Bgolearn

Bgolearn is among the first unified Bayesian optimization frameworks purpose-built for the materials science community.

Language: English | 简体中文 | 日本語

Tip

Bgolearn is among the first unified Bayesian optimization frameworks purpose-built for the materials science community.
While most Bayesian optimization libraries were originally developed for generic machine learning or black-box optimization, Bgolearn systematically bridges Bayesian optimization, active learning, and materials discovery within a lightweight yet extensible framework. It integrates single-objective and multi-objective optimization, uncertainty-aware surrogate modeling, acquisition-driven experiment recommendation, and automated virtual screening into a unified workflow tailored for real-world materials design. By dramatically reducing experimental search costs while maintaining high discovery efficiency, Bgolearn represents an important step toward fully autonomous, AI-driven materials optimization and closed-loop scientific discovery.

About

Bgolearn is a research-oriented Python framework for Bayesian Global Optimization (BGO), developed to accelerate data-driven materials discovery and scientific design.

The framework provides:

• Unified regression and classification modeling
• Modular acquisition functions
• Multi-objective optimization
• Active learning workflows
• Virtual screening pipelines

Bgolearn emphasizes reproducibility, extensibility, and research-grade rigor, making it suitable for both academic research and industrial applications.

---

Run the Interface

1. Open the terminal.

2. Clone the repository:

git clone https://github.com/Bin-Cao/Bgolearn.git

3. Navigate to the project directory:

cd Bgolearn

4. Launch the UI:

python bgolearn_ui.py

This will start the Bgolearn user interface.

http://127.0.0.1:8787

---

Installation

Install from PyPI:

pip install Bgolearn

Upgrade to the latest version:

pip install --upgrade Bgolearn

Check installed version:

pip show Bgolearn

---

Citation

If you use Bgolearn in your research, please cite:

@article{cao2026bgolearn,
  title        = {Bgolearn: a Unified Bayesian Optimization Framework for Accelerating Materials Discovery},
  author       = {Cao, Bin and Xiong, Jie and Ma, Jiaxuan and Tian, Yuan and Hu, Yirui and He, Mengwei and Zhang, Longhan and Wang, Jiayu and Hui, Jian and Liu, Li and Xue, Dezhen and Lookman, Turab and Zhang, Tong-Yi},
  journal      = {arXiv preprint arXiv:2601.06820},
  year         = {2026},
  eprint       = {2601.06820},
  archivePrefix= {arXiv},
  primaryClass = {cond-mat.mtrl-sci},
  doi          = {https://doi.org/10.48550/arXiv.2601.06820}
}

---

Funding

Bgolearn is selected for the Open-Source Artificial Intelligence Support Program (2025) by the Shanghai Municipal Commission of Economy and Informatization (上海市经信委).

Project material: https://github.com/Bin-Cao/Bgolearn/blob/main/figures/funding.png

---

Contributors