John Nardini, Erica Rutter, Kevin Flores
This minisymposium highlights the development of novel data-driven methods, including statistics, machine learning, parameter estimation, and uncertainty quantification, and combinations thereof, towards modeling biological systems. These newly developed methods will tackle challenges that are commonly encountered when modeling real-world experimental, field, pre-clinical, or clinical data. Examples of such challenges include high dimensionality, computational complexity, sparse sampling, model bias, and intra- or inter-individual heterogeneity. The methods introduced in this minisymposium are applicable to a broad range of biological areas, including neurobiology, epidemiology, oncology, electrophysiology, and genetics.