Neural networks for the peak-picking of nuclear magnetic resonance spectra

Authors:
Enrico A. Carrara;Franco Pagliari;Claudio Nicolini
Affiliations:
Università degli Studi di Genova, Italy and Cibernia Srl, Italy;Cibernia Srl, Italy;Università degli Studi di Genova, Italy
Venue:
Neural Networks
Year:
1993

Citing 3
Cited 1

Connectionist learning procedures

Artificial Intelligence
Pepto: an expert system for automatic peak assignment of two-dimensional nuclear magnetic resonance spectra of proteins

Journal of Computational Chemistry
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1

Identification of nuclear magnetic resonance signals via gaussian mixture decomposition

IDA'11 Proceedings of the 10th international conference on Advances in intelligent data analysis X

Quantified Score

Hi-index	0.00

Visualization

Abstract

Peak-picking is the lowest-level task of the interpretation of two-dimensional, and multidimensional Nuclear Magnetic Resonance (NMR) spectra in general, for protein structure determination. It consists of individuating peaks on two-dimensional frequency spectra, for further elaboration. The performances of several feedforward artificial neural networks trained with back propagation with temperature on the task of peak-picking are compared. The best one averages less than an approximate 5% error on well-defined spectral regions. The performances of the network are comparable with those of a human expert; the consequences of this fact on the possibility of improving further the performance of the network are discussed.