By Topic

A New Method to Combine Heterogeneous Data Sources for Candidate Gene Prioritization

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Yongjin Li ; Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore ; Patra, J.C. ; Jiabao Sun

How to effectively integrate heterogeneous data sources is becoming extremely challenging, because many useful but noisy data sources are available for the problem at hand.In this paper, for disease gene prioritization problem, we investigated multiple kernels learning (MKL) and N dimensional order statistics (NDOS) method, but found that neither could effectively extract useful information from noisy data. Especially, in MKL algorithm, ineffective data source may be given more weight,which downgrades the effectiveness of the combined kernel. We proposed an improved procedure based on NDOS. We first use cross validation to evaluate each individual data source, and only effective data sources are used in the prioritizations of candidate genes.

Published in:

Bioinformatics and BioEngineering, 2009. BIBE '09. Ninth IEEE International Conference on

Date of Conference:

22-24 June 2009