def test_subset_positions_Alignment(self):
rna1 = RnaSequence("UCG", name="rna1")
rna2 = RnaSequence("YCG", name="rna2")
rna3 = RnaSequence("CAR", name="rna3")
sub_aln = Alignment([rna1, rna2, rna3], moltype=RNA)
obs_sub_aln = self.aln.take_positions([0, 1, 5])
self.assertEqual(obs_sub_aln, sub_aln)
self.assertNotEqual(obs_sub_aln, self.aln)
# string representations should be the same. This fails right
# now, because sequence order is not maintained. See separate test.
self.assertEqual(str(obs_sub_aln), str(sub_aln))
def test_seq_ungapping(self):
rna1 = RnaSequence("U-C-A-G-", name="rna1")
model1 = ArraySequence("U-C-A-G-",
name="rna1",
alphabet=RNA.alphabets.degen_gapped)
self.assertEqual(rna1, "U-C-A-G-")
self.assertEqual(rna1.degap(), "UCAG")
# check is produces the right string from the beginning
self.assertEqual(str(model1), "U-C-A-G-")
self.assertEqual(model1._data, [0, 4, 1, 4, 2, 4, 3, 4])
# ArraySequence should maybe have the same degap method as normal seq
self.assertEqual(str(model1.degap()), "UCAG")
def test_full(self):
"""RdbParser: full data, valid and invalid"""
# when only good record, should work independent of strict
r1 = RnaSequence(
"-??GG-UGAA--CGCU---ACGU-N???---",
info=Info({
"Species": "unidentified Thermus OPB AF027020",
"Refs": {
"rRNA": ["AF027020"]
},
"OriginalSeq": "-o[oGG-U{G}AA--C^GC]U---ACGU-Nooo---",
}),
)
r2 = RnaSequence(
"---CGAUCG--UAUACG-N???-",
info=Info({
"Species": "Thermus silvanus X84211",
"Refs": {
"rRNA": ["X84211"]
},
"OriginalSeq": "---CGAU[C(G){--UA}U]ACG-Nooo-",
}),
)
obs = list(RdbParser(RDB_LINES_ONLY_GOOD.split("\n"), strict=True))
self.assertEqual(len(obs), 2)
self.assertEqual(obs[0], r1)
self.assertEqual(str(obs[0]), str(r1))
self.assertEqual(obs[0].info, r1.info)
self.assertEqual(obs[1], r2)
self.assertEqual(str(obs[1]), str(r2))
self.assertEqual(obs[1].info, r2.info)
obs = list(RdbParser(RDB_LINES_ONLY_GOOD.split("\n"), strict=False))
self.assertEqual(len(obs), 2)
self.assertEqual(obs[0], r1)
self.assertEqual(str(obs[0]), str(r1))
self.assertEqual(obs[0].info, r1.info)
# when strict, should raise error on invalid record
f = RdbParser(RDB_LINES_GOOD_BAD.split("\n"), strict=True)
self.assertRaises(RecordError, list, f)
# when not strict, malicious record is skipped
obs = list(RdbParser(RDB_LINES_GOOD_BAD.split("\n"), strict=False))
self.assertEqual(len(obs), 2)
self.assertEqual(obs[0], r1)
self.assertEqual(str(obs[0]), str(r1))
self.assertEqual(obs[0].info, r1.info)
self.assertEqual(obs[1], r2)
self.assertEqual(str(obs[1]), str(r2))
self.assertEqual(obs[1].info, r2.info)
def test_subset_seqs_Alignment(self):
rna1 = RnaSequence("UCG", name="rna1")
rna2 = RnaSequence("YCG", name="rna2")
rna3 = RnaSequence("CAR", name="rna3")
sub_aln = Alignment([rna2, rna3], moltype=RNA)
aln = Alignment([rna1, rna2, rna3], moltype=RNA)
obs_sub_aln = aln.take_seqs(["rna2", "rna3"])
self.assertEqual(obs_sub_aln, sub_aln)
self.assertEqual(str(obs_sub_aln), str(sub_aln))
# Selected sequences should be in specified order?
obs_sub_aln_1 = self.aln.take_seqs(["rna3", "rna2"])
obs_sub_aln_2 = self.aln.take_seqs(["rna2", "rna3"])
self.assertNotEqual(str(obs_sub_aln_1), str(obs_sub_aln_2))
def test_feature_copy_annotations_to(self):
"""test correct copy of annotations"""
orig = DnaSequence("TTTTTTTTTTAAAA", name="Orig")
annot = orig.add_annotation(Feature, "exon", "fred", [(0, 14)])
seq = RnaSequence("UUUUUUUUUUAAAA", name="Test")
got = annot.copy_annotations_to(seq)
self.assertEqual(len(orig.annotations), len(got.annotations))
for src, dest in zip(orig.annotations, got.annotations):
self.assertEqual(src.get_coordinates(), dest.get_coordinates())
self.assertIsInstance(src, dest.__class__)
self.assertIs(dest.parent, seq)
with self.assertRaises(AssertionError):
_ = annot.copy_annotations_to(seq[:-2])
def setUp(self):
"""setUp method for all tests"""
# named sequences
self.rna1 = RnaSequence("UCAGGG", name="rna1")
self.rna2 = RnaSequence("YCU-RG", name="rna2")
self.rna3 = RnaSequence("CAA-NR", name="rna3")
self.model1 = ArraySequence("UCAGGG",
name="rna1",
alphabet=RNA.alphabets.degen_gapped)
self.model2 = ArraySequence("YCU-RG",
name="rna2",
alphabet=RNA.alphabets.degen_gapped)
self.model3 = ArraySequence("CAA-NR",
name="rna3",
alphabet=RNA.alphabets.degen_gapped)
self.aln = Alignment([self.rna1, self.rna2, self.rna3], moltype=RNA)
self.da = ArrayAlignment(
[self.model1, self.model2, self.model3],
moltype=RNA,
alphabet=RNA.alphabets.degen_gapped,
)
# seqs no name
self.nn_rna1 = RnaSequence("UCAGGG")
self.nn_rna2 = RnaSequence("YCU-RG")
self.nn_rna3 = RnaSequence("CAA-NR")
self.nn_model1 = ArraySequence("UCAGGG",
alphabet=RNA.alphabets.degen_gapped)
self.nn_model2 = ArraySequence("YCU-RG",
alphabet=RNA.alphabets.degen_gapped)
self.nn_model3 = ArraySequence("CAA-NR",
alphabet=RNA.alphabets.degen_gapped)
self.nn_aln = Alignment([self.nn_rna1, self.nn_rna2, self.nn_rna3],
moltype=RNA)
self.nn_da = ArrayAlignment(
[self.nn_model1, self.nn_model2, self.nn_model3],
moltype=RNA,
alphabet=RNA.alphabets.degen_gapped,
)