MOF Synthesis Prediction Enabled by Automatic Data Mining and Machine Learning. Issue 19 (10th March 2022)

• Record Type: Journal Article
• Authors: Luo, Yi; Bag, Saientan; Zaremba, Orysia; Cierpka, Adrian; Andreo, Jacopo; Wuttke, Stefan; Friederich, Pascal; Tsotsalas, Manuel
• Is Part Of: Angewandte Chemie international edition. Volume 61:Issue 19(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-03-10
• Subjects: Data Mining -- Machine Learning -- Metal–Organic Frameworks -- Microporous Materials -- Synthesis Prediction; Chemistry -- Periodicals; 540
• DOI: 10.1002/anie.202200242
• Languages: English
• ISSNs: 1433-7851

Abstract

Abstract: Despite rapid progress in the field of metal–organic frameworks (MOFs), the potential of using machine learning (ML) methods to predict MOF synthesis parameters is still untapped. Here, we show how ML can be used for rationalization and acceleration of the MOF discovery process by directly predicting the synthesis conditions of a MOF based on its crystal structure. Our approach is based on: i) establishing the first MOF synthesis database via automatic extraction of synthesis parameters from the literature, ii) training and optimizing ML models by employing the MOF database, and iii) predicting the synthesis conditions for new MOF structures. The ML models, even at an initial stage, exhibit a good prediction performance, outperforming human expert predictions, obtained through a synthesis survey. The automated synthesis prediction is available via a web‐tool on https://mof‐synthesis.aimat.science . Abstract : An approach to rationalize and accelerate MOF discovery by directly predicting the synthesis conditions of a MOF based on its crystal structure is reported. The prediction is based on machine learning models, trained on the SynMOF database, constructed via automatic data mining of synthesis parameters from the literature. The model outperforms human expert predictions according to a synthesis survey.