From thermodynamics to protein design: Diffusion models for biomolecule generation towards autonomous protein engineering
It addresses the problem of designing proteins with desirable properties for applications in drug discovery and protein engineering, but it is incremental as it reviews existing methods rather than presenting new results.
This review tackles the challenge of protein design by exploring diffusion models, such as Denoising Diffusion Probabilistic Models and Score-based Generative Models, for generating biomolecules like proteins and peptides, with a focus on maintaining E(3) equivariance to ensure physical stability.
Protein design with desirable properties has been a significant challenge for many decades. Generative artificial intelligence is a promising approach and has achieved great success in various protein generation tasks. Notably, diffusion models stand out for their robust mathematical foundations and impressive generative capabilities, offering unique advantages in certain applications such as protein design. In this review, we first give the definition and characteristics of diffusion models and then focus on two strategies: Denoising Diffusion Probabilistic Models and Score-based Generative Models, where DDPM is the discrete form of SGM. Furthermore, we discuss their applications in protein design, peptide generation, drug discovery, and protein-ligand interaction. Finally, we outline the future perspectives of diffusion models to advance autonomous protein design and engineering. The E(3) group consists of all rotations, reflections, and translations in three-dimensions. The equivariance on the E(3) group can keep the physical stability of the frame of each amino acid as much as possible, and we reflect on how to keep the diffusion model E(3) equivariant for protein generation.