Abstract: Training a protein diffusion model includes receiving a representation of a protein as training data, the representation comprising at least three dimensions. It further includes training a protein diffusion model at least in part by performing rotational diffusion based at least in part on the representation of the protein. Generating proteins includes receiving protein conditioning information. It further includes, based at least in part on the protein conditioning information, performing conditional sampling of a protein diffusion model. The protein diffusion model is trained at least in part by performing rotational diffusion. Based at least in part on the conditional sampling of the protein diffusion model, the protein diffusion model generates one or more of a protein structure or a protein sequence.

Abstract: Fiber optically illuminated medical infusion tubes. Such an illuminated tube includes one or more infusion tubes, one or more optical fibers which is illuminated for the infusion tube and one or more light sources which lights up the optical fiber. The fiber is illuminated along the length of the infusion tube. The light sources have multiple light colors to identify each of the optical fiber. A light controller controls the lightings of the optical fiber, and the light controller can be programed for various lighting modes as desired.