---
language: en
tags:
  - bioinformatics
  - microbiology
  - microbiome
  - taxonomy-classification
  - deep-learning
  - 16s-rrna
datasets:
  - systems-genomics-lab/greengenes
metrics:
  - accuracy
  - precision
  - recall
  - f1
license: mit
model-index:
  - name: DeepTaxa Hybrid CNN-BERT (April 2025)
    results:
      - task:
          type: classification
          name: Hierarchical Taxonomy Classification
        dataset:
          type: systems-genomics-lab/greengenes
          name: Greengenes (2024-09 Validation Split)
          split: validation
        metrics:
          - type: accuracy
            value: 0.9999258655200534
            name: Domain Accuracy
          - type: accuracy
            value: 0.9992339437072182
            name: Phylum Accuracy
          - type: accuracy
            value: 0.9988879828008006
            name: Class Accuracy
          - type: accuracy
            value: 0.9971581782687128
            name: Order Accuracy
          - type: accuracy
            value: 0.9950824128302074
            name: Family Accuracy
          - type: accuracy
            value: 0.9833444535053253
            name: Genus Accuracy
          - type: accuracy
            value: 0.9528751822472632
            name: Species Accuracy
---

# DeepTaxa: Hybrid CNN-BERT Model (April 2025)

**DeepTaxa** is a deep learning framework for hierarchical taxonomy classification of 16S rRNA gene sequences. This repository hosts the pre-trained hybrid CNN-BERT model, combining convolutional neural networks (CNNs) and BERT for high-accuracy predictions across seven taxonomic levels: domain, phylum, class, order, family, genus, and species.

## Model Details
- **Architecture**: HybridCNNBERTClassifier (CNN + BERT)
- **Tokenizer**: `zhihan1996/DNABERT-2-117M`
- **Training Data**: Greengenes dataset (2024-09 split)
- **Levels Predicted**: 7 (Domain: 2 labels, Phylum: 106, Class: 244, Order: 630, Family: 1353, Genus: 4798, Species: 10547)
- **Total Parameters**: 72,635,154
- **Max Sequence Length**: 512
- **Dropout Probability**: 0.2
- **License**: MIT
- **Version**: April 2025
- **File**: `deeptaxa_april_2025.pt`

## Usage

### Download the Model
To get started, download the pre-trained model file `deeptaxa_april_2025.pt` from this repository:

- **Manual Download**: Visit [https://huggingface.co/systems-genomics-lab/deeptaxa](https://huggingface.co/systems-genomics-lab/deeptaxa), click on the "Files and versions" tab, and download `deeptaxa_april_2025.pt` (871 MB).
- **Command Line (wget)**:
  ```bash
  wget https://huggingface.co/systems-genomics-lab/deeptaxa/resolve/main/deeptaxa_april_2025.pt
  ```
- **Command Line (git clone)**:
  ```bash
  git clone https://huggingface.co/systems-genomics-lab/deeptaxa
  cd deeptaxa
  # The model file is now in the current directory
  ```

### Run Predictions
Once downloaded, use the model with the DeepTaxa CLI:
```bash
python -m deeptaxa.cli predict \
  --fasta-file /path/to/sequences.fna.gz \
  --checkpoint deeptaxa_april_2025.pt
```

Full instructions are available on the [GitHub repository](https://github.com/systems-genomics-lab/deeptaxa).

## Training Details
- **Dataset**: 161,866 training sequences, 40,467 validation sequences from [Greengenes](https://huggingface.co/datasets/systems-genomics-lab/greengenes) (`gg_2024_09_training.fna.gz`, `gg_2024_09_training.tsv.gz`)
- **Hyperparameters**:
  - Learning Rate: 0.0001
  - Batch Size: 16
  - Epochs: 10
  - Optimizer: AdamW (lr=0.0001, betas=[0.9, 0.999], weight_decay=0.01)
  - Focal Loss Gamma: 2.0
  - Level Weights: [1.0, 1.5, 2.0, 2.5, 3.0, 4.0, 5.0]
- **Training Time**: ~21 minutes (1,254 seconds) on NVIDIA A40 GPU
- **Timestamp**: Trained on 2025-04-04

## Performance
Validation metrics (on 40,467 sequences):
| Level    | Accuracy | Precision | Recall | F1-Score |
|----------|----------|-----------|--------|----------|
| Domain   | 99.99%   | 99.99%    | 99.99% | 99.99%   |
| Phylum   | 99.92%   | 99.92%    | 99.92% | 99.92%   |
| Class    | 99.89%   | 99.85%    | 99.89% | 99.87%   |
| Order    | 99.72%   | 99.64%    | 99.72% | 99.67%   |
| Family   | 99.51%   | 99.32%    | 99.51% | 99.40%   |
| Genus    | 98.33%   | 97.89%    | 98.33% | 98.01%   |
| Species  | 95.29%   | 94.34%    | 95.29% | 94.56%   |
- **Training Loss**: 0.283
- **Validation Loss**: 0.606


## Intended Use
- Taxonomy classification in microbiome research and microbial ecology.

## Limitations
- GPU recommended (trained on NVIDIA A40).
- Lower precision at species level due to label complexity (10,547 classes).

## Citation
If you use this model in your research, please cite:
```bibtex
@software{DeepTaxa,
  author = {{Systems Genomics Lab}},
  title = {DeepTaxa: Hierarchical Taxonomy Classification of 16S rRNA Sequences with Deep Learning},
  year = {2025},
  publisher = {GitHub},
  url = {https://github.com/systems-genomics-lab/deeptaxa},
}
```

## Contact
Open an issue on [GitHub](https://github.com/systems-genomics-lab/deeptaxa/issues) for support.

## Acknowledgements
- **[Dr. Olaitan I. Awe](https://github.com/laitanawe)** and the Omics Codeathon team for their mentorship and contributions.
- **[Hugging Face](https://huggingface.co/)** for providing a platform to host datasets and models.
- **The High-Performance Computing Team of [the School of Sciences and Engineering (SSE)](https://sse.aucegypt.edu/) at [the American University in Cairo (AUC)](https://www.aucegypt.edu/)** for their support and for granting access to GPU resources that enabled this work.