Fig. 2From: High-order dynamic Bayesian Network learning with hidden common causes for causal gene regulatory networkOverall Flow of the Proposed Algorithm. The steps are: 1) infer an initial GRN, 2) identify the genes with hidden common cause, 3) estimate the hidden common cause(s), which involves clustering and EM, 4) re-learn the GRN after estimation of the hidden common cause(s)Back to article page