Geometric Prediction: Moving Beyond Scalars

Understand

Many quantities we are interested in predicting are geometric tensors; we refer to this class of problems as geometric prediction.

• Attempts to perform geometric prediction in real-world scenarios have been limited to approximating them through scalar predictions, leading to losses in data efficiency.
• In this work, we demonstrate that equivariant networks have the capability to predict real-world geometric tensors without the need for such approximations.
• We show the applicability of this method to the prediction of force fields and then propose a novel formulation of an important task, biomolecular structure refinement, as a geometric prediction problem, improving state-of-the-art structural candidates.