def it_returns_the_fraction_of_all_dark_samples():
with tmp.tmp_folder(chdir=True):
n_samples = 5000
sim_params = _stub_sim_params(
ErrorModel.from_defaults(n_channels=2), n_samples)
prep_result = PrepResult.stub_prep_result(
pros=[".", "ABCDEFGHI"],
pro_is_decoys=[False, False],
peps=[".", "ABB"],
pep_pro_iz=[0, 1],
)
pep_seq_df = prep_result.pepseqs()
dyemat, radmat, recall = _make_arrays("test1",
n_peps=2,
n_samples=n_samples)
sim_worker._do_pep_sim(
pep_seq_df[pep_seq_df.pep_i == 1],
sim_params,
n_samples=n_samples,
output_dyemat=dyemat,
output_radmat=radmat,
output_recall=recall,
)
assert np.all((0.9 < recall[1]) & (recall[1] < 1.0))
def it_computes_p_bright_from_product():
error_model = ErrorModel.no_errors(n_channels=2)
error_model.labels[0].p_failure_to_bind_amino_acid = 0.9
error_model.labels[1].p_failure_to_bind_amino_acid = 0.8
error_model.labels[0].p_failure_to_attach_to_dye = 0.7
error_model.labels[1].p_failure_to_attach_to_dye = 0.6
error_model.dyes[0].p_non_fluorescent = 0.5
error_model.dyes[1].p_non_fluorescent = 0.4
sim_params = SimParams.construct_from_aa_list(("A", "C"),
error_model=error_model,
n_edmans=3)
flu, p_bright = sim_worker._step_1_create_flu_and_p_bright(
pep_seq_df, sim_params)
assert flu.shape == (2, 4)
expected = np.array([
[
((1 - 0.9) * (1 - 0.7) * (1 - 0.5)),
0,
0,
0,
],
[
0,
0,
((1 - 0.8) * (1 - 0.6) * (1 - 0.4)),
0,
],
])
assert np.allclose(p_bright, expected)
def zest_step_5_make_radmat():
# fmt: off
dyemat = npf([
[
[2, 1],
[2, 1],
],
[
[0, 0],
[0, 0],
],
])
sim_params = SimParams.construct_from_aa_list(
["DE", "C"],
error_model=ErrorModel.no_errors(n_channels=2, beta=7500.0,
sigma=0.16),
n_pres=1,
n_mocks=0,
n_edmans=1,
)
radmat = sim_worker._step_5_make_radmat(dyemat, sim_params)
def it_makes_radmat():
assert np.all(radmat[0] > 4000.0)
def it_deals_with_zeros():
assert np.all(radmat[1] == 0.0)
# fmt: on
zest()
def it_labels_in_tail():
sim_params = SimParams.construct_from_aa_list(
("A", "C"),
error_model=ErrorModel.no_errors(n_channels=2),
n_edmans=6,
)
pep_seq_df = pd.DataFrame(
[
(1, "B", 0),
(1, "B", 1),
(1, "B", 2),
(1, "B", 3),
(1, "A", 4),
(1, "C", 5),
],
columns=PrepResult.pep_seqs_columns,
)
flu, p_bright = sim_worker._step_1_create_flu_and_p_bright(
pep_seq_df, sim_params)
assert np.all(flu == [
[0, 0, 0, 0, 1, 0, 0],
[0, 0, 0, 0, 0, 1, 0],
])
assert np.all(p_bright == [
[0, 0, 0, 0, 1, 0, 0],
[0, 0, 0, 0, 0, 1, 0],
])
def _before():
nonlocal sim_params
sim_params = SimParams.construct_from_aa_list(
["DE", "C"],
error_model=ErrorModel.no_errors(n_channels=2, beta=7500.0),
n_pres=0,
n_mocks=1,
n_edmans=1,
)
def it_extends_short_peptides():
sim_params = SimParams.construct_from_aa_list(
("A", "C"),
error_model=ErrorModel.no_errors(n_channels=2),
n_edmans=6,
)
flu, p_bright = sim_worker._step_1_create_flu_and_p_bright(
pep_seq_df, sim_params)
assert flu.shape == (2, 7)
assert np.all(flu[:, 3:] == 0.0)
def it_copies():
error_model = ErrorModel.from_defaults(n_channels=2)
src_params = SimParams.construct_from_aa_list(["DE", "Y"],
error_model=error_model)
src_params._build_join_dfs()
src_bleach = src_params.error_model.dyes[0].p_bleach_per_cycle
dst_params = src_params.copy()
dst_params.error_model.set_dye_param("p_bleach_per_cycle", 1.0)
_src_bleach = src_params.error_model.dyes[0].p_bleach_per_cycle
_dst_bleach = dst_params.error_model.dyes[0].p_bleach_per_cycle
assert _src_bleach == src_bleach
assert _dst_bleach == 1.0
def copy(self):
# REMOVE everything that _build_join_dfs put in
utils.safe_del(self, "df")
utils.safe_del(self, "by_channel")
utils.safe_del(self, "ch_by_aa")
utils.safe_del(self, "channel_i_to_gain")
