lnmbiclust {lnmCluster}

Logistic Normal Multinomial Biclustering algorithm

Description

Main function that can do LNM biclustering and select the best model based on BIC, AIC or ICL.

Usage

lnmbiclust(W_count, range_G, range_Q, model, criteria, iter, permutation, X)

Arguments

W_count

The microbiome count matrix

range_G

All possible number of components. A vector.

range_Q

All possible number of bicluster for each component. A vector

model

The covaraince structure you choose, there are 16 different models belongs to this family:UUU, UUG, UUD, UUC, UGU, UGG, UGD, UGC, GUU, GUG, GUD, GUC, GGU, GGG, GGD, GGC. You can choose more than 1 covarance structure to do model selection.

criteria

one of AIC, BIC or ICL. The best model is depends on the criteria you choose. The default is BIC

iter

Max iterations, defaul is 150.

permutation

Only has effect when model contains UUU, UUG, UUD or UUC. If TRUE, it assume the number of biclusters could be different for different components. If FALSE, it assume the number of biclusters are the same cross all components. Default is FALSE.

X

The regression covariate matrix, which is generated by model.matrix.

Value

z_ig Estimated latent variable z

cluster Component labels

mu_g Estimated component mean

pi_g Estimated component proportion

B_g Estimated bicluster membership

T_g Estimated covariance of latent variable u

D_g Estimated error covariance

COV Estimated sparsity component covariance

beta_g Estimated covariate coefficients

sigma Estimated original component covariance

overall_loglik Complete log likelihood value for each iteration

ICL ICL value

BIC BIC value

AIC AIC value

all_fitted_model display all names of fitted models in a data.frame.

Examples

#generate toy data with n=100, K=5,
#set up parameters
n<-100
p<-5
mu1<-c(-2.8,-1.3,-1.6,-3.9,-2.6)
B1<-matrix(c(1,0,1,0,1,0,0,1,0,1),nrow = p, byrow=TRUE)
T1<-diag(c(2.9,0.5))
D1<-diag(c(0.52, 1.53, 0.56, 0.19, 1.32))
cov1<-B1%*%T1%*%t(B1)+D1
mu2<-c(1.5,-2.7,-1.1,-0.4,-1.4)
B2<-matrix(c(1,0,1,0,0,1,0,1,0,1),nrow = p, byrow=TRUE)
T2<-diag(c(0.2,0.003))
D2<-diag(c(0.01, 0.62, 0.45, 0.01, 0.37))
cov2<-B2%*%T2%*%t(B2)+D2

#generate normal distribution
library(mvtnorm)
simp<-rmultinom(n,1,c(0.6,0.4))
lab<-as.factor(apply(t(simp),1,which.max))
df<-matrix(0,nrow=n,ncol=p)
for (i in 1:n) {
 if(lab[i]==1){df[i,]<-rmvnorm(1,mu1,sigma = cov1)}
 else if(lab[i]==2){df[i,]<-rmvnorm(1,mu2,sigma = cov2)}
}
#apply inverse of additive log ratio and transform normal to count data
f_df<-cbind(df,0)
z<-exp(f_df)/rowSums(exp(f_df))
W_count<-matrix(0,nrow=n,ncol=p+1)
for (i in 1:n) {
 W_count[i,]<-rmultinom(1,runif(1,10000,20000),z[i,])
}

#'#if run one model let range_Q be an integer
res<-lnmbiclust(W_count,2,2,model="UUU")

#following will run 2 combinations of Q: 2 2, and 3 3 with G=2.
res<-lnmbiclust(W_count,2,range_Q=c(2:3),model="UUU")

#if run model selection let range_Q and range_G be a vector.
#model selection for all 16 models with G=1 to 3, Q=1 to 3.
res<-lnmbiclust(W_count,c(1:3),c(1:3))