Abstract
Discrete stochastic models of gene regulatory network models are indispensable tools for biological inquiry since they allow the modeler to predict how molecular interactions give rise to nonlinear system output. Model exploration with the objective of generating qualitative hypotheses about the workings of a pathway is usually the first step in the modeling process. It involves simulating the gene network model under a very large range of conditions, due to the the large uncertainty in interactions and kinetic parameters. This makes model exploration highly computational demanding. Furthermore, with no prior information about the model behavior, labour-intensive manual inspection of very large amounts of simulation results becomes necessary. This limits systematic computational exploration to simplistic models. We address this by developing an interactive, smart workflow for model exploration based on semi-supervised learning and human-in-the-loop labeling of data. The proposed methodology lets a modeler rapidly discover ranges of interesting behaviors predicted by a model. Utilizing the notion that similar simulation output is in proximity of each other in feature space, the modeler can focus on informing the system about what behaviors are more interesting than others instead of configuring and analyzing simulation results. This large reduction in time-consuming manual work by the modeler early in a modeling project can substantially reduce the time needed to go from an initial model to testable predictions and downstream analysis.
