Predicting Subcellular Localization via Protein Motif Co-Occurrence

Abstract

The prediction of subcellular localization of proteins from their primary sequence is a challenging problem in bioinformatics. We have created a Bayesian network localization predictor called PSLT that is based on the combinatorial presence of InterPro motifs and specific membrane domains in human proteins. This probabilistic framework generates a likelihood of localization to all organelles and allows to predict multicompartmental proteins. When used to predict on nine compartments, PSLT achieves an accuracy of 78% as estimated by using a 10-fold cross-validation test and a coverage of 74%. When used to predict the localization of proteins from other closely related species, it achieves a prediction accuracy and a coverage >80%. We compared the localization predictions of PSLT to those determined through GFP-tagging and microscopy for a group of human proteins. We found two general classes of proteins that are mislocalized by the GFP-tagging strategy but are correctly localized by PSLT. This suggests that PSLT can be used in combination with experimental approaches for localization to identify proteins for which additional experimental validation is required. We used our predictor to annotate all 9793 human proteins from SWISS-PROT release 41.25, 16% of which are predicted by PSLT to be present in more than one compartment.

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

“…Through the development of new approaches in computer science, coupled with an increased data set of proteins of known localization (as available in Arabidopsis), computational tools can now provide fast and reasonably accurate localization predictions for many organisms. Many prediction systems now exceed the accuracy of some highthroughput laboratory methods for the identification of protein subcellular localization (Scott et al, 2004;Rey et al, 2005). This has resulted in subcellular Table VIII.…”

“…those based on domain or motif co-occurrence). These methods have previously been reviewed in detail (Mott et al, 2002;Scott et al, 2004). However, in bioinformatics in general, and in subcellular localization prediction in particular, it is often debated whether predictions should be done over broad systematic groups such as all eukaryotes or all plants, or over narrower groups such as dicots, or even at the single-species level.…”

“…Although some recent reviews/advances in the prediction of protein-targeting signals have stressed the need for "species-specific" prediction tools (Schneider and Fechner, 2004;Chou and Shen, 2007a), very few have been developed/reported in the literature. The PSLT method (Scott et al, 2004), a Bayesian framework that uses a combination of InterPro motifs, signaling peptides, and transmembrane domains, was developed for predicting genome-wide subcellular localization of human proteins. Two others, HSLpred (Garg et al, 2005) and Hum-PLoc (Chou and Shen, 2006), were also developed specifically for human proteins; another species-specific system, TBpred, was developed for Mycobacterium tuberculosis (Rashid et al, 2007).…”

Speeding up subcellular localization by extracting informative regions of protein sequences for profile alignment

“…A number of approaches to solving this problem have been proposed in the literature. These methods can be generally divided into four categories, including predictions based on sorting signals [1], [2], [3], [4], [5], global sequence properties [6], [7], [8], [9], homology [10], [11], [12], and other information in addition to sequences [13], [14].…”

Proteome-wide remodeling of protein location and function by stress

“…Early methods attempted to infer protein function based mainly on individual protein features, such as sequence similarity or structural homology (3,(5)(6)(7)(8)(9)(10)(11)(12)(13)(14)(15)(16)(17). These methods range from simple sequence-sequence comparisons to profile-or pattern-based supervised learning methods.…”