Skip to main content
Fig. 5 | Journal of Cheminformatics

Fig. 5

From: “Ask Ernö”: a self-learning tool for assignment and prediction of nuclear magnetic resonance spectra

Fig. 5

Evolution of the cumulative error distributions during training. The fraction of predictions is given relative to the total number of protons in the test set for which chemical shift can be predicted (2007 protons in total). To generate these curves, the set of chemical shift prediction errors was split into 100 bins of 0.01 ppm, plus a last bin containing predictions with an error equal or greater than 1 ppm. This last bin being larger explains the sudden increase observed at the end of the curves

Back to article page