flexynesis 0.2.2__tar.gz → 0.2.3__tar.gz

{flexynesis-0.2.2 → flexynesis-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: flexynesis
-Version: 0.2.2
+Version: 0.2.3
 Summary: A deep-learning based multi-omics bulk sequencing data integration suite with a focus on (pre-)clinical endpoint prediction.
 Author-email: Bora Uyar <bora.uyar@mdc-berlin.de>, Taras Savchyn <Taras.Savchyn@mdc-berlin.de>, Ricardo Wurmus <Ricardo.Wurmus@mdc-berlin.de>, Ahmet Sarigun <Ahmet.Sariguen@mdc-berlin.de>
 Project-URL: homepage, https://github.com/BIMSBbioinfo/flexynesis

{flexynesis-0.2.2 → flexynesis-0.2.3}/flexynesis/__main__.py

@@ -46,6 +46,7 @@ def main():
         --use_loss_weighting (str): Whether to apply loss-balancing using uncertainty weights method. Choices are ['True', 'False']. Default is 'True'.
         --evaluate_baseline_performance (str): Whether to run Random Forest + SVMs to see the performance of off-the-shelf tools on the same dataset. Choices are ['True', 'False']. Default is 'True'.
         --threads (int): How many threads to use when using CPU. Default is 4.
+        --num_workers (int): How many workers to use for model training. Default is 2
         --use_gpu (bool): If set, the system will attempt to use CUDA/GPU if available.
         --disable_marker_finding (bool): If set, marker discovery after model training is disabled.
         --string_organism (int): STRING DB organism id. Default is 9606.
@@ -99,6 +100,7 @@ def main():
     parser.add_argument("--use_loss_weighting", help="whether to apply loss-balancing using uncertainty weights method", type=str, choices=['True', 'False'], default = 'True')
     parser.add_argument("--evaluate_baseline_performance", help="whether to run Random Forest + SVMs to see the performance of off-the-shelf tools on the same dataset", type=str, choices=['True', 'False'], default = 'True')
     parser.add_argument("--threads", help="(Optional) How many threads to use when using CPU (default is 4)", type=int, default = 4)
+    parser.add_argument("--num_workers", help="(Optional) How many workers to use for model training (default is 2)", type=int, default = 2)
     parser.add_argument("--use_gpu", action="store_true", 
                         help="(Optional) If set, the system will attempt to use CUDA/GPU if available.")
     parser.add_argument("--disable_marker_finding", action="store_true", 
@@ -253,7 +255,8 @@ def main():
                                             device_type = device_type,
                                             gnn_conv_type = gnn_conv_type,
                                             input_layers = input_layers,
-                                            output_layers = output_layers)    
+                                            output_layers = output_layers, 
+                                            num_workers = args.num_workers)    
     
     # do a hyperparameter search training multiple models and get the best_configuration 
     model, best_params = tuner.perform_tuning(hpo_patience = args.hpo_patience)

{flexynesis-0.2.2 → flexynesis-0.2.3}/flexynesis/config.py

@@ -6,28 +6,28 @@ epochs = [500]
 search_spaces = {
     'DirectPred': [
         Integer(16, 128, name='latent_dim'),
-        Real(0.2, 1, name='hidden_dim_factor'), # relative size of the hidden_dim w.r.t input_dim 
+        Real(0.2, 0.5, name='hidden_dim_factor'), # relative size of the hidden_dim w.r.t input_dim 
         Real(0.0001, 0.01, prior='log-uniform', name='lr'),
         Integer(8, 32, name='supervisor_hidden_dim'),
         Categorical(epochs, name='epochs')
     ], 
     'supervised_vae': [
         Integer(16, 128, name='latent_dim'),
-        Real(0.2, 1, name='hidden_dim_factor'), # relative size of the hidden_dim w.r.t input_dim 
+        Real(0.2, 0.5, name='hidden_dim_factor'), # relative size of the hidden_dim w.r.t input_dim 
         Integer(8, 32, name='supervisor_hidden_dim'),
         Real(0.0001, 0.01, prior='log-uniform', name='lr'),
         Categorical(epochs, name='epochs')
     ],
     'CrossModalPred': [
         Integer(16, 128, name='latent_dim'),
-        Real(0.2, 1, name='hidden_dim_factor'), # relative size of the hidden_dim w.r.t input_dim 
+        Real(0.2, 0.5, name='hidden_dim_factor'), # relative size of the hidden_dim w.r.t input_dim 
         Integer(8, 32, name='supervisor_hidden_dim'),
         Real(0.0001, 0.01, prior='log-uniform', name='lr'),
         Categorical(epochs, name='epochs')
     ],
     'MultiTripletNetwork': [
         Integer(16, 128, name='latent_dim'),
-        Real(0.2, 1, name='hidden_dim_factor'), # relative size of the hidden_dim w.r.t input_dim 
+        Real(0.2, 0.5, name='hidden_dim_factor'), # relative size of the hidden_dim w.r.t input_dim 
         Integer(8, 32, name='supervisor_hidden_dim'),
         Real(0.0001, 0.01, prior='log-uniform', name='lr'),
         Categorical(epochs, name='epochs')

