Bayesian Longitudinal Regularized Quantile Mixed Model

Description

In this package, we provide implementations of a set of high-dimensional robust Bayesian mixed-effect models to dissect longitudinal gene-environment interactions. The proposed method conducts robust Bayesian variable selection on both the main and interaction effects corresponding to individual and group levels (i.e. bi-level), respectively. Alternatively, selections only on individual levels by ignoring the grouping structure can also be performed. In addition, intra-cluster correlations among repeated measures are modeled via random intercept-and-slope and/or random intercept models. Imposing exact sparsity through spike-and-slab priors can be conducted on fixed effects with bi-level and/or individual level. In total, package mixedBayes provides implementations on 2 (robust and non-robust) × 2 ( types of fixed effects) × 2 ( types of random effects) × 2 (spike-and-slab or Laplacian priors) = 16 methods. Please read the details below for how to configure the method used.

Details

The user friendly, integrated interface mixedBayes() allows users to flexibly choose the fitting methods by specifying the following parameter:

The function mixedBayes() returns a mixedBayes object that contains the posterior estimates of each coefficients. S3 generic functions selection()and print() are implemented for mixedBayes objects. selection() takes a mixedBayes object and returns the variable selection results.

References

Fan, K., Jiang, Y., Ma, S., Wang, W. and Wu, C. (2025). Robust Sparse Bayesian Regression for Longitudinal Gene-Environment Interactions. Journal of the Royal Statistical Society Series C: Applied Statistics, qlaf027 doi:10.1093/jrsssc/qlaf027

Zhou, F., Ren, J., Li, G., Jiang, Y., Li, X., Wang, W. and Wu, C. (2019). Penalized Variable Selection for Lipid-Environment Interactions in a Longitudinal Lipidomics Study. Genes, 10(12), 1002 doi:10.3390/genes10121002

Zhou, F., Ren, J., Liu, Y., Li, X., Wang, W., and Wu, C. (2022). Interep: An r package for high-dimensional interaction analysis of the repeated measurement data. Genes, 13(3), 544 doi:10.3390/genes13030544

Zhou, F., Lu, X., Ren, J., Fan, K., Ma, S., and Wu, C. (2022). Sparse group variable selection for gene–environment interactions in the longitudinal study. Genetic epidemiology, 46(5-6), 317-340 doi:10.1002/gepi.22461

Ren, J., Zhou, F., Li, X., Ma, S., Jiang, Y. and Wu, C. (2023). Robust Bayesian variable selection for gene-environment interactions. Biometrics,79(2),684-694 doi:10.1111/biom.13670

Wu, C., and Ma, S. (2015). A selective review of robust variable selection with applications in bioinformatics. Briefings in Bioinformatics, 16(5), 873–883 doi:10.1093/bib/bbu046

Zhou, F., Ren, J., Lu, X., Ma, S. and Wu, C. (2021). Gene–Environment Interaction: a Variable Selection Perspective. Epistasis. Methods in Molecular Biology. 2212:191–223 doi:10.1007/978-1-0716-0947-7_13

Ren, J., Zhou, F., Li, X., Chen, Q., Zhang, H., Ma, S., Jiang, Y. and Wu, C. (2020) Semi-parametric Bayesian variable selection for gene-environment interactions. Statistics in Medicine, 39: 617– 638 doi:10.1002/sim.8434

Wu, C., Jiang, Y., Ren, J., Cui, Y. and Ma, S. (2018). Dissecting gene-environment interactions: A penalized robust approach accounting for hierarchical structures. Statistics in Medicine, 37:437–456 doi:10.1002/sim.7518

Wu, C., Cui, Y., and Ma, S. (2014). Integrative analysis of gene–environment interactions under a multi–response partially linear varying coefficient model. Statistics in Medicine, 33(28), 4988–4998 doi:10.1002/sim.6287

Wu, C., Zhong, P.S. and Cui, Y. (2013). High dimensional variable selection for gene-environment interactions. Technical Report. Michigan State University.

See Also

mixedBayes

Construct Gene-Environment (G×E) Interaction Matrix

Description

Construct Gene-Environment (G×E) Interaction Matrix

Usage

GE(g,e)

Arguments

Value

the G×E interaction terms.

simulated data for demonstrating the features of mixedBayes

Description

simulated data for demonstrating the features of mixedBayes

Format

The data object consists of seven components: y, e, X, g, w ,k and coeff. coeff contains the true values of parameters (main and interaction effects) used for generating Y.

