def test_strand_symmetry(self):
"""correctly compute test of strand symmetry"""
from cogent3 import get_moltype
from cogent3.core.alignment import Aligned
seq = DnaSequence("ACGGCTGAAGCGCTCCGGGTTTAAAACG")
ssym = seq.strand_symmetry(motif_length=1)
assert_allclose(ssym.observed.array, [[7, 5], [7, 9]])
assert_allclose(ssym.expected.array, [[6, 6], [8, 8]])
# RNA too
seq = seq.to_rna()
ssym = seq.strand_symmetry(motif_length=1)
assert_allclose(ssym.observed.array, [[7, 5], [7, 9]])
# Aligned
seq = DnaSequence("ACGGCTGAAGCGCTCCGGGTTTAAAACG")
m, s = seq.parse_out_gaps()
seq = Aligned(m, s)
ssym = seq.strand_symmetry(motif_length=1)
assert_allclose(ssym.observed.array, [[7, 5], [7, 9]])
with self.assertRaises(TypeError):
text = get_moltype("text")
m, s = text.make_seq(
"ACGGCTGAAGCGCTCCGGGTTTAAAACG").parse_out_gaps()
s.strand_symmetry(motif_length=1)
# with motif_length=2
seq = DnaSequence("AC GG CT GA AG CG CT CC GG GT TT AA AA CG".replace(
" ", ""))
ssym = seq.strand_symmetry(motif_length=2)
self.assertLessEqual(len(ssym.observed.keys()), 8)
assert_allclose(ssym.observed["AA"].to_array(), [2, 1])
assert_allclose(ssym.observed["CC"].to_array(), [1, 2])
def test_DnaSequence(self):
"""DnaSequence should behave as expected"""
x = DnaSequence("tcag")
# note: no longer preserves case
self.assertEqual(x, "TCAG")
x = DnaSequence("aaa") + DnaSequence("ccc")
# note: doesn't preserve case
self.assertEqual(x, "AAACCC")
assert x.moltype is DNA
self.assertRaises(AlphabetError, x.__add__, "z")
self.assertEqual(DnaSequence("TTTAc").rc(), "GTAAA")
def test_single_constructor(self):
"""RdbParser should use constructors if supplied"""
to_dna = lambda x, info: DnaSequence(str(x).replace("U", "T"), info=info)
f = list(RdbParser(self.oneseq, to_dna))
self.assertEqual(len(f), 1)
a = f[0]
self.assertEqual(a, "AGTCATCTAGATHCATHC")
self.assertEqual(
a.info, Info({"Species": "H.Sapiens", "OriginalSeq": "AGUCAUCUAGAUHCAUHC"})
)
def alternativeConstr(header_lines):
info = Info()
for line in header_lines:
all = line.strip().split(":", 1)
# strip out empty lines, lines without name, lines without
# colon
if not all[0] or len(all) != 2:
continue
name = all[0].upper()
value = all[1].strip().upper()
info[name] = value
return info
f = list(RdbParser(self.oneseq, to_dna, alternativeConstr))
self.assertEqual(len(f), 1)
a = f[0]
self.assertEqual(a, "AGTCATCTAGATHCATHC")
exp_info = Info(
{"OriginalSeq": "AGUCAUCUAGAUHCAUHC", "Refs": {}, "SEQ": "H.SAPIENS"}
)
self.assertEqual(
a.info,
Info({"OriginalSeq": "AGUCAUCUAGAUHCAUHC", "Refs": {}, "SEQ": "H.SAPIENS"}),
)
def test_to_html(self):
"""produce correct html formatted text"""
seq = DnaSequence("ACGGTGGGGGGGGG")
got = seq.to_html(wrap=50)
# ensure balanced tags are in the txt
for tag in [
"<style>", "</style>", "<div", "</div>", "<table>", "</table>"
]:
self.assertTrue(tag in got)
seq_row = ('<tr><td class="label">None</td>'
'<td><span class="A_dna">A</span>'
'<span class="C_dna">C</span>'
'<span class="G_dna">G</span>'
'<span class="G_dna">G</span>'
'<span class="T_dna">T</span>'
'<span class="G_dna">G</span>'
'<span class="G_dna">G</span>'
'<span class="G_dna">G</span>'
'<span class="G_dna">G</span>'
'<span class="G_dna">G</span>'
'<span class="G_dna">G</span>'
'<span class="G_dna">G</span>'
'<span class="G_dna">G</span>'
'<span class="G_dna">G</span></td></tr>')
self.assertTrue(seq_row in got)
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 Dna(seq, *args, **kwargs):
seq = seq.replace("u", "t")
seq = seq.replace("U", "T")
d = DnaSequence(seq, *args, **kwargs)
return d
def dnastrict(x, **kwargs):
try:
return DnaSequence(x, **kwargs)
except Exception:
raise RecordError("Could not convert sequence")
def test_to_html_deprecation_warning(self):
"""produce correct html formatted text"""
seq = DnaSequence("ACGGTGGGGGGGGG")
with self.assertWarns(DeprecationWarning):
seq.to_html(interleave_len=50)