AlphaFold
出典: フリー百科事典『ウィキペディア（Wikipedia）』 (2024/03/08 14:11 UTC 版)
AlphaFold（アルファフォールド）は、タンパク質の構造予測を実行するGoogleのDeepMindによって開発された人工知能プログラムである[1]。このプログラムは、タンパク質の折り畳み構造を原子の幅に合わせて予測する深層学習システムとして設計されている[2]。
- ^ “AlphaFold”. Deepmind. 2020年11月30日閲覧。
- ^ a b c d e f “DeepMind's protein-folding AI has solved a 50-year-old grand challenge of biology” (英語). MIT Technology Review. 2020年11月30日閲覧。
- ^ Shead, Sam (2020年11月30日). “DeepMind solves 50-year-old 'grand challenge' with protein folding A.I.” (英語) 2020年11月30日閲覧。
- ^ a b c d e f g Robert F. Service, ‘The game has changed.’ AI triumphs at solving protein structures, Science, 30 November 2020
- ^ a b c d e f Mohammed AlQuraishi, CASP14 scores just came out and they’re astounding, twitter, 30 November 2020.
- ^ a b c d Callaway, Ewen (2020-11-30). “'It will change everything': DeepMind's AI makes gigantic leap in solving protein structures” (英語). Nature. doi:10.1038/d41586-020-03348-4.
- ^ AlQuraishi, Mohammed (2020年12月8日). “AlphaFold2 @ CASP14: “It feels like one’s child has left home.”. The Method” (英語). Some Thoughts on a Mysterious Universe. 2020年12月15日閲覧。
- ^ Stephen Curry, No, DeepMind has not solved protein folding, Reciprocal Space (blog), 2 December 2020
- ^ Demis Hassabis, "Brief update on some exciting progress on #AlphaFold!" (tweet), via twitter, 18 June 2021
- ^ a b c “AlphaFold: Using AI for scientific discovery”. Deepmind. 2020年11月30日閲覧。
- ^ Jumper, John; Evans, Richard; Pritzel, Alexander; Green, Tim; Figurnov, Michael; Ronneberger, Olaf; Tunyasuvunakool, Kathryn; Bates, Russ et al. (2021-07-15). “Highly accurate protein structure prediction with AlphaFold” (英語). Nature 596 (7873): 583–589. Bibcode: 2021Natur.596..583J. doi:10.1038/s41586-021-03819-2. PMC 8371605. PMID 34265844.
- ^ a b c d “AlphaFold: a solution to a 50-year-old grand challenge in biology”. Deepmind. 2020年11月30日閲覧。
- ^ Mohammed AlQuraishi (May 2019), AlphaFold at CASP13, Bioinformatics, 35(22), 4862–4865 doi:10.1093/bioinformatics/btz422. See also Mohammed AlQuraishi (December 9, 2018), AlphaFold @ CASP13: “What just happened?” (blog post).
Mohammed AlQuraishi (15 January 2020), A watershed moment for protein structure prediction, Nature 577, 627-628 doi:10.1038/d41586-019-03951-0 - ^ AlphaFold: Machine learning for protein structure prediction, Foldit, 31 January 2020
- ^ Torrisi, Mirko et al. (22 Jan. 2020), Deep learning methods in protein structure prediction. Computational and Structural Biotechnology Journal vol. 18 1301-1310. doi:10.1016/j.csbj.2019.12.011 (CC-BY-4.0)
- ^ a b c “DeepMind is answering one of biology's biggest challenges”. The Economist. (2020年11月30日). ISSN 0013-0613 2020年11月30日閲覧。
- ^ a b Jeremy Kahn, Lessons from DeepMind’s breakthrough in protein-folding A.I., Fortune, 1 December 2020
- ^ a b John Jumper et al (December 2020)
- ^ a b c d See block diagram. Also John Jumper et al. (1 December 2020), AlphaFold2 presentation, slide 10
- ^ The structure module is stated to use a "3-d equivariant transformer architecture" (John Jumper et al. (1 December 2020), AlphaFold2 presentation, slide 12). One design for a transformer network with SE(3)-equivariance was proposed in Fabian Fuchs et al SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks, NeurIPS 2020; also website. It is not known how similar this may or may not be to what was used in AlphaFold. See also the blog post by AlQuaraishi on this.
- ^ John Jumper et al. (1 December 2020), AlphaFold2 presentation, slides 12 to 20
- ^ Group performance based on combined z-scores, CASP 13, December 2018. (AlphaFold = Team 043: A7D)
- ^ a b Sample, Ian (2018年12月2日). “Google's DeepMind predicts 3D shapes of proteins”. The Guardian 2020年11月30日閲覧。
- ^ “AlphaFold: Using AI for scientific discovery”. Deepmind. 2020年11月30日閲覧。
- ^ Singh, Arunima (2020). “Deep learning 3D structures” (英語). Nature Methods 17 (3): 249. doi:10.1038/s41592-020-0779-y. ISSN 1548-7105. PMID 32132733.
