Premium
Design and training of a neural network for predicting the solvent accessibility of proteins
Author(s) -
Ahmad Shandar,
Gromiha M. Michael
Publication year - 2003
Publication title -
journal of computational chemistry
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.907
H-Index - 188
eISSN - 1096-987X
pISSN - 0192-8651
DOI - 10.1002/jcc.10298
Subject(s) - maxima and minima , artificial neural network , computer science , training set , coding (social sciences) , machine learning , training (meteorology) , set (abstract data type) , artificial intelligence , test set , mathematics , statistics , mathematical analysis , physics , meteorology , programming language
A feed‐forward neural network has been developed to predict the solvent accessibility/accessible surface area (ASA) of proteins using improved design and training methods. Several network issues ranging from the coding of ASA states to the problem of local minima of learning curve, have been addressed. Successful new approaches to overcome these problems are presented. Set of trained network weights for each ASA threshold is provided. It has been established that the prediction accuracy results with neural network are better than other reported results of ASA prediction, despite a high test to training data ratio. © 2003 Wiley Periodicals, Inc. J Comput Chem 11: 1313–1320, 2003