Using collective knowledge to assign oxidation states
- 1. Laboratory of Molecular Simulation (LSMO), Institut des Sciences et Ingenierie Chimiques (ISIC), École Polytechnique Fédérale de Lausanne (EPFL), Sion, VS, Switzerland
* Contact person
Description
Knowledge of the oxidation state of a metal centre in a material is essential to understand its properties. Chemists have developed theories to predict the oxidation state based on counting rules, which can fail to describe the oxidation states of systems such as metal-organic frameworks. Here we present a data-driven approach to automatically assign oxidation states, using a machine learning model trained on assignments by chemists encoded in the chemical names in the Cambridge Crystallographic Database. Our approach only considers the immediate local environment around a metal centre, and is robust to experimental uncertainties (like incorrect protonation, unbound solvents, or changes in bondlength). We find such excellent accuracy in our predictions that we can use our method to detect incorrect assignments. This work nicely illustrates how powerful the collective knowledge of chemists is. Machine learning can harvest this knowledge and convert it into a useful tool for chemists.
Files
File preview
files_description.md
All files
References
Preprint (Preprint where the data and model is discussed.) K. M. Jablonka, D. Ongari, S. M. Moosavi, B. Smit, Using Collective Knowledge to Assign Oxidation States. ChemRxiv preprint (2020)., doi: 10.26434/chemrxiv.11604129.v1
Software (Code that can be used to generate the feature matrix.) K. M. Jablonka, D. Ongari, S. M. Moosavi, B. Smit, Zenodo (2019)., doi: 10.5281/zenodo.3567274
Software (Software that implements the code to train and test the models.) K. M. Jablonka, D. Ongari, S. M. Moosavi, B. Smit, Zenodo (2019)., doi: 10.5281/zenodo.3567011
Journal reference K. M. Jablonka, D. Ongari, S. M. Moosavi, B. Smit, Nature Chemistry 13, 771-777 (2021), doi: 10.1038/s41557-021-00717-y