mofclassifier 0.1.2

A Machine Learning Approach for Validating Computation-Ready Metal-Organic Frameworks

MOFClassifier: A Machine Learning Approach for Validating Computation-Ready Metal-Organic Frameworks

Installation

pip install MOFClassifier

Examples

from MOFClassifier import CLscore
result = CLscore.predict(root_cif="./example.cif", model="core")

• root_cif: the path of your structure
• model: the model name: a. "core": training with CoRE MOF DB; b. "qsp": training with CoRE MOF DB and QMOF DB; c. "h": training with ToBaCCo (Hypothetical MOFs)
• result: a. cifid: the name of structure; b. all_score: the CLscore predicted by 100 models (bags); c. mean_score: the mean CLscore of CLscores

from MOFClassifier import CLscore
results = CLscore.predict_batch(root_cifs=["./example1.cif""./example2.cif","./example3.cif"], model="core", batch_size=512)

• root_cifs: the path of your structures
• model: the model name: a. "core": training with CoRE MOF DB; b. "qsp": training with CoRE MOF DB and QMOF DB; c. "h": training with ToBaCCo (Hypothetical MOFs)
• batch_size: the number of samples
• results: a. cifid: the name of structure; b. all_score: the CLscore predicted by 100 models (bags); c. mean_score: the mean CLscore of CLscores

Citation

Guobin Zhao, Pengyu Zhao and Yongchul G. Chung. Journal of the American Chemical Society, 2025, 147, 37, 33343–33349. DOI: 10.1021/jacs.5c10126

Acknowledgments

We thank henk789 for contribution to batch prediction.