IMIX_cor_twostep {IMIX}

IMIX-Cor-Twostep

Description

Fitting a correlated multivariate mixture model with fixed mean from estimated parameters of IMIX-ind. Input of summary statistics z scores or p values of two or three data types.

Usage

IMIX_cor_twostep(
  data_input,
  data_type = c("p", "z"),
  g = 8,
  mu_vec,
  cov,
  p,
  tol = 1e-06,
  maxiter = 1000,
  seed = 10,
  verbose = FALSE
)

Arguments

data_input

An n x d data frame or matrix of the summary statistics z score or p value, n is the nubmer of genes, d is the number of data types. Each row is a gene, each column is a data type.

data_type

Whether the input data is the p values or z scores, default is p value

g

The number of components, default is 8 for three data types

mu_vec

Input of the mean value output from IMIX-Ind result, a list of the mean vectors for each component.

cov

A list of initial values for the covariance matrices. If there are three data types and 8 components, then the initial is a list of 8 covariance matrices, each matix is 3*3.

p

Initial value for the proportion of the distribution in the Gaussian mixture model

tol

The convergence criterion. Convergence is declared when the change in the observed data log-likelihood increases by less than epsilon.

maxiter

The maximum number of iteration, default is 1000

seed

set.seed, default is 10

verbose

Whether to print the full log-likelihood for each iteration, default is FALSE

Value

A list of the results of IMIX-cor-twostep

posterior prob

Posterior probability matrix of each gene for each component

Full LogLik all

Full log-likelihood of each iteration

Full MaxLogLik final

The final log-likelihood of the converged model

iterations

Number of iterations run

pi

Estimated proportion of each component, sum to 1

mu

A list of mean vectors of each component for each data type, this is the prespecified mean

cov

A list of estimated variance-covariance matrix of each component

g

Number of components

References

Ziqiao Wang and Peng Wei. 2020. “IMIX: a multivariate mixture model approach to association analysis through multi-omics data integration.” Bioinformatics. <doi:10.1093/bioinformatics/btaa1001>.