A predictive system may access a set of physical structures corresponding to a molecule. Each physical structure is representative of a configuration. The predictive system may encode the accessed physical structures to produce a set of encoded physical structures by encoding, for each accessed physical structure, a position of each constituent unit of the molecule within the accessed physical structure. The predictive system may train a machine-learned model using the encoded physical structures. The predictive system may retrain the machine-learned model by iteratively: accessing a set of two or more candidate physical structures, determining a first energy difference among the set of candidate physical structures, obtaining a second energy difference between a set of physical structures corresponding to the set of candidate physical structures using a method to calculate reference energy values.