Transmembrane topology and signal peptide prediction using dynamic Bayesian networks

Sheila M. Reynolds, Lukas Käll, Michael E. Riffle, Jeff A. Bilmes and William Stafford Noble

PLoS Computational Biology. 4(11):e1000213, 2008.


Abstract

Hidden Markov models (HMM) have been successfully applied to the tasks of transmembrane protein topology prediction and signal peptide prediction. In this paper we expand upon this work by making use of the more powerful class of dynamic Bayesian networks (DBN). Our model, Philius, is inspired by a previously published HMM, Phobius, and combines a signal peptide sub-model with a transmembrane sub-model. We introduce a two-stage DBN decoder which combines the power of posterior decoding with the grammar constraints of Viterbi-style decoding. Philius also provides protein type, segment, and topology confidence metrics to aid in the interpretation of the predictions.

We report a relative improvement of 13% over Phobius in full-topology prediction accuracy on transmembrane proteins, and a sensitivity and specificity of 0.96 in detecting signal peptides. We also show that our confidence metrics correlate well with the observed precision. In addition, we have made predictions on all 6.3 million proteins in the Yeast Resource Center (YRC) database.

All DBNs are implemented using the Graphical Models Toolkit (GMTK).



Copyright 2008 University of Washington