Ambient Proteins: Training Diffusion Models on Low Quality Structures
Giannis Daras, Jeffrey Ouyang-Zhang, Krithika Ravishankar, William Daspit, Costis Daskalakis, Qiang Liu, Adam R. Klivans, Daniel J. Diaz
Treating low-confidence AlphaFold structures as noisy data at pLDDT-dependent diffusion times lets a 16.7M-parameter model generate long proteins with higher diversity, designability and novelty than Proteína.
bioRxiv · Jul 3, 2025 · PreprintBioengineering✦ In-depth digest