AlphaFold System

From GM-RKB
(Redirected from AlphaFold)
Jump to navigation Jump to search

An AlphaFold System is an AI system that is a protein folding prediction system.



References

2023a

  • (ChapGPT-OpenAI, 2023) ⇒ chat
    • Q: If AlphaFold's model is not autoregressive because it does not generate structural features sequentially. What name can we give a model that produces sequence predictions simultaneously.
    • A: A model that produces sequence predictions simultaneously, like AlphaFold, can be referred to as a "fully parallel" or "non-autoregressive" model. These models process and generate predictions for all elements in the sequence at once, rather than sequentially predicting one element at a time based on previous predictions.

      Fully parallel or non-autoregressive models offer several advantages, such as faster inference and the ability to capture complex relationships between elements in the sequence more effectively. However, they may face challenges when it comes to capturing long-range dependencies or generating coherent outputs in certain sequence prediction tasks, especially when there's a strong dependency between elements in the sequence.

      In summary, AlphaFold's model, which produces sequence predictions simultaneously, can be called a fully parallel or non-autoregressive model.

2023b

  • (Wikipedia, 2023) ⇒ https://en.wikipedia.org/wiki/AlphaFold Retrieved:2023-3-18.
    • AlphaFold is an artificial intelligence (AI) program developed by DeepMind, a subsidiary of Alphabet, which performs predictions of protein structure. The program is designed as a deep learning system.[1]

      AlphaFold AI software has had two major versions. A team of researchers that used AlphaFold 1 (2018) placed first in the overall rankings of the 13th Critical Assessment of Structure Prediction (CASP) in December 2018. The program was particularly successful at predicting the most accurate structure for targets rated as the most difficult by the competition organisers, where no existing template structures were available from proteins with a partially similar sequence.

      A team that used AlphaFold 2 (2020) repeated the placement in the CASP competition in November 2020.[2] The team achieved a level of accuracy much higher than any other group. [3] It scored above 90 for around two-thirds of the proteins in CASP's global distance test (GDT), a test that measures the degree to which a computational program predicted structure is similar to the lab experiment determined structure, with 100 being a complete match, within the distance cutoff used for calculating GDT. [4]

      AlphaFold 2's results at CASP were described as "astounding"[5] and "transformational."[6] Some researchers noted that the accuracy is not high enough for a third of its predictions, and that it does not reveal the mechanism or rules of protein folding for the protein folding problem to be considered solved.[7] Nevertheless, there has been widespread respect for the technical achievement.

      On 15 July 2021 the AlphaFold 2 paper was published at Nature as an advance access publication alongside open source software and a searchable database of species proteomes.[8]

  1. "DeepMind's protein-folding AI has solved a 50-year-old grand challenge of biology". MIT Technology Review. Retrieved 2020-11-30.
  2. Shead, Sam (2020-11-30). "DeepMind solves 50-year-old 'grand challenge' with protein folding A.I." CNBC. Retrieved 2020-11-30.
  3. Stoddart, Charlotte (1 March 2022). "Structural biology: How proteins got their close-up". Knowable Magazine. doi:10.1146/knowable-022822-1. Retrieved 25 March 2022.
  4. Robert F. Service, ‘The game has changed.’ AI triumphs at solving protein structures, Science, 30 November 2020
  5. Mohammed AlQuraishi, CASP14 scores just came out and they’re astounding, Twitter, 30 November 2020.
  6. Callaway, Ewen (2020-11-30). "'It will change everything': DeepMind's AI makes gigantic leap in solving protein structures". Nature. 588 (7837): 203–204. Bibcode:2020Natur.588..203C. doi:10.1038/d41586-020-03348-4. PMID 33257889.
  7. Stephen Curry, No, DeepMind has not solved protein folding, Reciprocal Space (blog), 2 December 2020
  8. Jumper, John; Evans, Richard; Pritzel, Alexander; Green, Tim; Figurnov, Michael; Ronneberger, Olaf; Tunyasuvunakool, Kathryn; Bates, Russ; Žídek, Augustin; Potapenko, Anna; et al. (2021-07-15). "Highly accurate protein structure prediction with AlphaFold". Nature. 596 (7873): 583–589. Bibcode:2021Natur.596..583J. doi:10.1038/s41586-021-03819-2. PMC 8371605. PMID 34265844.

2021