注册 |登录

许培扬博客分享 http://blog.sciencenet.cn/u/xupeiyang 跟踪国际前沿 服务国内科研

博文

2024年诺贝尔化学奖得主John M. Jumper AlphaFold3 2024年获奖论文分析报告

已有 1304 次阅读 2024-10-11 06:22 |个人分类:诺贝尔奖|系统分类:观点评述

 2024年诺贝尔化学奖得主John M. Jumper   AlphaFold3 2024年  当年论文获奖  

1. Accurate structure prediction of biomolecular interactions with AlphaFold 3.

Josh Abramson,Jonas Adler,Jack Dunger,Richard Evans,Tim Green,Alexander Pritzel,Olaf Ronneberger,Lindsay Willmore,Andrew J Ballard,Joshua Bambrick,Sebastian W Bodenstein,David A Evans,Chia-Chun Hung,Michael O'Neill,David Reiman,Kathryn Tunyasuvunakool,Zachary Wu,Akvilė Žemgulytė,Eirini Arvaniti,Charles Beattie,Ottavia Bertolli,Alex Bridgland,Alexey Cherepanov,Miles Congreve,Alexander I Cowen-Rivers,Andrew Cowie,Michael Figurnov,Fabian B Fuchs,Hannah Gladman,Rishub Jain,Yousuf A Khan,Caroline M R Low,Kuba Perlin,Anna Potapenko,Pascal Savy,Sukhdeep Singh,Adrian Stecula,Ashok Thillaisundaram,Catherine Tong,Sergei Yakneen,Ellen D Zhong,Michal Zielinski,Augustin Žídek,Victor Bapst,Pushmeet Kohli,Max Jaderberg,Demis Hassabis,John M Jumper

Core Contributor, Google DeepMind, London, UK.

jaderberg@isomorphiclabs.com

Nature (P 1476-4687 E 0028-0836) H指数：1096 2024 年 630 卷 8016 期 493-500 页

PMID：38718835 相似文献

文摘 DOI链接 Nature Publishing Group

http://www.pubmedplus.cn/P/SearchQuickResult?wd=6846f457-e1f5-48fa-9d58-474acf2e2587

陈德旺   38岁的诺奖得主给年轻人才成长的几点启示 精选

2018年开发的AlphaFold功能还比较弱，只能解析几十个蛋白质结构。 AlphaFold2于2020年面市，能在超过2亿个蛋白质结构中做出精准预测，大大解放了做蛋白质解析的科研人员。2024年5月的AlphaFold3，将蛋白质带入广泛的生物分子领域，为生物开发与药物设计、基因组学研究奠定了基础。

https://blog.sciencenet.cn/blog-57940-1454689.html

 2024年诺贝尔化学奖得主John M. Jumper   2024年 原文

https://pubmed.ncbi.nlm.nih.gov/38718835/

Nature

. 2024 Jun;630(8016):493-500.

 doi: 10.1038/s41586-024-07487-w. Epub 2024 May 8.

Accurate structure prediction of biomolecular interactions with AlphaFold 3

Josh Abramson # 1, Jonas Adler # 1, Jack Dunger # 1, Richard Evans # 1, Tim Green # 1, Alexander Pritzel # 1, Olaf Ronneberger # 1, Lindsay Willmore # 1, Andrew J Ballard 1, Joshua Bambrick 2, Sebastian W Bodenstein 1, David A Evans 1, Chia-Chun Hung 2, Michael O'Neill 1, David Reiman 1, Kathryn Tunyasuvunakool 1, Zachary Wu 1, Akvilė Žemgulytė 1, Eirini Arvaniti 3, Charles Beattie 3, Ottavia Bertolli 3, Alex Bridgland 3, Alexey Cherepanov 4, Miles Congreve 4, Alexander I Cowen-Rivers 3, Andrew Cowie 3, Michael Figurnov 3, Fabian B Fuchs 3, Hannah Gladman 3, Rishub Jain 3, Yousuf A Khan 3 5, Caroline M R Low 4, Kuba Perlin 3, Anna Potapenko 3, Pascal Savy 4, Sukhdeep Singh 3, Adrian Stecula 4, Ashok Thillaisundaram 3, Catherine Tong 4, Sergei Yakneen 4, Ellen D Zhong 3 6, Michal Zielinski 3, Augustin Žídek 3, Victor Bapst 1, Pushmeet Kohli 1, Max Jaderberg 7, Demis Hassabis 8 9, John M Jumper 10

Affiliations expand

Abstract

The introduction of AlphaFold 21 has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design2-6. Here we describe our AlphaFold 3 model with a substantially updated diffusion-based architecture that is capable of predicting the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues. The new AlphaFold model demonstrates substantially improved accuracy over many previous specialized tools: far greater accuracy for protein-ligand interactions compared with state-of-the-art docking tools, much higher accuracy for protein-nucleic acid interactions compared with nucleic-acid-specific predictors and substantially higher antibody-antigen prediction accuracy compared with AlphaFold-Multimer v.2.37,8. Together, these results show that high-accuracy modelling across biomolecular space is possible within a single unified deep-learning framework.

