Density physics-informed neural networks reveal sources of cell heterogeneity in signal transduction

Abstract

Understanding cellular signaling pathways is crucial because their dysregulation can lead to diseases and treatment resistance. For instance, if signaling pathways that respond to antibiotics or cancer therapeutics show a large heterogeneity in response between cells, some cells could survive the treatment, while others are killed by it. Valuable information about the signaling pathway, such as its speed, precision, and structure, can be inferred from the transduction time, the time it takes for a signal to travel from its initiation to its final response. Therefore, developing methods that can estimate the transduction-time distribution of a signaling pathway could enable the identification of sources of cellular heterogeneity and could ultimately help develop better treatment agents that can avoid or overcome heterogeneous cellular responses.