The errors in lattice energy minimisation studies: sensitivity to experimental variations in the molecular structure of paracetamol

Fourteen experimental crystal structure determinations of paracetamol, covering two polymorphic forms and a range of temperatures, show the usual minor variations in the molecular structure, which reflect the limitations of X-ray crystallography and dynamical motion of the methyl group. Minima in the intermolecular lattice energy have been found starting from these experimental structures, keeping the molecular structure rigid and using the same distributed multipole-based model intermolecular potential in all calculations. These have been compared and contrasted with the lattice energy minima obtained using an ab initio optimised molecular model. Genuine crystal structure prediction requires the use of non-crystallographic molecular models, and so in this study we illustrate the accuracy that could be achieved in such a prediction study. The small variations in the experimental molecular structure produce variations of a few percent in the cell lengths and a few kJ mol(-1) of the lattice energy in the rigid-molecule crystal structure minima. This produces considerable uncertainty in the calculated energy difference between the polymorphs. The structural and lattice energy differences between the experimental crystal structures and the corresponding lattice energy minima vary sufficiently with temperature and determination to show that the uncertainties in the molecular structure and neglect of temperature dominate this difference (of around 3% in the cell lengths). Thus, this study suggests that the level of significance for refining model potentials by comparing lattice energy minima and experimental crystal structures is a few % in the cell lengths. This is comparable with previous estimates based on the thermal expansion of this type of organic crystal structure between 0 K and room temperature.