Secondary structure of proteins have been predicted using neural networks (NN) from their Fourier transform infrared spectra. Leave-one-out approach has been used to demonstrate the applicability of the method. A form of cross-validation is used to train NN to prevent the overfitting problem. Multiple neural network outputs are averaged to reduce the variance of predictions. The networks realized have been tested and rms errors of 7.7% for alpha -helix, 6.4% for beta -sheet and 4.8% for turns have been achieved. These results indicate that the methodology introduced is effective and estimation accuracies are in some cases better than those previously reported in the literature. (C) 2001 Elsevier Science B.V. All rights reserved.