Subcellular Localization Prediction

Subcellular localization can be considered as a type of gene function. Indeed the Gene Ontology organizes terms for describing localization in a DAG named cellular component. Some proteins have a signal peptide typically at its N-terminal region, which are recognized by a transporting protein and later often cleaved off. Therefore a direct way to predict subcellular localization is to recognize these signals.94 Since molecular protein sorting mechanism differs in prokaryotes and eukaryotes, predictionmethods is usually specifically designed for either one of them or for a sub-category, such as plants. PSORT is one of the earliest prediction methods, which uses multiple sequence features including signal peptides, amino acid composition, sequence motifs, and predicted trans-membrane domains in the form of a decision rule or a classifier.95,96 They have an extensive collection of links to prediction methods and related resources at their web site,demonstrate that cellular localization is an evolutionarily conserved property andhomologs tend to occur at the same cellular sites. Proteome Analyst99 obtains annotationscorresponding to homologous sequences detected using BLAST and then uses them withan organism specific Bayesian classifier to classify the query protein to localization sites.Some methods100–102 use SVM to classify proteins across different cellular components based on the frequency of twenty amino acids. The phylogenetic profile can be also used to predict localization.