A graphical model for protein secondary structure prediction

In this paper, we present a graphical model for protein secondary structure prediction. This model extends segmental semi-Markov models (SSMM) to exploit multiple sequence alignment profiles which contain information from evolutionarily related sequences. A novel parameterized model is proposed as the likelihood function for the SSMM to capture the segmental conformation. By incorporating the information from long range interactions in -sheets, this model is capable of carrying out inference on contact maps. The numerical results on benchmark data sets show that incorporating the profiles results in substantial improvements and the generalization performance is promising.

• Type: Conference
• Year: 2004
• Where: ICML
• Authors: Wei Chu, Zoubin Ghahramani, David L. Wild
• Keywords: ICML 2004, Machine Learning, Segmental Conformation, Segmental Semi-Markov Models, Sequence Alignment Profiles