def create_adjusted_atlases(
linear: Model,
poly: Model,
ids: AnalysisIdentifiers,
atlas_indices: Optional[List[int]] = None,
free_text: str = "",
) -> List[str]:
"""
input:
linear_model: instance of class Model with first order model
poly_model: instance of class Model with second order model
ids: an AnalysisIds object matching the one used in the main notebook
atlas_indices: list of integers for which adjusted atlases to create
0: EMA_Unlab
1: QCv3_Unlab
2: ISv5_Unlab
3: ISv5_13C15N
4: IS_LabUnlab2
free_text: arbitrary string to append to atlas name
returns a list of the names of atlases
"""
# pylint: disable=too-many-locals
assert ids.chromatography in ["HILIC", "C18"]
default_atlas_indices = [0, 1] if ids.chromatography == "C18" else [0, 4]
atlas_indices = default_atlas_indices if atlas_indices is None else atlas_indices
plot_vars = [
(polarity, idx, model)
for polarity in ["positive", "negative"]
for idx in atlas_indices
for model in [linear, poly]
]
out_atlas_names = []
for polarity, idx, model in tqdm(plot_vars, unit="atlas"):
template_atlas = get_template_atlas(ids, polarity, idx)
out_atlas_names.append(get_atlas_name(template_atlas.name, ids, model, free_text))
logger.info("Creating atlas %s", out_atlas_names[-1])
out_atlas_file_name = os.path.join(ids.output_dir, f"{out_atlas_names[-1]}.csv")
out_atlas_df = adjust_atlas(template_atlas, model, ids)
write_utils.export_dataframe_die_on_diff(
out_atlas_df, out_atlas_file_name, "predicted atlas", index=False, float_format="%.6e"
)
dp.make_atlas_from_spreadsheet(
out_atlas_df,
out_atlas_names[-1],
filetype="dataframe",
sheetname="",
polarity=polarity,
store=True,
mz_tolerance=10 if ids.chromatography == "C18" else 12,
)
return out_atlas_names
def make_atlas_from_df(data: pd.DataFrame, name: str, polarity: str,
mz_tolerance: float) -> metob.Atlas:
atlas = dp.make_atlas_from_spreadsheet(data,
name,
filetype="dataframe",
polarity=polarity,
store=False,
mz_tolerance=mz_tolerance)
return fill_atlas_compound_fields(atlas)
def _clone_source_atlas(self) -> metob.Atlas:
logger.info("Retriving source atlas: %s", self.ids.source_atlas)
source_atlas = get_atlas(cast(AtlasName, self.ids.source_atlas),
cast(Username, "*"))
source_atlas_df = ma_data.make_atlas_df(source_atlas)
logger.info("Cloning atlas %s", self.ids.source_atlas)
return dp.make_atlas_from_spreadsheet(
source_atlas_df,
self.ids.atlas,
filetype="dataframe",
sheetname="",
polarity=self.ids.polarity,
store=True,
mz_tolerance=source_atlas.compound_identifications[0].
mz_references[0].mz_tolerance,
)
def test_make_atlas_from_spreadsheet(mocker, sqlite_with_atlas):
csv_data = pd.DataFrame({
"rt_min": [1.1],
"rt_peak": [1.3],
"rt_max": [1.5],
"mz": [234.6578]
})
mocker.patch("metatlas.plots.dill2plots._get_dataframe",
return_value=csv_data)
atlas = dill2plots.make_atlas_from_spreadsheet("foo.csv",
"test_atlas_99",
"csv",
polarity="positive",
mz_tolerance=5)
assert len(atlas.compound_identifications) == 1
assert atlas.compound_identifications[0].rt_references[0].rt_peak == 1.3
def generate_template_atlas(raw_file_name: str,
confidence_levels: List[str],
polarity: str,
name: str,
mz_tolerance: float = 10) -> metob.Atlas:
data = pd.read_csv(raw_file_name, sep="\t")
acceptable = data[data["confidence_category"].isin(confidence_levels)]
by_polarity = acceptable[acceptable["polarity"] == polarity]
by_polarity = by_polarity.assign(label=None)
atlas = dp.make_atlas_from_spreadsheet(by_polarity,
name,
filetype="dataframe",
polarity=polarity,
store=False,
mz_tolerance=mz_tolerance)
inchi_keys = [
cid.compound[0].inchi_key for cid in atlas.compound_identifications
]
pubchem_results = query_pubchem(inchi_keys)
for cid in atlas.compound_identifications:
fill_fields(cid.compound[0], pubchem_results)
cid.name = cid.compound[0].name
return atlas