README.md

metadata

title: Flare
emoji: 🔥
colorFrom: green
colorTo: blue
sdk: streamlit
pinned: false
python_version: 3.11.7

🔥 FLARE

Fine-grained Learning for Aligment of spectra-molecule REpresentation

Authors

Yan Zhou Chen, Soha Hassoun
Department of Computer Science, Tufts University

---

FLARE is a framework for ranking molecular candidates given a mass spectrum. Beyond candidate ranking, FLARE provides visualization of peak-to-node attribution, enabling deeper insights into how spectral peaks correspond to molecular graph nodes.

---

🌐 Visualize Peak-to-Node Correspondence

Explore our interactive app to visualize peak-to-node attributes in real time.

---

🛠 Set up

Clone repository

git clone https://huggingface.co/spaces/HassounLab/FLARE
cd flare

Set up environment and install dependencies

conda create -n flare python=3.11
conda activate flare
pip install -r requirements.txt

---

🚀 Usage

Modify params.yaml as necessary

# preprocess data
python subformula_assign/assign_subformulae.py --spec-files ../data/sample/data.tsv --output-dir ../data/sample/subformulae --labels-file ../data/sample/data.tsv --max-formulae 60

# train 
python train.py

# test
python test.py

---

🙏 Acknowledgments

• Training Data: MassSpecGym
• Subformula Assigner Code: MIST

---

📧 Contact

For questions, reach out to [email protected]