Embedding From:
Resnet50 （CV-based）
Network architecture:
ResNet(
(conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(layer1): Sequential(
(0): Bottleneck(
(conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(2): Bottleneck(
(conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(layer2): Sequential(
(0): Bottleneck(
(conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(2): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(3): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(layer3): Sequential(
(0): Bottleneck(
(conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(2): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(3): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(4): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(5): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(layer4): Sequential(
(0): Bottleneck(
(conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(2): Bottleneck(
(conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
(fc): Linear(in_features=2048, out_features=1000, bias=True)
)
Parameters:
Total params: 25,557,032
Trainable params: 25,557,032
Non-trainable params: 0
Input size (MB): 0.57
Forward/backward pass size (MB): 286.56
Params size (MB): 97.49
Estimated Total Size (MB): 384.62
Training process works:
Pretrained
Final dimensionality of the drug embedding:
2048 (Full Connection layer)
Embedding:
DinoVit (CV-Based)
Network architecture:
ViTModel(
(embeddings): ViTEmbeddings(
(patch_embeddings): ViTPatchEmbeddings(
(projection): Conv2d(3, 768, kernel_size=(16, 16), stride=(16, 16))
)
(dropout): Dropout(p=0.0, inplace=False)
)
(encoder): ViTEncoder(
(layer): ModuleList(
(0-11): 12 x ViTLayer(
(attention): ViTAttention(
(attention): ViTSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.0, inplace=False)
)
(output): ViTSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.0, inplace=False)
)
)
(intermediate): ViTIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): ViTOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(dropout): Dropout(p=0.0, inplace=False)
)
(layernorm_before): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(layernorm_after): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
)
)
)
(layernorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(pooler): ViTPooler(
(dense): Linear(in_features=768, out_features=768, bias=True)
(activation): Tanh()
)
)
Parameters:
N/A
model_size=327MB
Training process works:
Pretrained
Final dimensionality of the drug embedding:
768 (last layer)
——————————————————————————————
Embedding:
Bart (NLP-based)
Network architecture:
BartModel(
(shared): Embedding(50265, 1024, padding_idx=1)
(encoder): BartEncoder(
(embed_tokens): BartScaledWordEmbedding(50265, 1024, padding_idx=1)
(embed_positions): BartLearnedPositionalEmbedding(1026, 1024)
(layers): ModuleList(
(0-11): 12 x BartEncoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(activation_fn): GELUActivation()
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
)
(layernorm_embedding): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
(decoder): BartDecoder(
(embed_tokens): BartScaledWordEmbedding(50265, 1024, padding_idx=1)
(embed_positions): BartLearnedPositionalEmbedding(1026, 1024)
(layers): ModuleList(
(0-11): 12 x BartDecoderLayer(
(self_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(activation_fn): GELUActivation()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): BartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
)
(layernorm_embedding): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
)
Parameters:
17，500，000
model_size: 971MB
Training process works:
Pretrained
Final dimensionality of the drug embedding:
1024 (last layer)
——————————————————————————————Embedding:
Sapbert (NLP-based)
Network architecture:
BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(30522, 768, padding_idx=0)
(position_embeddings): Embedding(512, 768)
(token_type_embeddings): Embedding(2, 768)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(encoder): BertEncoder(
(layer): ModuleList(
(0-11): 12 x BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(pooler): BertPooler(
(dense): Linear(in_features=768, out_features=768, bias=True)
(activation): Tanh()
)
)
Parameters:
N/A
model_size:417MB
Training process works:
Pretrained
Final dimensionality of the drug embedding:
768 (last layer)
Citation:
M. Lewis et al., ‘BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension’, Oct. 29, 2019, arXiv: arXiv:1910.13461. Accessed: Dec. 23, 2023. [Online]. Available: http://arxiv.org/abs/1910.13461
——————————————————————————————
Embedding:
SCIbert (NLP-based)
Network architecture:
BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(31090, 768, padding_idx=0)
(position_embeddings): Embedding(512, 768)
(token_type_embeddings): Embedding(2, 768)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(encoder): BertEncoder(
(layer): ModuleList(
(0-11): 12 x BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(pooler): BertPooler(
(dense): Linear(in_features=768, out_features=768, bias=True)
(activation): Tanh()
)
)
Parameters:
N/A
model_size:421MB
Training process works:
Pretrained
Final dimensionality of the drug embedding:
768
Citation:
I. Beltagy, K. Lo, and A. Cohan, ‘SciBERT: A Pretrained Language Model for Scientific Text’, Sep. 10, 2019, arXiv: arXiv:1903.10676. Accessed: Dec. 14, 2023. [Online]. Available: http://arxiv.org/abs/1903.10676
——————————————————————————————
Embedding:
Biogpt (NLP-based)
Network architecture:
BioGptModel(
(embed_tokens): BioGptScaledWordEmbedding(57726, 1600, padding_idx=1)
(embed_positions): BioGptLearnedPositionalEmbedding(2050, 1600)
(layers): ModuleList(
(0-47): 48 x BioGptDecoderLayer(
(self_attn): BioGptAttention(
(k_proj): Linear(in_features=1600, out_features=1600, bias=True)
(v_proj): Linear(in_features=1600, out_features=1600, bias=True)
(q_proj): Linear(in_features=1600, out_features=1600, bias=True)
(out_proj): Linear(in_features=1600, out_features=1600, bias=True)
)
(activation_fn): GELUActivation()
(self_attn_layer_norm): LayerNorm((1600,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1600, out_features=6400, bias=True)
(fc2): Linear(in_features=6400, out_features=1600, bias=True)
(final_layer_norm): LayerNorm((1600,), eps=1e-05, elementwise_affine=True)
)
)
(layer_norm): LayerNorm((1600,), eps=1e-05, elementwise_affine=True)
)
Parameters:
N/A
model_size:5.85GB
Training process works:
Pretrained
Final dimensionality of the drug embedding:
1600
Citation:
R. Luo et al., ‘BioGPT: generative pre-trained transformer for biomedical text generation and mining’, Briefings in Bioinformatics, vol. 23, no. 6, p. bbac409, Nov. 2022, doi: 10.1093/bib/bbac409.
