Publication
HoneyBee has been officially published in Nature Digital Medicine!
Tripathi, A., Waqas, A., Schabath, M.B. et al. HONeYBEE: enabling scalable multimodal AI in oncology through foundation model-driven embeddings. npj Digit. Med. 8, 622 (2025). https://doi.org/10.1038/s41746-025-02003-4
Overview
HoneyBee is a comprehensive multimodal AI framework designed specifically for oncology research and clinical applications. It seamlessly integrates and processes diverse medical data types—clinical text, radiology images, pathology slides, and molecular data—through a unified, modular architecture. Built with scalability and extensibility in mind, HoneyBee empowers researchers to develop sophisticated AI models for cancer diagnosis, prognosis, and treatment planning.
Key Features
- Multimodal data support: clinical text, radiology (DICOM/NIFTI), pathology (WSI), and molecular data
- 3-layer modular architecture: clean separation between loaders, processors, and embedding models
- Clinical NLP pipeline: OCR, cancer entity extraction, temporal parsing, and medical ontology mapping
- Whole Slide Image processing: tissue detection, patch extraction, stain normalization, and quality filtering
- State-of-the-art embedding models: GatorTron, BioBERT, PubMedBERT, UNI, REMEDIS, RadImageNet, and more
- Cross-modal integration: unified patient-level representations from multiple data modalities
- Survival analysis: Cox PH, Random Survival Forest, and DeepSurv
- Similar patient retrieval: find patients with matching clinical profiles
- Interactive visualization: t-SNE dashboards for embedding exploration
- GPU-accelerated: CuCIM backend for WSI processing with OpenSlide fallback
Quick Start
System Dependencies
# Ubuntu/Debian
sudo apt-get install -y openslide-tools tesseract-ocr
# macOS
brew install openslide tesseract
Installation
pip install honeybee-ml
python -c "import nltk; nltk.download('punkt'); nltk.download('punkt_tab')"
Optional Extras
| Extra | Command | Includes |
|---|---|---|
| Clinical | pip install honeybee-ml[clinical] |
NLP, OCR, and text processing dependencies |
| Pathology | pip install honeybee-ml[pathology] |
WSI loading and image processing |
| Molecular | pip install honeybee-ml[molecular] |
Genomics and expression data support |
| All | pip install honeybee-ml[all] |
Everything above |
Research Applications
HoneyBee has been successfully applied to:
- Cancer Subtype Classification: Automated identification of cancer subtypes from multimodal data
- Survival Prediction: Risk stratification and outcome prediction for treatment planning
- Similar Patient Retrieval: Finding patients with similar clinical profiles for precision medicine
- Biomarker Discovery: Identifying multimodal patterns associated with treatment response
License
See the LICENSE file for details.
Citation
If you use HoneyBee in your research, please cite our paper:
Tripathi, A., Waqas, A., Schabath, M.B. et al. HONeYBEE: enabling scalable multimodal AI in
oncology through foundation model-driven embeddings. npj Digit. Med. 8, 622 (2025).
https://doi.org/10.1038/s41746-025-02003-4
Metadata
Release files for honeybee-ml 0.3.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| honeybee_ml-0.3.0.tar.gz | 160.1 kB | Without provenance | Details for honeybee_ml-0.3.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| honeybee_ml-0.3.0-py3-none-any.whl | Python 3 | none | any | Details for honeybee_ml-0.3.0-py3-none-any.whl |
Total release size: 348.8 kB
Release files / honeybee_ml-0.3.0.tar.gz
| Download URL | honeybee_ml-0.3.0.tar.gz |
|---|---|
| Size | 160.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
89df2eed2e7ce949763bb83c494cc255e3be541001de7876f7b422eb7015c04b
|
|
BLAKE2b-256 checksum How to use checksums |
eac362ecbc146e8b8286b16b7c4d53e4b0eab7936715e044e2abe0cec941effc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Release files / honeybee_ml-0.3.0-py3-none-any.whl
| Download URL | honeybee_ml-0.3.0-py3-none-any.whl |
|---|---|
| Size | 188.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ef65fac0ae0ad202eac5b445f56904e5f7271500947d48ce06beb97601063bcd
|
|
BLAKE2b-256 checksum How to use checksums |
2d6ba8e7b7cb1abf2f61188e58a046689614d76a8786b42e3b3b390c878324ff
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Security for honeybee-ml 0.3.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.