# Model card - tox21_xgb_classifier
### Model details
- Model name: XGBoost Tox21 Baseline
- Developer: JKU Linz
- Paper URL: https://cran.ms.unimelb.edu.au/web/packages/xgboost/vignettes/xgboost.pdf
- Model type / architecture:
    - Extreme Gradient Boosting implemented using `xgboost`.
    - Hyperparameters: https://huggingface.co/spaces/ml-jku/tox21_xgb_classifier/blob/main/config/config.json
    - A separate single-task RF is trained for each Tox21 target.
- Inference: Access via FastAPI endpoint. Upon receiving a Tox21 prediction request,
the model generates and returns predictions for all Tox21 targets simultaneously.
- Model version: v0
- Model date: 14.10.2025
- Reproducibility: Code for full training is available and enables reproducible retraining
of the model from scratch.

### Intended use
This model serves as a baseline benchmark for evaluating and comparing toxicity prediction
methods across the 12 pathway assays of the Tox21 dataset. It is not intended for clinical
decision-making without experimental validation.

### Metric
Each Tox21 task is evaluated using the area under the receiver operating characteristic curve (AUC). Overall performance is reported as the mean AUC across all individual tasks.

### Training data
Tox21 training and validation sets.

### Evaluation data
Tox21 test set.