Conformational analysis of aspirin dataset

These datasets contain the mean energy of different conformers of aspirin corresponding to the rotation of carboxylic acid and ester groups. The clusters C1 and C2 are selected based on the distribution of dihedral angles using the mean +/- standard deviation as a criteria. The energy difference between clusters C1 and C2 is calculated from the distribution of the test set (20000 points) as well as from the distribution of model predictions.