Parametrization of Non-Bonded Force Field Terms for Metal-Organic Frameworks Using Machine Learning Approach

TL;DR

This paper introduces a machine learning approach to accurately parametrize non-bonded force field terms for metal-organic frameworks, enabling efficient and precise modeling of host-guest interactions for high-throughput screening.

Contribution

It develops ML models that reproduce quantum-level properties for MOFs, improving force field transferability and accuracy in simulating complex interactions.

Findings

ML models accurately reproduce DFT-calculated properties

Enhanced force field transferability for MOFs

Facilitates hybrid simulation workflows

Abstract

The enormous structural and chemical diversity of metal-organic frameworks (MOFs) forces researchers to actively use simulation techniques on an equal footing with experiments. MOFs are widely known for outstanding adsorption properties, so precise description of host-guest interactions is essential for high-throughput screening aimed at ranking the most promising candidates. However, highly accurate ab initio calculations cannot be routinely applied to model thousands of structures due to the demanding computational costs. On the other side, methods based on force field (FF) parametrization suffer from low transferability. To resolve this accuracy-efficiency dilemma, we apply the machine learning (ML) approach. The trained models reproduce atom-in-material quantities, including partial charges, polarizabilities, dispersion coefficients, quantum Drude oscillator and electron cloud parameters within the accuracy of underlying density functional theory method. The aforementioned FF precursors make it possible to thoroughly describe non-covalent interactions typical for MOF-adsorbate systems: electrostatic, dispersion, polarization, and short-range repulsion. The presented approach can also significantly facilitate hybrid atomistic simulations/ML workflows.