def test_rts04(analysis_ids, sqlite_with_atlas, mocker, lcmsrun, df_container):
mocker.patch(
"metatlas.io.metatlas_get_data_helper_fun.df_container_from_metatlas_file",
return_value=df_container)
mocker.patch("metatlas.plots.dill2plots.get_metatlas_files",
return_value=[lcmsrun])
first = mads.MetatlasDataset(ids=analysis_ids)
first.set_rt(0, "rt_max", 1.11)
second = mads.MetatlasDataset(ids=analysis_ids)
assert second.rts[0].rt_max == 1.11
second.set_rt(0, "rt_max", 2.22)
third = mads.MetatlasDataset(ids=analysis_ids)
assert third.rts[0].rt_max == 2.22
def test_get_atlas03(mocker, analysis_ids, caplog, username):
mocker.patch("metatlas.datastructures.metatlas_objects.retrieve",
return_value=[0, 0])
with pytest.raises(ValueError):
mads.MetatlasDataset(ids=analysis_ids)
atlas = f"505892_OakGall_final_FinalEMA-HILIC_POS_{username}_0_0"
assert f"2 atlases with name {atlas} and owned by {username} already exist." in caplog.text
def test_get_atlas02(mocker, analysis_ids, caplog):
mocker.patch("metatlas.datastructures.metatlas_objects.retrieve",
return_value=[])
caplog.set_level(logging.INFO)
with pytest.raises(ValueError):
mads.MetatlasDataset(ids=analysis_ids)
assert "Database does not contain an atlas" in caplog.text
def test_metatlas_dataset_build02(mocker, atlas, group_with_2_lcmsruns,
df_container, analysis_ids):
# need to mock multiprocessing for this to work
mocker.patch(
"metatlas.io.metatlas_get_data_helper_fun.df_container_from_metatlas_file",
return_value=df_container)
metatlas_dataset = mads.MetatlasDataset(ids=analysis_ids, max_cpus=2)
assert len(metatlas_dataset) == 2
assert len(metatlas_dataset[0]) == 1
def test_get_atlas01(mocker, analysis_ids, df_container, lcmsrun, atlas,
username):
mocker.patch(
"metatlas.io.metatlas_get_data_helper_fun.df_container_from_metatlas_file",
return_value=df_container)
mocker.patch("metatlas.plots.dill2plots.get_metatlas_files",
return_value=[lcmsrun])
mocker.patch("glob.glob", return_value=range(10))
metatlas_dataset = mads.MetatlasDataset(ids=analysis_ids)
assert metatlas_dataset.atlas.name == f"505892_OakGall_final_FinalEMA-HILIC_POS_{username}_0_0"
def pre_process_data_for_all_notebooks(
ids: AnalysisIdentifiers,
atlases: Sequence[str],
cpus: int,
use_poly_model: bool,
num_points: Optional[int],
peak_height: Optional[float],
msms_score: Optional[float],
) -> None:
"""
inputs:
ids: an AnalysisIds object matching the one used in the main notebook
atlases: list of atlas names to consider generating hits for
cpus: max number of cpus to use
use_poly_model: If True, use the polynomial model, else use linear model
Both types of models are always generated, this only determines which ones
are pre-populated into the generated notebooks
num_points: minimum number of data points in a peak
peak_height: threshold intensity level for filtering
msms_score: minimum spectra similarity score to pass filtering
Calls MetatlasDataset().hits, which will create a hits cache file
Filters compounds by signal strength to reduce atlas size
"""
for atlas_name in atlases:
if (use_poly_model and "linear" in atlas_name) or (not use_poly_model and "polynomial" in atlas_name):
continue
current_ids = AnalysisIdentifiers(
source_atlas=atlas_name,
experiment=ids.experiment,
output_type=get_output_type(ids.chromatography, atlas_name),
polarity="positive" if "_POS_" in atlas_name else "negative",
analysis_number=ids.analysis_number,
project_directory=ids.project_directory,
google_folder=ids.google_folder,
rt_predict_number=ids.rt_predict_number,
)
metatlas_dataset = mads.MetatlasDataset(ids=current_ids, max_cpus=cpus)
if current_ids.output_type == "ISTDsEtc":
generate_qc_plots(metatlas_dataset, current_ids)
_ = metatlas_dataset.hits
if "EMA" in current_ids.output_type:
metatlas_dataset.filter_compounds_by_signal(num_points, peak_height, msms_score)
def test_rts03(metatlas_dataset, analysis_ids):
assert metatlas_dataset.rts[0].rt_max != 9.99
metatlas_dataset.set_rt(0, "rt_max", 9.99)
second_metatlas_dataset = mads.MetatlasDataset(ids=analysis_ids)
assert second_metatlas_dataset.rts[0].rt_max == 9.99
assert len(second_metatlas_dataset.rts) == 1