AUTHOR=Lei Xiujuan , Zhang Cheng , Wang Yueyue 

TITLE=Predicting Metabolite-Disease Associations Based on Spy Strategy and ABC Algorithm

JOURNAL=Frontiers in Molecular Biosciences

VOLUME=Volume 7 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/molecular-biosciences/articles/10.3389/fmolb.2020.603121

DOI=10.3389/fmolb.2020.603121

ISSN=2296-889X

ABSTRACT=It has been a significant focus in biomedical domain to reveal latent metabolite-disease associations over recent years as more and more experimental evidences have been testified that metabolite correlates with diagnosis of human complex diseases. Several computational methods have been developed to detect potential metabolite-disease associations. In this article, we propose a novel method based on spy strategy and artificial bee colony (ABC) algorithm for the metabolite-disease association prediction (SSABCMDA). Due to there are large parts of missing associations in the unconfirmed metabolite-disease pairs, spy strategy is adopted to extract reliable negative samples from the unconfirmed pairs. Considering the effects of parameters, the ABC algorithm is utilized to optimize parameters. In the relevant cross-validation experiments, our method achieves excellent predictive performance. Moreover, three types of case studies are conducted on three common diseases to demonstrate the validity and utility of SSABCMDA method. Relevant experimental results indicate that our method can effectively predict potential associations between metabolites and diseases.