Protein secondary structure prediction available via mail server

Nomi Harris harris at
Fri Aug 20 13:37:51 EST 1993

nnpredict is a program that predicts the secondary structure type for
each residue in an input amino acid sequence.  The basis of the
prediction is a two-layer, feed-forward neural network.  nnpredict can
take into account the tertiary class of the protein (either none, all-
alpha, all-beta, or alpha/beta) when predicting secondary structure.

We are making nnpredict available via a mail server.  You can mail in
an amino acid squence, and nnpredict will predict secondary structure
for your sequence and mail the prediction to you.

For instructions on using the nnpredict server, send mail to:
	nnpredict at

Other correspondence, bug reports, etc. can be sent to
	nnpredict-request at

The mail server was written by Nomi Harris
Copyright (C) 1993 Regents of the University of California
(Note: don't bother asking Nomi about the details of the nnpredict
algorithm, because she didn't write nnpredict.)

nnpredict was written by Donald Kneller
Copyright (C) 1991 Regents of the University of California

(1)     J. L. McClelland and D. E. Rumelhart. (1988)
        "Explorations in Parallel Distributed Processing"
        vol 3. pp 318-362.
        MIT Press, Cambridge MA.

(2)     D. G. Kneller, F. E. Cohen and R. Langridge (1990)
        "Improvements in Protein Secondary Structure Prediction by an
        Enhanced Neural Network"
        J. Mol. Biol. (214) 171-182.

Abstract for (2):
Computational neural networks have recently been used to predict the
mapping between protein sequence and secondary structure.  They have
proven adequate for determining the first-order dependence between these
two sets, but have, until now, been unable to garner higher-order
information that helps determine secondary structure. By adding neural
network units that detect periodicities in the input sequence, we have
modestly increased the secondary structure prediction accuracy. The use
of tertiary structural class causes a marked increase in accuracy. The
best case prediction was 79% for the class of all-alpha proteins. A
scheme for employing neural networks to validate and refine structural
hypotheses is proposed. The operational difficulties of applying a
learning algorithm to a dataset where sequence heterogeneity is
under-represented and where local and global effects are inadequately
partitioned are discussed.

More information about the Bio-soft mailing list