Genome-wide prediction of prokaryotic two-component system networks using a sequence-based meta-predictor

Standard

Genome-wide prediction of prokaryotic two-component system networks using a sequence-based meta-predictor. / Kara, Altan; Vickers, Martin; Swain, Martin; Whitworth, David E; Fernandez-Fuentes, Narcis.

In: BMC Bioinformatics, Vol. 16, No. 1, 297, 2015.

Research output: Contribution to journalArticle

Bibtex - Download

@article{93b1cde7f998436fa558afcad01706d3,
title = "Genome-wide prediction of prokaryotic two-component system networks using a sequence-based meta-predictor",
abstract = "BACKGROUND: Two component systems (TCS) are signalling complexes manifested by a histidine kinase (receptor) and a response regulator (effector). They are the most abundant signalling pathways in prokaryotes and control a wide range of biological processes. The pairing of these two components is highly specific, often requiring costly and time-consuming experimental characterisation. Therefore, there is considerable interest in developing accurate prediction tools to lessen the burden of experimental work and cope with the ever-increasing amount of genomic information.RESULTS: We present a novel meta-predictor, MetaPred2CS, which is based on a support vector machine. MetaPred2CS integrates six sequence-based prediction methods: in-silico two-hybrid, mirror-tree, gene fusion, phylogenetic profiling, gene neighbourhood, and gene operon. To benchmark MetaPred2CS, we also compiled a novel high-quality training dataset of experimentally deduced TCS protein pairs for k-fold cross validation, to act as a gold standard for TCS partnership predictions. Combining individual predictions using MetaPred2CS improved performance when compared to the individual methods and in comparison with a current state-of-the-art meta-predictor.CONCLUSION: We have developed MetaPred2CS, a support vector machine-based metapredictor for prokaryotic TCS protein pairings. Central to the success of MetaPred2CS is a strategy of integrating individual predictors that improves the overall prediction accuracy, with the in-silico two-hybrid method contributing most to performance. MetaPred2CS outperformed other available systems in our benchmark tests, and is available online at http://metapred2cs.ibers.aber.ac.uk , along with our gold standard dataset of TCS interaction pairs.",
keywords = "two-component signalling system, protein-protein interactions, protein-protein interaction predictions, meta-predictor, support vector machine, web server, genome context, co-evoluation",
author = "Altan Kara and Martin Vickers and Martin Swain and Whitworth, {David E} and Narcis Fernandez-Fuentes",
year = "2015",
doi = "10.1186/s12859-015-0741-7",
language = "English",
volume = "16",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "Springer Nature",
number = "1",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Genome-wide prediction of prokaryotic two-component system networks using a sequence-based meta-predictor

AU - Kara, Altan

AU - Vickers, Martin

AU - Swain, Martin

AU - Whitworth, David E

AU - Fernandez-Fuentes, Narcis

PY - 2015

Y1 - 2015

N2 - BACKGROUND: Two component systems (TCS) are signalling complexes manifested by a histidine kinase (receptor) and a response regulator (effector). They are the most abundant signalling pathways in prokaryotes and control a wide range of biological processes. The pairing of these two components is highly specific, often requiring costly and time-consuming experimental characterisation. Therefore, there is considerable interest in developing accurate prediction tools to lessen the burden of experimental work and cope with the ever-increasing amount of genomic information.RESULTS: We present a novel meta-predictor, MetaPred2CS, which is based on a support vector machine. MetaPred2CS integrates six sequence-based prediction methods: in-silico two-hybrid, mirror-tree, gene fusion, phylogenetic profiling, gene neighbourhood, and gene operon. To benchmark MetaPred2CS, we also compiled a novel high-quality training dataset of experimentally deduced TCS protein pairs for k-fold cross validation, to act as a gold standard for TCS partnership predictions. Combining individual predictions using MetaPred2CS improved performance when compared to the individual methods and in comparison with a current state-of-the-art meta-predictor.CONCLUSION: We have developed MetaPred2CS, a support vector machine-based metapredictor for prokaryotic TCS protein pairings. Central to the success of MetaPred2CS is a strategy of integrating individual predictors that improves the overall prediction accuracy, with the in-silico two-hybrid method contributing most to performance. MetaPred2CS outperformed other available systems in our benchmark tests, and is available online at http://metapred2cs.ibers.aber.ac.uk , along with our gold standard dataset of TCS interaction pairs.

AB - BACKGROUND: Two component systems (TCS) are signalling complexes manifested by a histidine kinase (receptor) and a response regulator (effector). They are the most abundant signalling pathways in prokaryotes and control a wide range of biological processes. The pairing of these two components is highly specific, often requiring costly and time-consuming experimental characterisation. Therefore, there is considerable interest in developing accurate prediction tools to lessen the burden of experimental work and cope with the ever-increasing amount of genomic information.RESULTS: We present a novel meta-predictor, MetaPred2CS, which is based on a support vector machine. MetaPred2CS integrates six sequence-based prediction methods: in-silico two-hybrid, mirror-tree, gene fusion, phylogenetic profiling, gene neighbourhood, and gene operon. To benchmark MetaPred2CS, we also compiled a novel high-quality training dataset of experimentally deduced TCS protein pairs for k-fold cross validation, to act as a gold standard for TCS partnership predictions. Combining individual predictions using MetaPred2CS improved performance when compared to the individual methods and in comparison with a current state-of-the-art meta-predictor.CONCLUSION: We have developed MetaPred2CS, a support vector machine-based metapredictor for prokaryotic TCS protein pairings. Central to the success of MetaPred2CS is a strategy of integrating individual predictors that improves the overall prediction accuracy, with the in-silico two-hybrid method contributing most to performance. MetaPred2CS outperformed other available systems in our benchmark tests, and is available online at http://metapred2cs.ibers.aber.ac.uk , along with our gold standard dataset of TCS interaction pairs.

KW - two-component signalling system

KW - protein-protein interactions

KW - protein-protein interaction predictions

KW - meta-predictor

KW - support vector machine

KW - web server

KW - genome context

KW - co-evoluation

UR - http://hdl.handle.net/2160/30439

U2 - 10.1186/s12859-015-0741-7

DO - 10.1186/s12859-015-0741-7

M3 - Article

C2 - 26384938

VL - 16

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

IS - 1

M1 - 297

ER -

Show download statistics
View graph of relations
Citation formats