dataset_qm9: QM9 Small Molecule Chemical Dataset

In rdinnager/rspektral: What the Package Does (One Line, Title Case)

Description

Loads the QM9 chemical data set of small molecules. Nodes represent heavy atoms (hydrogens are discarded), edges represent chemical bonds. The node features represent the chemical properties of each atom, and are loaded according to the nf_keys argument. See rspektral_datasets$qm9$NODE_FEATURES for possible node features, and see this link for the meaning of each property. Usually, it is sufficient to load the atomic number. The edge features represent the type and stereoscopy of each chemical bond between two atoms. See rspektral_datasets$qm9$EDGE_FEATURES for possible edge features, and see this link for the meaning of each property. Usually, it is sufficient to load the type of bond.

Usage

dataset_qm9(
  nf_keys = NULL,
  ef_keys = NULL,
  auto_pad = TRUE,
  self_loops = FALSE,
  amount = NULL,
  return_type = "numpy"
)

Arguments

nf_keys	list or str, node features to return (see rspektral_datasets$qm9$NODE_FEATURES for available features);
ef_keys	list or str, edge features to return (see rspektral_datasets$qm9$EDGE_FEATURES for available features);
auto_pad	if return_type='numpy', zero pad graph matrices to have the same number of nodes
amount	the amount of molecules to return (in ascending order by number of atoms).
return_type	Data format to return data in. One of either "list", or "tidygraph"
self_loops:	add self loops to adjacency matrices

Value

• if return_type='list', a list of the adjacency matrix, node features, edge features, and a dataframe containing labels

• if return_type="tidygraph, a list tidygraph objects with node and edge features as node and edge data columns, labels will be the names of the lists's elements

rdinnager/rspektral documentation built on June 12, 2021, 1:26 a.m.