Prediction of subcellular localization using sequence-biased recurrent networks

Boden, Mikael and Hawkins, John (2005) Prediction of subcellular localization using sequence-biased recurrent networks. Bioinformatics, 21 10: 2279-2286. doi:10.1093/bioinformatics/bti372

Author Boden, Mikael
Hawkins, John
Title Prediction of subcellular localization using sequence-biased recurrent networks
Journal name Bioinformatics   Check publisher's open access policy
ISSN 1367-4803
Publication date 2005-05-01
Year available 2005
Sub-type Article (original research)
DOI 10.1093/bioinformatics/bti372
Open Access Status DOI
Volume 21
Issue 10
Start page 2279
End page 2286
Total pages 8
Editor A. Bateman
A. Valencia
Place of publication Oxford
Publisher Oxford University Press
Language eng
Subject C1
280210 Simulation and Modelling
700100 Computer Software and Services
Abstract Motivation: Targeting peptides direct nascent proteins to their specific subcellular compartment. Knowledge of targeting signals enables informed drug design and reliable annotation of gene products. However, due to the low similarity of such sequences and the dynamical nature of the sorting process, the computational prediction of subcellular localization of proteins is challenging. Results: We contrast the use of feed forward models as employed by the popular TargetP/SignalP predictors with a sequence-biased recurrent network model. The models are evaluated in terms of performance at the residue level and at the sequence level, and demonstrate that recurrent networks improve the overall prediction performance. Compared to the original results reported for TargetP, an ensemble of the tested models increases the accuracy by 6 and 5% on non-plant and plant data, respectively.
Keyword Mathematics, Interdisciplinary Applications
Biochemical Research Methods
Biotechnology & Applied Microbiology
Computer Science, Interdisciplinary Applications
Statistics & Probability
Protein Secondary Structure
Support Vector Machines
Signal Peptides
Cleavage Sites
Q-Index Code C1
Institutional Status UQ

Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 81 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 93 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Wed, 15 Aug 2007, 17:05:48 EST