Interpretable Machine Learning (IML) for the Discovery of Metal-Organic Frameworks (MOFs)

This repository contains the data and scripts involved in the publication:

Interpretable Machine Learning for Accelerating the Discovery of Metal-Organic Frameworks for Ethane/Ethylene Separation

Requirements

Library (Python 3.7)

• matminer: calculation of classical force-field inspired descriptors for MOFs
• scikit-learn: development of ML models
• SHAP: interpretation of ML models
• matplotlib & seaborn: visualization

Software

• PaDEL-Descriptor: calculation of PubChem fingerprints for MOFs

Authors

• Zihao Wang
• Prof. Dr.-Ing. Teng Zhou
• Prof. Dr.-Ing. Kai Sundmacher