Three different techniques have been used to analyse the relationship between the structure of 62 organic compounds and their sublimation enthalpies. Using a neural network based on molecular structure descriptors (molecular formula, hydrogen bonding and π-characteristics), sublimation enthalpies can be modelled. The best of the neural network models yielded an average error of 2.5 kcal mol^–1 in a series of ‘leave-one-out experiments’. The same sublimation enthalpy data have been studied using theoretical techniques based upon crystal packing calculations, and also with a simple three parameter multilinear regression model. The latter two methodss produced results that were superior to the neural network in this particular study (mean errors of 1.4 and 1.8 kcal mol^–1, respectively), although in the case of MLRA, this is the result of the model fitting exercise, and not a predictive run. It was surprising to find such a simple linear relationship between characteristics describing the molecular formula and the sublimation enthalpy. Nevertheless, the results here have highlighted the potential of neural networks and MLRA as useful tools for the approximate prediction of physical reperties, as demonstrated for a series of compounds not included in the training set.