqual(obs_score, 41.0)
self.assertEqual(obs_start_end, [(0, 16), (0, 14)])
obs_msa, obs_score, obs_start_end = global_pairwise_align_nucleotide(
DNA("GACCTTGACCAGGTACC"),
DNA("GAACTTTGACGTAAC"),
gap_open_penalty=10.,
gap_extend_penalty=0.5,
match_score=5,
mismatch_score=-4)
self.assertEqual(
obs_msa,
TabularMSA([DNA("-GACCTTGACCAGGTACC"),
DNA("GAACTTTGAC---GTAAC")]))
self.assertEqual(obs_score, 32.0)
self.assertEqual(obs_start_end, [(0, 16), (0, 14)])
# DNA sequences with metadata
obs_msa, obs_score, obs_start_end = global_pairwise_align_nucleotide(
DNA("GACCTTGACCAGGTACC", metadata={'id': "s1"}),
DNA("GAACTTTGACGTAAC", metadata={'id': "s2"}),
gap_open_penalty=10.,
gap_extend_penalty=0.5,
match_score=5,
mismatch_score=-4)
self.assertEqual(
obs_msa,
TabularMSA([
DNA("-GACCTTGACCAGGTACC", metadata={'id': "s1"}),
DNA("GAACTTTGAC---GTAAC", metadata={'id': "s2"})
]))
self.assertEqual(obs_score, 32.0)
self.assertEqual(obs_start_end, [(0, 16), (0, 14)])
# Align one DNA sequence and one TabularMSA, score computed manually
obs_msa, obs_score, obs_start_end = global_pairwise_align_nucleotide(
TabularMSA([
DNA("GACCTTGACCAGGTACC", metadata={'id': "s1"}),
DNA("GACCATGACCAGGTACC", metadata={'id': "s2"})
]),
DNA("GAACTTTGACGTAAC", metadata={'id': "s3"}),
gap_open_penalty=10.,
gap_extend_penalty=0.5,
match_score=5,
mismatch_score=-4)
self.assertEqual(
obs_msa,
TabularMSA([
DNA("-GACCTTGACCAGGTACC", metadata={'id': "s1"}),
DNA("-GACCATGACCAGGTACC", metadata={'id': "s2"}),
DNA("GAACTTTGAC---GTAAC", metadata={'id': "s3"})
]))
self.assertEqual(obs_score, 27.5)
self.assertEqual(obs_start_end, [(0, 16), (0, 14)])
# TypeError on invalid input
self.assertRaises(TypeError, global_pairwise_align_nucleotide, 42,
DNA("ACGT"))
self.assertRaises(TypeError, global_pairwise_align_nucleotide,
DNA("ACGT"), 42)
def test_global_pairwise_align_invalid_type(self):
with self.assertRaisesRegex(
TypeError, "GrammaredSequence.*"
"TabularMSA.*'Sequence'"):
global_pairwise_align(DNA('ACGT'), Sequence('ACGT'), 1.0, 1.0, {})
def test_global_pairwise_align_protein_invalid_dtype(self):
with self.assertRaisesRegex(
TypeError, "TabularMSA with Protein dtype.*dtype "
"'DNA'"):
global_pairwise_align_protein(TabularMSA([Protein('PAW')]),
TabularMSA([DNA('ACGT')]))
def test_reverse_transcribe_does_not_modify_input(self):
seq = RNA('AUAU')
self.assertEqual(seq.reverse_transcribe(), DNA('ATAT'))
self.assertEqual(seq, RNA('AUAU'))
print("Building kmer tree using average linkage with an average number of allowed based of: {} {}".format(degen_base_num,time.asctime()))
Z = fastcluster.average(kmerdist)
kmer_length=final.shape[1]
maxdist=round((degen_base_num/kmer_length), 2)
clusters = fcluster(Z,maxdist,criterion='distance')
myclusters = {key:[] for key in set(clusters)}
for index, clust in enumerate(clusters):
myclusters[clust].append(index)
clustergroups = []
for amp in Counter(clusters).keys():
clustergroups.append(final.iloc[myclusters[amp]])
