Time-Varying DBN Inference with the ARTIVA (Auto Regressive TIme
VArying) Model
Description
Reversible Jump MCMC (RJ-MCMC)sampling for approximating the posterior
distribution of a time varying regulatory network, under the Auto Regressive TIme VArying
(ARTIVA) model (for a detailed description of the algorithm, see Lebre et al. BMC Systems
Biology, 2010). Starting from time-course gene expression measurements for a gene of
interest (referred to as "target gene") and a set of genes (referred to as "parent genes")
which may explain the expression of the target gene, the ARTIVA procedure identifies
temporal segments for which a set of interactions occur between the "parent genes" and the
"target gene". The time points that delimit the different temporal segments are referred to
as changepoints (CP).