Feature Selection with Interactions in Logistic Regression Models Using Multivariate Synergies for a GWAS Application

Overview

Journal BMC Genomics

Publisher Biomed Central

Specialty Genetics

Date 2018 Mar 29

PMID 29589561

Citations 4

Authors

Easton Li Xu

Xiaoning Qian

Qilian Yu

Han Zhang

Shuguang Cui

Affiliations

Soon will be listed here.

Abstract

Background: Genotype-phenotype association has been one of the long-standing problems in bioinformatics. Identifying both the marginal and epistatic effects among genetic markers, such as Single Nucleotide Polymorphisms (SNPs), has been extensively integrated in Genome-Wide Association Studies (GWAS) to help derive "causal" genetic risk factors and their interactions, which play critical roles in life and disease systems. Identifying "synergistic" interactions with respect to the outcome of interest can help accurate phenotypic prediction and understand the underlying mechanism of system behavior. Many statistical measures for estimating synergistic interactions have been proposed in the literature for such a purpose. However, except for empirical performance, there is still no theoretical analysis on the power and limitation of these synergistic interaction measures.

Results: In this paper, it is shown that the existing information-theoretic multivariate synergy depends on a small subset of the interaction parameters in the model, sometimes on only one interaction parameter. In addition, an adjusted version of multivariate synergy is proposed as a new measure to estimate the interactive effects, with experiments conducted over both simulated data sets and a real-world GWAS data set to show the effectiveness.

Conclusions: We provide rigorous theoretical analysis and empirical evidence on why the information-theoretic multivariate synergy helps with identifying genetic risk factors via synergistic interactions. We further establish the rigorous sample complexity analysis on detecting interactive effects, confirmed by both simulated and real-world data sets.

Citing Articles

Artificial Intelligence for Antimicrobial Resistance Prediction: Challenges and Opportunities towards Practical Implementation.

Ali T, Ahmed S, Aslam M Antibiotics (Basel). 2023; 12(3).

PMID: 36978390 PMC: 10044311. DOI: 10.3390/antibiotics12030523.

Machine Learning for Antimicrobial Resistance Prediction: Current Practice, Limitations, and Clinical Perspective.

Kim J, Maguire F, Tsang K, Gouliouris T, Peacock S, McAllister T Clin Microbiol Rev. 2022; 35(3):e0017921.

PMID: 35612324 PMC: 9491192. DOI: 10.1128/cmr.00179-21.

Computational analysis and prediction of lysine malonylation sites by exploiting informative features in an integrative machine-learning framework.

Zhang Y, Xie R, Wang J, Leier A, Marquez-Lago T, Akutsu T Brief Bioinform. 2018; 20(6):2185-2199.

PMID: 30351377 PMC: 6954445. DOI: 10.1093/bib/bby079.

Selected research articles from the 2017 International Workshop on Computational Network Biology: Modeling, Analysis, and Control (CNB-MAC).

Yoon B, Qian X, Kahveci T, Pal R BMC Bioinformatics. 2018; 19(Suppl 3):69.

PMID: 29589557 PMC: 5872518. DOI: 10.1186/s12859-018-2058-9.

References

Guo X, Zhang J, Cai Z, Du D, Pan Y . Searching Genome-Wide Multi-Locus Associations for Multiple Diseases Based on Bayesian Inference. IEEE/ACM Trans Comput Biol Bioinform. 2016; 14(3):600-610. DOI: 10.1109/TCBB.2016.2527648. View

Chung Y, Lee S, Elston R, Park T . Odds ratio based multifactor-dimensionality reduction method for detecting gene-gene interactions. Bioinformatics. 2006; 23(1):71-6. DOI: 10.1093/bioinformatics/btl557. View

Wheeler D, Srinivasan M, Egholm M, Shen Y, Chen L, McGuire A . The complete genome of an individual by massively parallel DNA sequencing. Nature. 2008; 452(7189):872-6. DOI: 10.1038/nature06884. View

Reijonen H, Novak E, Kochik S, Heninger A, Liu A, Kwok W . Detection of GAD65-specific T-cells by major histocompatibility complex class II tetramers in type 1 diabetic patients and at-risk subjects. Diabetes. 2002; 51(5):1375-82. DOI: 10.2337/diabetes.51.5.1375. View

