Encoding neuronal shape in the stochastic dynamics of branching processes

Cell shape critically influences function, yet how complex and reproducible morphologies emerge from stochastic cellular dynamics remains unclear. Here, we investigate dendritic morphogenesis of two classes of Drosophila mechanosensory neurons with contrasting architectures, combining in vivo live imaging, quantitative analysis, cytoskeletal perturbations, and computational modeling. We show that despite sharing similar local stochastic branching rules, the two classes exhibit divergent growth dynamics that cannot be explained by standard, diffusive growth models. This discrepancy arises because Class I neurons display subdiffusive branch dynamics over long timescales, unlike Class IV. Based on these findings, we develop a minimal model with only four parameters that separates short- and long-term branch behaviors, and successfully recapitulates growth dynamics and final morphologies in both classes. Cytoskeletal perturbations reveal a functional separation between actin, which drives short-term exploratory branch fluctuations and arbor expansion, and microtubules, which tune long-term branch diffusivity and determine class-specific morphology. Together, these results establish a parsimonious, generalizable framework linking local cytoskeletal regulation to global neuronal architecture and reveal how stochastic dynamics encode reproducible cell shapes.