کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
1178405 1491449 2012 9 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
MetaLocGramN: A meta-predictor of protein subcellular localization for Gram-negative bacteria
موضوعات مرتبط
مهندسی و علوم پایه شیمی شیمی آنالیزی یا شیمی تجزیه
پیش نمایش صفحه اول مقاله
MetaLocGramN: A meta-predictor of protein subcellular localization for Gram-negative bacteria
چکیده انگلیسی

Subcellular localization is a key functional characteristic of proteins. It is determined by signals encoded in the protein sequence. The experimental determination of subcellular localization is laborious. Thus, a number of computational methods have been developed to predict the protein location from sequence. However predictions made by different methods often disagree with each other and it is not always clear which algorithm performs best for the given cellular compartment. We benchmarked primary subcellular localization predictors for proteins from Gram-negative bacteria, PSORTb3, PSLpred, CELLO, and SOSUI-GramN, on a common dataset that included 1056 proteins. We found that PSORTb3 performs best on the average, but is outperformed by other methods in predictions of extracellular proteins. This motivated us to develop a meta-predictor, which combines the primary methods by using the logistic regression models, to take advantage of their combined strengths, and to eliminate their individual weaknesses. MetaLocGramN runs the primary methods, and based on their output classifies protein sequences into one of five major localizations of the Gram-negative bacterial cell: cytoplasm, plasma membrane, periplasm, outer membrane, and extracellular space. MetaLocGramN achieves the average Matthews correlation coefficient of 0.806, i.e. 12% better than the best individual primary method. MetaLocGramN is a meta-predictor specialized in predicting subcellular localization for proteins from Gram-negative bacteria. According to our benchmark, it performs better than all other tools run independently. MetaLocGramN is a web and SOAP server available for free use by all academic users at the URL http://iimcb.genesilico.pl/MetaLocGramN. This article is part of a Special Issue entitled: Computational Methods for Protein Interaction and Structural Prediction.


► Subcellular localization is a key functional characteristic of proteins.
► We benchmarked subcellular localization predictors for Gram-negative bacteria.
► We developed a meta-predictor MetaLocGramN.
► Our method outperforms all the primary subcellular localization predictors.
► The web/soap server is freely available at http://iimcb.genesilico.pl/MetaLocGramN/.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Biochimica et Biophysica Acta (BBA) - Proteins and Proteomics - Volume 1824, Issue 12, December 2012, Pages 1425–1433
نویسندگان
, , ,