Diffusion models in bioinformatics and computational biology

被引：28
作者：
Guo, Zhiye [1 ,2 ]
Liu, Jian [1 ,2 ]
Wang, Yanli [1 ,2 ]
Chen, Mengrui [1 ,2 ]
Wang, Duolin [1 ,2 ]
Xu, Dong [1 ,2 ]
Cheng, Jianlin [1 ,2 ]
机构：
[1] Univ Missouri, Dept Elect Engn & Comp Sci, Columbia, MO 65211 USA
[2] Univ Missouri, NextGen Precis Hlth, Columbia, MO 65211 USA
来源：
NATURE REVIEWS BIOENGINEERING | 2024年 / 2卷 / 02期
基金：
美国国家科学基金会; 美国国家卫生研究院;
关键词：
NOVO PROTEIN DESIGN; CRYO-EM; ENERGY FUNCTION; NETWORKS; DOCKING; PREDICTION; VISUALIZATION; REFINEMENT; POTENTIALS; MICROSCOPY;
D O I：
10.1038/s44222-023-00114-9
中图分类号：
R318 [生物医学工程];
学科分类号：
0831 ;
摘要：
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.
引用
收藏
页码：136 / 154
页数：19
相关论文
共 236 条
  • [1] LeCun Y., Bengio Y., Hinton G., Deep learning, Nature, 521, pp. 436-444, (2015)
  • [2] Eickholt J., Cheng J., Predicting protein residue–residue contacts using deep networks and boosting, Bioinformatics, 28, pp. 3066-3072, (2012)
  • [3] Baek M., Baker D., Deep learning and protein structure modeling, Nat. Methods, 19, pp. 13-14, (2022)
  • [4] Kulmanov M., Hoehndorf R., DeepGOPlus: improved protein function prediction from sequence, Bioinformatics, 36, pp. 422-429, (2020)
  • [5] Aggarwal D., Hasija Y., A Review of Deep Learning Techniques for Protein Function Prediction, (2022)
  • [6] Gligorijevic V., Et al., Structure-based protein function prediction using graph convolutional networks, Nat. Commun, 12, (2021)
  • [7] Bileschi M.L., Et al., Using deep learning to annotate the protein universe, Nat. Biotechnol, 40, pp. 932-937, (2022)
  • [8] Cai Y., Wang J., Deng L., SDN2GO: an integrated deep learning model for protein function prediction, Front. Bioeng. Biotechnol, 8, (2020)
  • [9] Ko C.W., Huh J., Park J.-W., Deep learning program to predict protein functions based on sequence information, MethodsX, 9, (2022)
  • [10] Dhakal A., McKay C., Tanner J.J., Cheng J., Artificial intelligence in the prediction of protein–ligand interactions: recent advances and future directions, Brief. Bioinform, 23, (2022)
12345678910