Dataset not found. Browse the registry.
Molecular properties
Blood-Brain Barrier Penetration (Martins)
The Martins dataset labels compounds by whether they cross the blood-brain barrier. The benchmark uses molecular fingerprints to distinguish compounds labelled as penetrating the barrier from those labelled as non-penetrating.
Binary classificationLicence: CC BY 4.0 via TDC; underlying source terms require verification before re-hostingTDC-BBB-MartinsTarget: Ytdc ↗
Loading model results…
At this operating point
Model comparison
p=10,000, n=100 · Higher Macro-F1 is better
No scores at this operating point. Select another feature or sample budget.
Random Forest is marked with a diamond. Models are ordered by the selected metric.
Across sample budgets
Learning curves
All metric values at this operating point
| Model | Macro-F1 | MCC | Balanced accuracy | ROC-AUC |
|---|---|---|---|---|
| RealMLP | 0.7275 | 0.4751 | 0.7048 | 0.7641 |
| RealTabPFN 2.5 | 0.7159 | 0.5098 | 0.6822 | 0.7669 |
| TabDPT † | 0.7128 | 0.461 | 0.6904 | 0.7679 |
| TabICL v2 | 0.7074 | 0.4312 | 0.6964 | 0.7877 |
| TabFM | 0.7029 | 0.4397 | 0.6842 | 0.7816 |
| AutoGluon | 0.6999 | 0.4686 | 0.6748 | 0.7877 |
| MITRA | 0.696 | 0.4881 | 0.6651 | 0.7706 |
| Logistic Regression | 0.6889 | 0.4688 | 0.661 | 0.7793 |
| MLP | 0.6883 | 0.433 | 0.6709 | 0.7379 |
| TabPFN Wide (8k) ‡ | 0.6862 | 0.4585 | 0.6582 | 0.7781 |
| TabPFN 3 | 0.6825 | 0.4703 | 0.6542 | 0.789 |
| RealTabPFN v2 | 0.6788 | 0.4596 | 0.651 | 0.7747 |
| TabM | 0.676 | 0.4548 | 0.6492 | 0.7885 |
| TabPFN Wide 5k (ne3) ‡ | 0.6742 | 0.4587 | 0.6469 | 0.7833 |
| Random Forest | 0.669 | 0.4563 | 0.6425 | 0.7789 |
| Extra Trees | 0.663 | 0.4477 | 0.6382 | 0.7831 |
| CatBoost | 0.6598 | 0.4408 | 0.6357 | 0.7559 |
| XGBoost | 0.6576 | 0.4031 | 0.6395 | 0.735 |
| LightGBM | 0.6315 | 0.3221 | 0.6166 | 0.7023 |
| KNN | 0.5796 | 0.3345 | 0.579 | 0.692 |