Abstract: The invention refers to an apparatus (100) for determining properties of a substance. A providing unit (110) provides atomic descriptors that are indicative of characteristics of atoms of the substance with respect to the structure of the specific molecule. A model providing unit (120) provides a trained property model, wherein the trained property model has been trained to determine a property of the substance as output when provided with the atomic descriptors. The property model comprises a) an atomic classifier adapted to classify atoms of the substance into one or more atom classes based on the atomic descriptors and b) a regression model adapted to determine the property based on the atom classes determined for the substance. A determination unit (130) determines the property of the substance by applying the trained property model to the atomic descriptors.

Abstract: A computing system for predicting protein structure ensembles includes processing circuitry configured to, in a first training phase, ingest a synthetic dataset of protein sequences, perform structure-based clustering on the synthetic dataset to produce clusters of protein structures, filter the clusters of protein structures, and train a diffusion model on training pairs. In a second training phase, the processing circuitry receives a predicted protein structure for an input training protein sequence from the diffusion model, and compares the predicted protein structure to a corresponding training protein structure from a molecular dynamics simulation. In a third training phase, the processing circuitry receives a predicted value for a property of sampled protein structures, compares the predicted value to an actual value of the property, and backpropagates the diffusion model with the difference.