Merge pull request #226 from daisybio/development

v1.3.2

Author: JudithBernett

.gitattributes

@@ -0,0 +1 @@
+* text=auto

.github/workflows/publish_docs.yml

@@ -13,7 +13,7 @@ jobs:
       - name: Setup Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.12"
+          python-version: "3.13"
 
       - name: Install pip
         run: |

.github/workflows/python-package.yml

@@ -15,7 +15,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.11", "3.12"]
+        python-version: ["3.11", "3.12", "3.13"]
 
     steps:
       - name: Check out the repository

.github/workflows/run_tests.yml

@@ -127,6 +127,6 @@ jobs:
         run: nox --force-color --session=coverage -- xml -i
 
       - name: Upload coverage report
-        uses: codecov/codecov-action@v5.4.2
+        uses: codecov/codecov-action@v5.4.3
         with:
           token: ${{ secrets.CODECOV_TOKEN }}

.pre-commit-config.yaml

@@ -35,26 +35,20 @@ repos:
         types: [python]
         require_serial: true
         args:
-          - --ignore=D212,W503,C901
+          - --ignore=D212,W503,C901,N803,N806
       - id: pyupgrade
         name: pyupgrade
         description: Automatically upgrade syntax for newer versions.
         entry: pyupgrade
         language: system
         types: [python]
         args: [--py39-plus, --keep-runtime-typing]
-      - id: trailing-whitespace
-        name: Trim Trailing Whitespace
-        entry: trailing-whitespace-fixer
-        language: system
-        types: [text]
-        stages: [pre-commit, pre-push, manual]
   - repo: https://github.com/pre-commit/mirrors-prettier
     rev: v2.5.1
     hooks:
       - id: prettier
   - repo: https://github.com/pycqa/isort
-    rev: 5.12.0
+    rev: 6.0.1
     hooks:
       - id: isort
         name: isort (python)
@@ -64,3 +58,7 @@ repos:
       - id: isort
         name: isort (pyi)
         types: [pyi]
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: trailing-whitespace

README.md

@@ -8,7 +8,11 @@
 [![Precommit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 
-Focus on Innovating Your Models — DrEval Handles the Rest!
+**News:** Our preprint is out on [biorxiv](https://www.biorxiv.org/content/10.1101/2025.05.26.655288v1)!
+
+Documentation at [ReadTheDocs](https://drevalpy.readthedocs.io/en/latest/index.html#).
+
+**Focus on Innovating Your Models — DrEval Handles the Rest!**
 
 - DrEval is a toolkit that ensures drug response prediction evaluations are statistically sound, biologically meaningful, and reproducible.
 - Focus on model innovation while using our automated standardized evaluation protocols and preprocessing workflows.
@@ -59,6 +63,7 @@ From source:
 git clone https://github.com/daisybio/drevalpy.git
 cd drevalpy
 pip install poetry
+pip install poetry-plugin-export
 poetry install
 ```
 
@@ -67,44 +72,86 @@ poetry install
 To run models from the catalog, you can run:
 
 ```bash
-python run_suite.py --run_id my_first_run --models ElasticNet SimpleNeuralNetwork --dataset GDSC2 --test_mode LCO
+python run_suite.py --run_id my_first_run --models NaiveTissueMeanPredictor NaiveDrugMeanPredictor --baselines NaiveMeanEffectsPredictor --dataset TOYv1 --test_mode LCO
 ```
 
-This will train and tune a neural network and an elastic net model on gene expression features and drug fingerprint
-features to predict IC50 values of the GDSC2 database. It will evaluate in "LCO" which is the leave-cell-line-out
-splitting strategy using 5 fold cross validation.
+This will train our baseline models which just predict the drug or tissue means or the mean drug and cell line effects.
+It will evaluate in "LCO" which is the leave-cell-line-out splitting strategy using 7 fold cross validation.
 The results will be stored in
 
 ```bash
-results/my_first_run/LCO
+results/my_first_run/TOYv1/LCO
 ```
 
 You can visualize them using
 
 ```bash
-python create_report.py --run_id my_first_run --dataset GDSC2
+python create_report.py --run_id my_first_run --dataset TOYv1
 ```
 
-This will create an index.html file which you can open in your webbrowser.
+This will create an index.html file which you can open in your web browser.
 
 You can also run a drug response experiment using Python:
 