utils.safe_del(self, "channel_i_to_vpd")
dst = utils.munch_deep_copy(self, klass_set={SimParams})
dst.error_model = ErrorModel(**dst.error_model)
assert isinstance(dst, SimParams)
return dst
def sim(aa_list, err_set, **sim_kws):
if isinstance(err_set, ErrorModel):
error_model = err_set
else:
error_model = ErrorModel.from_err_set(err_set)
assert sim_kws.get("n_edmans", 0) > 1
n_pres = sim_kws.get("n_pres", 0)
n_mocks = sim_kws.get("n_mocks", 0)
assert (
n_pres + n_mocks >= 1
), "You must include at least 1 pre or mock cycle to capture the initial image"
return Munch(
sim=Munch(
version="1.0",
inputs=Munch(prep="../prep"),
parameters=Munch(
**SimParams.construct_from_aa_list(
aa_list, error_model=error_model, include_dfs=False, **sim_kws
)
),
)
)
)
from plaster.tools.schema import check
def _stub_sim_params(error_model, n_samples):
return SimParams.construct_from_aa_list(
["A", "C"],
error_model=error_model,
n_samples=n_samples,
n_pres=1,
n_mocks=0,
n_edmans=2,
)
some_error_model = ErrorModel.no_errors(n_channels=2, sigma=0.16)
no_error_model = ErrorModel.no_errors(n_channels=2)
def _stub_dyemat_and_true():
dyemat = np.array([
[[2.0, 1.0, 0.0], [1.0, 1.0, 1.0]],
[[2.0, 1.0, 0.0], [1.0, 1.0, 1.0]],
[[2.0, 1.0, 0.0], [1.0, 1.0, 1.0]],
[[3.0, 2.0, 1.0], [2.0, 1.0, 0.0]],
[[3.0, 2.0, 1.0], [2.0, 1.0, 0.0]],
[[2.0, 1.0, 0.0], [1.0, 1.0, 1.0]],
[[0.1, 0.1, 0.0], [0.1, 0.1, 0.1]],
])
def __init__(self, include_dfs=True, **kwargs):
kwargs["error_model"] = kwargs.pop("error_model", ErrorModel())
super().__init__(**kwargs)
if include_dfs:
self._build_join_dfs()
def zest_step_1_create_flu():
sim_params = SimParams.construct_from_aa_list(
("A", "C"),
error_model=ErrorModel.no_errors(n_channels=2),
)
pep_seq_df = pd.DataFrame([
(1, "A", 0),
(1, "B", 1),
(1, "C", 2),
],
columns=PrepResult.pep_seqs_columns)
def it_return_flu_and_p_bright():
flu, p_bright = sim_worker._step_1_create_flu_and_p_bright(
pep_seq_df, sim_params)
assert np.all(flu == [
[
1,
0,
0,
],
[
0,
0,
1,
],
])
assert np.all(p_bright == [
[
1,
0,
0,
],
[
0,
0,
1,
],
])
def it_extends_short_peptides():
sim_params = SimParams.construct_from_aa_list(
("A", "C"),
error_model=ErrorModel.no_errors(n_channels=2),
n_edmans=6,
)
flu, p_bright = sim_worker._step_1_create_flu_and_p_bright(
pep_seq_df, sim_params)
assert flu.shape == (2, 7)
assert np.all(flu[:, 3:] == 0.0)
def it_computes_p_bright_from_product():
error_model = ErrorModel.no_errors(n_channels=2)
error_model.labels[0].p_failure_to_bind_amino_acid = 0.9
error_model.labels[1].p_failure_to_bind_amino_acid = 0.8
error_model.labels[0].p_failure_to_attach_to_dye = 0.7
error_model.labels[1].p_failure_to_attach_to_dye = 0.6
error_model.dyes[0].p_non_fluorescent = 0.5
error_model.dyes[1].p_non_fluorescent = 0.4
sim_params = SimParams.construct_from_aa_list(("A", "C"),
error_model=error_model,
n_edmans=3)
flu, p_bright = sim_worker._step_1_create_flu_and_p_bright(
pep_seq_df, sim_params)
assert flu.shape == (2, 4)
expected = np.array([
[
((1 - 0.9) * (1 - 0.7) * (1 - 0.5)),
0,
0,
0,
],
[
0,
0,
((1 - 0.8) * (1 - 0.6) * (1 - 0.4)),
0,
],
])
assert np.allclose(p_bright, expected)
def it_labels_in_tail():
sim_params = SimParams.construct_from_aa_list(
("A", "C"),
error_model=ErrorModel.no_errors(n_channels=2),
n_edmans=6,
)
pep_seq_df = pd.DataFrame(
[
(1, "B", 0),
(1, "B", 1),
(1, "B", 2),
(1, "B", 3),
(1, "A", 4),
(1, "C", 5),
],
columns=PrepResult.pep_seqs_columns,
)
flu, p_bright = sim_worker._step_1_create_flu_and_p_bright(
pep_seq_df, sim_params)
assert np.all(flu == [
[0, 0, 0, 0, 1, 0, 0],
[0, 0, 0, 0, 0, 1, 0],
])
assert np.all(p_bright == [
[0, 0, 0, 0, 1, 0, 0],
[0, 0, 0, 0, 0, 1, 0],
])
zest()