Guided protein structure generation for pathway discovery: a showcase for RAF dimerization
Understanding the mechanisms underlying large scale protein conformational changes in signaling pathways is critical for elucidating disease processes and developing targeted therapeutics. However, existing experimental and computational methods struggle to resolve the dynamic ensembles of intermediate states that mediate such transitions, particularly in large biomolecular complexes. Here, we introduce a two-stage generative diffusion modeling framework designed to support pathway discovery in protein complexes, demonstrated using RAF kinase dimerization, a key event for kinase activation and oncogenic signaling. Our approach first generates ultra-coarse-grained structures conditioned on low dimensional descriptors along the monomer-to-dimer transition. It then applies a super-resolution model to recover detailed coarse-grained topologies suitable for molecular simulation. We show that this framework produces physically plausible, diverse, and robust intermediate structures, even for previously unseen interpolated descriptor values. The resulting ensemble enables generation of closely spaced candidate intermediate structures between biophysically distinct states, providing valuable starting points for downstream adaptive sampling and mechanistic studies. Overall, our results highlight the potential of diffusion-based generative models to bridge the gap between static structural data and isolated ensembles, and the dynamic complexity of protein signaling pathways.