Structure prediction
Diffusion-based structure prediction can be guided by backpropagating to the conditioning embeddings rather than the atomic coordinates directly, and such embeddings can be re-refined in subsequent iterations
Diffusion-based biomolecular structure prediction, which is used in latest-generation methods like AlphaFold3[1] and BioEmu[2], can be guided or steered into specific conformations by backpropagating to the conditioning representations rather than the atomic coordinates being diffused [3][4]. This was recently shown by two methods, EmbedOpt and IT-Optimization. There