K. Huang et al., PERFORMANCE OF A NEURAL-NETWORK-BASED DETERMINATION OF AMINO-ACID CLASS AND SECONDARY STRUCTURE FROM H-1-N-15 NMR DATA, Journal of biomolecular NMR, 10(1), 1997, pp. 45-52
A neural network which can determine both amino acid class and seconda
ry structure using NMR data from N-15-labeled proteins is described. W
e have included nitrogen chemical shifts, (3)J(H)N(H) alpha coupling c
onstants, ex-proton chemical shifts, and side-chain proton chemical sh
ifts as input to a three-layer feedforward network. The network was tr
ained with 456 spin systems from several proteins containing various t
ypes of secondary structure, and tested on human ubiquitin, which has
no sequence homology with any of the proteins in the training set. A v
ery limited set of data. representative of those from a TOCSY-HSQC and
HNHA experiment, was used. Nevertheless, in 60% of the spin systems t
he correct amino acid class was among the top two choices given by the
network, while in 96% of the spin systems the secondary structure was
correctly identified. The performance of this network clearly shows t
he potential of the neural network algorithm in the automation of NMR
spectral analysis.