Interpretable-Machine-Learning-MOFs-Arsenic-Adsorption

Environment requirements:

Python 3.8.19:

Molecular fingerprint generation, model training, and interpretation

R 4.2.1

Visualization

Code files:

.ipynb:

The .ipynb file was uesed to interpret and visualize the models.

.py:

The .py files were used to generate the molecular fingerprints and training the predictive models.

.R:

The .R files were used to visualize the data.

package:

requirement.txt

Use pip install -r requirements.txt to configure the environment

Citing:

If you use the dataset or any trained models in your work, please cite the following article-

Z. Lin, H. Cai, H. Peng, Y. Fang, P. Pan, H. Li, Y. Yang and J. Yao, Enhancing arsenate removal through interpretable machine learning guiding the modular design of metal–organic frameworks. Chemical Engineering Journal 2024.