A Bayesian system integrating expression data with sequence patterns for localizing proteins: comprehensive application to the yeast genome 1 1Edited by F. Cohen

Abstract

We develop a probabilistic system for predicting the subcellular localization of proteins and estimating the relative population of the various compartments in yeast. Our system employs a Bayesian approach, updating a protein's probability of being in a compartment based on a diverse range of 30 features. These range from specific motifs (e.g. signal sequences or HDEL) to overall properties of a sequence (e.g. surface composition or isoelectric point) to whole-genome data (e.g. absolute mRNA expression levels or their fluctuations). The strength of our approach is the easy integration of many features, particularly the whole-genome expression data. We construct a training and testing set of ~1300 yeast proteins with an experimentally known localization from merging, filtering, and standardizing the annotation in the MIPS, Swiss-Prot and YPD databases, and we achieve 75% accuracy on individual protein predictions using this dataset. Moreover, we are able to estimate the relative protein population of the various compartments without requiring a definite localization for every protein. This approach, which is based on an analogy to formalism in quantum mechanics, gives greater accuracy in determining relative compartment populations than that obtained by simply tallying the localization predictions for individual proteins (on the yeast proteins with known localization, 92% vs. 74%). Our training and testing also highlights which of the 30 features are informative and which are redundant (19 being particularly useful). After developing our system, we apply it to the 4700 yeast proteins with currently unknown localization and estimate the relative population of the various compartments in the entire yeast genome. An unbiased prior is essential to this extrapolated estimate; for this, we use the MIPS localization catalogue, and adapt recent results on the localization of yeast proteins obtained by Snyder and colleagues using a minitransposon system. Our final localizations for all ~6000 proteins in the yeast genome are available over the web at

Predicting Subcellular Localization via Protein Motif Co-Occurrence

“…Predictors that determine protein localization by integrating various protein characteristics, including targeting motifs of different organelles. Such predictors include PSORT (Nakai and Kanehisa 1992) and a Bayesian framework (Drawid and Gerstein 2000). PSORT is a publicly available integrated expert system based on the sequential application of if/then rules relating to amino acid composition and the presence of targeting signals to various organelles.…”

Bayesian methods for proteomics

“…This system utilized 30 features that ranged from genome data to specific characteristics of a sequence [46]. By using Bayesian logic, these features allowed for a constant update of a protein's probability of a particular localization.…”

“…In trials of 1300 proteins, their method was accurate in 75% of protein localization predictions [46]. A year later, using Bayesian reasoning, Kumar et al (including Drawid and Gerstein) created a proteome localizome (localization of proteins) for yeast.…”

Protein Interaction Prediction by Integrating Genomic Features and Protein Interaction Network Analysis

“…However, protein localization data provide indirect information if we assume that proteins in different compartments do not interact. A list of $2.7 million protein pairs in different compartments are compiled from the current yeast localization data in which proteins are attributed to one of five compartments as has been done previously (Drawid and Gerstein, 2000). These compartments are the nucleus (N), mitochondria (M), cytoplasm (C), membrane (T for transmembrane), and secretory pathway (E for endoplasmic reticulum or extracellular).…”