Refining Neural Network Predictions for Helical Transmembrane Proteins by Dynamic Programming

For transmembrane proteins experimental determina-tion of three-dimensional structure is problematic. However, membrane proteins have important impact for molecular biology in general, and for drug design in particular. Thus, prediction method are needed. Here we introduce a method that started from the output of the profile-based neural network system PHDhtm (Rost, et al. 1995). Instead of choosing the neural network output unit with maximal value as pre-diction, we implemented a dynamic programming-like refinement procedure that aimed at producing the best model for all transmembrane helices compatible with the neural network output. The refined prediction was used successfully to predict transmembrane topology based on an empirical rule for the charge difference between extra- and intra-cytoplasmic regions (posi-tive-inside rule). Preliminary results suggest that the refinement was clearly superior to the initial neural network system; and that the method predicted all transmembran...

• Type: Conference
• Year: 1996
• Where: ISMB
• Authors: Burkhard Rost, Rita Casadio, Piero Fariselli
• Keywords: Computational Biology, ISMB 1996, Neural Network, Neural Network Output, Refinement Procedure