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).
- Predictions on the YRC database
- Philius topology prediction web server
- Philius specification and parameter files
- GMTK binaries (32-bit Linux) and some useful python code
- Train and test scripts
- Data sets used in development and test:
- Descriptions of the above-mentioned files
Copyright 2008 University of Washington