Pétuya, Rémi 
ORCID: https://orcid.org/0000-0002-3118-6966, Durdy, Samantha, Antypov, Dmytro, Gaultois, Michael, Berry, Neil, Darling, George, Katsoulidis, Alexandros, Dyer, Matthew and Rosseinsky, Matthew
(2021)
Machine Learning Prediction of Metal-Organic Framework Guest Accessibility from Linker and Metal Chemistry.
[Data Collection]
Description
This data set contains the Jupyter notebook and four .csv files for 1M1L3D data set described in our paper. There is a summary file for the one-metal-one-linker-3D (1M1L3D) dataset that contains metal and linker identities for 14,296 3D MOFs reported in Cambridge Structural Database (CSD) that have exactly one type metal and linker. There are also three files that contain features used to train the machine learning models. The notebook implements 3 sequential models to predict the pore limiting diameter (sometimes referred to as a pore window, or a pore aperture) of a metal-organic framework structure that is likely to be observed for a given metal-linker combination defined by the user.
| Keywords: | metal-organic framework, machine learning, guest-accessibility, database, linker, porosity |
|---|---|
| Divisions: | Faculty of Science and Engineering > School of Physical Sciences > Chemistry |
| Depositing User: | Dmytro Antypov |
| Date Deposited: | 15 Dec 2021 14:44 |
| Last Modified: | 15 Dec 2021 14:50 |
| DOI: | 10.17638/datacat.liverpool.ac.uk/1494 |
| URI: | https://datacat.liverpool.ac.uk/id/eprint/1494 |
Available Files
Full Archive
Software: GNU GPL 4.0 |
Read me
Creative Commons: Attribution 4.0 |