def it_generates_flu_info():
with tmp.tmp_folder(chdir=True):
prep_result = PrepResult.prep_result_fixture(
pros=[".", "XAXCD", "XAXCDXX", "XCCXX"],
pro_is_decoys=[False, False, False, False],
peps=[".", "XAXCD", "XAXCDXX", "XCCXX"],
pep_pro_iz=[0, 1, 2, 3],
)
sim_params = _stub_sim_params(some_error_model, n_samples)
sim_result = sim_v1_worker.sim_v1(sim_params, prep_result)
sim_result._generate_flu_info(prep_result)
def it_computes_head_and_tail():
_flus = sim_result._flus
assert np.all(_flus[_flus.pep_i.isin([1, 2])].flu_count == 2)
assert np.all(_flus[_flus.pep_i.isin([1, 2])].n_head_ch_0 == 1)
assert np.all(_flus[_flus.pep_i.isin([1, 2])].n_head_ch_1 == 0)
assert np.all(_flus[_flus.pep_i.isin([1, 2])].n_tail_ch_0 == 0)
assert np.all(_flus[_flus.pep_i.isin([1, 2])].n_tail_ch_1 == 1)
assert np.all(_flus[_flus.pep_i == 3].flu_count == 1)
def it_peps__flus():
df = sim_result.peps__flus(prep_result)
assert "flustr" in df
assert len(df) == 4
def it_peps__flus__unique_flus():
df = sim_result.peps__flus__unique_flus(prep_result)
assert np.all(df.pep_i.values == [0, 3])
zest()
def it_drop_all_darks():
with tmp.tmp_folder(chdir=True):
prep_result = PrepResult.prep_result_fixture(
pros=[".", "DD", "EE"],
pro_is_decoys=[False, False, False],
peps=[".", "DD", "EE"],
pep_pro_iz=[0, 1, 2],
)
n_peptides = 3
sim_params = _stub_sim_params(no_error_model, n_samples)
sim_result = sim_v1_worker.sim_v1(sim_params, prep_result)
assert sim_result.test_dyemat.shape == (
0,
n_channels,
n_cycles,
)
assert sim_result.test_dyemat.dtype == np.uint8
assert np.all(sim_result.test_dyemat[:] == 0) # All dark
assert sim_result.train_dyemat.shape == (
1,
n_channels,
n_cycles,
)
assert sim_result.train_dyemat.dtype == np.uint8
assert np.all(sim_result.train_pep_recalls[:] == 0.0)
def start(self):
sim_params = SimV1Params(include_dfs=True, **self.config.parameters)
prep_result = PrepResult.load_from_folder(self.inputs.prep)
sim_result = sim_v1(
sim_params, prep_result, progress=self.progress, pipeline=self
)
sim_result._generate_flu_info(prep_result)
sim_result.save()
def result_from_prep_fixture(prep_result, labels, n_edmans=5, error_model=None):
labels = labels.split(",")
n_labels = len(labels)
if error_model is None:
error_model = ErrorModel.from_defaults(n_labels)
sim_v1_params = SimV1Params.from_aa_list_fixture(
labels, error_model=error_model, n_pres=1, n_mocks=0, n_edmans=n_edmans,
)
return sim_v1_worker.sim_v1(sim_v1_params, prep_result)
def it_surveys():
with tmp.tmp_folder(chdir=True):
n_samples = 1
sim_params = _stub_sim_params(some_error_model, n_samples)
sim_params.is_survey = True
sim_params.n_samples_train = n_samples
sim_params.n_samples_test = None
sim_result = sim_v1_worker.sim_v1(sim_params, prep_result)
assert sim_result.train_dyemat.shape == (
n_peptides * n_samples,
n_channels,
n_cycles,
)
assert sim_result.train_dyemat.dtype == np.uint8
assert sim_result.test_dyemat is None
def it_raises_if_train_and_test_identical():
with tmp.tmp_folder(chdir=True):
with zest.raises(in_message="are identical"):
sim_params = _stub_sim_params(no_error_model, n_samples)
sim_v1_worker.sim_v1(sim_params, prep_result)
def it_removes_decoys_for_test():
with tmp.tmp_folder(chdir=True):
sim_params = _stub_sim_params(some_error_model, n_samples)
sim_result = sim_v1_worker.sim_v1(sim_params, prep_result)
assert not np.any(sim_result.test_true_pep_iz == 4)
