Predicting ruthenium catalysed hydrogenation of esters using machine learning

Mishra, Challenger; Wolff, Niklas von; Tripathi, A.K.; Brodie, Claire N; Lawrence, Neil D.; Ravuri, Aditya; Brémond, Éric; Preiss, A.; Kumar, Amit

doi:10.1039/d3dd00029j

Cited by 2 publications

(1 citation statement)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other studies such as those by Friederich et al for predicting barrier heights of dihydrogen activation by Vaska complexes and Jones et al for the prediction of C–H bond activation by iron(IV)-oxo compounds show the utility of various featurization methods on reactions that include transition metals. In general, there have been a wide variety of approaches of applying machine learning models to reaction barrier heights from dealing with featurization methods to generating complex deep learning methodologies. − Grayson and co-workers recently provided an overview of the use of machine learning models for predicting reaction activation energies …”

Section: Results and Discussionmentioning

confidence: 99%

Machine Learning Models for Predicting Zirconocene Properties and Barriers

Kirkland,

Kumawat,

Shaban Tameh

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Zr metallocenes have significant potential to be highly tunable polyethylene catalysts through modification of the aromatic ligand framework. Here we report the development of multiple machine learning models using a large library (>700 systems) of DFT-calculated zirconocene properties and barriers for ethylene polymerization. We show that very accurate machine learning models are possible for HOMO–LUMO gaps of precatalysts but the performance significantly depends on the machine learning algorithm and type of featurization, such as fingerprints, Coulomb matrices, smooth overlap of atomic positions, or persistence images. Surprisingly, the description of the bonding hapticity, the number of direct connections between Zr and the ligand aromatic carbons, only has a moderate influence on the performance of most models. Despite robust models for HOMO–LUMO gaps, these types of machine learning models based on structure connectivity type features perform poorly in predicting ethylene migratory insertion barrier heights. Therefore, we developed several relatively robust and accurate machine learning models for barrier heights that are based on quantum-chemical descriptors (QCDs). The quantitative accuracy of these models depends on which potential energy surface structure QCDs were harvested from. This revealed a Hammett-type principle to naturally emerge showing that QCDs from the π-coordination complexes provide much better descriptions of the transition states than other potential-energy structures. Feature importance analysis of the QCDs provides several fundamental principles that influence zirconocene catalyst reactivity.

show abstract