def test_recover_local_align_multiple_solutions(self):
# Classes example
ga_score, ga_trace, _ = local_align_multiple_solutions(
self.slides_seq2, self.slides_seq1, self.sm, -8)
rga = recover_local_align_multiple_solutions(ga_score, ga_trace,
self.slides_seq2,
self.slides_seq1)
self.assertEqual(rga, [['HSW', 'HGW'], ['HSWG', 'HGWA']])
ga_score, ga_trace, _ = local_align_multiple_solutions(
self.seq1, self.seq2, self.sm_dna, -1)
rga = recover_local_align_multiple_solutions(ga_score, ga_trace,
self.seq1, self.seq2)
self.assertEqual(rga, [['AT', 'AT'], ['CA', 'CA']])
seqs = BioSeq.read_fasta_file('tests/files/protein_sequences.fas')
ga_score, ga_trace, _ = local_align_multiple_solutions(
seqs['sp|C1F111'], seqs['sp|B7JC18'], self.sm, -3)
rga = recover_local_align_multiple_solutions(ga_score, ga_trace,
seqs['sp|C1F111'],
seqs['sp|B7JC18'])
# 4 local optimal alignments between sp|C1F111 & sp|B7JC18
self.assertEqual(len(rga), 4)
print('>> Passed test_recover_local_align_multiple_solutions()')
def test_compare_pairwise_num_local_align(self):
seqs = list(
BioSeq.read_fasta_file(
'tests/files/protein_sequences.fas').values())
cla = compare_pairwise_num_local_align(seqs, self.sm, -3)
# Some random values
self.assertEqual(
cla[4][3],
4) # Between sp|C1F111 & sp|B7JC18 - matches previous test
self.assertEqual(cla[0][0], 1)
self.assertEqual(cla[9][6], 144)
self.assertEqual(cla[8][10], 1152)
print('>> Passed test_compare_num_pairwise_local_align()')
def test_recover_global_align_multiple_solutions(self):
_, ga_trace = global_align_multiple_solutions(self.slides_seq1,
self.slides_seq2,
self.sm, -3)
rga = recover_global_align_multiple_solutions(ga_trace,
self.slides_seq1,
self.slides_seq2)
seq1_alignments = [align[0] for align in rga]
seq2_alignments = [align[1] for align in rga]
# Classes Example
self.assertTrue('-HGWAG' in seq1_alignments)
self.assertTrue('PHSW-G' in seq2_alignments)
# C2 example
_, ga_trace = global_align_multiple_solutions(self.seq1, self.seq2,
self.sm_dna, -1)
rga = recover_global_align_multiple_solutions(ga_trace, self.seq1,
self.seq2)
seq1_alignments = [align[0] for align in rga]
seq2_alignments = [align[1] for align in rga]
self.assertEqual(len(seq1_alignments), 3)
self.assertTrue('G-ATTACA' in seq1_alignments)
self.assertTrue('GCA-TGCT' in seq2_alignments)
self.assertTrue('GCAT-GCT' in seq2_alignments)
self.assertTrue('GCATG-CT' in seq2_alignments)
seqs = BioSeq.read_fasta_file('tests/files/protein_sequences.fas')
_, ga_trace = global_align_multiple_solutions(seqs['sp|C1F111'],
seqs['sp|B7JC18'],
self.sm, -3)
rga = recover_global_align_multiple_solutions(ga_trace,
seqs['sp|C1F111'],
seqs['sp|B7JC18'])
# 5760 global optimal alignments between sp|C1F111 & sp|B7JC18
self.assertEqual(len(rga), 5760)
print('>> Passed test_recover_global_align_multiple_solutions()')
print('Seq1: ' + str(align[0]) + '\nSeq2: ' + str(align[1]) + '\n')
wait_input()
print("\n-------------------------\n")
print("Now shall we make it a little bit more complex?\n")
wait_input()
print(
"So, lets load and use the proteins present in the 'tests/files/protein_sequences.fas' file!\n\
We need to use the read fasta functionality from the bioseq library to load them.\n"
)
wait_input()
print("The protein sequences are:\n")
seqs = BioSeq.read_fasta_file('tests/files/protein_sequences.fas')
for key, value in seqs.items():
print("> " + str(key) + ": " + str(value) + "\n")
wait_input()
print("::: GLOBAL ALIGNMENT with multiple solutions :::\n")
print(
"\nLets make the global alignment with two of our protein sequences: sp|B0C882: & sp|A1TQI0, the 'sm_dna' and a gap of -3, shall we?\n"
)
p_seq1 = seqs["sp|B0C882"]
p_seq2 = seqs["sp|A1TQI0"]
wait_input()
ga_score, ga_trace = global_align_multiple_solutions(
p_seq1, p_seq2, sm_blosum, -3)
print("Score matrix obtained:\n")