18– 21 These systems are trained on hundreds of thousands of validated experimental chemical shifts arising from tens of thousands of chemical structures. Such machines, trained on experimental data, for 1H and 13C chemical shifts based on 2-dimensional structures are well-established. Machine learning methods offer a solution to the time-demands of DFT NMR predictions, achieving them in seconds rather than hours or days. Naturally, in cases where multiple conformers or isomers must be considered (and thus predictions for multiple structures are required) this becomes days to months of computation for a single study. The largest proportion of this CPU time is occupied by the NMR computations, especially when computing scalar coupling constants. Accurate DFT-based predictions of chemical shift and scalar couplings typically take hours to days of CPU time for a single rigid molecule of even relatively low (∼500) molecular mass. The substantial downside of DFT is the significant computation time required when using methods that can provide sufficient accuracy in NMR predictions. 1 J CH predicted with <4 Hz accuracy to experiment 13– 15 (on values that range from roughly 100–250 Hz) and <0.2/<2 ppm 16, 17 (on ranges of ∼10/∼200 ppm) for 1H and 13C chemical shifts respectively. 9– 12 Optimal DFT methods can be accurate to within 1–2%, e.g. Finally, many NMR parameters, for example 1-bond 1H– 13C scalar coupling constants, 1 J CH, which are sensitive to both chemical connectivity and 3-dimensional structure are rarely used in isotropic studies precisely because there are no general fast predictive methods for 1 J CH.įor all of these reasons, the accurate prediction of NMR parameters in modern 3-dimensional structure determinations relies increasingly on the use of quantum chemical calculations, typically based on Density Functional Theory (DFT). carbohydrates, 8 are not applicable to the whole of chemical space. Multiple-bond 1H– 1H coupling constants are more directly linked to 3-dimensional structure, however generically applicable Karplus-style empirical relationships, such as the widely used equation reported by Haasnoot et al., 7 suffer from lower accuracy when confronted with complex chemical functionality while equations designed for specific sub-structures, e.g. flat-but-stereochemically-aware HOSE codes 3 or single conformer models of experimental systems 4– 6 but the improvements in 3-dimensional accuracy are limited as conformation and flexibility must necessarily be accounted for completely to achieve maximum accuracy. Some modifications to treating 3-dimensional structures have been made by e.g. However their applicability is limited by being based on 2-dimensional structures and cannot readily deal with 3-dimensional conformational or stereochemical analysis. In such comparisons, the use of fast and accurate NMR prediction methods is crucial.įast empirical predictions of chemical shifts for 2-dimensional chemical structures have been used for decades, with the additivity rules exemplified by Pretsch 1 and HOSE-code 2 variants forming the basis of many analyses. The prediction of these parameters, especially in studies of 3-dimensional molecular structure, are increasingly moving towards quantitative comparison between computed values for proposed chemical structures and experiment. NMR spectroscopy remains the pre-eminent analytical technique for elucidating molecular structure in solution, with the prediction and interpretation of 1H and 13C chemical shifts and scalar coupling constants playing a key role.