Model

alphafold-2

5 entries · November 2020 – July 2025

AlphaFold 2 is a protein-structure prediction system from DeepMind, rather than a chatbot: it predicts a protein's three-dimensional shape directly from its amino-acid sequence. At the CASP14 assessment in late 2020 it reached accuracy comparable to experimental methods for many targets, and organisers described the decades-old protein-folding problem as substantially solved; the method and source code were published in Nature in July 2021, alongside a database of predicted structures. It became a standard tool in structural biology and drug discovery, cited tens of thousands of times, and in 2024 Demis Hassabis and John Jumper shared a Nobel Prize for the work.

Appears alongside

Featured in threads

Tracks

  • Models & capabilities 3
  • Open weights & ecosystem 2
  • Culture & impact 1
  • Benchmarks & progress 1

  1. Google DeepMind marks five years of AlphaFold's impact on biology

    DeepMind said the AlphaFold Protein Structure Database, launched with over 200 million predicted structures, had been cited in more than 35,000 papers and drawn users in over 190 countries.

    Models & capabilities

  2. Hassabis and Jumper share the Nobel Prize in Chemistry

    Half the prize went to Baker for computational protein design; the other half was split between Hassabis and Jumper for AlphaFold's structure prediction.

    Culture & impact

  3. The AlphaFold Protein Structure Database opens

    The initial release covered around 350,000 predicted structures across the human proteome and twenty other organisms, with a stated plan to expand to over 100 million.

    Open weights & ecosystem

  4. AlphaFold 2 is published in Nature and open-sourced

    The method behind DeepMind's CASP14 result seven months earlier was released in full, with source code, rather than kept as a demonstrated but undisclosed system.

    Models & capabilities · Open weights & ecosystem

  5. AlphaFold 2 solves protein structure prediction at CASP14

    DeepMind's system predicted protein structures to roughly experimental accuracy, ending a fifty-year-old open problem in biology.

    Models & capabilities · Benchmarks & progress