Lee K, Wucherpfennig K, Wiley D . Structure of a human insulin peptide-HLA-DQ8 complex and susceptibility to type 1 diabetes. Nat Immunol. 2001; 2(6):501-7. DOI: 10.1038/88694. View

Wan X, Yang C, Yang Q, Xue H, Fan X, Tang N . BOOST: A fast approach to detecting gene-gene interactions in genome-wide case-control studies. Am J Hum Genet. 2010; 87(3):325-40. PMC: 2933337. DOI: 10.1016/j.ajhg.2010.07.021. View

Ignac T, Skupin A, Sakhanenko N, Galas D . Discovering pair-wise genetic interactions: an information theory-based approach. PLoS One. 2014; 9(3):e92310. PMC: 3966778. DOI: 10.1371/journal.pone.0092310. View

Subramanian A, Tamayo P, Mootha V, Mukherjee S, Ebert B, Gillette M . Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles. Proc Natl Acad Sci U S A. 2005; 102(43):15545-50. PMC: 1239896. DOI: 10.1073/pnas.0506580102. View

. Genome-wide association study of 14,000 cases of seven common diseases and 3,000 shared controls. Nature. 2007; 447(7145):661-78. PMC: 2719288. DOI: 10.1038/nature05911. View

10.

Reshef D, Reshef Y, Finucane H, Grossman S, McVean G, Turnbaugh P . Detecting novel associations in large data sets. Science. 2011; 334(6062):1518-24. PMC: 3325791. DOI: 10.1126/science.1205438. View

11.

Purcell S, Neale B, Todd-Brown K, Thomas L, Ferreira M, Bender D . PLINK: a tool set for whole-genome association and population-based linkage analyses. Am J Hum Genet. 2007; 81(3):559-75. PMC: 1950838. DOI: 10.1086/519795. View

12.

Adl A, Qian X, Xu P, Vehik K, Krischer J . Feature ranking based on synergy networks to identify prognostic markers in DPT-1. EURASIP J Bioinform Syst Biol. 2013; 2013(1):12. PMC: 3849336. DOI: 10.1186/1687-4153-2013-12. View

13.

Watkinson J, Wang X, Zheng T, Anastassiou D . Identification of gene interactions associated with disease from gene expression data using synergy networks. BMC Syst Biol. 2008; 2:10. PMC: 2258206. DOI: 10.1186/1752-0509-2-10. View

14.

Howson J, Walker N, Clayton D, Todd J . Confirmation of HLA class II independent type 1 diabetes associations in the major histocompatibility complex including HLA-B and HLA-A. Diabetes Obes Metab. 2009; 11 Suppl 1:31-45. PMC: 2779837. DOI: 10.1111/j.1463-1326.2008.01001.x. View

15.

Harris M, Clark J, Ireland A, Lomax J, Ashburner M, Foulger R . The Gene Ontology (GO) database and informatics resource. Nucleic Acids Res. 2003; 32(Database issue):D258-61. PMC: 308770. DOI: 10.1093/nar/gkh036. View

16.

Sakhanenko N, Galas D . Biological data analysis as an information theory problem: multivariable dependence measures and the shadows algorithm. J Comput Biol. 2015; 22(11):1005-24. PMC: 4642827. DOI: 10.1089/cmb.2015.0051. View

17.

Wu J, Devlin B, Ringquist S, Trucco M, Roeder K . Screen and clean: a tool for identifying interactions in genome-wide association studies. Genet Epidemiol. 2010; 34(3):275-85. PMC: 2915560. DOI: 10.1002/gepi.20459. View

18.

Foulis A, Farquharson M, Hardman R . Aberrant expression of class II major histocompatibility complex molecules by B cells and hyperexpression of class I major histocompatibility complex molecules by insulin containing islets in type 1 (insulin-dependent) diabetes mellitus. Diabetologia. 1987; 30(5):333-43. PMC: 7087521. DOI: 10.1007/BF00299027. View

19.

Kim H, Watkinson J, Anastassiou D . Biomarker discovery using statistically significant gene sets. J Comput Biol. 2011; 18(10):1329-38. PMC: 3179615. DOI: 10.1089/cmb.2010.0085. View

20.

Song L, Langfelder P, Horvath S . Comparison of co-expression measures: mutual information, correlation, and model based indices. BMC Bioinformatics. 2012; 13:328. PMC: 3586947. DOI: 10.1186/1471-2105-13-328. View