A Fragmentation-Based Graph Embedding Framework for QM/ML

We introduce a new fragmentation-based molecular representation framework FragGraph for QM/ML methods involving embedding fragment-wise fingerprints onto molecular graphs. Our model is specifically designed for delta machine learning (Delta-ML) with the central goal of correcting the deficiencies of approximate methods such as DFT to achieve high accuracy. Our framework is based on a judicious combination of ideas from fragmentation, error cancellation, and a state-of-the-art deep learning architecture. Broadly, we develop a general graph-network framework for molecular machine learning by incorporating the inherent advantages prebuilt into error cancellation methods such as the generalized Connectivity-Based Hierarchy. More specifically, we develop a QM/ML representation through a fragmentationbased attributed graph representation encoded with fragment-wise molecular fingerprints. The utility of our representation is demonstrated through a graph network fingerprint encoder in which a global fingerprint is generated through message passing of local neighborhoods of fragment-wise fingerprints, effectively augmenting standard fingerprints to also include the inbuilt molecular graph structure. On the 130k-GDB9 dataset, our method predicts an out-of-sample mean absolute error significantly lower than 1 kJ/mol compared to target G4(MP2) calculated energies, rivaling current deep learning methods with reduced computational scaling.

Automated summary

This study introduces a new fragmentation-based molecular representation framework FragGraph for QM/ML methods, aimed at achieving high accuracy by correcting the deficiencies of approximate methods through ideas from fragmentation, error cancellation, and deep learning architecture. The framework combines the advantages of error cancellation methods into molecular machine learning by incorporating a general graph-network framework.