Network Reconstruction and Changepoint Detection
Make a network structure or hyperparameter move.
Calculate network prior ratio with Poisson prior.
Tune the proposal width for betas.
Propose a new real hyperparameter value.
Propose a new discrete value.
Sample initial parameters for the MCMC simulation.
Sample initial sigma squared.
Calculates the potential scale reduction factor.
Check the potential scale reduction factors for all parameters (edges)...
Checks the potential scale reduction factor for the hyperparameters.
Read target data.
Samples from the inverse gamma distribution.
Setup and run the MCMC simulation.
Sample initial regression coefficients.
Sample regression coefficients.
Sample delta squared.
Sample initial number of changepoints.
Check if move is acceptable.
Add the proposed new network to the new.nets list.
Makes a binomial hyperparameter move.
Calculates the MH ratio of the binomial prior.
Computes the acceptance ratio of two changepoint configurations.
Builds response Y and predictor X.
Function to calculate the number of differences between adjaccent netw...
Calculated the global changepoint probabilities.
Calculate the changepoint probabilities.
Calculate the edge probabilities.
Calculate edge probabilities for fixed segments.
Calculate the edge posterior probabilities for each timepoint.
Calculates the ratio of two likelihoods in a structure move.
Calculates the network prior ratio.
Collects all the network information in one list.
Compute projection matrix.
Calculate proposal frequencies for changepoint moves.
Convert internal representation of networks.
Make changepoint birth move.
Make changepoint death move.
Makes a changepoint shift move.
Set the default options for the MCMC simulation.
Calculate inverse gamma distribution.
Allows for network reconstruction and changepoint detection.
Wrapper function for starting an MCMC simulation
Makes an exponential hyperparameter move.
Calculates the ratio of an exponential hyperparameter move.
Modify network to ensure stationarity.
Generate a random network.
Make a hyperparameter move.
Sets up initial values of hyperparameters.
Initialise the MCMC simulation.
Main function of the MCMC simulation.
Makes a structure move.
Calculates the prior probability of the network segments under the bin...
Calculates the prior probability of the network using the exponential ...
Calculates the ratio of binomial prior probabilites.
Calculates the ratio of exponential network prior probabilities.
Collects and saves output.
Generate network and simulate data.
Update sigma squared variances.
Sample new values for sigma squared.
Package EDISON (Estimation of Directed Interactions from Sequences Of Non-homogeneous gene expression) runs an MCMC simulation to reconstruct networks from time series data, using a non-homogeneous, time-varying dynamic Bayesian network. Networks segments and changepoints are inferred concurrently, and information sharing priors provide a reduction of the inference uncertainty.