mGOASVM: Multi-label protein subcellular localization based on gene ontology and support vector machines

Abstract

BackgroundAlthough many computational methods have been developed to predict protein subcellular localization, most of the methods are limited to the prediction of single-location proteins. Multi-location proteins are either not considered or assumed not existing. However, proteins with multiple locations are particularly interesting because they may have special biological functions, which are essential to both basic research and drug discovery.ResultsThis paper proposes an efficient multi-label predictor, namely mGOASVM, for predicting the subcellular localization of multi-location proteins. Given a protein, the accession numbers of its homologs are obtained via BLAST search. Then, the original accession number and the homologous accession numbers of the protein are used as keys to search against the Gene Ontology (GO) annotation database to obtain a set of GO terms. Given a set of training proteins, a set of T relevant GO terms is obtained by finding all of the GO terms in the GO annotation database that are relevant to the training proteins. These relevant GO terms then form the basis of a T-dimensional Euclidean space on which the GO vectors lie. A support vector machine (SVM) classifier with a new decision scheme is proposed to classify the multi-label GO vectors. The mGOASVM predictor has the following advantages: (1) it uses the frequency of occurrences of GO terms for feature representation; (2) it selects the relevant GO subspace which can substantially speed up the prediction without compromising performance; and (3) it adopts an efficient multi-label SVM classifier which significantly outperforms other predictors. Briefly, on two recently published virus and plant datasets, mGOASVM achieves an actual accuracy of 88.9% and 87.4%, respectively, which are significantly higher than those achieved by the state-of-the-art predictors such as iLoc-Virus (74.8%) and iLoc-Plant (68.1%).ConclusionsmGOASVM can efficiently predict the subcellular locations of multi-label proteins. The mGOASVM predictor is available online at http://bioinfo.eie.polyu.edu.hk/mGoaSvmServer/mGOASVM.html.

Progress in Machine Learning-based Predicting Subcellular Localizations of Proteins with Multiple Sites

“…With the aid of kernel function, a non-linear classification problem in a low dimension space can be transformed to a linear one after mapped it to a high dimension space. Recently, algorithms based on SVM are emerged massively [19,20].…”

Prediction of protein subcellular localization using support vector machine with the choice of proper kernel

“…However, the number of newly discovered proteins has been growing exponentially, which in turn makes the subcellular localization prediction by purely laboratory tests prohibitively expensive (Wan et al, 2012). In this context, computational methods have been developed to help biologists in the selection of target proteins and in the design of related experiments.…”

“…Conventional methods for subcellular localization prediction can be roughly divided into sequence-based methods and annotation-based methods (Yang et al, 2006;Wan et al, 2012;Simha et al, 2014). Sequencebased predictors employ: 1) sequence-coded sorting signals (Bannai et al, 2002;Petsalaki et al, 2006), such as PSORT (Nakai and Kanehisa, 1991), WoLF PSORT (Horton et al, 2007), TargetP (Emanuelsson et al, 2000) and SignalP (Nielsen et al, 1997); 2) amino acid composition information (King and Guda, 2007), such as amino-acid compositions (AAC) (Nakashima and Nishikawa, 1994), amino-acid pair compositions (PairAA) (Nakashima and Nishikawa, 1994), gapped amino-acid pair compositions (GapAA) (Park and Kanehisa, 2003), and pseudo aminoacid composition (PseAA) (Chou and Cai, 2003); and 3) both information sources (Höglund et al, 2006;Horton et al, 2007).…”

“…In recent times, a support vector machine (SVM) (Höglund et al, 2006;Li et al, 2012;Wan et al, 2012;Wan et al, 2014;Hasan et al, 2015,) has been extensively applied to provide potential solutions for the prediction of protein subcellular localization. However, the selection of an appropriate kernel and its parameters for a given classification problem influences the performance of the SVM.…”

“…However, there is no theoretical method for selecting the kernel function and its parameters. The literature survey has shown that most of the researchers have applied the radial basis function (RBF) kernel to build SVM based subcellular localization prediction system (Chou and Cai, 2002;Park and Kanehisa, 2003;Li et al, 2011;Wan et al, 2012;Wan et al, 2013) and have found the value of its parameter by using different techniques, such as trial and error, heuristics or grid search procedure (Wan et al, 2015). Surprisingly, still there are many other kernel functions which have not yet been applied in the protein subcellular localization prediction.…”