诺贝尔化学奖也花落AI领域!刚刚,AlphaFold开发者等人获奖 | 深度解读
▎药明康德内容团队编辑
就在人工智能学者出人意料地摘得2024年诺贝尔物理学奖之后,北京时间10月9日下午,诺贝尔基金会宣布将今年的诺贝尔化学奖颁发给了三位研究领域与人工智能相关的科学家。
其中,被誉为“AlphaFold之父”的谷歌DeepMind公司Demis Hassabis博士和John Jumper博士因为蛋白质结构预测获奖,而华盛顿大学的David Baker教授因计算蛋白设计荣获殊荣。他们开发的AI解决方案成功解决了50年来蛋白质结构预测领域的重大挑战,加速了生物医药领域的科学发现。
▲David Baker教授、Demis Hassabis博士与John Jumper博士(图片来源:诺贝尔奖官网)
下面,药明康德内容团队将与大家一道回顾这个革命性的AI解决方案的诞生和成长史。
AlphaFold的故事
David Baker与Rosetta的故事
小小的蛋白质里藏着天大的疑问
向梦想靠近,开发出蛋白质结构预测程序
开发Rosetta的意外收获
从预测到模拟,破解上帝之手的奥秘
遇劲敌,取长补短开启新一轮进化之路
下一站,剑指新药开发
[1] The Nobel Prize in Chemistry 2024, Retrieved October 9, 2024, from https://www.nobelprize.org/prizes/chemistry/2024/summary/
[2] 2023 Winners. Retrieved October 2, 2023, from https://laskerfoundation.org/winners/2023-winners/
[3] Google's DeepMind predicts 3D shapes of proteins. Retrieved October 2, 2023, from https://www.theguardian.com/science/2018/dec/02/google-deepminds-ai-program-alphafold-predicts-3d-shapes-of-proteins
[4] DeepMind and EMBL release the most complete database ofpredicted 3D structures of human proteins. Retrieved October 2, 2023, from https://www.ebi.ac.uk/about/news/press-releases/alphafold-database-launch
[5] AlphaFold reveals the structure of the protein universe. Retrieved October 2, 2023, from https://www.deepmind.com/blog/alphafold-reveals-the-structure-of-the-protein-universe
[6] 2023 CANADA GAIRDNER AWARD WINNERS ANNOUNCED. Retrieved October 2, 2023, from https://www.gairdner.org/resource-hub/2023-canada-gairdner-award-winners-announced
[7] Alphabet’s AI predicted the structure of 200 million proteins. Can it really speed up drug discovery? Retrieved October 2, 2023, from https://www.statnews.com/2022/10/13/can-alphabet-alphafold-really-speed-up-drug-discovery/
[9] WINNERS OF THE 2021 BREAKTHROUGH PRIZES IN LIFE SCIENCES, FUNDAMENTAL PHYSICS AND MATHEMATICS ANNOUNCED. Retrieved September 10, 2020, from https://breakthroughprize.org/News/60
[10] Scientists are finally learning how to design proteins from scratch. Drug development may never be the same. Retrieved June 24, 2022 from https://endpts.com/scientists-are-finally-learning-how-to-design-proteins-from-scratch-drug-development-may-never-be-the-same/
[11] Rosetta Commons- Overview. Retrieved June 24, 2022 from https://www.rosettacommons.org/software
[12] Baek, Minkyung et al. (2021) Accurate prediction of protein structures and interactions using a three-track neural network. Science. vol. 373,6557: 871-876. DOI:10.1126/science.abj8754
[13] RoseTTAFold: Accurate protein structure prediction accessible to all. Retrieved June 28, 2022 from https://www.ipd.uw.edu/2021/07/rosettafold-accurate-protein-structure-prediction-accessible-to-all/#:~:text=RoseTTAFold%20is%20a%20%E2%80%9Cthree-track%E2%80%9D%20neural%20network%2C%20meaning%20it,one%20another%2C%20and%20a%20protein%E2%80%99s%20possible%20three-dimensional%20structure.
[14] The protein design revolution. Retrieved June 30, 2022 from https://www.ipd.uw.edu/applications/
[15] Pan, Xingjie, and Tanja Kortemme. (2021) Recent advances in de novo protein design: Principles, methods, and applications. The Journal of biological chemistry 296: 100558. DOI:10.1016/j.jbc.2021.100558
[16] Mirdita, Milot et al. (2022) ColabFold: making protein folding accessible to all. Nature methods 19,6: 679-682. DOI:10.1038/s41592-022-01488-1
[17] Mohan, Kritika et al. (2019) Topological control of cytokine receptor signaling induces differential effects in hematopoiesis. Science 364,6442: eaav7532. DOI:10.1126/science.aav7532
[18] Silva, Daniel-Adriano et al. (2019) De novo design of potent and selective mimics of IL-2 and IL-15. Nature 565,7738: 186-191. DOI:10.1038/s41586-018-0830-7
[19] Khatib F, DiMaio F; Foldit Contenders Group; Foldit Void Crushers Group; Cooper S, Kazmierczyk M, Gilski M, Krzywda S, Zabranska H, Pichova I, Thompson J, Popović Z, Jaskolski M, Baker D. Crystal structure of a monomeric retroviral protease solved by protein folding game players. Nat Struct Mol Biol. 2011 Sep 18;18(10):1175-7. doi: 10.1038/nsmb.2119. Erratum in: Nat Struct Mol Biol. 2012 Mar;19(3):364. PMID: 21926992; PMCID: PMC3705907.
分享,点赞,在看,聚焦全球生物医药健康创新