Merge pull request #124 from daisybio/development

New release

Author: PascalIversen

.github/workflows/labeler.yml

@@ -13,6 +13,6 @@ jobs:
         uses: actions/checkout@v4
 
       - name: Run Labeler
-        uses: crazy-max/ghaction-github-labeler@v5.1.0
+        uses: crazy-max/ghaction-github-labeler@v5.2.0
         with:
           skip-delete: true

docs/conf.py

@@ -56,9 +56,9 @@
 # the built documents.
 #
 # The short X.Y version.
-version = "1.1.3"
+version = "1.1.4"
 # The full version, including alpha/beta/rc tags.
-release = "1.1.3"
+release = "1.1.4"
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

docs/usage.rst

@@ -100,6 +100,9 @@ prediction. This is why we also offer the possibility to compare your model to a
 the mean IC50 of all drugs in the training set. We also offer two more advanced naive predictors:
 **NaiveCellLineMeanPredictor** and **NaiveDrugMeanPredictor**. The former predicts the mean IC50 of a cell line in
 the training set and the latter predicts the mean IC50 of a drug in the training set.
+Finally, as the strongest naive baseline we offer the **NaiveMeanEffectPredictor**
+which combines the effects of cell lines and drugs.
+It is equivalent to the **NaiveCellLineMeanPredictor** and **NaiveDrugMeanPredictor** for the LDO and LPO settings, respectively.
 
 Available Models
 ------------------
@@ -119,6 +122,8 @@ For ``--models``, you can also perform randomization and robustness tests. The `
 +----------------------------+----------------------------+--------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
 | NaiveDrugMeanPredictor     | Baseline Method            | Multi-Drug Model                     | Predicts the mean response of a drug in the training set.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
 +----------------------------+----------------------------+--------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+| NaiveMeanEffectPredictor   | Baseline Method            | Multi-Drug Model                     | Predicts using ANOVA-like mean effect model of cell lines and drugs                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
++----------------------------+----------------------------+--------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
 | ElasticNet                 | Baseline Method            | Multi-Drug Model                     | Fits an `Sklearn Elastic Net <https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.ElasticNet.html>`_, `Lasso <https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Lasso.html>`_, or `Ridge <https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Ridge.html>`_ model on gene expression data and drug fingerprints (concatenated input matrix).                                                                                                                                                                                    |
 +----------------------------+----------------------------+--------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
 | GradientBoosting           | Baseline Method            | Multi-Drug Model                     | Fits an `Sklearn Gradient Boosting Regressor <https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html>`_ gene expression data and drug fingerprints.                                                                                                                                                                                                                                                                                                                                                                                             |

drevalpy/.DS_Store

@@ -1,5 +1,6 @@
 """Utility functions for datasets."""
 
+import os
 import zipfile
 from pathlib import Path
 from typing import Any
@@ -60,7 +61,7 @@ def download_dataset(
         with zipfile.ZipFile(file_path, "r") as z:
             for member in z.infolist():
                 if not member.filename.startswith("__MACOSX/"):
-                    z.extract(member, data_path)
+                    z.extract(member, os.path.join(data_path, dataset_name))
         file_path.unlink()  # Remove zip file after extraction
 
         print(f"{dataset_name} data downloaded and extracted to {data_path}")

drevalpy/datasets/utils.py

@@ -94,7 +94,7 @@ def drug_response_experiment(
     if baselines is None:
         baselines = []
     cross_study_datasets = cross_study_datasets or []
-    result_path = os.path.join(path_out, run_id, test_mode)
+    result_path = os.path.join(path_out, run_id, response_data._name, test_mode)
     split_path = os.path.join(result_path, "splits")
     result_folder_exists = os.path.exists(result_path)
     if result_folder_exists and overwrite:
@@ -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 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)
@@ -1142,8 +1143,7 @@ def make_model_list(models: list[type[DRPModel]], response_data: DrugResponseDat
 
 @pipeline_function
 def get_model_name_and_drug_id(model_name: str) -> tuple[str, str | None]:
-    """
-    Get the model name and drug id from the model name.
+    """Get the model name and drug id from the model name.
 