{flexynesis-0.2.2 → flexynesis-0.2.3}/flexynesis/main.py

@@ -56,7 +56,7 @@ class HyperparameterTuning:
                  cv_splits=5, use_loss_weighting=True, early_stop_patience=-1, device_type=None, gnn_conv_type=None,
                  input_layers=None, output_layers=None): Initializes the hyperparameter tuner with specific settings.
 
-        get_batch_space(min_size=16, max_size=256): Determines the batch size search space based on the dataset size.
+        get_batch_space(min_size=16, max_size=128): Determines the batch size search space based on the dataset size.
 
         setup_trainer(params, current_step, total_steps, full_train=False): Sets up the trainer with appropriate callbacks
             and configurations for either full training or validation based training.
@@ -80,7 +80,7 @@ class HyperparameterTuning:
                  val_size = 0.2,  use_cv = False, cv_splits = 5, 
                  use_loss_weighting = True, early_stop_patience = -1,
                  device_type = None, gnn_conv_type = None, 
-                 input_layers = None, output_layers = None):
+                 input_layers = None, output_layers = None, num_workers = 2):
         self.dataset = dataset # dataset for model initiation
         self.loader_dataset = dataset # dataset for defining data loaders (this can be model specific)
         self.model_class = model_class
@@ -107,6 +107,7 @@ class HyperparameterTuning:
         self.gnn_conv_type = gnn_conv_type
         self.input_layers = input_layers
         self.output_layers = output_layers 
+        self.num_workers = num_workers
         
         self.DataLoader = torch.utils.data.DataLoader # use torch data loader by default
         
@@ -128,7 +129,7 @@ class HyperparameterTuning:
             else:
                 raise ValueError(f"'{self.config_name}' not found in the default config.")
 
-    def get_batch_space(self, min_size = 32, max_size = 256):
+    def get_batch_space(self, min_size = 32, max_size = 128):
         m = int(np.log2(len(self.dataset) * 0.8))
         st = int(np.log2(min_size))
         end = int(np.log2(max_size))
@@ -214,9 +215,11 @@ class HyperparameterTuning:
                 train_subset = torch.utils.data.Subset(self.loader_dataset, train_index)
                 val_subset = torch.utils.data.Subset(self.loader_dataset, val_index)
                 train_loader = self.DataLoader(train_subset, batch_size=int(params['batch_size']), 
-                                               pin_memory=True, shuffle=True, drop_last=True, num_workers = 4, prefetch_factor = None, persistent_workers = True)
+                                               pin_memory=True, shuffle=True, drop_last=True, num_workers = self.num_workers, prefetch_factor = None, 
+                                               persistent_workers = self.num_workers > 0)
                 val_loader = self.DataLoader(val_subset, batch_size=int(params['batch_size']), 
-                                             pin_memory=True, shuffle=False, num_workers = 4, prefetch_factor = None, persistent_workers = True)
+                                             pin_memory=True, shuffle=False, num_workers = self.num_workers, prefetch_factor = None, 
+                                             persistent_workers = self.num_workers > 0)
 
                 model = self.model_class(**model_args)
                 trainer, early_stop_callback = self.setup_trainer(params, current_step, total_steps)

{flexynesis-0.2.2 → flexynesis-0.2.3}/flexynesis.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: flexynesis
-Version: 0.2.2
+Version: 0.2.3
 Summary: A deep-learning based multi-omics bulk sequencing data integration suite with a focus on (pre-)clinical endpoint prediction.
 Author-email: Bora Uyar <bora.uyar@mdc-berlin.de>, Taras Savchyn <Taras.Savchyn@mdc-berlin.de>, Ricardo Wurmus <Ricardo.Wurmus@mdc-berlin.de>, Ahmet Sarigun <Ahmet.Sariguen@mdc-berlin.de>
 Project-URL: homepage, https://github.com/BIMSBbioinfo/flexynesis

{flexynesis-0.2.2 → flexynesis-0.2.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "flexynesis"
-version = "0.2.2"
+version = "0.2.3"
 authors = [
     {name = "Bora Uyar", email = "bora.uyar@mdc-berlin.de"},
     {name = "Taras Savchyn", email = "Taras.Savchyn@mdc-berlin.de"},