EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Interpretable Machine-Learning Prediction of PPCP Adsorption by Metal–Organic Frameworks Using Different Molecular Fingerprints

Helu Liu, Xiaoliang Liu, Fang Tao, Hailu Fu, Jie Yu, Jie Ouyang, Baofeng Zhang, Hao Chen

Separations · 29.10.2026 · 13 (11) · 316

DOI: 10.3390/separations13110316 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Separations, online erschienen am 29.10.2026. Verfasst von Helu Liu und 7 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Research and Development Program of Zhejiang Province, Zhejiang Provincial Natural Science Foundation, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Pharmaceuticals and personal care products (PPCPs) are continuously introduced into aquatic environments, raising concerns about potential health risks from long-term exposure. Metal-organic frameworks (MOFs), owing to their abundant adsorption sites and tunable pore structures, show considerable potential for PPCP removal. However, experimental screening across diverse adsorbents and pollutants is time-consuming. This study developed a machine-learning framework to predict the adsorption capacity of PPCPs by MOFs at contact time and identify the key factors influencing model predictions. In total, 7324 adsorption records were collected; 7075 records covering 100 MOFs and 39 PPCPs were used for model development and internal evaluation, and 249 additional records were reserved for external validation. MACCS keys, binary Morgan fingerprints (BMF), and count-based Morgan fingerprints (CMF) were applied to encode PPCP structures, and eight machine learning models were systematically compared. Among all model–fingerprint combinations, BMF–CatBoost achieved the best predictive performance, with a test-set R2 of 0.9723, and was selected as the optimal model. SHAP and accumulated local effects (ALE) analyses identified key factors and favorable response ranges associated with enhanced adsorption capacity. Overall, this study provides a data-driven methodology for rapid adsorption capacity prediction, key factor identification, and experimental condition optimization in MOF-based PPCP adsorption.

Förderung

  • Key Research and Development Program of Zhejiang Province
  • Zhejiang Provincial Natural Science Foundation
  • National Natural Science Foundation of China
  • Hangzhou Agricultural and Social Development Research Guidance Project
  • National Key Research and Development Program of China

Zitieren

APA

Liu, H., Liu, X., Tao, F., Fu, H., Yu, J., Ouyang, J., Zhang, B., & Chen, H. (2026). Interpretable Machine-Learning Prediction of PPCP Adsorption by Metal–Organic Frameworks Using Different Molecular Fingerprints. Separations, 13(11), 316. https://doi.org/10.3390/separations13110316

Vancouver

Liu H, Liu X, Tao F, Fu H, Yu J, Ouyang J, et al. Interpretable Machine-Learning Prediction of PPCP Adsorption by Metal–Organic Frameworks Using Different Molecular Fingerprints. Separations. 2026;13(11):316. doi:10.3390/separations13110316

BibTeX
@article{Liu2026,
  author = {Liu, Helu and Liu, Xiaoliang and Tao, Fang and Fu, Hailu and Yu, Jie and Ouyang, Jie and Zhang, Baofeng and Chen, Hao},
  title = {Interpretable Machine-Learning Prediction of PPCP Adsorption by Metal–Organic Frameworks Using Different Molecular Fingerprints},
  journal = {Separations},
  year = {2026},
  volume = {13},
  number = {11},
  pages = {316},
  doi = {10.3390/separations13110316}
}
Kostenlos starten →