%0 Journal Article
%T Mapping the stabilome: a novel computational method for classifying metabolic protein stability
%A Ralph Patrick
%A Kim-Anh Cao
%A Melissa Davis
%A Bostjan Kobe
%A Mikael Bod¨Śn
%J BMC Systems Biology
%D 2012
%I BioMed Central
%R 10.1186/1752-0509-6-60
%X In this work we present five groups of features useful for predicting protein stability: (1) post-translational modifications, (2) domain types, (3) structural disorder, (4) the identity of a proteinĄŻs N-terminal residue and (5) amino acid sequence. We incorporate these features into a predictive model with promising accuracy. At a 20% false positive rate, the model exhibits an 80% true positive rate, outperforming the only previously proposed stability predictor. We also investigate the impact of N-terminal protein tagging as used to generate the data set, in particular the impact it may have on the measurements for secreted and transmembrane proteins; we train and test our model on a subset of the data with those proteins removed, and show that the model sustains high accuracy. Finally, we estimate system-wide metabolic stability by surveying the whole human proteome.We describe a variety of protein features that are significantly over- or under-represented in stable and unstable proteins, including phosphorylation, acetylation and destabilizing N-terminal residues. Bayesian networks are ideal for combining these features into a predictive model with superior accuracy and transparency compared to the only other proposed stability predictor. Furthermore, our stability predictions of the human proteome will find application in the analysis of functionally related proteins, shedding new light on regulation by protein synthesis and degradation.Innovative proteomics technologies promise to chart protein degradation on a large scale [1-3]. The resulting data sets present an opportunity to further our understanding of metabolic protein stability through informed data analysis and the development and testing of computational models. The present study makes use of Yen and colleaguesĄŻ [1] extensive data set which measures the metabolic stability of about 8000 human proteins. We use this data set to (a) identify the underlying properties that appear to influence protein half
%K Protein stability
%K Degradation
%K Machine learning
%K Post-translational modifications
%K Bayesian networks
%K Support vector machines
%K Prediction
%U http://www.biomedcentral.com/1752-0509/6/60