Information Technology Reference
In-Depth Information
consensus method to work well we need more methods competing with each other in
performance. And clearly this was not the case in this study. One method turned out to be
far better than the rest, causing the weights of the other prediction methods to be marginal:
instead of an agreement one method takes all the decisions. To make a useful consensus
method, prediction methods should be used which, ideally, have slightly complementary
predictions because they are based on different principles.
This could be expanded to assigning different weights to distinct secondary
structure elements. The results of the experiments show difference in performance in
predicting D-helix or E-sheet between different methods. This could be translated into
different sets of weights for prediction of D-helix or E-sheet accordingly, thus increasing
the overall performance.
Acknowledgements
The authors like to thank dr. T. Heskes (Dept. of Medical Physics and Biophysics,
University of Nijmegen, NL) for his expert help on neural networks and programming in
Matlab. Part of this work was performed as a student thesis project of JRdH under
supervision of JAML at the Centre for Molecular and Biomolecular Informatics (CMBI) of
the University of Nijmegen. The CMBI is gratefully acknowledged for the use of their
computing facilities.
References
[1]
P.Y. Chou and G.D. Fasman, Prediction of protein conformation, Biochemistry
13
(1974), 222-245.
[2]
P.Y. Chou and G.D. Fasman, Prediction of the secondary structure of proteins from their amino acid
sequence, Advanced Enzymology
47
(1978) 45-148.
[3]
V.I. Lim, Structural principles of the globular organisation of protein chains. A stereochemical theory
of globular protein secondary structure, Journal of Molecular Biology
88
(1974) 857-872.
[4]
V.I. Lim, Algorithms for prediction of alpha-helical and beta-structural regions in globular proteins,
Journal of Molecular Biology
88
(1974) 873-894.
[5]
J. Garnier, D.J. Osguthorpe and B. Robson, Analysis of the accuracy and implications of simple
methods for predicting the secondary structure of globular proteins, Journal of Molecular Biology
120
(1978) 97-120.
[6]
J. Selbig, T. Mevissen and T. Lengauer, Decision tree-based formation of consensus protein secondary
structure prediction, Bioinformatics
15
(1999) 1039-1046.
[7]
S. Pongor and A. Szalay, Prediction of homology and divergence in the secondary structure of
polypeptides, Proceedings of the National Academy of Science U.S.A.
82
(1985) 366-370.
[8]
J. Garnier, J.-F. Gibrat and B. Robson, GOR method for predicting protein secondary structure from
amino acid sequence, Methods in Enzymology
266
(1996) 540-553.
[9]
J-F. Gibrat, J. Garnier and B. Robson, Further developments of protein secondary structure prediction
using information theory, Journal of Molecular Biology
198
(1987) 425-443.
[10]
D.T. Jones, Protein secondary structure prediction based on position-specific scoring matrices, Journal
of Molecular Biology
292
(1999) 195-202.
[11]
J.-M. Chandonia and M. Karplus, New methods for accurate prediction of protein secondary structure,
Proteins (structure, function and genetics)
35
(1999) 293-306.
[12]
A.A. Salamov and V.V. Solovyev, Prediction of protein secondary structure by combining nearest-
neighbour algorithms and multiply sequence alignments, Journal of Molecular Biology
247
(1995) 11-
15.
[13]
T.M. Yi and S. Lander, Protein secondary structure prediction using nearest-neighbour methods
,
Journal of Molecular Biology
232
(1993) 1117-1129.
[14]
R.D. King and M.J.E. Sternberg, Identification and application of the concepts important for accurate
and reliable protein secondary structure prediction, Protein Science
5
(1996) 2298-2310.
[15]
D. Frishman and P. Argos, 75% accuracy in protein secondary structure prediction, Proteins
27
(1997)
329-335.
