Search papers, labs, and topics across Lattice.
This paper redefines protein structure prediction by framing it as a state-space inference problem, focusing on the dynamic nature of proteins that occupy multiple conformational states rather than identifying a single dominant structure. The authors highlight the importance of understanding energetic and kinetic relationships among these states, as well as their context-dependent behaviors and responses to perturbations. By reviewing current strategies such as deep learning ensemble generators and physics-based simulations, they propose a comprehensive roadmap for advancing state-space prediction in protein dynamics.
Understanding proteins as dynamic systems rather than static structures could revolutionize how we approach protein function and drug design.
Recent AI advances have enabled protein structure prediction at near-experimental accuracy, largely solving the problem of identifying a dominant conformation from sequence. Many proteins, however, function as dynamic systems populating multiple conformational states with activity emerging from shifts in relative occupancy--an incomplete picture when reduced to one structure. Here, we argue that structure prediction should be reformulated as a state-space inference problem: recovering not one conformation's coordinates but accessible states, their energetic and kinetic relationships, context dependence, and responses to perturbations. We review emerging strategies--deep learning ensemble generators, physics-based simulations, and experimental constraints--and outline a roadmap toward state-space prediction.
