Subcellular Localisation Predictor Version 1.2
Protein Prowler Subcellular Localisation Predictor V1.2
Protein Prowler Subcellular Localisation Predictor V1.2 Home | Datasets | References
   

The PProwler subcellular localisation predictor is largely based on the ideas behind TargetP. All versions of PProweler have been trained and tested on the TargetP training data which can be retrieved from the TargetP web site. The development of the PProwler predictor is presented and evaluated in the following papers.

 
    Hawkins, J. and Bodén, M., Detecting and Sorting Targeting Peptides with Recurrent Networks and Support Vector Machines. Journal of Bioinformatics and Computational Biology. In press.
 
    Bodén, M. and Hawkins, J. Prediction of subcellular localisation using sequence-biased recurrent networks. Bioinformatics. 21(10), pp. 2279-2286, 2005.
 

Analysis of the targeting peptide detection networks is presented in

 
    Bodén, M. and Hawkins, J. Detecting residues in targeting peptides. In Proceedings of the Asia-Pacific Bioinformatics Conference. Singapore. 2005.
 

A comprehensive study of recurrent networks for sequence analysis and for subcellular localisation in particular is presented in

 
    Bodén, M. and Hawkins, J. Improved access to sequential motifs: A note on the architectural bias of recurrent networks. IEEE Transactions on Neural Networks. 16(2), 491-494, 2005.
 
    Hawkins, J. and Bodén, M. The Applicability of Recurrent Neural Networks for Biological Sequence Analysis. IEEE/ACM Transactions on Computational Biology and Bioinformatics. 2(2), 2005.
 

 

The development of the PTS1Prowler Peroxisomal matrix protein predictor is presented in

 
    Hawkins, J. and Bodén, M., Predicting Peroxisomal Proteins. (Submitted) 2005 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology
 
    Wakabayashi, M., Hawkins, J., Maetschke, S. and Bodén, M., Exploiting sequence dependencies in the prediction of peroxisomal proteins. In Intelligent Data Engineering and Automated Learning - IDEAL 2005, pp. 454-461, 2005.
 

This web service has been developed by Mark Wakabayashi, John Hawkins, Mikael Bodén, and James Watson

Contact: mikael@itee.uq.edu.au