PERFORMANCE OF A NEURAL-NETWORK-BASED DETERMINATION OF AMINO-ACID CLASS AND SECONDARY STRUCTURE FROM H-1-N-15 NMR DATA

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.