def test_from_df_pop_mol_column():
df = dm.data.freesolv().iloc[:10] # type: ignore
mols = [dm.to_mol(smiles) for smiles in df["smiles"]]
df: pd.DataFrame = dm.to_df(mols, mol_column="mol") # type: ignore
df["dummy"] = "hello"
# test with provided mol column
mols = dm.from_df(df.copy(), mol_column="mol")
assert set(mols[0].GetPropsAsDict().keys()) == {"smiles", "dummy"}
# test with automatic mol column detection
mols = dm.from_df(df.copy())
assert set(mols[0].GetPropsAsDict().keys()) == {"smiles", "dummy"}
def test_to_image():
# Get a list of molecules
data = dm.data.freesolv()
mols = dm.from_df(data) # type: ignore
mols = mols[:8]
# With multiple molecules
legends = [dm.to_smiles(mol) for mol in mols]
image = dm.viz.to_image(mols, legends=legends, n_cols=4, mol_size=(200, 200))
# image = _convert_ipython_to_array(image)
image = np.array(image)
assert image.dtype == np.uint8
assert image.shape == (400, 800, 3)
assert image.shape[1] == 200 * 4
# With a single molecule
mol = mols[0]
legends = dm.to_smiles(mol)
image = dm.viz.to_image(mol, legends=legends, mol_size=(200, 200))
# image = _convert_ipython_to_array(image)
image = np.array(image)
assert image.dtype == np.uint8
assert image.shape == (200, 200, 3)
dm.viz.to_image(mol, indices=True, mol_size=400)
def test_to_df_smiles_warning(datadir, caplog):
data_path = datadir / "freesolv.csv"
df = dm.read_csv(data_path)
mols = dm.from_df(df, conserve_smiles=True)
df = dm.to_df(mols)
assert sum(df.columns == "smiles") == 2
assert "WARNING" in caplog.text
assert (
"The SMILES column name provided ('smiles') is already present in the properties of the molecules"
in caplog.text)
def test_from_df(datadir):
data_path = datadir / "TUBB3-observations.sdf"
df = dm.read_sdf(data_path, as_df=True)
mols = dm.from_df(df)
assert len(mols) == 10
assert isinstance(mols[0], Chem.rdchem.Mol)
assert set(mols[0].GetPropsAsDict().keys()) == {
"zinc_id",
"ortholog_name",
"gene_name",
"affinity",
"chembldocid",
"title",
"reference.pubmed_id",
"reference.doi",
"reference.chembl_id",
"reference.journal",
"reference.year",
}
assert dm.from_df(pd.DataFrame()) == []
def to_sdf(
mols: Union[Chem.rdchem.Mol, Sequence[Chem.rdchem.Mol], pd.DataFrame],
urlpath: Union[str, os.PathLike, TextIO],
smiles_column: Optional[str] = "smiles",
mol_column: str = None,
):
"""Write molecules to a file.
Args:
mols: a dataframe, a molecule or a list of molecule.
urlpath: Path to a file or a file-like object. Path can be remote or local.
smiles_column: Column name to extract the molecule.
mol_column: Column name to extract the molecule. It takes
precedence over `smiles_column`.
"""
if isinstance(mols, pd.DataFrame):
mols = dm.from_df(mols,
smiles_column=smiles_column,
mol_column=mol_column)
elif isinstance(mols, Chem.rdchem.Mol):
mols = [mols]
# Filter out None values
mols = [mol for mol in mols if mol is not None]
# File-like object
if isinstance(urlpath, io.IOBase):
writer = Chem.SDWriter(urlpath)
for mol in mols:
writer.write(mol)
writer.close()
# Regular local or remote paths
else:
with fsspec.open(urlpath, mode="w") as f:
writer = Chem.SDWriter(f)
for mol in mols:
writer.write(mol)
writer.close()
def test_from_df_conserve_smiles(datadir):
data_path = datadir / "freesolv.csv"
df = dm.read_csv(data_path)
mols = dm.from_df(df, conserve_smiles=True)
assert "smiles" in mols[0].GetPropsAsDict().keys()
