In the last decade, the prediction of protein secondary structure has been
optimized using essentially one and the same assignment scheme known as DSS
P. We present here a different scheme, which is more predictable. This sche
me predicts directly the hydrogen bonds, which stabilize the secondary stru
ctures. Single sequence prediction of the new three category assignment giv
es an overall prediction improvement of 3.1% and 5.1%, compared to the DSSP
assignment and schemes where the helix category consists of a-helix and 3(
10)-helix, respectively. These results were achieved using a standard feed-
forward neural network with one hidden layer on a data set identical to the
one used in earlier work. (C) 2001 Federation of European Biochemical Soci
eties. Published by Elsevier Science B.V. All rights reserved.