Machine-Learning Prediction of Metal-Organic Framework Guest Accessibility from Linker and Metal Chemistry

Rémi Pétuya; Samantha Durdy; Dmytro Antypov; Michael W Gaultois; Neil G Berry; George R Darling; Alexandros P Katsoulidis; Matthew S Dyer; Matthew J Rosseinsky

doi:10.1002/anie.202114573

Machine-Learning Prediction of Metal-Organic Framework Guest Accessibility from Linker and Metal Chemistry

Angew Chem Int Ed Engl. 2022 Feb 21;61(9):e202114573. doi: 10.1002/anie.202114573. Epub 2022 Jan 12.

Authors

Rémi Pétuya^{1

2}, Samantha Durdy^{3

4}, Dmytro Antypov^{1

3}, Michael W Gaultois^{1

3}, Neil G Berry¹, George R Darling¹, Alexandros P Katsoulidis^{1

3}, Matthew S Dyer^{1

3}, Matthew J Rosseinsky^{1

3}

Affiliations

¹ Department of Chemistry and Materials Innovation Factory, University of Liverpool, 51 Oxford Street, Liverpool, L7 3NY, UK.
² Present address: Nextmol (Bytelab Solutions SL), 08018, Barcelona, Spain.
³ Leverhulme Research Centre for Functional Materials Design, University of Liverpool, 51 Oxford Street, Liverpool, L7 3NY, UK.
⁴ Department of Computer Science, University of Liverpool, Ashton Street, Liverpool, L69 3BX, UK.

Abstract

The choice of metal and linker together define the structure and therefore the guest accessibility of a metal-organic framework (MOF), but the large number of possible metal-linker combinations makes the selection of components for synthesis challenging. We predict the guest accessibility of a MOF with 80.5 % certainty based solely on the identity of these two components as chosen by the experimentalist, by decomposing reported experimental three-dimensional MOF structures in the Cambridge Structural Database into metal and linker and then learning the connection between the components' chemistry and the MOF porosity. Pore dimensions of the guest-accessible space are classified into four ranges with three sequential models. Both the dataset and the predictive models are available to download and offer simple guidance in prioritization of the choice of the components for exploratory MOF synthesis for separation and catalysis based on guest accessibility considerations.

Keywords: Database; Guest accessibility; Machine learning; Metal-organic frameworks; Porosity.

Abstract

Grants and funding