def test_allow_extended_3_letter_abbrv():
seq = minimal(
protein(
single_letter_protein=False,
allow_ambiguous=False,
allow_extended=True,
min_size=1,
max_size=1,
),
lambda x: x not in norm_AA.values(),
)
assert seq == "Asx"
def test_allow_ambiguous():
seq = minimal(
protein(
single_letter_protein=True,
allow_ambiguous=True,
allow_extended=False,
min_size=1,
max_size=1,
),
lambda x: x not in norm_AA.keys(),
)
assert seq == "X"
def test_max_size_3_letter_abbrv():
seq = minimal(protein(single_letter_protein=False, max_size=10))
assert len(seq) <= 30
assert len(seq) % 3 == 0
def test_2_mer():
assert minimal(protein(min_size=2)) == "AA"
def test_2_mer_3_letter_abbrv():
seq = minimal(protein(single_letter_protein=False, min_size=2))
assert len(seq) == 6
assert seq == "AlaAla"
def test_smallest_non_empty_example():
assert minimal(protein(min_size=1)) == "A"
def test_smallest_non_empty_example_3_letter_abbrv():
seq = minimal(protein(single_letter_protein=False, min_size=1))
assert len(seq) == 3
assert seq == "Ala"
def test_not_uppercase_only_3_letter_abbrv():
seq = minimal(
protein(single_letter_protein=False, uppercase_only=False, min_size=1),
# lambda x: all(not c.isupper() for c in x)
)
assert seq == "Ala"
def test_smallest_example_3_letter_abbrv():
assert minimal(protein(single_letter_protein=False)) == ""
def test_not_uppercase_only():
seq = minimal(
protein(single_letter_protein=True, uppercase_only=False, min_size=1),
lambda x: all(not c.isupper() for c in x),
)
assert seq == "a"
def test_smallest_example():
assert minimal(protein()) == ""
def test_uppercase_only_3_letter_abbrv():
seq = minimal(
protein(single_letter_protein=False, uppercase_only=True, min_size=1))
assert seq == "ALA"
def test_uppercase_only():
seq = minimal(
protein(single_letter_protein=True, uppercase_only=True, min_size=1))
assert seq == "A"
from hypothesis import given
from hypothesis_bio import protein
from .minimal import minimal
@given(protein())
def test_protein_type(seq):
assert type(seq) == str
def test_smallest_example():
assert minimal(protein()) == ""
def test_smallest_example_3_letter_abbrv():
assert minimal(protein(single_letter_protein=False)) == ""
def test_smallest_non_empty_example():
assert minimal(protein(min_size=1)) == "A"
def test_smallest_non_empty_example_3_letter_abbrv():
seq = minimal(protein(single_letter_protein=False, min_size=1))
assert len(seq) == 3
assert seq == "Ala"
def test_2_mer():
def test_fastq_entry_minimal_protein_source():
actual = minimal(fastq_entry(min_size=1, sequence_source=protein(min_size=1)))
expected = "@\nA\n+\n0"
assert actual == expected
import pytest
from hypothesis import given, settings
from hypothesis_bio import protein
from bio_embeddings.embed import EmbedderInterface, name_to_embedder
from tests.shared import check_embedding
# We need to create each embedder once for all hypothesis tests
# and destroy it before the next test so we don't run out of memory
# https://stackoverflow.com/a/44568273/3549270
@pytest.fixture(scope="session")
def cached_embedder(request) -> EmbedderInterface:
return request.param()
@pytest.mark.skipif(
not os.environ.get("RUN_VERY_SLOW_TESTS"),
reason="Hypothesis is the slowest of them all",
)
@pytest.mark.parametrize("cached_embedder",
name_to_embedder.values(),
indirect=True)
@settings(deadline=timedelta(seconds=10))
@given(sequence=protein(uppercase_only=True))
def test_foo(sequence, cached_embedder: EmbedderInterface):
embedding = cached_embedder.embed(sequence)
check_embedding(cached_embedder, embedding, sequence)
