def get_nonzero_feature_indices(self, node_idx):
""" Gets indices of the nonzero values in a one-hot encoded atomic feature
vector (for converting a feature vector into an `rdkit.Atom` object).
Args:
node_idx (int) : Index for a specific node in the `PreprocessingGraph`.
Returns:
segment_idc (list) : Contains the nonzero indices of the atom
type, formal charge, number of implicit Hs, and chirality that
describe a specific node in a feature vector. The indices are
"corrected" for each one-hot encoded segment of the feature vector.
"""
fv_idc = util.get_feature_vector_indices()
# **note: "idx" == "idx", "idc" == "indices"
idc = np.nonzero(self.node_features[node_idx])[0]
# correct for the concatenation of the different segments
# of each node feature vector
segment_idc = [idc[0]]
for idx, value in enumerate(idc[1:]):
segment_idc.append(value - fv_idc[idx])
return segment_idc
def get_node_feature_distribution(molecular_graphs):
""" Returns a `tuple` of histograms (`torch.Tensor`s) for atom types, formal
charges, number of implicit Hs, and chiral states that are present in the
input `molecular_graphs` (`list` of `MolecularGraph`s). Each histogram is a
`list` where the nth item corresponds to the count of the nth property in
`atom_types`, `formal_charge`, `imp_H`, and `chirality`, respectively.
"""
# sum up all node feature vectors to get an un-normalized histogram
if type(molecular_graphs[0].node_features) == torch.Tensor:
nodes_hist = torch.zeros(C.n_node_features, device="cuda")
else:
nodes_hist = np.zeros(C.n_node_features)
# loop over all the node feature matrices of the input `TrainingGraph`s
for molecular_graph in molecular_graphs:
try:
nodes_hist += torch.sum(molecular_graph.node_features, dim=0)
except TypeError:
nodes_hist += np.sum(molecular_graph.node_features, axis=0)
idc = util.get_feature_vector_indices() # **note: "idc" == "indices"
# split up `nodes_hist` into atom types hist, formal charge hist, etc
# `atom_type_histogram` and `formal_charge_histogram` are calculated by
# default, and if specified, also `numh_histogram` and `chirality_histogram`
atom_type_histogram = nodes_hist[:idc[0]]
formal_charge_histogram = nodes_hist[idc[0]:idc[1]]
if not C.use_explicit_H and not C.ignore_H:
numh_histogram = nodes_hist[idc[1]:idc[2]]
else:
numh_histogram = [0] * C.n_imp_H
if C.use_chirality:
correction = int(not C.use_explicit_H and not C.ignore_H)
chirality_histogram = nodes_hist[idc[1 + correction]:idc[2 +
correction]]
else:
chirality_histogram = [0] * C.n_chirality
return (atom_type_histogram, formal_charge_histogram, numh_histogram,
chirality_histogram)
def _get_node_feature_distribution(molecular_graphs : list) -> \
Tuple[Union[torch.Tensor, np.ndarray], ...]:
"""
Returns a `tuple` of histograms (`torch.Tensor`s) for atom types, formal charges,
number of implicit Hs, and chiral states that are present in the input
`molecular_graphs`. Each histogram is a `list` where the nth item corresponds to the
count of the nth property in `atom_types`, `formal_charge`, `imp_H`, and `chirality`.
"""
# sum up all node feature vectors to get an un-normalized histogram
if type(molecular_graphs[0].node_features) == torch.Tensor:
nodes_hist = torch.zeros(constants.n_node_features,
device=constants.device)
else:
nodes_hist = np.zeros(constants.n_node_features)
# loop over all the node feature matrices of the input `TrainingGraph`s
for molecular_graph in molecular_graphs:
try:
nodes_hist += torch.sum(molecular_graph.node_features,
dim=0)
except TypeError:
nodes_hist += np.sum(molecular_graph.node_features, axis=0)
idc = util.get_feature_vector_indices(
) # **note: "idc" == "indices"
# split up `nodes_hist` into atom types hist, formal charge hist, etc
atom_type_histogram = nodes_hist[:idc[0]]
formal_charge_histogram = nodes_hist[idc[0]:idc[1]]
if not constants.use_explicit_H and not constants.ignore_H:
numh_histogram = nodes_hist[idc[1]:idc[2]]
else:
numh_histogram = [0] * constants.n_imp_H
if constants.use_chirality:
correction = int(not constants.use_explicit_H
and not constants.ignore_H)
chirality_histogram = nodes_hist[
idc[1 + correction]:idc[2 + correction]]
else:
chirality_histogram = [0] * constants.n_chirality
return (atom_type_histogram, formal_charge_histogram,
numh_histogram, chirality_histogram)