Protein Function Prediction Using Semantic Similarity Metrics and Random Walk Algorithm

Abstract

Most protein function prediction methods that have been proposed, are based on sequence or structure protein similarity and do not take into consideration the semantic similarity extracted from protein knowledge databases such as Gene Ontology. In this paper we present an approach for protein function prediction using semantic similarity metrics and the whole network topology of a protein interaction network by using a—semantic driven “random walk with restart. Different semantic similarity metrics are explored and future results should show the relevance of different semantic similarity metrics on protein function prediction using random walk with restart. To achieve the final goal of protein function prediction, the best semantic similarity metric should be used.