torch_geometric.datasets.AQSOL

class AQSOL(root: str, split: str = 'train', transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None, pre_filter: Optional[Callable] = None)[source]

Bases: InMemoryDataset

The AQSOL dataset from the Benchmarking Graph Neural Networks paper based on AqSolDB, a standardized database of 9,982 molecular graphs with their aqueous solubility values, collected from 9 different data sources.

The aqueous solubility targets are collected from experimental measurements and standardized to LogS units in AqSolDB. These final values denote the property to regress in the AQSOL dataset. After filtering out few graphs with no bonds/edges, the total number of molecular graphs is 9,833. For each molecular graph, the node features are the types of heavy atoms and the edge features are the types of bonds between them, similar as in the ZINC dataset.

Parameters

  • root (str) – Root directory where the dataset should be saved.

  • split (str, optional) – If "train", loads the training dataset. If "val", loads the validation dataset. If "test", loads the test dataset. (default: "train")

  • transform (callable, optional) – A function/transform that takes in an torch_geometric.data.Data object and returns a transformed version. The data object will be transformed before every access. (default: None)

  • pre_transform (callable, optional) – A function/transform that takes in an torch_geometric.data.Data object and returns a transformed version. The data object will be transformed before being saved to disk. (default: None)

  • pre_filter (callable, optional) – A function that takes in an torch_geometric.data.Data object and returns a boolean value, indicating whether the data object should be included in the final dataset. (default: None)

STATS:

#graphs

#nodes

#edges

#features

#classes

9,833

~17.6

~35.8

1

1