Details

The data and model setting

Consider a longitudinal study on n subjects with k repeated measurement for each subject. Let Y_{ij} be the measurement for the ith subject at each time point j(1\leq i \leq n, 1\leq j \leq k) .We use the m-dimensional vector G_{ij} to denote measurements of genetics factors for the ith subject at time point j, where G_{ij} = (G_{ij1},...,G_{ijm})^\top. Also, we use p-dimensional vector E_{ij} to denote the environment factors, where E_{ij} = (E_{ij1},...,E_{ijp})^\top. X_{ij} = (1, T_{ij})^\top, where T_{ij}^\top is a vector of time effects . Z_{ij} is a h \times 1 covariate associated with random effects and \alpha_{i} is a h\times 1 vector of random effects. In a typical one-way repeated measure ANOVA with a fixed number (say four) of factor levels, the environment (or treatment) factor is modelled as a group of three dummy variables. Therefore, gene-environment (or treatment) interaction leads to variable selections on individual levels (main effects) and group levels (interaction effect) simultaneously. Considering the genetics factors, environment (or treatment) factors and their interactions that are jointly associated with the longitudinal phenotype, we have the following mixed-effects model:

Y_{ij} = X_{ij}^\top\gamma_{0}+E_{ij}^\top\gamma_{1}+G_{ij}^\top\gamma_{2}+(G_{ij}\bigotimes E_{ij})^\top\gamma_{3}+Z_{ij}^\top\alpha_{i}+\epsilon_{ij}.

where \gamma_{1},\gamma_{2},\gamma_{3} are p,m and mp dimensional vectors that represent the coefficients of the environment effects, the genetics effects and interactions effects, respectively. In addition, \gamma_0 is the coefficient vector for X_{ij}. The gene–environment interactions that can be expressed as a Kronecker product between the two types of main effects as a mp-dimensional vector:

G_{ij}\bigotimes E_{ij} = [G_{ij1}E_{ij1},G_{ij1}E_{ij2},...,G_{ij1}E_{ijp},G_{ij2}E_{ij1},...,G_{ijm}E_{ijp}]^\top.

The above model also includes Z_{ij} with random effects \alpha_{i} to account for intra-correlations among repeated measurements. For random intercept-and-slope model, Z_{ij}^\top = (1,j) and \alpha_{i} = (\alpha_{i1},\alpha_{i2})^\top. For random intercept model, Z_{ij}^\top = 1 and \alpha_{i} = \alpha_{i1}.

In this example, we generate data under random intercept-and-slope model.

See Also

mixedBayes

Examples

data(data)
length(y)
dim(g)
dim(e)
dim(w)
print(k)
print(X)
print(coeff)

fit a Bayesian longitudinal regularized quantile mixed model

Description

fit a Bayesian longitudinal regularized quantile mixed model

Usage

mixedBayes(
  y,
  e,
  X,
  g,
  w,
  k,
  iterations = 10000,
  burn.in = NULL,
  slope = TRUE,
  robust = TRUE,
  quant = 0.5,
  sparse = TRUE,
  structure = c("bi-level", "individual")
)

Arguments

Details

Data layout

Consider a longitudinal study with repeated measurements per subject. The response vector y and the design matrices X, e, g, and w must all be provided in long format and share the same row ordering. In practice, each row corresponds to one observation from a particular subject at a particular time point.

Model

Consider the data model described in "data":

Y_{ij} = X_{ij}^\top\gamma_{0}+E_{ij}^\top\gamma_{1}+\sum_{l=1}^{p}G_{ijl}\gamma_{2l}+\sum_{l=1}^{p}W_{ijl}^\top\gamma_{3l}+Z_{ij}^\top\alpha_{i}+\epsilon_{ij}.

, with W_{ij} = G_{ij}\bigotimes E_{ij}.

where \gamma_{0} is the coefficient vector for X_{ij}, \gamma_{1} is the coefficient vector for E_{ij}, \gamma_{2l} is the coefficient for the main effect of the lth genetic variant, and \gamma_{3l} is the coefficient vector for the interaction effect of the lth genetic variant with environment factors.

