Detecting and sorting targeting peptides wtih neural networks and support vector machines

This paper presents a composite multi-layer classifier system for predicting the subcellular localization of proteins based on their amino acid sequence. The work is an extension of our previous predictor PProwler v1.1 which is itself built upon the series of predictors SignalP and TargetP. In this study we outline experiments conducted to improve the classifier design. The major improvement came from using Support Vector machines as a "smart gate" sorting the outputs of several different targeting peptide detection networks. Our final model (PProwler v1.2) gives MCC values of 0.873 for non-plant and 0.849 for plant proteins. The model improves upon the accuracy of our previous subcellular localization predictor (PProwler v1.1) by 2% for plant data (which represents 7.5% improvement upon TargetP).

A sensitive HPLC method for measuring bacterial proteolysis and proteinase activity in UHT milk

A sensitive quantitative reversed-phase HPLC method is described for measuring bacterial proteolysis and proteinase activity in UHT milk. The analysis is performed on a TCA filtrate of the milk. The optimum concentration of TCA was found to be 4%; at lower concentrations, non-precipitated protein blocked the HPLC while higher concentrations yielded lower amounts of peptides. The method showed greater sensitivity and reproducibility than a fluorescamine-based method. Quantification of the HPLC method was achieved by use of an external dipeptide standard or a standard proteinase. (c) 2006 Elsevier Ltd. All rights reserved.