 ```python
-
 from drevalpy.experiment import drug_response_experiment
+from drevalpy.models import MODEL_FACTORY
+from drevalpy.datasets import AVAILABLE_DATASETS
+
+naive_mean = MODEL_FACTORY["NaiveMeanEffectsPredictor"]
+rf = MODEL_FACTORY["RandomForest"]
+simple_nn = MODEL_FACTORY["SimpleNeuralNetwork"]
+
+toyv2 = AVAILABLE_DATASETS["TOYv2"](path_data="data", measure="LN_IC50_curvecurator")
 
 drug_response_experiment(
-            models=["MultiOmicsNeuralNetwork"],
-            baselines=["RandomForest"],
-            response_data="GDSC1",
-            metric="mse",
-            n_cv_splits=5,
-            test_mode="LPO",
+            models=[rf, simple_nn],
+            baselines=[naive_mean],
+            response_data=toyv2,
+            metric="RMSE",
+            n_cv_splits=7,
+            test_mode="LCO",
             run_id="my_second_run",
+            path_data="data",
+            hyperparameter_tuning=False,
         )
 ```
 
-We recommend the use of our nextflow pipeline for computational demanding runs and for improved reproducibility. No knowledge of nextflow is required to run it. The nextflow pipeline is available here: [nf-core-drugresponseeval](https://github.com/JudithBernett/nf-core-drugresponseeval).
+This will run the Random Forest and Simple Neural Network models on the CTRPv2 dataset, using the Naive Mean Effects Predictor as a baseline. The results will be stored in `results/my_second_run/CTRPv2/LCO`.
+To obtain evaluation metrics, you can use:
+
+```python
+from drevalpy.visualization.utils import parse_results, prep_results, write_results
+import pathlib
+
+# load data, evaluate per CV run
+(
+        evaluation_results,
+        evaluation_results_per_drug,
+        evaluation_results_per_cell_line,
+        true_vs_pred,
+    ) = parse_results(path_to_results="results/my_second_run", dataset='TOYv2')
+# reformat, calculate normalized metrics
+(
+        evaluation_results,
+        evaluation_results_per_drug,
+        evaluation_results_per_cell_line,
+        true_vs_pred,
+    ) = prep_results(
+        evaluation_results, evaluation_results_per_drug, evaluation_results_per_cell_line, true_vs_pred, pathlib.Path("data")
+    )
+
+write_results(
+        path_out="results/my_second_run",
+        eval_results=evaluation_results,
+        eval_results_per_drug=evaluation_results_per_drug,
+        eval_results_per_cl=evaluation_results_per_cell_line,
+        t_vs_p=true_vs_pred,
+    )
+```
+
+We recommend the use of our Nextflow pipeline for computational demanding runs and for improved reproducibility.
+No knowledge of Nextflow is required to run it. The nextflow pipeline is available here: [nf-core-drugresponseeval](https://github.com/JudithBernett/nf-core-drugresponseeval).
 
 ## Example Report
 
@@ -115,4 +162,4 @@ We recommend the use of our nextflow pipeline for computational demanding runs a
 Main developers:
 
 - [Judith Bernett](mailto:judith.bernett@tum.de), [Data Science in Systems Biology](https://www.mls.ls.tum.de/daisybio/startseite/), TUM
-- [Pascal Iversen](mailto:Pascal.Iversen@hpi.de), [Data Integration in the Life Sciences](https://www.mi.fu-berlin.de/w/DILIS/WebHome), FU Berlin, Hasso Plattner Institute
+- [Pascal Iversen](mailto:Pascal.Iversen@hpi.de), [Data Integration in the Life Sciences](https://www.mi.fu-berlin.de/w/DILIS/WebHome), FU Berlin, Hasso-Plattner-Institut

README.rst

@@ -40,12 +40,15 @@ DrEvalPy: Python Cancer Cell Line Drug Response Prediction Suite
 Overview
 =======
 
-Focus on Innovating Your Models — DrEval Handles the Rest!
+Check out our preprint on `bioRxiv <https://www.biorxiv.org/content/10.1101/2025.05.26.655288v1>`_!
+
+**Focus on Innovating Your Models — DrEval Handles the Rest!**
+
 -  DrEval is a toolkit that ensures drug response prediction evaluations are statistically sound, biologically meaningful, and reproducible.
 -  Focus on model innovation while using our automated standardized evaluation protocols and preprocessing workflows.
--  A flexible model interface supports all model types (e.g. Machine Learning, Stats, Network-based analyses)
+-  A flexible model interface supports all model types (e.g. machine learning, statistical models, network-based analyses).
 
-Use DrEval to Build Drug Response Models That Have an Impact
+Use DrEval to build drug response models that have an impact
 
     1. Maintained, up-to-date baseline catalog, no need to re-implement literature models
 

create_report.py

@@ -74,13 +74,14 @@
             result_path=result_path,
         )
         # draw figures for each algorithm with all randomizations etc
-        unique_algos = set(unique_algos) - {
+        unique_algos_set = set(unique_algos) - {
             "NaiveMeanEffectsPredictor",
             "NaivePredictor",
             "NaiveCellLineMeansPredictor",