_______________________________________________________________________________________
Embeddings:
SMILEFIN (SMILE-based features/embedding)
Github:
https://github.com/tticoin/DESC_MOL-DDIE/tree/master/fingerprint
Citation：
M. Asada, M. Miwa, and Y. Sasaki, ‘Using drug descriptions and molecular structures for drug-drug interaction extraction from literature’, Bioinformatics, vol. 37, no. 12, pp. 1739–1746, Jul. 2021, doi: 10.1093/bioinformatics/btaa907.
Final dimensionality of the drug embedding:
1000
——————————————————————————————
Embddings:
RDF2VEC (SMILE-based features/embedding)
RDF2Vec_sg_300_5_5_15_2_500_d5_uniform.txt
Github:
https://github.com/rezacsedu/Drug-Drug-Interaction-Prediction
Citation:
Karim, Md Rezaul, Michael Cochez, Joao Bosco Jares, Mamtaz Uddin, Oya Beyan, and Stefan Decker. “Drug-drug interaction prediction based on knowledge graph embeddings and convolutional-LSTM network.” In Proceedings of the 10th ACM international conference on bioinformatics, computational biology and health informatics, pp. 113-123. 2019
Final dimensionality of the drug embedding:
300
—————————————————————————————–
Embeddings:
ChemBERTa-2 (SMILE-based embedding)
Network architecture:
RobertaModel(
(embeddings): RobertaEmbeddings(
(word_embeddings): Embedding(600, 384, padding_idx=1)
(position_embeddings): Embedding(515, 384, padding_idx=1)
(token_type_embeddings): Embedding(1, 384)
(LayerNorm): LayerNorm((384,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.144, inplace=False)
)
(encoder): RobertaEncoder(
(layer): ModuleList(
(0-2): 3 x RobertaLayer(
(attention): RobertaAttention(
(self): RobertaSelfAttention(
(query): Linear(in_features=384, out_features=384, bias=True)
(key): Linear(in_features=384, out_features=384, bias=True)
(value): Linear(in_features=384, out_features=384, bias=True)
(dropout): Dropout(p=0.109, inplace=False)
)
(output): RobertaSelfOutput(
(dense): Linear(in_features=384, out_features=384, bias=True)
(LayerNorm): LayerNorm((384,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.144, inplace=False)
)
)
(intermediate): RobertaIntermediate(
(dense): Linear(in_features=384, out_features=464, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): RobertaOutput(
(dense): Linear(in_features=464, out_features=384, bias=True)
(LayerNorm): LayerNorm((384,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.144, inplace=False)
)
)
)
)
(pooler): RobertaPooler(
(dense): Linear(in_features=384, out_features=384, bias=True)
(activation): Tanh()
)
)
Model:
https://huggingface.co/DeepChem/ChemBERTa-77M-MLM/tree/main
Modelsize=13.3MB
Citation:
W. Ahmad, E. Simon, S. Chithrananda, G. Grand, and B. Ramsundar, ‘ChemBERTa-2: Towards Chemical Foundation Models’, 2022, arXiv. doi: 10.48550/ARXIV.2209.01712.
Final dimensionality of the drug embedding:
384
——————————————————————————————
Embeddings:
GADNN (Graph-based embeddings)
Github:
https://github.com/MarziehNejati/GADNN
Final dimensionality of the drug embedding:
128
Citation:
M. Nejati and A. Lakizadeh, ‘GADNN: A graph attention-based method for drug-drug association prediction considering the contribution rate of different types of drug-related features’, Informatics in Medicine Unlocked, vol. 44, p. 101429, 2024, doi: 10.1016/j.imu.2023.101429.
——————————————————————————————