def test_two_alignments_same_reference(self):
mut_df = pd.DataFrame([{
"mutated_seq": "AAAAAAAA",
"naive_seq": "AAAAAAAG",
"mutated_seq_id": "s1",
"mutation_index": 7,
"gl_base": "G",
"mutated_base": "A"
}])
r1 = SeqRecord("TTTT", name="r1")
r2 = SeqRecord("TAAAGAAA", name="r2")
kmer_dict = make_kmer_dictionary([r1, r2], k=3)
nalign = n_alignments_per_mutation(mut_df, kmer_dict, k=3)
# two templates for the mutation, both from r2
self.assertEqual(
nalign.loc[nalign.query_name == "s1", "n_alignments"].item(), 2)
def test_one_alignment(self):
mut_df = pd.DataFrame([{
"mutated_seq": "AAAAAAAA",
"naive_seq": "AAAAAAAG",
"mutated_seq_id": "s1",
"mutation_index": 7,
"gl_base": "G",
"mutated_base": "A"
}])
r1 = SeqRecord("TTTT", name="r1")
r2 = SeqRecord("TAAA", name="r2")
kmer_dict = make_kmer_dictionary([r1, r2], k=3)
nalign = n_alignments_per_mutation(mut_df, kmer_dict, k=3)
# there is one AAA sequence in r1 that could serve as a
# template for the mutation
self.assertEqual(
nalign.loc[nalign.query_name == "s1", "n_alignments"].item(), 1)
def test_no_alignments(self):
mut_df = pd.DataFrame([{
"mutated_seq": "AAAAAAAA",
"naive_seq": "AAAAAAAG",
"mutated_seq_id": "s1",
"mutation_index": 7,
"gl_base": "G",
"mutated_base": "A"
}])
r1 = SeqRecord("TTTT", name="r1")
r2 = SeqRecord("TCTC", name="r2")
kmer_dict = make_kmer_dictionary([r1, r2], k=3)
nalign = n_alignments_per_mutation(mut_df, kmer_dict, k=3)
# there are no AAA sequences in the references (r1 and r2), so
# we should get no alignments
self.assertEqual(
nalign.loc[nalign.query_name == "s1", "n_alignments"].item(), 0)