---
title: Rasayan Tox21 Classifier
emoji: ☠️
colorFrom: red
colorTo: purple
sdk: docker
app_port: 7860
pinned: false
license: apache-2.0
short_description: SNN ensemble for Tox21 toxicity prediction
tags:
  - toxicity
  - tox21
  - drug-discovery
  - chemistry
  - snn
  - molecular-property-prediction
models:
  - rasayan-labs/rasayan-tox21-snn
---

# Rasayan Tox21 Classifier

<p align="center">
  <img src="https://img.shields.io/badge/Tox21-Challenge-red" alt="Tox21">
  <img src="https://img.shields.io/badge/Architecture-SNN-blue" alt="SNN">
  <img src="https://img.shields.io/badge/Endpoints-12-green" alt="12 Endpoints">
  <img src="https://img.shields.io/badge/License-Apache_2.0-yellow" alt="License">
</p>

A production-ready **Self-Normalizing Neural Network (SNN) ensemble** for predicting molecular toxicity across the 12 Tox21 Challenge endpoints. Built for the [ml-jku Tox21 Leaderboard](https://huggingface.co/spaces/ml-jku/tox21_leaderboard).

## Model Overview

| Property | Value |
|----------|-------|
| **Architecture** | 10-fold ensemble of SNNs |
| **Parameters** | ~19M total |
| **Hidden Layers** | 8 layers × 768 units |
| **Activation** | SELU + AlphaDropout |
| **Training** | 300 epochs, 40-fold CV |
| **CV AUC** | 0.882 ± 0.021 |

## Molecular Features (11,377 total)

| Feature Type | Dimensions | Description |
|--------------|------------|-------------|
| **ECFP6** | 8,192 | Extended-connectivity fingerprints (radius 3) |
| **MACCS Keys** | 167 | Structural keys for substructure screening |
| **RDKit Descriptors** | 208 | Physicochemical properties (LogP, TPSA, MW, etc.) |
| **Toxicophores** | 1,868 | SMARTS-based toxicity structural alerts |
| **Structural Filters** | 815 | PAINS, BRENK, NIH, ZINC filter alerts |
| **Target Similarity** | 127 | Tanimoto similarity to known receptor ligands |

## Training Details

- **Loss Function**: Focal Loss (γ=2.5, α=0.25) for class imbalance
- **Regularization**: Label smoothing (0.1), Mixup augmentation (α=0.2)
- **Feature Selection**: Variance-based selection per fold (ECFP, toxicophores)
- **Normalization**: SquashScaler (StandardScaler → tanh → StandardScaler)
- **Ensemble Selection**: Top-10 folds from 40-fold stratified CV

## Tox21 Endpoints

### Nuclear Receptor Panel
| Endpoint | Target | Biological Significance |
|----------|--------|------------------------|
| **NR-AR** | Androgen Receptor | Male reproductive toxicity |
| **NR-AR-LBD** | AR Ligand Binding Domain | Direct AR modulation |
| **NR-AhR** | Aryl Hydrocarbon Receptor | Dioxin-like toxicity, carcinogenesis |
| **NR-Aromatase** | CYP19A1 Enzyme | Estrogen synthesis disruption |
| **NR-ER** | Estrogen Receptor | Endocrine disruption |
| **NR-ER-LBD** | ER Ligand Binding Domain | Direct ER modulation |
| **NR-PPAR-gamma** | PPARγ | Metabolic disruption |

### Stress Response Panel
| Endpoint | Target | Biological Significance |
|----------|--------|------------------------|
| **SR-ARE** | Antioxidant Response Element | Oxidative stress |
| **SR-ATAD5** | ATAD5 | DNA damage response |
| **SR-HSE** | Heat Shock Element | Protein folding stress |
| **SR-MMP** | Mitochondrial Membrane Potential | Mitochondrial toxicity |
| **SR-p53** | Tumor Protein p53 | Genotoxicity |

## API Endpoints

| Endpoint | Method | Description |
|----------|--------|-------------|
| `/metadata` | GET | Model configuration and capabilities |
| `/predict` | POST | Toxicity predictions for SMILES |
| `/health` | GET | Health check |

## Usage

### Python
```python
import requests

response = requests.post(
    "https://rasayan-labs-rasayan-tox21.hf.space/predict",
    json={"smiles": ["CC(=O)Nc1ccc(O)cc1", "c1ccccc1"]}
)

predictions = response.json()["predictions"]
for smiles, scores in predictions.items():
    print(f"{smiles}:")
    for target, prob in sorted(scores.items(), key=lambda x: -x[1])[:3]:
        print(f"  {target}: {prob:.1%}")
```

### cURL
```bash
curl -X POST "https://rasayan-labs-rasayan-tox21.hf.space/predict" \
  -H "Content-Type: application/json" \
  -d '{"smiles": ["CCO", "c1ccccc1"]}'
```

## Response Format

```json
{
  "predictions": {
    "CCO": {
      "NR-AR": 0.041,
      "NR-AR-LBD": 0.040,
      "NR-AhR": 0.049,
      "NR-Aromatase": 0.078,
      "NR-ER": 0.133,
      "NR-ER-LBD": 0.076,
      "NR-PPAR-gamma": 0.058,
      "SR-ARE": 0.100,
      "SR-ATAD5": 0.038,
      "SR-HSE": 0.066,
      "SR-MMP": 0.082,
      "SR-p53": 0.052
    }
  },
  "model_info": {
    "name": "Rasayan Tox21 SNN Ensemble",
    "version": "1.0.0"
  }
}
```

## Interpretation Guide

| Probability | Risk Level | Recommendation |
|-------------|------------|----------------|
| < 0.2 | Minimal | Unlikely to be active |
| 0.2 - 0.4 | Low | Monitor for chronic exposure |
| 0.4 - 0.7 | Moderate | Further investigation warranted |
| ≥ 0.7 | High | Strong toxicity signal |

## References

- **Tox21 Challenge**: [NIH Tox21 Data Challenge](https://tripod.nih.gov/tox21/challenge/)
- **SNN Architecture**: [Klambauer et al., 2017](https://arxiv.org/abs/1706.02515)
- **Leaderboard**: [ml-jku Tox21 Leaderboard](https://huggingface.co/spaces/ml-jku/tox21_leaderboard)

## License

Apache 2.0

---

<p align="center">
  Built by <a href="https://rasayan.ai">Rasayan Labs</a>
</p>