Optimizing Neural Networks for Proteins Structure Prediction

• Activity Number: 223
• Type: Contributed
• Date/Time: Tuesday, August 10, 2004 : 10:30 AM to 12:20 PM
• Sponsor: Biometrics Section
• Author(s): Blythe Durbin*+
• Companies: University of California, Berkeley
• Keywords: neural networks ; protein structure prediction ; bioinformatics

Abstract

Neural networks are a popular method for predicting the secondary structure of a protein from its amino acid sequence. However, overfitting poses a serious obstacle to effective use of neural networks for this and other problems. Due to the huge number of parameters in a typical neural network, one may obtain a network fit which perfectly predicts the training data yet fails to generalize to other datasets. Overfitting may be avoided by altering the network topology so that some connections are removed, thus reducing the total number of parameters. In the area of secondary structure prediction, work has focused on optimizing the network architecture by hand based on subject-matter knowledge. We propose instead a method for selecting an optimal network architecture in a data-adaptive fashion using the deletion/substitution/addition algorithm introduced in Sinisi and van der Laan (2003) and Molinaro and van der Laan (2003), and demonstrate the application of this approach to protein secondary-structure prediction.