Mimicking Cellular Sorting Improves Prediction of Subcellular Localization

Combining Machine Learning and Homology-Based Approaches to Accurately Predict Subcellular Localization in Arabidopsis

“…For example, TAIR is currently using the TargetP system (Emanuelsson et al, 2000) for annotating the complete subcellular proteome of Arabidopsis (ftp://ftp.arabidopsis.org/home/ tair/Proteins/Properties/TargetP_analysis.tair9). We compared not only TargetP but some other tools, such as LOCtree (Nair and Rost, 2005), PA-SUB (Lu et al, 2004), MultiLoc (Hö glund et al, 2006), WoLF PSORT (Horton et al, 2007), and Plant-PLoc (Chou and Shen, 2007b), all of which originally reported good accuracy. However, a number of previous researchers (Emanuelsson, 2002;Heazlewood et al, 2004Heazlewood et al, , 2005 found only 40% to 50% accuracy of the existing systems in their experimental data sets when testing the available tools for Arabidopsis annotation.…”

“…the separating hyperplane solely depends on the support vectors and not on the complete data set, thereby making it less prone to overfitting than other classification methods such as the artificial neural networks; Byvatov and Schneider, 2003). Apart from its efficient application in subcellular localization prediction (Hua and Sun, 2001;Park and Kanehisa, 2003;Bhasin and Raghava, 2004;Garg et al, 2005;Nair and Rost, 2005;Xie et al, 2005), it has also been diversely used in the classification of microarray data (Brown et al, 2000), protein secondary structure prediction (Ward et al, 2003), and disease forecasting (Kaundal et al, 2006). In this study, we used SVM_light (Joachims, 1999), a freely downloadable package of SVM (http://svmlight.joachims.org/old/svm_light_v4.00.html), to develop various classifiers.…”

“…We compared the performance of AtSubP on two diverse Arabidopsisspecific independent data sets (I and II) with some of the widely used tools, such as TargetP (Emanuelsson et al, 2000), LOCtree (Nair and Rost, 2005), PA-SUB (Lu et al, 2004), MultiLoc (Höglund et al, 2006), WoLF PSORT (Horton et al, 2007), and Plant-PLoc (Chou and Shen, 2007b). Although technically, the comparison with other methods might not be fair, as each of these methods was developed with different sets of training data, our main emphasis was to demonstrate how these general tools performed for individual genome annotation (e.g.…”

“…In plants, some widely used prediction tools are TargetP (Emanuelsson et al, 2000), LOCtree (Nair and Rost, 2005), PA-SUB (Lu et al, 2004), MultiLoc (Hö glund et al, 2006), WoLF PSORT (updated version of PSORT II; Horton et al, 2007), and Plant-PLoc (Chou and Shen, 2007b), all having good accuracy (greater than 70%). A recent computational effort was made in developing a plant species-specific prediction system, RSLpred, for genome-wide subcellular localization annotations of rice (Oryza sativa) proteins (Kaundal and Raghava, 2009).…”

Enhanced grass carp reovirus resistance of Mx-transgenic rare minnow (Gobiocypris rarus)

“…Intra-domain features were predicted by a scan of the sequence against the PROSITE database (http://us.expasy.org/tools/scanprosite) [26]. The subcellular localization of this protein was predicted using LOCtree software (http://cubic.bioc.columbia.edu/services/loctree/) [27].…”