     :param model_name: model name, e.g., SimpleNeuralNetwork or MOLIR.Afatinib
     :returns: tuple of model name and, potentially drug id if it is a single drug model

drevalpy/experiment.py

@@ -94,6 +94,10 @@ def train(
                 "ignore",
                 message=".*does not have many workers which may be a bottleneck.*",
             )
+            warnings.filterwarnings(
+                "ignore",
+                message="Starting from v1\\.9\\.0, `tensorboardX` has been removed.*",
+            )
             self.model.fit(
                 output_train=output,
                 cell_line_input=cell_line_input,

drevalpy/models/.DS_Store

@@ -1,5 +1,6 @@
 """Utility functions for the simple neural network models."""
 
+import os
 import secrets
 from typing import Any
 
@@ -229,11 +230,14 @@ def fit(
         monitor = "train_loss" if (val_loader is None) else "val_loss"
 
         early_stop_callback = EarlyStopping(monitor=monitor, mode="min", patience=patience)
-        name = "version-" + "".join(
-            [secrets.choice("0123456789abcdef") for i in range(20)]
-        )  # preventing conflicts of filenames
+
+        unique_subfolder = os.path.join(model_checkpoint_dir, "run_" + secrets.token_hex(8))
+        os.makedirs(unique_subfolder, exist_ok=True)
+
+        # prevent conflicts
+        name = "version-" + "".join([secrets.choice("0123456789abcdef") for _ in range(10)])
         self.checkpoint_callback = pl.callbacks.ModelCheckpoint(
-            dirpath=model_checkpoint_dir,
+            dirpath=unique_subfolder,
             monitor=monitor,
             mode="min",
             save_top_k=1,
@@ -262,7 +266,7 @@ def fit(
 
         # load best model
         if self.checkpoint_callback.best_model_path is not None:
-            checkpoint = torch.load(self.checkpoint_callback.best_model_path)  # noqa: S614
+            checkpoint = torch.load(self.checkpoint_callback.best_model_path, weights_only=True)  # noqa: S614
             self.load_state_dict(checkpoint["state_dict"])
         else:
             print("checkpoint_callback: No best model found, using the last model.")

drevalpy/models/SimpleNeuralNetwork/simple_neural_network.py

@@ -4,13 +4,16 @@
     "NaivePredictor",
     "NaiveDrugMeanPredictor",
     "NaiveCellLineMeanPredictor",
+    "NaiveMeanEffectsPredictor",
     "ElasticNetModel",
     "RandomForest",
     "SVMRegressor",
     "SimpleNeuralNetwork",
     "MultiOmicsNeuralNetwork",
     "MultiOmicsRandomForest",
     "SingleDrugRandomForest",
+    "SingleDrugElasticNet",
+    "SingleDrugProteomicsElasticNet",
     "SRMF",
     "GradientBoosting",
     "MOLIR",
@@ -22,7 +25,13 @@
 ]
 
 from .baselines.multi_omics_random_forest import MultiOmicsRandomForest
-from .baselines.naive_pred import NaiveCellLineMeanPredictor, NaiveDrugMeanPredictor, NaivePredictor
+from .baselines.naive_pred import (
+    NaiveCellLineMeanPredictor,
+    NaiveDrugMeanPredictor,
+    NaiveMeanEffectsPredictor,
+    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
@@ -38,13 +47,16 @@
     "SingleDrugRandomForest": SingleDrugRandomForest,
     "MOLIR": MOLIR,
     "SuperFELTR": SuperFELTR,
+    "SingleDrugElasticNet": SingleDrugElasticNet,
+    "SingleDrugProteomicsElasticNet": SingleDrugProteomicsElasticNet,
 }
 
 # MULTI_DRUG_MODEL_FACTORY is used in the pipeline!
 MULTI_DRUG_MODEL_FACTORY: dict[str, type[DRPModel]] = {
     "NaivePredictor": NaivePredictor,
     "NaiveDrugMeanPredictor": NaiveDrugMeanPredictor,
     "NaiveCellLineMeanPredictor": NaiveCellLineMeanPredictor,
+    "NaiveMeanEffectsPredictor": NaiveMeanEffectsPredictor,
     "ElasticNet": ElasticNetModel,
     "RandomForest": RandomForest,
     "SVR": SVMRegressor,