$\Delta$-ML Ensembles for Selecting Quantum Chemistry Methods to Compute Intermolecular Interactions

TL;DR

This paper introduces a $ ext{ extDelta}$-ML ensemble framework that predicts errors of quantum chemistry methods for intermolecular interactions, enabling efficient method selection and comparison with high accuracy.

Contribution

The work presents a novel ensemble of $ ext{ extDelta}$-ML models trained on neural network features to estimate errors between quantum chemistry methods, improving method selection and understanding.

Findings

Achieves mean-absolute-errors below 0.1 kcal/mol across methods

Identifies method groupings consistent with theoretical expectations

Enables efficient selection of computationally suitable methods

Abstract

Ab initio quantum chemical methods for accurately computing interactions between molecules have a wide range of applications but are often computationally expensive. Hence, selecting an appropriate method based on accuracy and computational cost remains a significant challenge due to varying performance of methods. In this work, we propose a framework based on an ensemble of $\Delta$-ML models trained on features extracted from a pre-trained atom-pairwise neural network to predict the error of each method relative to all other methods including the ``gold standard'' coupled cluster with single, double, and perturbative triple excitations at the estimated complete basis set limit [CCSD(T)/CBS]. Our proposed approach provides error estimates across various levels of theories and identifies the computationally efficient approach for a given error range utilizing only a subset of the dataset. Further, this approach allows comparison between various theories. We demonstrate the effectiveness of our approach using an extended BioFragment dataset, which includes the interaction energies for common biomolecular fragments and small organic dimers. Our results show that the proposed framework achieves very small mean-absolute-errors below 0.1 kcal/mol regardless of the given method. Furthermore, by analyzing all-to-all $\Delta$-ML models for present levels of theory, we identify method groupings that align with theoretical hypotheses, providing evidence that $\Delta$-ML models can easily learn corrections from any level of theory to any other level of theory.