Variable selection in regression with compositional covariates

Motivated by research problems arising in the analysis of gut microbiome and metagenomic data, we consider variable selection and estimation in high-dimensional regression with compositional covariates. We propose an l1 regularization method for the linear log-contrast model that respects the unique features of compositional data. We formulate the proposed procedure as a constrained convex optimization problem and introduce a coordinate descent method of multipliers for efficient computation. In the high-dimensional setting where the dimensionality grows at most exponentially with the sample size, model selection consistency and $\ell _{\infty }$ bounds for the resulting estimator are established under conditions that are mild and interpretable for compositional data. The numerical performance of our method is evaluated via simulation studies and its usefulness is illustrated by an application to a microbiome study relating human body mass index to gut microbiome composition.

[1]  J. Atchison,et al.  Logistic-normal distributions:Some properties and uses , 1980 .

[2]  Dimitri P. Bertsekas,et al.  Constrained Optimization and Lagrange Multiplier Methods , 1982 .

[3]  J. Aitchison,et al.  Log contrast models for experiments with mixtures , 1984 .

[4]  John Aitchison,et al.  The Statistical Analysis of Compositional Data , 1986 .

[5]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[6]  F. Bäckhed,et al.  Obesity alters gut microbial ecology. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[7]  E. Mardis,et al.  An obesity-associated gut microbiome with increased capacity for energy harvest , 2006, Nature.

[8]  P. Turnbaugh,et al.  Microbial ecology: Human gut microbes associated with obesity , 2006, Nature.

[9]  Peng Zhao,et al.  On Model Selection Consistency of Lasso , 2006, J. Mach. Learn. Res..

[10]  R. Tibshirani,et al.  PATHWISE COORDINATE OPTIMIZATION , 2007, 0708.1485.

[11]  Martin J. Wainwright,et al.  Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using $\ell _{1}$ -Constrained Quadratic Programming (Lasso) , 2009, IEEE Transactions on Information Theory.

[12]  Yingcun Xia,et al.  Shrinkage Estimation of the Varying Coefficient Model , 2008 .

[13]  Tso-Jung Yen,et al.  Discussion on "Stability Selection" by Meinshausen and Buhlmann , 2010 .

[14]  R. Tibshirani,et al.  The solution path of the generalized lasso , 2010, 1005.1971.

[15]  F. Bushman,et al.  Linking Long-Term Dietary Patterns with Gut Microbial Enterotypes , 2011, Science.

[16]  Sara van de Geer,et al.  Statistics for High-Dimensional Data: Methods, Theory and Applications , 2011 .

[17]  Hongzhe Li,et al.  VARIABLE SELECTION FOR SPARSE DIRICHLET-MULTINOMIAL REGRESSION WITH AN APPLICATION TO MICROBIOME DATA ANALYSIS. , 2013, The annals of applied statistics.

[18]  F. Bushman,et al.  Structure-constrained sparse canonical correlation analysis with an application to microbiome data analysis. , 2013, Biostatistics.

[19]  Yingying Fan,et al.  Tuning parameter selection in high dimensional penalized likelihood , 2013, 1605.03321.