Learn R Programming

dependentsimr (version 1.0.0.0)

Simulate Omics-Scale Data with Dependency

Description

Using a Gaussian copula approach, this package generates simulated data mimicking a target real dataset. It supports normal, Poisson, empirical, and 'DESeq2' (negative binomial with size factors) marginal distributions. It uses an low-rank plus diagonal covariance matrix to efficiently generate omics-scale data. Methods are described in: Yang, Grant, and Brooks (2025) .

Copy Link

Version

Install

install.packages('dependentsimr')

Monthly Downloads

133

Version

1.0.0.0

License

MIT + file LICENSE

Maintainer

Thomas Brooks

Last Published

July 23rd, 2025

Functions in dependentsimr (1.0.0.0)

draw_from_multivariate_corr

Draw random samples from the given random structure
remove_dependence

Remove all dependence in a random structure
read_counts

GSE151923: cortex from 6-month-old wildtype C57BL/6 mice
sample_spiked_wishart_and_jac

Efficiently sample the singular values corresponding to a random Wishart matrix with spiked eigenvalues and the Jacobian I.e., these are the singular values of G if GG^T is Wishart. The square of these give the eigenvalues of the random Wishart matrix.
match_with_spiked_wishart

Compute what spiked SD values will give you the desired top eigenvalues by iteratively solving
multi_sample_spiked_wishart

Compute means of each singular value and the mean Jacobian, see sample_spiked_wishart_and_jac
get_random_structure

Compute structure of dependency from a given data
sample_spiked_wishart

Efficiently sample the singular values corresponding to a random Wishart matrix with spiked eigenvalues Specifically, if W = G G^T with each column of G drawn iid from N(0, Sigma), then W is a Wishart matrix and this function samples the singular values of G. The eigenvalues of W are just the squares of the singular values. Here, Sigma is diagonal with its leading entries from spiked_sd^2 and all remaining entries are population_sd^2.