The subject-specific random effects \alpha_i capture within-subject correlation. For random intercept-and-slope model, Z_{ij}^\top = (1,j) and \alpha_{i} = (\alpha_{i1},\alpha_{i2})^\top. For random intercept model, Z_{ij}^\top = 1 and \alpha_{i} = \alpha_{i1}.

When 'structure="bi-level"', bi-level selection will be conducted. If 'structure="individual"', individual-level selection will be conducted.

When 'slope=TRUE' (default), random intercept-and-slope model will be used as the mixed effects model.

When 'sparse=TRUE' (default), spike-and-slab priors are imposed to identify important main and interaction effects. Otherwise, Laplacian shrinkage will be used.

When 'robust=TRUE' (default), the distribution of \epsilon_{ij} is defined as an asymmetric Laplace distribution with density.

f(\epsilon_{ij}|\theta,\tau) = \theta(1-\theta)\exp\left\{-\tau\rho_{\theta}(\epsilon_{ij})\right\} , (i=1,\dots,n,j=1,\dots,k ), which leads to a Bayesian formulation of quantile regression. If 'robust=FALSE', \epsilon_{ij} follows a normal distribution.

Please check the references for more details about the prior distributions.

Value

an object of class ‘mixedBayes’ is returned, which is a list with component:

See Also

data

Examples

data(data)

## default method (robust sparse bi-level selection under random intercept-and-slope model)
fit = mixedBayes(y,e,X,g,w,k,structure=c("bi-level"))
fit$coefficient

## Compute TP and FP
b = selection(fit,sparse=TRUE)
index = which(coeff!=0)
pos = which(b != 0)
tp = length(intersect(index, pos))
fp = length(pos) - tp
list(tp=tp, fp=fp)

## alternative: robust sparse individual level selections under random intercept-and-slope model
fit = mixedBayes(y,e,X,g,w,k,structure=c("individual"))
fit$coefficient

## alternative: non-robust sparse bi-level selection under random intercept-and-slope model
fit = mixedBayes(y,e,X,g,w,k,robust=FALSE, structure=c("bi-level"))
fit$coefficient

## alternative: robust sparse bi-level selection under random intercept model
fit = mixedBayes(y,e,X,g,w,k,slope=FALSE, structure=c("bi-level"))
fit$coefficient

Make predictions from a mixedBayes object

Description

Make predictions from a mixedBayes object

Usage

predict_mixedBayes(object, y, X, e, g, w, k, slope, loss)

Arguments

Value

an object of class ‘mixedBayes.pred’ is returned, which is a list with components:

See Also

mixedBayes

Examples

data(data)

fit <- mixedBayes(y, e, X, g, w, k, structure = c("bi-level"))
pred1 <- predict_mixedBayes(fit, y, X, e, g, w, k, slope = TRUE, loss = "L1")
print(pred1$pred_error)
pred2 <- predict_mixedBayes(fit, y, X, e, g, w, k, slope = TRUE, loss = "L2")
print(pred2$pred_error)

This function changes the format of the longitudinal data from wide format to long format

Description

This function changes the format of the longitudinal data from wide format to long format

Usage

reformat(k,y,x)

Arguments

Value

a list containing the reformatted response vector and predictor matrix.

Variable selection for a mixedBayes object

Description

Variable selection for a mixedBayes object

Usage

selection(obj, sparse)

Arguments

Details

If sparse, the median probability model (MPM) (Barbieri and Berger, 2004) is used to identify predictors that are significantly associated with the response variable. Otherwise, variable selection is based on 95% credible interval. Please check the references for more details about the variable selection.

Value

an object of class ‘selection’ is returned, which is a list with component:

References

Ren, J., Zhou, F., Li, X., Ma, S., Jiang, Y. and Wu, C. (2023). Robust Bayesian variable selection for gene-environment interactions. Biometrics,79(2),684-694 doi:10.1111/biom.13670

Barbieri, M.M. and Berger, J.O. (2004). Optimal predictive model selection. Ann. Statist, 32(3):870–897

See Also

mixedBayes

Examples

data(data)
## sparse
fit = mixedBayes(y,e,X,g,w,k,structure=c("bi-level"))
selected=selection(fit,sparse=TRUE)
selected


## non-sparse
fit = mixedBayes(y,e,X,g,w,k,sparse=FALSE,structure=c("bi-level"))
selected=selection(fit,sparse=FALSE)
selected