def test_add_array_gap(self):
from multicov.binary import BinaryAlignment
from multicov.alphabet import dna_alphabet, rna_alphabet
bin_align = BinaryAlignment(
[[0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0]],
dna_alphabet,
include_gaps=True)
bin_align.add(
[[0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0]],
rna_alphabet)
self.assertSequenceEqual(bin_align.alphabets, [(dna_alphabet, 4),
(rna_alphabet, 4)])
self.assertTrue(
np.array_equal(
bin_align.data.todense(),
np.asmatrix([[
0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1,
0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1
],
[
0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0,
0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0,
0, 1, 0, 0, 0, 0, 0, 0, 0, 1
],
[
0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0,
0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0,
1, 0, 0, 0, 0, 0, 1, 0, 0, 0
]])))
def test_raise_on_add_wrong_width(self):
from multicov.binary import BinaryAlignment
from multicov.alphabet import protein_alphabet, rna_alphabet
bin_align = BinaryAlignment(
[[
0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
],
[
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
],
[
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
]], protein_alphabet)
data = np.asmatrix([[0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1]])
# don't raise on properly-sized data
try:
bin_align.add(data, rna_alphabet)
except ValueError:
self.fail(
"BinaryAlignment.add() raised ValueError on properly-sized data."
)
# raised on improperly-sized
with self.assertRaises(ValueError):
bin_align.add(data[:, :-1], rna_alphabet)
def test_set_default_reference_on_empty(self):
from multicov.binary import BinaryAlignment
from multicov.alignment import ReferenceMapping
from multicov.alphabet import rna_alphabet
bin_align = BinaryAlignment()
bin_align.add([[0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1]],
rna_alphabet)
self.assertEqual(bin_align.reference, ReferenceMapping(list(range(4))))
def test_add_to_empty(self):
from multicov.binary import BinaryAlignment
from multicov.alphabet import dna_alphabet
bin_align1 = BinaryAlignment(
[[0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1]], dna_alphabet)
bin_align2 = BinaryAlignment()
bin_align2.add(bin_align1)
self.assertEqual(bin_align1, bin_align2)
def test_equal_self_multi_alpha(self):
from multicov.binary import BinaryAlignment
from multicov.alphabet import rna_alphabet, dna_alphabet
bin_align = BinaryAlignment(
[[0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1]], dna_alphabet)
bin_align.add([[0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0]],
rna_alphabet)
self.assertTrue(bin_align == bin_align)
self.assertFalse(bin_align != bin_align)
def test_add_alignment_gap_to_gap(self):
from multicov.binary import BinaryAlignment
from multicov.alphabet import protein_alphabet, dna_alphabet
bin_align1 = BinaryAlignment(
[[
0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
],
[
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,
0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
],
[
1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
]],
protein_alphabet,
include_gaps=True)
bin_align2 = BinaryAlignment(
[[0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0]],
dna_alphabet,
include_gaps=True)
bin_align = BinaryAlignment(bin_align1)
bin_align.add(bin_align2)
self.assertNotEqual(bin_align, bin_align1)
self.assertNotEqual(bin_align, bin_align2)
self.assertSequenceEqual(bin_align.alphabets, [(protein_alphabet, 2),
(dna_alphabet, 4)])
self.assertTrue(
np.array_equal(
bin_align.data.todense(),
np.asmatrix([[
0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0,
0, 1
],
[
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,
0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,
0, 1
],
[
1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0,
0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0,
0, 0
]])))
def test_unequal_different_annotations(self):
from multicov.binary import BinaryAlignment
from multicov.alphabet import dna_alphabet, rna_alphabet
bin_align1 = BinaryAlignment(
[[0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1]], dna_alphabet)
bin_align1.add([[0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0]],
rna_alphabet)
bin_align2 = BinaryAlignment(bin_align1)
bin_align2.annotations['seqw'] = [0.5, 1.2]
bin_align2.annotations['fitness'] = [0, -1]
self.assertTrue(bin_align1 != bin_align2)
self.assertFalse(bin_align1 == bin_align2)
def test_raise_on_add_wrong_length(self):
from multicov.binary import BinaryAlignment
from multicov.alphabet import protein_alphabet, rna_alphabet
bin_align = BinaryAlignment(
[[
0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
],
[
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
],
[
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
]], protein_alphabet)
with self.assertRaises(ValueError):
bin_align.add([[0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1]],
rna_alphabet)
def test_return_self(self):
from multicov.binary import BinaryAlignment
from multicov.alphabet import dna_alphabet, rna_alphabet
bin_align = BinaryAlignment(
[[0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1],
[1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0]], dna_alphabet)
ret_align = bin_align.add(
[[0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1],
[1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0]], rna_alphabet)
self.assertIs(bin_align, ret_align)
def test_set_default_reference_on_nonempty(self):
from multicov.binary import BinaryAlignment
from multicov.alphabet import protein_alphabet, dna_alphabet
bin_align = BinaryAlignment(
[[
0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
],
[
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
],
[
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
]], protein_alphabet)
bin_align.add([[0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1],
[1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0]],
dna_alphabet)
self.assertEqual(len(bin_align.reference.seqs), 2)
self.assertSequenceEqual(bin_align.reference.seqs[1], list(range(4)))
def test_multi(self):
from multicov.binary import BinaryAlignment
from multicov.alphabet import protein_alphabet, dna_alphabet
bin_align = BinaryAlignment(
[[
0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
],
[
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
],
[
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
]], protein_alphabet)
bin_align.add([[0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1],
[1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0]],
dna_alphabet)
self.assertEqual(len(bin_align.alphabets), 2)
self.assertEqual(bin_align.alphabets[0], (protein_alphabet, 2))
self.assertEqual(bin_align.alphabets[1], (dna_alphabet, 4))
def test_unequal_different_alphabet_widths(self):
from multicov.binary import BinaryAlignment
from multicov.alphabet import rna_alphabet, dna_alphabet
bin_align1 = BinaryAlignment(
[[0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1]], dna_alphabet)
bin_align1.add([[0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0]],
rna_alphabet)
bin_align2 = BinaryAlignment([[0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0],
[0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0]],
dna_alphabet)
bin_align2.add(
[[0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0]],
rna_alphabet)
self.assertTrue(
np.array_equal(bin_align1.data.todense(),
bin_align2.data.todense()))
self.assertTrue(bin_align1 != bin_align2)
self.assertFalse(bin_align1 == bin_align2)