adds single drug elastic net

drevalpy/experiment.py

@@ -903,10 +903,11 @@ def train_and_predict(
 
     train_dataset.reduce_to(cell_line_ids=cell_lines_to_keep, drug_ids=drugs_to_keep)
     prediction_dataset.reduce_to(cell_line_ids=cell_lines_to_keep, drug_ids=drugs_to_keep)
-    print(f"Reduced training dataset from {len_train_before} to {len(train_dataset)}, because of missing features")
-    print(
-        f"Reduced prediction dataset from {len_pred_before} to {len(prediction_dataset)}, because of missing features"
-    )
+    if len(train_dataset) < len_train_before or len(prediction_dataset) < len_pred_before:
+        print(f"Reduced training dataset from {len_train_before} to {len(train_dataset)}, due to of missing features")
+        print(
+            f"Reduced prediction dataset from {len_pred_before} to {len(prediction_dataset)}, due to missing features"
+        )
 
     if early_stopping_dataset is not None:
         len_es_before = len(early_stopping_dataset)
@@ -1149,6 +1150,8 @@ def get_model_name_and_drug_id(model_name: str) -> tuple[str, str | None]:
     :returns: tuple of model name and, potentially drug id if it is a single drug model
     :raises AssertionError: if the model name is not found in the model factory
     """
+    print(model_name)
+    print(MULTI_DRUG_MODEL_FACTORY.keys())
     if model_name in MULTI_DRUG_MODEL_FACTORY:
         return model_name, None
     else:

drevalpy/models/__init__.py

@@ -11,6 +11,8 @@
     "MultiOmicsNeuralNetwork",
     "MultiOmicsRandomForest",
     "SingleDrugRandomForest",
+    "SingleDrugElasticNet",
+    "SingleDrugProteomicsElasticNet",
     "SRMF",
     "GradientBoosting",
     "MOLIR",
@@ -23,6 +25,7 @@
 
 from .baselines.multi_omics_random_forest import MultiOmicsRandomForest
 from .baselines.naive_pred import NaiveCellLineMeanPredictor, NaiveDrugMeanPredictor, NaivePredictor
+from .baselines.singledrug_elastic_net import SingleDrugElasticNet, SingleDrugProteomicsElasticNet
 from .baselines.singledrug_random_forest import SingleDrugRandomForest
 from .baselines.sklearn_models import ElasticNetModel, GradientBoosting, RandomForest, SVMRegressor
 from .DIPK.dipk import DIPKModel
@@ -38,6 +41,8 @@
     "SingleDrugRandomForest": SingleDrugRandomForest,
     "MOLIR": MOLIR,
     "SuperFELTR": SuperFELTR,
+    "SingleDrugElasticNet": SingleDrugElasticNet,
+    "SingleDrugProteomicsElasticNet": SingleDrugProteomicsElasticNet,
 }
 
 # MULTI_DRUG_MODEL_FACTORY is used in the pipeline!

drevalpy/models/baselines/hyperparameters.yaml

@@ -100,3 +100,33 @@ GradientBoosting:
     - 1.0
     - 0.8
     - 0.5
+SingleDrugElasticNet:
+  l1_ratio:
+    - 0.2
+    - 0.5
+    - 0.9
+  alpha:
+    - 1
+    - 0.8
+    - 0.6
+    - 0.4
+    - 0.2
+    - 0.1
+    - 5
+    - 10
+    - 100
+SingleDrugProteomicsElasticNet:
+  l1_ratio:
+    - 0.2
+    - 0.5
+    - 0.9
+  alpha:
+    - 1
+    - 0.8
+    - 0.6
+    - 0.4
+    - 0.2
+    - 0.1
+    - 5
+    - 10
+    - 100

drevalpy/models/baselines/singledrug_random_forest.py

@@ -94,3 +94,13 @@ def predict(
             drug_input=None,
         )
         return self.model.predict(x)
+
+    def load_drug_features(self, data_path, dataset_name):
+        """
+        Load drug features. Not needed for SingleDrugRandomForest.
+
+        :param data_path: path to the data
+        :param dataset_name: name of the dataset
+        :returns: None
+        """
+        return None

tests/individual_models/test_baselines.py

@@ -13,6 +13,8 @@
     NaiveCellLineMeanPredictor,
     NaiveDrugMeanPredictor,
     NaivePredictor,
+    SingleDrugElasticNet,
+    SingleDrugProteomicsElasticNet,
     SingleDrugRandomForest,
 )
 from drevalpy.models.baselines.sklearn_models import SklearnModel
@@ -93,7 +95,9 @@ def test_baselines(
         )
 
 
-@pytest.mark.parametrize("model_name", ["SingleDrugRandomForest"])
+@pytest.mark.parametrize(
+    "model_name", ["SingleDrugRandomForest", "SingleDrugElasticNet", "SingleDrugProteomicsElasticNet"]
+)
 @pytest.mark.parametrize("test_mode", ["LPO", "LCO"])
 def test_single_drug_baselines(
     sample_dataset: tuple[DrugResponseDataset, FeatureDataset, FeatureDataset], model_name: str, test_mode: str
@@ -122,8 +126,13 @@ def test_single_drug_baselines(
     random_drug = all_unique_drugs[:1]
 
     all_predictions = np.zeros_like(val_dataset.drug_ids, dtype=float)
+    if model_name == "SingleDrugElasticNet":
+        model = SingleDrugElasticNet()
+    elif model_name == "SingleDrugProteomicsElasticNet":
+        model = SingleDrugProteomicsElasticNet()
+    else:
+        model = SingleDrugRandomForest()
 
-    model = SingleDrugRandomForest()
     hpam_combi = model.get_hyperparameter_set()[0]
     hpam_combi["n_estimators"] = 2  # reduce test time
     hpam_combi["max_depth"] = 2  # reduce test time