Diffusion models in bioinformatics and computational biology

• Published in: Nature reviews bioengineering Vol. 2; no. 2; pp. 136 - 154
• Main Authors: Guo, Zhiye, Liu, Jian, Wang, Yanli, Chen, Mengrui, Wang, Duolin, Xu, Dong, Cheng, Jianlin
• Format: Journal Article
• Language: English
• Published: England Nature Publishing Group 01.02.2024
• Subjects: Artificial intelligence; Bioinformatics; Biology; Computer applications; Computer vision; Data analysis; Deep learning; Differential equations; Diffusion; Drug development; Electron microscopy; Generative artificial intelligence; Image processing; Interaction models; Ligands; Machine learning; Markov analysis; Microscopy; Modelling; Natural language processing; Neural networks; Noise reduction; Ordinary differential equations; Probabilistic models; Probability; Probability distribution; Proteins
• ISSN: 2731-6092; 2731-6092
• DOI: 10.1038/s44222-023-00114-9

Denoising diffusion models embody a type of generative artificial intelligence that can be applied in computer vision, natural language processing and bioinformatics. In this Review, we introduce the key concepts and theoretical foundations of three diffusion modelling frameworks (denoising diffusion probabilistic models, noise-conditioned scoring networks and score stochastic differential equations). We then explore their applications in bioinformatics and computational biology, including protein design and generation, drug and small-molecule design, protein-ligand interaction modelling, cryo-electron microscopy image data analysis and single-cell data analysis. Finally, we highlight open-source diffusion model tools and consider the future applications of diffusion models in bioinformatics.