def test_init_minimal(self):
"""MolType should init OK with just monomers"""
a = MolType("Abc")
self.assertIn("A", a.alphabet)
self.assertNotIn("a", a.alphabet) # case-sensitive
self.assertIn("b", a.alphabet)
self.assertNotIn("B", a.alphabet)
self.assertNotIn("x", a.alphabet)
def test_init_minimal(self):
"""MolType should init OK with just monomers"""
a = MolType("Abc")
self.assertContains(a.alphabet, "A")
self.assertNotContains(a.alphabet, "a") # case-sensitive
self.assertContains(a.alphabet, "b")
self.assertNotContains(a.alphabet, "B")
self.assertNotContains(a.alphabet, "x")
def test_count_gaps(self):
"""MolType count_gaps should return correct gap count"""
c = RnaMolType.count_gaps
self.assertEqual(c(""), 0)
self.assertEqual(c("ACUGUCAGUACGHFSDKJCUICDNINS"), 0)
self.assertEqual(c("GUACGUIACAKJDC-SDFHJDSFK"), 1)
self.assertEqual(c("-DSHFUHDSF"), 1)
self.assertEqual(c("UACHASJAIDS-"), 1)
self.assertEqual(c("---CGAUgCAU---ACGHc---ACGUCAGU---"), 12)
a = MolType({"A": 1}, gaps=dict.fromkeys("!@#$%"))
c = a.count_gaps
self.assertEqual(c(""), 0)
self.assertEqual(c("!!!"), 3)
self.assertEqual(c("!@#$!@#$!@#$"), 12)
self.assertEqual(c("cguua!cgcuagua@cguasguadc#"), 3)
def test_gap_indices(self):
"""MolType gap_indices should return correct gap positions"""
g = RnaMolType.gap_indices
self.assertEqual(g(""), [])
self.assertEqual(g("ACUGUCAGUACGHFSDKJCUICDNINS"), [])
self.assertEqual(g("GUACGUIACAKJDC-SDFHJDSFK"), [14])
self.assertEqual(g("-DSHFUHDSF"), [0])
self.assertEqual(g("UACHASJAIDS-"), [11])
self.assertEqual(
g("---CGAUgCAU---ACGHc---ACGUCAGU---"),
[0, 1, 2, 11, 12, 13, 19, 20, 21, 30, 31, 32],
)
a = MolType({"A": 1}, gaps=dict.fromkeys("!@#$%"))
g = a.gap_indices
self.assertEqual(g(""), [])
self.assertEqual(g("!!!"), [0, 1, 2])
self.assertEqual(g("!@#$!@#$!@#$"), list(range(12)))
self.assertEqual(g("cguua!cgcuagua@cguasguadc#"), [5, 14, 25])
def test_init_everything(self):
"""MolType should init OK with all parameters set"""
k = dict.fromkeys
a = MolType(
k("Abc"),
ambiguities={"d": "bc"},
gaps=k("~"),
complements={"b": "c", "c": "b"},
pairs={},
add_lower=False,
)
for i in "Abcd~":
self.assertIn(i, a)
self.assertEqual(a.complement("b"), "c")
self.assertEqual(a.complement("AbcAA"), "AcbAA")
self.assertEqual(a.first_degenerate("AbcdA"), 3)
self.assertEqual(a.first_gap("a~c"), 1)
self.assertEqual(a.first_invalid("Abcx"), 3)
def test_iter(self):
"""MolType iter should iterate over monomer order"""
self.assertEqual(list(RnaMolType),
["U", "C", "A", "G", "u", "c", "a", "g"])
a = MolType("ZXCV")
self.assertEqual(list(a), ["Z", "X", "C", "V"])
__email__ = "*****@*****.**"
__status__ = "Production"
# ind some of the standard alphabets to reduce typing
RnaBases = RNA.alphabets.base
DnaBases = DNA.alphabets.base
AminoAcids = PROTEIN.alphabets.base
# the following classes are to preserve compatibility for older test code
# that assumes mixed-case is OK.
RnaMolType = MolType(
seq_constructor=sequence.RnaSequence,
motifset=IUPAC_RNA_chars,
ambiguities=IUPAC_RNA_ambiguities,
label="rna_with_lowercase",
mw_calculator=RnaMW,
complements=IUPAC_RNA_ambiguities_complements,
pairs=RnaStandardPairs,
add_lower=True,
preserve_existing_moltypes=True,
make_alphabet_group=True,
)
DnaMolType = MolType(
seq_constructor=sequence.DnaSequence,
motifset=IUPAC_DNA_chars,
ambiguities=IUPAC_DNA_ambiguities,
label="dna_with_lowercase",
mw_calculator=DnaMW,
complements=IUPAC_DNA_ambiguities_complements,
pairs=DnaStandardPairs,
add_lower=True,
preserve_existing_moltypes=True,