print("Building alignments for kmer motifs. {}".format(time.asctime()))
#group resulting clusters into de facto alignment objects
alignments = []
for c in clustergroups:
group = [DNA(''.join(c.loc[i].map(numeric_to_dna))) for i in c.index]
alignments.append(skbio.alignment.TabularMSA(group))
oligos = []
#find representative IUPAC base of observed positional variance
for n,a in enumerate(alignments):
position_vars = [tuple(set(str(x))) for x in a.iter_positions()]
degenseq = ''.join([basekey[tuple(sorted(p))] for p in position_vars])
oligos.append(SeqRecord(Seq(degenseq,IUPAC.ambiguous_dna),id=pickle_file.split(sep='_')[0]+str(n),description=''))
print("Writing {} degenerate kmers as fasta file. {}".format(len(oligos),time.asctime()))
SeqIO.write(oligos,pickle_file.split(sep='.')[0]+str(degen_base_num)+'_degenerate_primers.fasta','fasta')
def test_translate_genetic_code_object(self):
gc = GeneticCode('M' * 64, '-' * 64)
for seq in RNA('AAAUUUAUGCAU'), DNA('AAATTTATGCAT'):
obs = seq.translate(gc)
self.assertEqual(obs, Protein('MMMM'))
def test_translate_six_frames_invalid_id(self):
for seq in RNA('AUG'), DNA('ATG'):
with six.assertRaisesRegex(self, ValueError, 'table_id.*42'):
seq.translate_six_frames(42)
def time_object_creation_validate(self):
DNA(dna_bytes)
def time_object_creation(self):
DNA(dna_bytes, validate=False)
import numpy as np
num_bases = 1000000
size = int(num_bases / 4)
short_len = 100
dna_template_bytes = [ord(x) for x in 'ACGT']
dna_template_bytes_gapped = [ord(x) for x in 'AC-.']
rna_template_bytes = [ord(x) for x in 'ACGU']
dna_bytes = np.array(dna_template_bytes * size, dtype=np.uint8)
dna_bytes_short = dna_bytes[:short_len]
dna_bytes_gapped = np.array(dna_template_bytes_gapped * size, dtype=np.uint8)
rna_bytes = np.array(rna_template_bytes * size, dtype=np.uint8)
dna_seq = DNA(dna_bytes)
dna_seq_short = DNA(dna_bytes_short)
dna_gapped = DNA(dna_bytes_gapped)
rna_seq = RNA(rna_bytes)
motif_1 = "GGTGCAAGCCGGTGGAAACA"
motif_1_regex = '(' + motif_1 + ')'
def consume_iterator(iterator):
for _ in iterator:
pass
class BenchmarkSuite:
def test_majority_consensus(self):
# empty cases
self.assertEqual(self.empty.majority_consensus(), Sequence(''))
self.assertEqual(self.no_positions.majority_consensus(), RNA(''))
# alignment where all sequences are the same
aln = Alignment(
[DNA('AG', metadata={'id': 'a'}),
DNA('AG', metadata={'id': 'b'})])
self.assertEqual(aln.majority_consensus(), DNA('AG'))
# no ties
d1 = DNA('TTT', metadata={'id': "d1"})
d2 = DNA('TT-', metadata={'id': "d2"})
d3 = DNA('TC-', metadata={'id': "d3"})
a1 = Alignment([d1, d2, d3])
self.assertEqual(a1.majority_consensus(), DNA('TT-'))
# ties
d1 = DNA('T', metadata={'id': "d1"})
d2 = DNA('A', metadata={'id': "d2"})
a1 = Alignment([d1, d2])
self.assertTrue(a1.majority_consensus() in [DNA('T'), DNA('A')])
def test_init_not_equal_lengths(self):
invalid_seqs = [
self.d1, self.d2, self.d3,
DNA('.-ACC-GTGC--', metadata={'id': "i2"})
]
self.assertRaises(AlignmentError, Alignment, invalid_seqs)