- ^ See CASP 13 data tables for 043 A7D, 322 Zhang, and 089 MULTICOM
- ^ Wei Zheng et al,Deep-learning contact-map guided protein structure prediction in CASP13, Proteins: Structure, Function, and Bioinformatics, 87(12) 1149-1164 doi:10.1002/prot.25792; and slides
- ^ Jie Hou et al (2019), Protein tertiary structure modeling driven by deep learning and contact distance prediction in CASP13, Proteins: Structure, Function, and Bioinformatics, 87(12) 1165-1178 doi:10.1002/prot.25697
- ^ a b “DeepMind Breakthrough Helps to Solve How Diseases Invade Cells” (英語). Bloomberg.com. (2020年11月30日) 2020年11月30日閲覧。
- ^ “deepmind/deepmind-research” (英語). GitHub. 2020年11月30日閲覧。
- ^ “DeepMind's protein-folding AI has solved a 50-year-old grand challenge of biology” (英語). MIT Technology Review. 2020年11月30日閲覧。
- ^ For the GDT-TS measure used, each atom in the prediction scores a quarter of a point if it is within 8 Å (0.80 nm) of the experimental position; half a point if it is within 4 Å, three-quarters of a point if it is within 2 Å, and a whole point if it is within 1 Å.
- ^ To achieve a GDT-TS score of 92.5, mathematically at least 70% of the structure must be accurate to within 1 Å, and at least 85% must be accurate to within 2 Å.
- ^ a b c Andriy Kryshtafovych (30 November 2020), Experimentalists: Are models useful? CASP 14 presentation. See also CASP 14 video stream day 1 part 1, from 0:34:30
- ^ a b c John Moult (30 November 2020), CASP 14 introductory presentation, slide 19. See also CASP 14 video stream day 1 part 1, from 00:22:46
- ^ Lisa Kinch et al, CASP14 Tertiary Structure Prediction Assessment:Topology (FM) Category (CASP 14 presentation), slide 11. See also CASP 14 video stream day 1 part 3, from 0:18:25
- ^ Artificial intelligence solution to a 50-year-old science challenge could ‘revolutionise’ medical research (press release), CASP organising committee, 30 November 2020
- ^ Brigitte Nerlich, Protein folding and science communication: Between hype and humility, University of Nottingham blog, 4 December 2020
- ^ Michael Le Page, DeepMind's AI biologist can decipher secrets of the machinery of life, New Scientist, 30 November 2020
- ^ The predictions of DeepMind’s latest AI could revolutionise medicine, New Scientist, 2 December 2020
- ^ Jeremy Kahn, In a major scientific breakthrough, A.I. predicts the exact shape of proteins, Fortune, 30 November 2020
- ^ Jeremy Kahn, Lessons from DeepMind's breakthrough in protein-folding A.I., Fortune, 1 December 2020
- ^ “DeepMind is answering one of biology's biggest challenges”. The Economist. (2020年11月30日). ISSN 0013-0613 2020年11月30日閲覧。
- ^ “DeepMind Breakthrough Helps to Solve How Diseases Invade Cells” (英語). Bloomberg.com. (2020年11月30日) 2020年11月30日閲覧。
- ^ Julia Merlot, Forscher hoffen auf Durchbruch für die Medikamentenforschung (Researchers hope for a breakthrough for drug research), Der Spiegel, 2 December 2020
- ^ Bissan Al-Lazikani, The solving of a biological mystery, The Spectator, 1 December 2020
- ^ Cade Metz, London A.I. Lab Claims Breakthrough That Could Accelerate Drug Discovery, New York Times, 30 November 2020
- ^ Ian Sample,DeepMind AI cracks 50-year-old problem of protein folding, The Guardian, 30 November 2020
- ^ Lizzie Roberts, 'Once in a generation advance' as Google AI researchers crack 50-year-old biological challenge. Daily Telegraph, 30 November 2020
- ^ Nuño Dominguez, La inteligencia artificial arrasa en uno de los problemas más importantes de la biología (Artificial intelligence takes out one of the most important problems in biology), El País, 2 December 2020
- ^ Tom Whipple, "Deepmind computer solves new puzzle: life", The Times, 1 December 2020. front page image, via Twitter.
- ^ Tom Whipple, Deepmind finds biology’s ‘holy grail’ with answer to protein problem, The Times (online), 30 November 2020. In all science editor Tom Whipple wrote six articles on the subject for The Times on the day the news broke. (thread).
- ^ Callaway, Ewen (2020-11-30). “'It will change everything': DeepMind's AI makes gigantic leap in solving protein structures” (英語). Nature. doi:10.1038/d41586-020-03348-4.
- ^ Tim Hubbard, The secret of life, part 2: the solution of the protein folding problem., medium.com, 30 November 2020
- ^ “DeepMind's protein-folding AI has solved a 50-year-old grand challenge of biology” (英語). MIT Technology Review. 2020年11月30日閲覧。
- ^ “DeepMind's protein-folding AI has solved a 50-year-old grand challenge of biology” (英語). MIT Technology Review. 2020年11月30日閲覧。
- ^ “AI Can Help Scientists Find a Covid-19 Vaccine” (英語). Wired. ISSN 1059-1028 2020年12月1日閲覧。
- ^ “Computational predictions of protein structures associated with COVID-19”. Deepmind. 2020年12月1日閲覧。
- ^ “How DeepMind's new protein-folding A.I. is already helping to combat the coronavirus pandemic.” (英語). Fortune. 2020年12月1日閲覧。
[続きの解説]
「AlphaFold」の続きの解説一覧
- 1 AlphaFoldとは
- 2 AlphaFoldの概要
- 3 コンテスト
- 4 反響
- 5 応用
- 6 推薦文献
- AlphaFoldのページへのリンク
