Genome-scale protein function prediction in yeast Saccharomyces cerevisiae through integrating multiple sources of high-throughput data

As we are moving into the post genome-sequencing era, various high-throughput experimental techniques have been developed to characterize biological systems at the genome scale. Discovering new biological knowledge from high-throughput biological data is a major challenge for bioinformatics today. To address this challenge, we developed a Bayesian statistical method together with Boltzmann machine and simulated annealing for protein function prediction in the yeast Saccharomyces cerevisiae through integrating various high-throughput biological data, including protein binary interactions, protein complexes and microarray gene expression profiles. In our approach, we quantified the relationship between functional similarity and high-throughput data. Based on our method, 1802 out of 2280 unannotated proteins in the yeast were assigned functions systematically. The related computer package is available upon request.