-
Notifications
You must be signed in to change notification settings - Fork 0
/
utils.py
154 lines (129 loc) · 6.26 KB
/
utils.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
import os
from torch_geometric.data import InMemoryDataset, DataLoader, Batch
from torch_geometric import data as DATA
import torch
import torch.nn as nn
# initialize the dataset
class DTADataset(InMemoryDataset):
def __init__(self, root='/tmp', dataset='davis',
xd=None, y=None, transform=None,
pre_transform=None, smile_graph=None, target_key=None, target_graph=None):
super(DTADataset, self).__init__(root, transform, pre_transform)
self.dataset = dataset
self.process(xd, target_key, y, smile_graph, target_graph)
@property
def raw_file_names(self):
pass
# return ['some_file_1', 'some_file_2', ...]
@property
def processed_file_names(self):
return [self.dataset + '_data_mol.pt', self.dataset + '_data_pro.pt']
def download(self):
# Download to `self.raw_dir`.
pass
def _download(self):
pass
def _process(self):
if not os.path.exists(self.processed_dir):
os.makedirs(self.processed_dir)
def process(self, xd, target_key, y, smile_graph, target_graph):
assert (len(xd) == len(target_key) and len(xd) == len(y)), 'The three lists must be the same length!'
data_list_mol = []
data_list_pro = []
data_len = len(xd)
for i in range(data_len):
smiles = xd[i]
tar_key = target_key[i]
labels = y[i]
# convert SMILES to molecular representation using rdkit
c_size, features, edge_index = smile_graph[smiles]
target_size, target_features, target_edge_index = target_graph[tar_key]
# print(np.array(features).shape, np.array(edge_index).shape)
# print(target_features.shape, target_edge_index.shape)
# make the graph ready for PyTorch Geometrics GCN algorithms:
GCNData_mol = DATA.Data(x=torch.Tensor(features),
edge_index=torch.LongTensor(edge_index).transpose(1, 0),
y=torch.FloatTensor([labels]))
GCNData_mol.__setitem__('c_size', torch.LongTensor([c_size]))
GCNData_pro = DATA.Data(x=torch.Tensor(target_features),
edge_index=torch.LongTensor(target_edge_index).transpose(1, 0),
y=torch.FloatTensor([labels]))
GCNData_pro.__setitem__('target_size', torch.LongTensor([target_size]))
# print(GCNData.target.size(), GCNData.target_edge_index.size(), GCNData.target_x.size())
data_list_mol.append(GCNData_mol)
data_list_pro.append(GCNData_pro)
if self.pre_filter is not None:
data_list_mol = [data for data in data_list_mol if self.pre_filter(data)]
data_list_pro = [data for data in data_list_pro if self.pre_filter(data)]
if self.pre_transform is not None:
data_list_mol = [self.pre_transform(data) for data in data_list_mol]
data_list_pro = [self.pre_transform(data) for data in data_list_pro]
self.data_mol = data_list_mol
self.data_pro = data_list_pro
def __len__(self):
return len(self.data_mol)
def __getitem__(self, idx):
return self.data_mol[idx], self.data_pro[idx]
CE = torch.nn.MSELoss()
betas = [1e-1, 1e-2, 1e-3, 1e-4, 1e-5, 1e-6, 1e-7]
beta = 2#0，1，3，4，5，6
def calc_loss(y_pred, labels, enc_mean, enc_std, beta=1e-3):
"""
y_pred : [batch_size,2]
label : [batch_size,1]
enc_mean : [batch_size,z_dim]
enc_std: [batch_size,z_dim]
"""
ce = CE(y_pred, labels)
KL = 0.5 * torch.sum(enc_mean.pow(2) + enc_std.pow(2) - 2 * enc_std.log() - 1)
return (ce + beta * KL) / y_pred.shape[0]
# TODO end
# training function at each epoch
def train(model, device, train_loader, optimizer, epoch):
print('Training on {} samples...'.format(len(train_loader.dataset)))
model.train()
LOG_INTERVAL = 10
TRAIN_BATCH_SIZE = 512
# loss_fn = torch.nn.MSELoss()
for batch_idx, data in enumerate(train_loader):
#print("data",data)
data_mol = data[0].to(device)
#print("data_mol",data_mol)
data_pro = data[1].to(device)
#print("data_pro",data_pro)
optimizer.zero_grad()
output, enc_means, enc_stds = model(data_mol, data_pro)
# loss = loss_fn(output, data_mol.y.view(-1, 1).float().to(device))
loss = calc_loss(output,
data_mol.y.view(-1, 1).float().to(device),
enc_means, enc_stds, betas[beta])
# loss = calc_loss(y_pred, label, end_means, enc_stds, betas[2]
# train_pred = outputs.argmax(dim=1)
# _, train_pred = torch.max(output, 1)
loss.backward()
optimizer.step()
if batch_idx % LOG_INTERVAL == 0:
print('Train epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(epoch,
batch_idx * TRAIN_BATCH_SIZE,
len(train_loader.dataset),
100. * batch_idx / len(train_loader),
loss.item()))
# predict
def predicting(model, device, loader):
model.eval()
total_preds = torch.Tensor()
total_labels = torch.Tensor()
print('Make prediction for {} samples...'.format(len(loader.dataset)))
with torch.no_grad():
for data in loader:
data_mol = data[0].to(device)
data_pro = data[1].to(device)
output,enc_mean, enc_std = model(data_mol, data_pro)
total_preds = torch.cat((total_preds, output.cpu()), 0)
total_labels = torch.cat((total_labels, data_mol.y.view(-1, 1).cpu()), 0)
return total_labels.numpy().flatten(), total_preds.numpy().flatten()
#prepare the protein and drug pairs
def collate(data_list):
batchA = Batch.from_data_list([data[0] for data in data_list])
batchB = Batch.from_data_list([data[1] for data in data_list])
return batchA, batchB