Predicting phosphorus NMR shifts using neural networks

NMR signal processing, prediction, and structure verification with machine learning techniques

“…The mere mention of the term prediction points directly to a potential application of ML techniques. Indeed, already in the first years of development of NN techniques, they were applied to the prediction of NMR, initially to specific groups of organic compounds such as alkanes, alkenes, or benzenes and then generalized to nearly every class of organic molecules for different nuclides, including 31 P, 13 C, and 1 H . NN‐based predictions, available both in commercial and in free application packages were followed by other ML techniques such as supported vector machines (SVMs), random forests classification, and principal least regression (PLS) …”

Ab initio NMR chemical-shift calculations based on the combined fragmentation method

“…The analysis can be carried out on proteins in varying situations such as solution phase and solid state. 1 Previously, both empirical [2][3][4][5][6][7] and ab initio [8][9][10][11][12][13][14][15][16][17] methods have been established for predicting NMR chemical shifts of small molecules. Empirical methods predict NMR chemical shifts using a large database and the success of this model depends upon the parametrization and quality of the database.…”

Development of artificial neural networks for spectral interference correction in optical emission spectrometry

“…Artificial neural networks have been successfully applied to fields as diverse as calibration 17 , nonlinear system identification 18,19 , classification 20 , process control 21 , interpretation of IR-spectra 20, 21 and UV-spectra 22 , atomic emission spectrometry 23 , atomic absorption spectrometry 24 , nuclear magnetic resonance (NMR) [25][26][27] and ion mobility spectrometry (IMS) 28 .…”