bioRxiv Genomics· Masaki, N., Acharya, S., Malysheva, V., Koturan, S., Bottolo, L., Spivakov, M. ·· 1 day agoPickScore63
SPARK: Bayesian structure learning of enhancer-based gene regulatory networks from single-cell multiomics data and prior knowledge
In brief
The authors propose SPARK, a framework that combines single-cell multiomics data with mechanistic prior knowledge to reconstruct enhancer-based gene regulatory networks through Bayesian inference. SPARK represents eGRNs as directed acyclic graphs (DAGs), with network structure priors drawn from heterogeneous evidence. Simulation studies show it benefits from prior knowledge and outperforms existing DAG-based and regression-based algorithms.
Why it matters
SPARK incorporates mechanistic priors into Bayesian reconstruction of single-cell eGRNs and reports performance gains over DAG and regression baselines in simulations, aiding comparative method design.
Source: bioRxiv Genomics · biorxiv.org