aprile.utils module
- aprile.utils.args_parse_pred(drug_index_1, drug_index_2, side_effect_index, n_drug, n_side_effect)
- Parameters
drug_index_1 – char ‘*’ or string of the format list of int, like 2,3,4
drug_index_2 – char ‘*’ or string of the format list of int
side_effect_index – char ‘*’ or string of the format list of int
- Returns
three lists of int
- aprile.utils.args_parse_train(drug_index_1, drug_index_2, side_effect_index, rg, et, idx)
- Parameters
drug_index_1 – char ‘*’ or string of the format list of int, like 2,3,4
drug_index_2 – char ‘*’ or string of the format list of int
side_effect_index – char ‘*’ or string of the format list of int
rg – int tensor of shape (n_side_effect, 2)
et – int tensor of shape (n_dd_edge)
idx – int tensor of shape (2, n_dd_edge)
- Returns
three lists of int
- aprile.utils.auprc_auroc_ap(target_tensor, score_tensor)
- aprile.utils.dense_id(n)
- aprile.utils.dict_ep_to_nparray(out_dict, epoch)
- aprile.utils.get_edge_index_from_coo(mat, bidirection)
- aprile.utils.get_indices_mask(indices, in_indices)
- aprile.utils.get_range_list(edge_list)
- aprile.utils.negative_sampling(pos_edge_index, num_nodes)
- aprile.utils.normalize(input)
- aprile.utils.process_edges(raw_edge_list, p=0.9)
- aprile.utils.remove_bidirection(edge_index, edge_type)
- aprile.utils.sparse_id(n)
- aprile.utils.to_bidirection(edge_index, edge_type=None)
- aprile.utils.typed_negative_sampling(pos_edge_index, num_nodes, range_list)
- aprile.utils.uniform(size, tensor)
- aprile.utils.visualize_graph(pp_idx, pp_weight, pd_idx, pd_weight, d1, d2, out_path, protein_name_dict=None, drug_name_dict=None, hiden=True, size=(40, 40))
- visualize Aprile-Exp’s outputs
use different color for pp and pd edges
annotate the weight of each edge near the edge (or annotate with the tranparentness of edges for each edge)
annotate the name of each node near the node, if name_dict=None, then annotate with node’s index
- Parameters
pp_idx (torch.Tensor) – integer tensor (2, n_pp_edges)
pp_weight (torch.Tensor) – float tensor (1, n_pp_edges), values with (0, 1)
pd_idx (torch.Tensor) – integer tensor (2, n_pd_edges)
pd_weight (torch.Tensor) – float tensor (1, n_pd_edges), values with (0, 1)
d1 (list) – drug list
d2 (list) – drug list pairing with d1
out_path (str) – output path
protein_name_dict (dict, optional) – the mapping for protein makers’ text. Defaults to None.
drug_name_dict (dict, optional) – the mapping for drug markers’ text. Defaults to None.
hiden (bool, optional) – if show related edge with edge weight of 0.01. Defaults to True.
size (tuple, optional) – the figure size. Defaults to (40, 40).
- Returns
the graph object matplotlib.pyplot.figure: the ploted figure
- Return type
networkx.Graph