feat: stable

DeepDRA.py

@@ -22,8 +22,7 @@ class DeepDRA(nn.Module):
     - mlp_output_dim (int): Output dimension for the MLP.
     """
 
-    def __init__(self, cell_modality_sizes, drug_modality_sizes, cell_ae_latent_dim, drug_ae_latent_dim, mlp_input_dim,
-                 mlp_output_dim):
+    def __init__(self, cell_modality_sizes, drug_modality_sizes, cell_ae_latent_dim, drug_ae_latent_dim):
         super(DeepDRA, self).__init__()
 
         # Initialize cell and drug autoencoders
@@ -35,7 +34,7 @@ class DeepDRA(nn.Module):
         self.drug_modality_sizes = drug_modality_sizes
 
         # Initialize MLP
-        self.mlp = MLP(mlp_input_dim, mlp_output_dim)
+        self.mlp = MLP(cell_ae_latent_dim+drug_ae_latent_dim, 1)
 
     def forward(self, cell_x, drug_x):
         """
@@ -88,7 +87,7 @@ class DeepDRA(nn.Module):
         return torch.square(w).sum()
 
 
-def train(model, train_loader, val_loader,  num_epochs, class_weights):
+def train(model, train_loader, val_loader,  num_epochs,class_weights):
     """
     Trains the DeepDRA (Deep Drug Response Anticipation) model.
 

main.py

@@ -19,8 +19,6 @@ batch_size = 64
 
 # Step 2: Instantiate the combined model
 ae_latent_dim = 50
-mlp_input_dim = 2 * ae_latent_dim
-mlp_output_dim = 1
 num_epochs = 25
 
 def train_DeepDRA(x_cell_train, x_cell_test, x_drug_train, x_drug_test, y_train, y_test, cell_sizes, drug_sizes,device):
@@ -43,7 +41,7 @@ def train_DeepDRA(x_cell_train, x_cell_test, x_drug_train, x_drug_test, y_train,
     """
 
 
-    model = DeepDRA(cell_sizes, drug_sizes, ae_latent_dim, ae_latent_dim, mlp_input_dim, mlp_output_dim)
+    model = DeepDRA(cell_sizes, drug_sizes, ae_latent_dim, ae_latent_dim)
     model.to(device)
     # Step 3: Convert your training data to PyTorch tensors
     x_cell_train_tensor = torch.Tensor(x_cell_train.values)
@@ -112,7 +110,7 @@ def cv_train(x_cell_train, x_drug_train, y_train, cell_sizes,
 
         train_sampler = SubsetRandomSampler(train_idx)
         test_sampler = SubsetRandomSampler(val_idx)
-        model = DeepDRA(cell_sizes, drug_sizes, ae_latent_dim, ae_latent_dim, mlp_input_dim, mlp_output_dim)
+        model = DeepDRA(cell_sizes, drug_sizes, ae_latent_dim, ae_latent_dim)
         # Convert your training data to PyTorch tensors
         x_cell_train_tensor = torch.Tensor(x_cell_train.values)
         x_drug_train_tensor = torch.Tensor(x_drug_train.values)
@@ -163,8 +161,8 @@ def run(k, is_test=False ):
 
     # Step 2: Load training data
     train_data, train_drug_screen = RawDataLoader.load_data(data_modalities=DATA_MODALITIES,
-                                                            raw_file_directory=RAW_BOTH_DATA_FOLDER,
-                                                            screen_file_directory=BOTH_SCREENING_DATA_FOLDER,
+                                                            raw_file_directory=GDSC_RAW_DATA_FOLDER,
+                                                            screen_file_directory=GDSC_SCREENING_DATA_FOLDER,
                                                             sep="\t")
 
     # Step 3: Load test data if applicable

utils.py

@@ -30,7 +30,7 @@ SIM_KERNEL = {'cell_CN': ('euclidean', 0.001), 'cell_exp': ('euclidean', 0.01),
 SAVE_MODEL = False  # Change it to True to save the trained model
 VARIATIONAL_AUTOENCODERS = False
 # DATA_MODALITIES=['cell_CN','cell_exp','cell_methy','cell_mut','drug_comp','drug_DT'] # Change this list to only consider specific data modalities
-DATA_MODALITIES = ['cell_CN','cell_exp','cell_mut', 'drug_desc']
+DATA_MODALITIES = ['cell_exp', 'drug_desc']
 RANDOM_SEED = 42  # Must be used wherever can be used