Here we propose new module-based approaches to identify differentially regulated network sub-modules combining temporal trajectories of expression profiles with static network skeletons. Starting from modules identified by network clustering of static networks, our analysis refines pre-defined genesets by partitioning them into smaller homogeneous sets by non-paramettric Bayesian methods. Especially for case-control time series data we developed multi-time point discriminative models and identified each network module as a mixture or admixture of dynamic discriminative functions. Our results shows that our proposed approach outperformed existing geneset enrichment methods in simulation studies. Moreover we applied the methods to neural stem cell differentiation data, and discovered novel modules differentially perturbed in different developmental stages.