+            "NaiveTissueMeansPredictor",
             "NaiveDrugMeanPredictor",
         }
-        for algorithm in unique_algos:
+        for algorithm in unique_algos_set:
             draw_algorithm_plots(
                 model=algorithm,
                 ev_res=evaluation_results,

docs/_static/example_data/fingerprints_example.csv

@@ -0,0 +1,36 @@
+pubchem_id,dim_0,dim_1,dim_2,dim_3,dim_4,dim_5,dim_6,dim_7,dim_8,dim_9,dim_10,dim_11,dim_12,dim_13,dim_14,dim_15,dim_16,dim_17,dim_18,dim_19,dim_20,dim_21,dim_22,dim_23,dim_24,dim_25,dim_26,dim_27,dim_28,dim_29,dim_30,dim_31
+16720766,1.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,1.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0
+24821094,1.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,1.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0
+5284616,0.0,1.0,1.0,0.0,1.0,0.0,1.0,1.0,1.0,0.0,1.0,1.0,1.0,0.0,1.0,1.0,1.0,0.0,1.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,1.0,1.0,0.0,1.0,1.0,1.0
+44632017,1.0,0.0,1.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0,1.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,1.0,0.0,0.0
+444795,0.0,0.0,1.0,1.0,1.0,1.0,0.0,0.0,1.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0
+2733526,0.0,0.0,1.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,1.0,1.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0
+6505803,1.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,1.0,1.0,1.0,0.0,0.0,1.0,0.0,1.0,0.0,1.0,0.0,0.0,1.0,1.0,0.0,0.0,1.0,0.0,1.0,1.0,1.0,1.0
+44137675,1.0,1.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,1.0,0.0,1.0,1.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0,0.0,0.0,1.0,1.0,0.0,1.0,1.0
+9933475,1.0,0.0,1.0,0.0,1.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,1.0,1.0,1.0,0.0,0.0,1.0,1.0,1.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0
+176870,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,1.0,0.0,0.0,1.0,1.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0
+10385095,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
+135398516,1.0,0.0,1.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0,1.0,0.0,0.0,0.0,1.0,0.0,1.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,1.0,0.0
+5494449,1.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0,1.0,0.0,1.0,1.0,0.0,1.0,0.0,1.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0
+123631,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0,0.0,1.0,1.0,1.0,0.0,0.0,1.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,1.0,0.0
+60750,1.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0
+637858,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,1.0,0.0,1.0,1.0
+6450551,1.0,1.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
+24771867,1.0,0.0,1.0,0.0,0.0,1.0,0.0,1.0,1.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,1.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0
+6914657,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,1.0,1.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,1.0,1.0,1.0
+68289010,0.0,1.0,1.0,1.0,0.0,1.0,0.0,0.0,1.0,0.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0,1.0,1.0,1.0
+156422,1.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,1.0,1.0,1.0,1.0,0.0,0.0,1.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0
+36314,1.0,1.0,1.0,1.0,0.0,1.0,0.0,0.0,0.0,1.0,1.0,1.0,1.0,0.0,0.0,0.0,1.0,1.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,1.0,1.0,1.0,0.0
+11977753,1.0,1.0,0.0,1.0,0.0,1.0,0.0,0.0,1.0,1.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
+9926054,1.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,0.0,1.0
+24785538,1.0,0.0,1.0,1.0,1.0,1.0,1.0,0.0,1.0,0.0,1.0,1.0,1.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0
+216239,1.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,1.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0,1.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0
+3062316,1.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0
+9927531,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0
+135398738,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
+462382,1.0,1.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0
+117072552,1.0,1.0,1.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,1.0,1.0
+46224516,1.0,1.0,1.0,0.0,1.0,1.0,0.0,0.0,1.0,0.0,0.0,0.0,1.0,1.0,1.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,1.0,1.0,1.0,1.0,0.0
+11152667,1.0,0.0,0.0,1.0,1.0,0.0,1.0,0.0,1.0,1.0,1.0,1.0,1.0,1.0,0.0,1.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,1.0,0.0,1.0,0.0
+11228183,1.0,1.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0,1.0,1.0,1.0,0.0,0.0,1.0,1.0,1.0,0.0,1.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,1.0
+11433190,1.0,1.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,1.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,1.0,1.0,0.0,0.0,1.0,0.0