PROJECT TITLE :

Predicting Protein Function via Semantic Integration of Multiple Networks

ABSTRACT:

Determining the biological functions of proteins is one among the key challenges in the post-genomic era. The rapidly accumulated massive volumes of proteomic and genomic information drives to develop computational models for automatically predicting protein perform in large scale. Recent approaches focus on integrating multiple heterogeneous information sources and that they usually get higher results than methods that use single data source alone. During this paper, we investigate a way to integrate multiple biological information sources with the biological information, i.e., Gene Ontology (GO), for protein function prediction. We have a tendency to propose a technique, called SimNet, to Semantically integrate multiple useful association Networks derived from heterogenous knowledge sources. SimNet firstly utilizes GO annotations of proteins to capture the semantic similarity between proteins and introduces a semantic kernel based mostly on the similarity. Next, SimNet constructs a composite network, obtained as a weighted summation of individual networks, and aligns the network with the kernel to get the weights assigned to individual networks. Then, it applies a network-primarily based classifier on the composite network to predict protein function. Experiment results on heterogenous proteomic information sources of Yeast, Human, Mouse, and Fly show that, SimNet not only achieves better (or comparable) results than different related competitive approaches, however conjointly takes much less time. The Matlab codes of SimNet are on the market at https://sites.google.com/web site/guoxian85/simnet.