Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Learning predictive interactions using information gain and Bayesian network scoring

Jiang, X and Jao, J and Neapolitan, R (2015) Learning predictive interactions using information gain and Bayesian network scoring. PLoS ONE, 10 (12).

[img]
Preview
PDF
Published Version
Available under License : See the attached license file.

Download (1MB)
[img] Plain Text (licence)
Available under License : See the attached license file.

Download (1kB)

Abstract

© 2015 Jiang et al.This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Background The problems of correlation and classification are long-standing in the fields of statistics and machine learning, and techniques have been developed to address these problems. We are now in the era of high-dimensional data, which is data that can concern billions of variables. These data present new challenges. In particular, it is difficult to discover predictive variables, when each variable has little marginal effect. An example concerns Genomewide Association Studies (GWAS) datasets, which involve millions of single nucleotide polymorphism (SNPs), where some of the SNPs interact epistatically to affect disease status. Towards determining these interacting SNPs, researchers developed techniques that addressed this specific problem. However, the problem is more general, and so these techniques are applicable to other problems concerning interactions. A difficulty with many of these techniques is that they do not distinguish whether a learned interaction is actually an interaction or whether it involves several variables with strong marginal effects. Methodology/Findings We address this problem using information gain and Bayesian network scoring. First, we identify candidate interactions by determining whether together variables provide more information than they do separately. Then we use Bayesian network scoring to see if a candidate interaction really is a likely model. Our strategy is called MBS-IGain. Using 100 simulated datasets and a real GWAS Alzheimer's dataset, we investigated the performance of MBS-IGain. Conclusions/Significance When analyzing the simulated datasets, MBS-IGain substantially out-performed nine previous methods at locating interacting predictors, and at identifying interactions exactly. When analyzing the real Alzheimer's dataset, we obtained new results and results that substantiated previous findings. We conclude that MBS-IGain is highly effective at finding interactions in high-dimensional datasets. This result is significant because we have increasingly abundant high-dimensional data in many domains, and to learn causes andperform prediction/classification using these data, we often must first identify interactions.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: Article
Status: Published
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Jiang, Xxij6@pitt.eduXIJ6
Jao, J
Neapolitan, R
Contributors:
ContributionContributors NameEmailPitt UsernameORCID
EditorEmmert-Streib, FrankUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Date: 1 December 2015
Date Type: Publication
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Journal or Publication Title: PLoS ONE
Volume: 10
Number: 12
DOI or Unique Handle: 10.1371/journal.pone.0143247
Institution: University of Pittsburgh
Schools and Programs: School of Medicine > Biomedical Informatics
Refereed: Yes
Date Deposited: 23 Aug 2016 14:53
Last Modified: 13 Oct 2017 21:56
URI: http://d-scholarship.pitt.edu/id/eprint/28349

Metrics

Monthly Views for the past 3 years

Plum Analytics

Altmetric.com


Actions (login required)

View Item View Item