© 2024. The Author(s).

PubMed Disclaimer

Conflict of interest statement

Author-affiliated entities have filed US provisional patent applications including 63/611,674, 63/611,638 and 63/546,444 relating to predicting 3D structures of molecule complexes using embedding neural networks and generative models. All of the authors other than A.B., Y.A.K. and E.D.Z. have commercial interests in the work described.

Figures

Fig. 1

Fig. 1. AF3 accurately predicts structures across…

 Fig. 2

Fig. 2. Architectural and training details. 

a…

 Fig. 3

Fig. 3. Examples of predicted complexes. 

Selected…

 Fig. 4

Fig. 4. AF3 confidences track accuracy. 

a…

 Fig. 5

Fig. 5. Model limitations. 

a , Antibody…

 Extended Data Fig. 1

Extended Data Fig. 1. Disordered region prediction.

All figures (14)

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Jumper J, et al. Highly accurate protein structure prediction with AlphaFold. Nature. 2021;596:583–589. - PMC - PubMed

    1. Kreitz J, et al. Programmable protein delivery with a bacterial contractile injection system. Nature. 2023;616:357–364. - PMC - PubMed

    1. Lim Y, et al. In silico protein interaction screening uncovers DONSON’s role in replication initiation. Science. 2023;381:eadi3448. - PMC - PubMed

    1. Mosalaganti S, et al. AI-based structure prediction empowers integrative structural analysis of human nuclear pores. Science. 2022;376:eabm9506. - PubMed

    1. Anand, N. & Achim, T. Protein structure and sequence generation with equivariant denoising diffusion probabilistic models. Preprint at arXiv10.48550/arXiv.2205.15019 (2022).

Show all 73 references

MeSH terms

  • Antibodies / chemistry

  • Antibodies / metabolism

  • Antigens / chemistry

  • Antigens / metabolism

  • Deep Learning* / standards

  • Humans

  • Ions / chemistry

  • Ions / metabolism

  • Ligands*

  • Models, Molecular*

  • Molecular Docking Simulation

  • Nucleic Acids / chemistry

  • Nucleic Acids / metabolism

  • Protein Binding

  • Protein Conformation

  • Proteins* / chemistry

  • Proteins* / metabolism

  • Reproducibility of Results

  • Software* / standards

Substances

  • Antibodies

  • Antigens

  • Ions

  • Ligands

  • Nucleic Acids

  • Proteins

Related informationLinkOut - more resources

AlphaFold3 研究文献分析如下

http://www.pubmedplus.cn/P/SearchQuickResult?wd=51348148-5f67-4019-bfdc-f8ba843eac3c

01.无法确认6 篇27.273%
02.20249 篇40.909%
01.biorxiv2 篇9.091%
02.int j biol macromol2 篇9.091%
03.nature2 篇9.091%
04.arxiv1 篇4.545%
05.bioinformatics1 篇4.545%
06.chembiochem1 篇4.545%
07.int j mol sci1 篇4.545%
08.j am chem soc1 篇4.545%
09.j chem inf model1 篇4.545%
10.j magn reson1 篇4.545%
01.美国7 篇31.818%
02.加拿大3 篇13.636%
03.中国2 篇9.091%
04.奥地利1 篇4.545%
05.荷兰1 篇4.545%
06.瑞士1 篇4.545%
07.土耳其1 篇4.545%
01.中国上海1 篇4.545%
02.中国福州1 篇4.545%
03.中国衡阳1 篇4.545%
01.Protein Conformation6 篇27.273%
02.Protein Folding5 篇22.727%
03.Proteins5 篇22.727%
04.Software5 篇22.727%
05.Models, Molecular3 篇13.636%
06.Algorithms2 篇9.091%
07.Artificial Intelligence2 篇9.091%
08.Computational Biology2 篇9.091%
09.Deep Learning2 篇9.091%
10.Humans2 篇9.091%

