| --- |
| license: cc-by-nc-4.0 |
| tags: |
| - chemistry |
| - biology |
| --- |
| # ByteFF2 |
|
|
| This repository contains the model and example data used for ByteFF-GNN and ByteFF-Pol. |
|
|
| * [ByteFF-GNN](https://pubs.rsc.org/en/content/articlehtml/2025/sc/d4sc06640e) is a molecular mechanics force field parameterized by an edge-augmented, symmetry-preserving graph neural network (GNN), trained on large-scale high-level quantum mechanics (QM) data. ByteFF-GNN enables fast, one-pass prediction of bonded and non-bonded parameters for drug-like molecules, achieving SOTA accuracy across torsional energy profiles, relaxed geometries, conformational energies, and off-equilibrium energies and forces. |
|
|
| * [ByteFF-Pol](https://www.nature.com/articles/s41467-026-73566-3) is a polarizable force field parameterized by a graph neural network (GNN), trained on high-level quantum mechanics (QM) data, thus eliminating the need for experimental calibration. ByteFF-Pol achieves exceptional accuracy in predicting the thermodynamic and transport properties of small-molecule liquids and electrolytes, outperforming SOTA traditional and ML force fields. |
|
|
| # Trained Models |
| * **ByteFF-Pol**: Two model versions are provided: |
| - `ByteFF-Pol/trained_models_v2/` — latest model (**recommended**). |
| - `trained_models/` — legacy v1 model, kept at the original path for backward compatibility (paired with `valid_data/`). |
| * **ByteFF-GNN**: Example training data in `ByteFF-GNN/example_data/`. |
|
|
|
|
| # How to use |
| Code and examples are available in the [byteff2](https://github.com/ByteDance-Seed/byteff2) repository. |
|
|
| ## Citation |
| If you find ByteFF-Pol or ByteFF-GNN is useful for your research and applications, feel free to give us a star ⭐ or cite us using: |
|
|
| ```bibtex |
| |
| @article{zheng2026bridging, |
| title = {Bridging quantum mechanics to liquid properties via a universal organic force field}, |
| author = {Tianze Zheng and Xingyuan Xu and Zhi Wang and Zhenze Yang and Yuanheng Wang and Xu Han and Lei Chen and Zhenliang Mu and Ziqing Zhang and Siyuan Liu and Sheng Gong and Kuang Yu and Wen Yan}, |
| year = {2026}, |
| journal = {Nature Communications}, |
| doi = {10.1038/s41467-026-73566-3}, |
| url = {https://www.nature.com/articles/s41467-026-73566-3} |
| } |
| |
| @Article{D4SC06640E, |
| author = {Tianze Zheng and Ailun Wang and Xu Han and Yu Xia and Xingyuan Xu and Jiawei Zhan and Yu Liu and Yang Chen and Zhi Wang and Xiaojie Wu and Sheng Gong and Wen Yan}, |
| title = {Data-driven parametrization of molecular mechanics force fields for expansive chemical space coverage}, |
| journal = {Chem. Sci.}, |
| year = {2025}, |
| pages = {-}, |
| publisher = {The Royal Society of Chemistry}, |
| doi = {10.1039/D4SC06640E}, |
| url = {http://dx.doi.org/10.1039/D4SC06640E} |
| } |
| |
| ``` |
