Loading deepchem/data/data_loader.py +1 −1 Original line number Diff line number Diff line Loading @@ -714,7 +714,7 @@ class SDFLoader(DataLoader): def __init__(self, tasks: List[str], featurizer: Featurizer, sanitize: bool = True, sanitize: bool = False, log_every_n: int = 1000): """Initialize SDF Loader Loading deepchem/molnet/load_function/qm7_datasets.py +12 −1 Original line number Diff line number Diff line Loading @@ -22,7 +22,8 @@ class _QM7Loader(_MolnetLoader): dc.utils.data_utils.download_url(url=GDB7_URL, dest_dir=self.data_dir) dc.utils.data_utils.untargz_file( os.path.join(self.data_dir, "gdb7.tar.gz"), self.data_dir) loader = dc.data.SDFLoader(tasks=self.tasks, featurizer=self.featurizer) loader = dc.data.SDFLoader( tasks=self.tasks, featurizer=self.featurizer, sanitize=True) return loader.create_dataset(dataset_file, shard_size=8192) Loading Loading @@ -81,6 +82,16 @@ def load_qm7( save_dir: str a directory to save the dataset in Note ---- DeepChem 2.4.0 has turned on sanitization for SDF files by default. For the QM7 dataset, this means that calling this function will return 6838 compounds instead of 7160 in the source dataset file. This appears to be due to valence specification mismatches in the dataset that weren't caught in earlier more lax versions of RDKit. Note that this may subtly affect benchmarking results on this dataset. References ---------- .. [1] Rupp, Matthias, et al. "Fast and accurate modeling of molecular Loading deepchem/molnet/load_function/qm8_datasets.py +12 −1 Original line number Diff line number Diff line Loading @@ -24,7 +24,8 @@ class _QM8Loader(_MolnetLoader): dc.utils.data_utils.download_url(url=GDB8_URL, dest_dir=self.data_dir) dc.utils.data_utils.untargz_file( os.path.join(self.data_dir, "gdb8.tar.gz"), self.data_dir) loader = dc.data.SDFLoader(tasks=self.tasks, featurizer=self.featurizer) loader = dc.data.SDFLoader( tasks=self.tasks, featurizer=self.featurizer, sanitize=True) return loader.create_dataset(dataset_file, shard_size=8192) Loading Loading @@ -90,6 +91,16 @@ def load_qm8( save_dir: str a directory to save the dataset in Note ---- DeepChem 2.4.0 has turned on sanitization for SDF files by default. For the QM8 dataset, this means that calling this function will return 21747 compounds instead of 21786 in the source dataset file. This appears to be due to valence specification mismatches in the dataset that weren't caught in earlier more lax versions of RDKit. Note that this may subtly affect benchmarking results on this dataset. References ---------- .. [1] Blum, Lorenz C., and Jean-Louis Reymond. "970 million druglike Loading deepchem/molnet/load_function/qm9_datasets.py +7 −6 Original line number Diff line number Diff line Loading @@ -23,7 +23,8 @@ class _QM9Loader(_MolnetLoader): dc.utils.data_utils.download_url(url=GDB9_URL, dest_dir=self.data_dir) dc.utils.data_utils.untargz_file( os.path.join(self.data_dir, "gdb9.tar.gz"), self.data_dir) loader = dc.data.SDFLoader(tasks=self.tasks, featurizer=self.featurizer) loader = dc.data.SDFLoader( tasks=self.tasks, featurizer=self.featurizer, sanitize=True) return loader.create_dataset(dataset_file, shard_size=8192) Loading Loading @@ -103,11 +104,11 @@ def load_qm9( ---- DeepChem 2.4.0 has turned on sanitization for SDF files by default. For the QM9 dataset, this means that calling this function will return a list of 132480 compounds instead of 133885 in the source dataset file. This appears to be due to valence specification mismatches in the dataset that weren't caught in earlier more lax versions of RDKit. Note that this may subtly affect benchmarking results on this dataset. return 132480 compounds instead of 133885 in the source dataset file. This appears to be due to valence specification mismatches in the dataset that weren't caught in earlier more lax versions of RDKit. Note that this may subtly affect benchmarking results on this dataset. References ---------- Loading Loading
