Energy-based models for atomic-resolution protein conformations
This work addresses the challenge of protein conformation scoring for structural biology and design, offering a data-driven alternative to physics-based methods, but it is incremental as it matches rather than surpasses existing benchmarks.
The authors tackled the problem of scoring atomic-resolution protein conformations by proposing an energy-based model trained solely on crystallized protein data, achieving performance close to the state-of-the-art Rosetta energy function on the rotamer recovery task.
We propose an energy-based model (EBM) of protein conformations that operates at atomic scale. The model is trained solely on crystallized protein data. By contrast, existing approaches for scoring conformations use energy functions that incorporate knowledge of physical principles and features that are the complex product of several decades of research and tuning. To evaluate the model, we benchmark on the rotamer recovery task, the problem of predicting the conformation of a side chain from its context within a protein structure, which has been used to evaluate energy functions for protein design. The model achieves performance close to that of the Rosetta energy function, a state-of-the-art method widely used in protein structure prediction and design. An investigation of the model's outputs and hidden representations finds that it captures physicochemical properties relevant to protein energy.