IMPRESSION generation 2 - accurate, fast and generalised neural network model for predicting NMR parameters in place of DFT

Abstract

Predicting 3D-aware Nuclear Magnetic Resonance (NMR) properties is critical for determining the 3D structure and dynamics, both stereochemical and conformational, of molecules in solution. Existing tools for such predictions are limited, being either relatively slow quantum chemical methods such as Density Functional Theory (DFT), or niche parameterised empirical or machine learning methods that only predict a single parameter type, often across only a limited chemical space. We present here IMPRESSION-Generation 2 (G2), a transformer-based neural network which can be used as a much faster alternative to high level DFT calculations in computational workflows of multiple classes of NMR parameter simultaneously, with time-savings of several orders of magnitude. IMPRESSION-G2 is the first system that simultaneously predicts all NMR chemical shifts, as well as scalar couplings for ¹H, ¹³C, ¹⁵N and ¹⁹F nuclei up to 4 bonds apart, in a single prediction event starting from a 3D molecular structure. Rapid NMR predictions take <50 ms to predict on average ∼5000 chemical shifts and scalar couplings per molecule, which is approximately 10⁶-times faster than DFT-based NMR predictions starting from a 3D structure. When combined with fast GFN2-xTB geometry optimisations to generate the 3D input structures themselves in just a few seconds, a complete workflow for NMR predictions on a new molecule is 10³-10⁴ times faster than a wholly DFT-based workflow for this. The accuracy of this multi-parameter predictor in reproducing DFT-quality results for a wide chemical space of organic molecules up to ∼1000 g mol^-1 containing C, H, N, O, F, Si, P, S, Cl, Br exceeds that of existing state-of-the-art empirical or machine learning systems (∼0.07 ppm for ¹H chemical shifts, ∼0.8 ppm for ¹³C chemical shifts, <0.15 Hz for ³ J _HH scalar coupling constants) and, critically, it also demonstrates generalisability when tested against molecules from sources that are completely independent of its own training data. When compared to experimental NMR data for ∼5000 compounds, IMPRESSION-G2 gives results in minutes on a standard laptop which are almost indistinguishable from DFT results that took days on a large scale High Performance Computing system. This accuracy and speed of IMPRESSION-G2 coupled to GFN-xTB shows that it can be used to simply replace DFT for predicting 3D-aware NMR parameters inside the wide chemical space of its training data.

Fig. 1. Workflow for training IMPRESSION-Generation 2 including DFT methodology and training and testing dataset sources. Full details can be found in the ESI.

Fig. 2. Table of mean absolute deviations and overlay of error distributions for DFT ωB97XD/6-311g(d,p) and IMPRESSION-Generation 2 vs. Exp5K, as well as DFT ωB97XD/6-311g(d,p) vs. IMPRESSION.

Fig. 3. Statistical measures of IMPRESSION-G2 predictions of chemical shifts and scalar couplings for strychnine diastereomers, compared to those reported for the natural product. Entries highlighted in green are those within 50% of the best value for each analysis.