The study of crystalline solids benefitted from the low dimensional representation of atomistic structure and defects. In contrast, the study of disordered solids has been challenging due to the lack of such a representation. We have constructed a predictive, one-dimensional representation, using supervised machine learning, to study disordered configurations. Our approach can be used to study simulations as well as experiments, with systems ranging from supercool liquids, glasses, granular pillars, colloidal structures to grain boundaries in polycrystals. We embed the ML representation in theoretical models of several phenomena in disordered solids, e.g. fragility, fragile-to-strong transition, out-of-equilibrium dynamics, aging, glassy thin film dynamics, and grain boundary dynamics. This approach leads to a unified perspective on disordered particle arrangements, from atoms to macroscopic grains spanning seven orders of magnitude in particle size. Finally, I will discuss the potential applications of very recent innovations in computer science to the study of materials.