Carbohydrate NMR chemical shift predictions using E(3) equivariant graph neural networks

TL;DR

This paper presents a novel E(3) equivariant graph neural network model for predicting carbohydrate NMR spectra, significantly improving accuracy and robustness over traditional methods, with broad implications for spectroscopy and molecular analysis.

Contribution

Introduces an E(3) equivariant graph neural network for NMR prediction that outperforms traditional models, especially with limited data, advancing spectral analysis techniques.

Findings

Achieves up to threefold reduction in mean absolute error.

Performs well even with limited training data.

Potential to accelerate research in biochemistry and pharmaceuticals.

Abstract

Carbohydrates, vital components of biological systems, are well-known for their structural diversity. Nuclear Magnetic Resonance (NMR) spectroscopy plays a crucial role in understanding their intricate molecular arrangements and is essential in assessing and verifying the molecular structure of organic molecules. An important part of this process is to predict the NMR chemical shift from the molecular structure. This work introduces a novel approach that leverages E(3) equivariant graph neural networks to predict carbohydrate NMR spectra. Notably, our model achieves a substantial reduction in mean absolute error, up to threefold, compared to traditional models that rely solely on two-dimensional molecular structure. Even with limited data, the model excels, highlighting its robustness and generalization capabilities. The implications are far-reaching and go beyond an advanced understanding of carbohydrate structures and spectral interpretation. For example, it could accelerate research in pharmaceutical applications, biochemistry, and structural biology, offering a faster and more reliable analysis of molecular structures. Furthermore, our approach is a key step towards a new data-driven era in spectroscopy, potentially influencing spectroscopic techniques beyond NMR.