Identification of gene pairs through penalized regression subject to constraints

BMC Bioinformatics

Methodology Article

Hui Jiang¹  Lan Luo¹  Rex Shen² 

[1] Department of Biostatistics, University of Michigan, 48109, Ann Arbor, MI, USA;The Blake School, 55403, Minneapolis, MN, USA;

关键词: Gene pair;    Biomarker;    Penalized regression;    ADMM;   

DOI  :  10.1186/s12859-017-1872-9

 received in 2017-02-21, accepted in 2017-10-17,  发布年份 2017

来源: Springer

【 摘 要 】

BackgroundThis article concerns the identification of gene pairs or combinations of gene pairs associated with biological phenotype or clinical outcome, allowing for building predictive models that are not only robust to normalization but also easily validated and measured by qPCR techniques. However, given a small number of biological samples yet a large number of genes, this problem suffers from the difficulty of high computational complexity and imposes challenges to the accuracy of identification statistically.ResultsIn this paper, we propose a parsimonious model representation and develop efficient algorithms for identification. Particularly, we derive an equivalent model subject to a sum-to-zero constraint in penalized linear regression, where the correspondence between nonzero coefficients in these models is established. Most importantly, it reduces the model complexity of the traditional approach from the quadratic order to the linear order in the number of candidate genes, while overcoming the difficulty of model nonidentifiablity. Computationally, we develop an algorithm using the alternating direction method of multipliers (ADMM) to deal with the constraint. Numerically, we demonstrate that the proposed method outperforms the traditional method in terms of the statistical accuracy. Moreover, we demonstrate that our ADMM algorithm is more computationally efficient than a coordinate descent algorithm with a local search. Finally, we illustrate the proposed method on a prostate cancer dataset to identify gene pairs that are associated with pre-operative prostate-specific antigen.ConclusionOur findings demonstrate the feasibility and utility of using gene pairs as biomarkers.

【 授权许可】

CC BY   
© The Author(s) 2017

【 图 表 】

Fig. 2

Fig. 3

Fig. 2

12936_2015_894_Article_IEq17.gif

Fig. 2

Fig. 1

12951_2015_155_Article_IEq37.gif

13690_2023_1196_Figb_HTML.png

13690_2023_1196_Figa_HTML.png

Fig. 1

12944_2023_1927_Article_IEq25.gif

12944_2023_1927_Article_IEq24.gif

Fig. 2

Fig. 5

12936_2017_2075_Article_IEq38.gif

Fig. 3

12944_2023_1927_Article_IEq21.gif

Fig. 1

12944_2023_1927_Article_IEq20.gif

Fig. 1

12944_2023_1927_Article_IEq18.gif

Fig. 4

12944_2023_1927_Article_IEq16.gif

Fig. 4

12944_2023_1927_Article_IEq13.gif

Fig. 1

12888_2023_5256_Article_IEq1.gif

Fig. 3

12944_2023_1927_Article_IEq7.gif

12944_2023_1927_Article_IEq6.gif

Fig. 9

Fig. 1

12951_2015_155_Article_IEq34.gif

12951_2015_155_Article_IEq33.gif

12951_2015_155_Article_IEq32.gif

Fig. 1

12864_2016_2889_Article_IEq3.gif

Fig. 1

Fig. 2

Fig. 2

Fig. 2

Fig. 1

12951_2015_155_Article_IEq30.gif

Fig. 5

Fig. 6

12951_2017_270_Article_IEq9.gif

Fig. 2

12951_2017_270_Article_IEq8.gif

Fig. 1

Fig. 1

Fig. 2

Fig. 4

Fig. 5

12951_2015_155_Article_IEq28.gif

42004_2023_1020_Article_IEq18.gif

Fig. 3

Fig. 7

13100_2023_302_Article_IEq1.gif

12951_2017_270_Article_IEq7.gif

42004_2023_1020_Article_IEq12.gif

Fig. 2

Fig. 7

Fig. 1

Fig. 3

12951_2015_111_Article_IEq2.gif

Fig. 1

Fig. 5

Fig. 6

12951_2015_155_Article_IEq27.gif

12951_2017_315_Article_IEq2.gif

12951_2015_155_Article_IEq26.gif

12951_2015_155_Article_IEq25.gif

12951_2015_155_Article_IEq24.gif

12951_2015_155_Article_IEq19.gif

12951_2015_155_Article_IEq18.gif

12951_2015_155_Article_IEq16.gif

Fig. 3

12951_2015_155_Article_IEq14.gif