DocumentCode :
1789745
Title :
A consensus approach to predict regulatory interactions
Author :
Mohammed, Sabah ; Akman, Ozgur E. ; Zheng Rong Yang
Author_Institution :
Sch. of Biosci., Univ. of Exeter, Exeter, UK
fYear :
2014
fDate :
14-16 Oct. 2014
Firstpage :
769
Lastpage :
775
Abstract :
Exploiting microarray gene expression data to predict regulatory interactions has become a key challenge in recent years, for which many network inference algorithms have been developed. Combining predictions of multiple algorithms qualitatively to produce a consensus network has been previously implemented. Here, we propose a quantitative consensus approach based on combining regulatory interactions using the Fisher´s combined probability test. Edge significance values of different network inference algorithms were combined statistically to determine whether the edges should be included in a resulting consensus network. We validated and tested our approach with a variety of benchmark datasets, including data from the DREAM4 challenge. We have evaluated our algorithm against static and dynamic Bayesian networks and other individual networking methods. The results demonstrate that consensus networks predict many biological interactions with higher performance measures and outperform individual methods. We conclude that consensus networks are more robust and provide high confidence to predict regulatory interactions.
Keywords :
bioinformatics; feature extraction; genetics; inference mechanisms; lab-on-a-chip; probability; statistical analysis; DREAM4 challenge; Fisher combined probability test; benchmark dataset; biological interaction prediction; confidence; consensus network; dynamic Bayesian network; edge significance value combination; individual networking method; microarray gene expression data; multiple algorithm prediction combination; network inference algorithm; performance measure; qualitative prediction combination; quantitative consensus approach; regulatory interaction combination; regulatory interaction prediction; robustness; static Bayesian network; statistical combination; Biomedical engineering; Bismuth; Electromagnetic interference; IEC standards; Informatics;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Engineering and Informatics (BMEI), 2014 7th International Conference on
Conference_Location :
Dalian
Print_ISBN :
978-1-4799-5837-5
Type :
conf
DOI :
10.1109/BMEI.2014.7002876
Filename :
7002876
Link To Document :
بازگشت