Correlated Protein Function Prediction via Maximization of Data-Knowledge Consistency

Protein function prediction in conventional computational approaches is usually conducted one function at a time, fundamentally. As a result, the functions are treated as separate target classes. However, biological processes are highly correlated, which makes functions assigned to proteins are not independent. Therefore, it would be beneficial to make use of function category correlations in predicting protein function. We propose a novel Maximization of Data-Knowledge Consistency (MDKC) approach to exploit function category correlations for protein function prediction. Our approach banks on the assumption that two proteins are likely to have large overlap in their annotated functions if they are highly similar according to certain experimental data. We first establish a new pairwise protein similarity using protein annotations from knowledge perspective. Then by maximizing the consistency between the established

knowledge similarity

upon annotations and the

data similarity

upon biological experiments, putative functions are assigned to unannotated proteins. Most importantly, function category correlations are elegantly incorporated through the knowledge similarity. Comprehensive experimental evaluations on

Saccharomyces cerevisiae

data demonstrate promising results that validate the performance of our methods.