Gene Regulatory Neural Network
Gene regulatory neural networks (GRNNs) leverage the inherent computational properties of gene regulatory networks (GRNs) to model and predict cellular behavior. Current research focuses on improving GRN inference from single-cell data, employing techniques like graph neural networks and transformer models to account for data noise (e.g., dropouts) and incorporate prior biological knowledge. These advancements aim to create more accurate models of GRNs, enabling better understanding of cellular processes and potentially leading to improved drug discovery and the development of novel bio-hybrid computing systems. The field is also exploring the use of causal inference methods to better understand the dynamic and often cyclic interactions within GRNs.