Predicting protein function via downward random walks on a gene ontology. Issue 1 (December 2015)

• Record Type: Journal Article
• Authors: Yu, Guoxian; Zhu, Hailong; Domeniconi, Carlotta; Liu, Jiming
• Is Part Of: BMC bioinformatics. Volume 16:Issue 1(2015)
• Page Start: 1
• Page End: 13
• Publication Date: 2015-12
• Subjects: Function prediction -- Downward random walk -- Gene ontology -- Partially annotated proteins; Bioinformatics -- Periodicals; Computational biology -- Periodicals; 570.285
• DOI: 10.1186/s12859-015-0713-y
• Languages: English
• ISSNs: 1471-2105

Abstract

Abstract Background High-throughput bio-techniques accumulate ever-increasing amount of genomic and proteomic data. These data are far from being functionally characterized, despite the advances in gene (or gene's product proteins) functional annotations. Due to experimental techniques and to the research bias in biology, the regularly updated functional annotation databases, i.e., the Gene Ontology (GO), are far from being complete. Given the importance of protein functions for biological studies and drug design, proteins should be more comprehensively and precisely annotated. Results We proposedd ownwardR andomW alks (dRW) to predict missing (or new) functions of partially annotated proteins. Particularly, we apply downward random walks with restart on the GO directed acyclic graph, along with the available functions of a protein, to estimate the probability of missing functions. To further boost the prediction accuracy, we extend dRW to dRW-k NN. dRW-k NN computes the semantic similarity between proteins based on the functional annotations of proteins; it then predicts functions based on the functions estimated by dRW, together with the functions associated with thek nearest proteins. Our proposed models can predict two kinds of missing functions: (i) the ones that are missing for a protein but associated with other proteins of interest; (ii) the ones that are not available for any protein of interest, but exist in the GO hierarchy. Experimental results on the proteins of Yeast and Human show that dRW and dRW-k NN can replenish functions more accurately than other related approaches, especially for sparse functions associated with no more than 10 proteins. Conclusion The empirical study shows that the semantic similarity between GO terms and the ontology hierarchy play important roles in predicting protein function. The proposed dRW and dRW-k NN can serve as tools for replenishing functions of partially annotated proteins.