AlphaFold3 研究相似文献分析如下

1. Accurate structure prediction of biomolecular interactions with AlphaFold 3.

Josh Abramson,Jonas Adler,Jack Dunger,Richard Evans,Tim Green,Alexander Pritzel,Olaf Ronneberger,Lindsay Willmore,Andrew J Ballard,Joshua Bambrick,Sebastian W Bodenstein,David A Evans,Chia-Chun Hung,Michael O'Neill,David Reiman,Kathryn Tunyasuvunakool,Zachary Wu,Akvilė Žemgulytė,Eirini Arvaniti,Charles Beattie,Ottavia Bertolli,Alex Bridgland,Alexey Cherepanov,Miles Congreve,Alexander I Cowen-Rivers,Andrew Cowie,Michael Figurnov,Fabian B Fuchs,Hannah Gladman,Rishub Jain,Yousuf A Khan,Caroline M R Low,Kuba Perlin,Anna Potapenko,Pascal Savy,Sukhdeep Singh,Adrian Stecula,Ashok Thillaisundaram,Catherine Tong,Sergei Yakneen,Ellen D Zhong,Michal Zielinski,Augustin Žídek,Victor Bapst,Pushmeet Kohli,Max Jaderberg,Demis Hassabis,John M Jumper

Core Contributor, Google DeepMind, London, UK.

jaderberg@isomorphiclabs.com

Nature (P 1476-4687 E 0028-0836) H指数：1096 2024 年 630 卷 8016 期 493-500 页

PMID：38718835 相似文献

文摘 DOI链接 Nature Publishing Group

http://www.pubmedplus.cn/P/SearchQuickResult?wd=28b5032e-bd31-4b49-8e2a-a0e9f0266981

01.无法确认7 篇7.000%
02.202412 篇12.000%
03.202320 篇20.000%
04.202211 篇11.000%
05.202112 篇12.000%
06.20207 篇7.000%
07.20184 篇4.000%
08.20172 篇2.000%
09.20163 篇3.000%
10.20157 篇7.000%
11.20141 篇1.000%
12.20121 篇1.000%
13.20111 篇1.000%
14.20103 篇3.000%
15.20091 篇1.000%
16.20081 篇1.000%
17.20071 篇1.000%
18.20061 篇1.000%
19.20051 篇1.000%
20.20011 篇1.000%
21.19991 篇1.000%
22.19972 篇2.000%
01.brief bioinform13 篇13.000%
02.proteins8 篇8.000%
03.j chem inf model7 篇7.000%
04.protein sci5 篇5.000%
05.j chem theory comput4 篇4.000%
06.nature4 篇4.000%
07.nucleic acids res4 篇4.000%
08.acc chem res3 篇3.000%
09.biorxiv3 篇3.000%
10.int j mol sci3 篇3.000%
01.美国38 篇38.000%
02.中国23 篇23.000%
03.英国9 篇9.000%
04.德国8 篇8.000%
05.日本5 篇5.000%
06.法国4 篇4.000%
07.韩国4 篇4.000%
08.加拿大4 篇4.000%
09.瑞典4 篇4.000%
10.瑞士4 篇4.000%
01.中国武汉5 篇5.000%
02.中国杭州3 篇3.000%
03.中国长沙3 篇3.000%
04.中国北京2 篇2.000%
05.中国长春2 篇2.000%
06.中国上海2 篇2.000%
07.中国深圳2 篇2.000%
08.中国香港2 篇2.000%
09.中国哈尔滨1 篇1.000%
10.中国常州1 篇1.000%
01.Proteins68 篇68.000%
02.Protein Binding50 篇50.000%
03.Protein Conformation47 篇47.000%
04.Ligands40 篇40.000%
05.Molecular Docking Simulation36 篇36.000%
06.Nucleic Acids34 篇34.000%
07.Models, Molecular29 篇29.000%
08.Software28 篇28.000%
09.Binding Sites21 篇21.000%
10.Deep Learning21 篇21.000%



https://blog.sciencenet.cn/blog-280034-1454725.html

上一篇：2024年诺贝尔化学奖得主John M. Jumper AlphaFold软件 文献分析报告
下一篇：日本诺贝尔奖 文献分析报告 1993 - 2024年
收藏 IP: 223.72.64.*| 热度|

4 宁利中 刘跃 高宏 郑永军

该博文允许注册用户评论 请点击登录 评论 (0 个评论)

数据加载中...

Archiver|手机版|科学网 ( 京ICP备07017567号-12 )

GMT+8, 2024-12-23 01:17

Powered by ScienceNet.cn

Copyright © 2007- 中国科学报社

返回顶部