Deep Picker: a deep neural network for accurate deconvolution of complex two-dimensional NMR spectra
Spectrum processing requirements, please read carefully.
- The number of points per peak (PPP), which is given by the number of data points that sample the
peak’s full width at half height (FWHH),
is allowed to vary either from 6 to 20 (optimal: 12) points or from 4 to 12 (optimal: 8) points.
This requirement can be fulfilled easily by applying proper fold of zero filling.
Typically, 4 to 8 times ( -zf 2 or 3 in nmrPipe ) of zero-filling is required to reach these PPPs.
- Please use the 2PI-Kaiser window function for apodization in the NMRPipe software
with the command “SP -off 0.5 -end 0.896 -pow 3.684”. The resulting peak shapes can then be
modeled in all dimensions with good accuracy using a Voigt profile that combines variable amounts
of Lorentzian vs. Gaussian character.
-
- When you adjust lowest contour level, peaks that are fall below it will become invisible. However, all
peaks will be kept in the downloaded file.
STEP2: Peak picking and peak fitting
Peak fitting is recommended only if compound quantification is planed. It may take up to several hours for a complex spectrum
Reference
Questions or comments? Please feel free to contact us.
Acknowledgement
This web server and the research that led to it is supported by the National Institutes of Health (Grant R01 GM 066041).
Most chemical shifts in COLMAR database were retrieved from the existing databases listed below, which all allow public access.