The last 15 years have seen the emergence of entire new classes of crystalline nanoporous materials, which exhibit large or anomalous responses to external physical or chemical stimulation. These modifications of framework structure and pore dimensions also involve, in turn, a modification of other physical and chemical properties, making such materials multifunctional (or “smart materials”). One of the outstanding challenges in this field is the systematic synthesis of materials with controlled functionality and porosity. We propose here to remedy this by the development of novel computational chemistry methods that can predict the response of structures under various physical or chemical stimuli. These methods will then be applied on known materials to generate a training dataset for a machine learning procedure, thus allowing to provide rapid screening of large databases of hypothetical materials.