deepchem/data/data_loader.py +1 −1 Original line number Diff line number Diff line Loading @@ -714,7 +714,7 @@ class SDFLoader(DataLoader): def __init__(self, tasks: List[str], featurizer: Featurizer, sanitize: bool = True, sanitize: bool = False, log_every_n: int = 1000): """Initialize SDF Loader Loading
deepchem/molnet/load_function/qm7_datasets.py +12 −1 Original line number Diff line number Diff line Loading @@ -22,7 +22,8 @@ class _QM7Loader(_MolnetLoader): dc.utils.data_utils.download_url(url=GDB7_URL, dest_dir=self.data_dir) dc.utils.data_utils.untargz_file( os.path.join(self.data_dir, "gdb7.tar.gz"), self.data_dir) loader = dc.data.SDFLoader(tasks=self.tasks, featurizer=self.featurizer) loader = dc.data.SDFLoader( tasks=self.tasks, featurizer=self.featurizer, sanitize=True) return loader.create_dataset(dataset_file, shard_size=8192) Loading Loading @@ -81,6 +82,16 @@ def load_qm7( save_dir: str a directory to save the dataset in Note ---- DeepChem 2.4.0 has turned on sanitization for SDF files by default. For the QM7 dataset, this means that calling this function will return 6838 compounds instead of 7160 in the source dataset file. This appears to be due to valence specification mismatches in the dataset that weren't caught in earlier more lax versions of RDKit. Note that this may subtly affect benchmarking results on this dataset. References ---------- .. [1] Rupp, Matthias, et al. "Fast and accurate modeling of molecular Loading
deepchem/molnet/load_function/qm8_datasets.py +12 −1 Original line number Diff line number Diff line Loading @@ -24,7 +24,8 @@ class _QM8Loader(_MolnetLoader): dc.utils.data_utils.download_url(url=GDB8_URL, dest_dir=self.data_dir) dc.utils.data_utils.untargz_file( os.path.join(self.data_dir, "gdb8.tar.gz"), self.data_dir) loader = dc.data.SDFLoader(tasks=self.tasks, featurizer=self.featurizer) loader = dc.data.SDFLoader( tasks=self.tasks, featurizer=self.featurizer, sanitize=True) return loader.create_dataset(dataset_file, shard_size=8192) Loading Loading @@ -90,6 +91,16 @@ def load_qm8( save_dir: str a directory to save the dataset in Note ---- DeepChem 2.4.0 has turned on sanitization for SDF files by default. For the QM8 dataset, this means that calling this function will return 21747 compounds instead of 21786 in the source dataset file. This appears to be due to valence specification mismatches in the dataset that weren't caught in earlier more lax versions of RDKit. Note that this may subtly affect benchmarking results on this dataset. References ---------- .. [1] Blum, Lorenz C., and Jean-Louis Reymond. "970 million druglike Loading
deepchem/molnet/load_function/qm9_datasets.py +7 −6 Original line number Diff line number Diff line Loading @@ -23,7 +23,8 @@ class _QM9Loader(_MolnetLoader): dc.utils.data_utils.download_url(url=GDB9_URL, dest_dir=self.data_dir) dc.utils.data_utils.untargz_file( os.path.join(self.data_dir, "gdb9.tar.gz"), self.data_dir) loader = dc.data.SDFLoader(tasks=self.tasks, featurizer=self.featurizer) loader = dc.data.SDFLoader( tasks=self.tasks, featurizer=self.featurizer, sanitize=True) return loader.create_dataset(dataset_file, shard_size=8192) Loading Loading @@ -103,11 +104,11 @@ def load_qm9( ---- DeepChem 2.4.0 has turned on sanitization for SDF files by default. For the QM9 dataset, this means that calling this function will return a list of 132480 compounds instead of 133885 in the source dataset file. This appears to be due to valence specification mismatches in the dataset that weren't caught in earlier more lax versions of RDKit. Note that this may subtly affect benchmarking results on this dataset. return 132480 compounds instead of 133885 in the source dataset file. This appears to be due to valence specification mismatches in the dataset that weren't caught in earlier more lax versions of RDKit. Note that this may subtly affect benchmarking results on this dataset. References ---------- Loading
