To convey sensory touch inputs, neurons must have the ability to sense and translate mechanical stimuli into electrical signals. This process, known as mechanosensation, relies on the proper structuring and development of neuronal dendritic trees (arborization). There is growing evidence supporting the required role of environmental cues in determining the definitive morphology of dendritic trees. In turn, arborization is expected to result from both intrinsic neuronal differentiation as well as extrinsic contributions from the external environment. However, there is little understanding of how mechanosensory signals regulate the morphological arborization process, and conversely how the morphology of dendritic trees affects mechanosensation. Yet, defects in neuronal development and mechanosensory function can contribute to neuro-developmental disorders such as Down’s syndrome and autism. In the present proposal, we aim at deepening our quantitative understanding of the influence of touch-based sensory input in determining dendritic patterns during development. The proposed work is built around three pillars of research using the model organism Caenorhabditis elegans. We will implement (i) live imaging techniques of mechanosensory touch neurons in whole organisms, (ii) statistical models using machine learning to quantify the structure and patterns of neuronal trees, and (iii) behavioral assays of C. elegans to characterize the influence of extrinsic sensory inputs on motility phenotypes. This latter step will rely heavily on engineering fluidics and quantitative visualization techniques. It is anticipated that an integral characterization of the coupling between mechanosensory input and dendritic arborization will pave the way towards a better understanding of neurodegenerative diseases and potential treatment strategies.