Skip to content

Commit 11819d1

Browse files
committed
Remove obsolete dataset
1 parent b4e3212 commit 11819d1

File tree

1 file changed

+0
-54
lines changed

1 file changed

+0
-54
lines changed

chebai/preprocessing/datasets/tox21.py

Lines changed: 0 additions & 54 deletions
Original file line numberDiff line numberDiff line change
@@ -138,60 +138,6 @@ class Tox21Graph(Tox21Base):
138138
READER = dr.GraphReader
139139

140140

141-
class Tox21Bloat(Tox21Base):
142-
@property
143-
def _name(self):
144-
return "tox21bloat"
145-
146-
def _load_dict(self, input_file_path):
147-
with open(input_file_path, "r") as input_file:
148-
reader = csv.DictReader(input_file)
149-
for row in reader:
150-
smiles = row["smiles"]
151-
labels = [
152-
bool(int(l)) if l else None for l in (row[k] for k in self.HEADERS)
153-
]
154-
yield dict(
155-
features=smiles,
156-
labels=labels,
157-
group=row["mol_id"],
158-
additional_kwargs=dict(original=True),
159-
)
160-
try:
161-
mol = pysmiles.read_smiles(smiles)
162-
except:
163-
pass
164-
else:
165-
166-
def keyfunc(idx):
167-
"""
168-
pysmiles uses this method to determine possible starting points
169-
"""
170-
return (
171-
mol.degree(idx),
172-
# True > False
173-
mol.nodes[idx].get("element", "*") == "C",
174-
idx,
175-
)
176-
177-
possible_starts = list(sorted(mol.nodes, key=keyfunc))[1:11]
178-
for n in possible_starts:
179-
try:
180-
alt_smiles = pysmiles.write_smiles(mol, start=n)
181-
except:
182-
pass
183-
else:
184-
yield dict(
185-
features=alt_smiles,
186-
labels=labels,
187-
group=row["mol_id"],
188-
additional_kwargs=dict(original=False),
189-
)
190-
191-
192-
class Tox21BloatChem(Tox21Bloat):
193-
READER = dr.ChemDataReader
194-
195141

196142
class Tox21ExtendedChem(MergedDataset):
197143
MERGED = [Tox21Chem, Hazardous, JCIExtendedTokenData]

0 commit comments

Comments
 (0)