AlphaFold 3

Extracted Attributes

• Type

  Artificial Intelligence (AI) program

• Function

  Predicts the structure of complexes containing proteins, DNA, RNA, ligands, and ions

• Developer

  Google DeepMind

• Predecessor

  AlphaFold 2

• Availability

  AlphaFold Server (free for non-commercial research)

• Co-developer

  Isomorphic Labs

• Announcement Date

  2024-05-08

• Commercialization

  Isomorphic Labs

• Core Architecture

  Pairformer

• Refinement Method

  Diffusion model

• Accuracy Improvement (general)

  Minimum 50% increase for protein interactions with other molecules compared to existing methods

• Accuracy Improvement (specific)

  Effectively doubled for certain key categories of interactions

Timeline

• AlphaFold 1 placed first in the 13th Critical Assessment of Structure Prediction (CASP) competition. (Source: Wikipedia)

  2018-12

• AlphaFold 2 placed first in the CASP14 competition, achieving significantly higher accuracy than other entries. (Source: Wikipedia)

  2020-11

• The AlphaFold 2 paper was published in Nature, alongside open-source software and a searchable database of species proteomes. (Source: Wikipedia)

  2021-07-15

• Demis Hassabis and John Jumper received the Breakthrough Prize in Life Sciences and the Albert Lasker Award for Basic Medical Research for their leadership of the AlphaFold project. (Source: Summary, Wikipedia)

  2023

• AlphaFold 3 was announced, capable of predicting the structure of complexes involving proteins, DNA, RNA, ligands, and ions. (Source: Summary, Wikipedia, Web Search)

  2024-05-08

• Demis Hassabis and John Jumper shared one half of the Nobel Prize in Chemistry for protein structure prediction. (Source: Summary, Wikipedia)

  2024

AlphaFold

AlphaFold is an artificial intelligence (AI) program developed by DeepMind, a subsidiary of Alphabet, which performs predictions of protein structure. It is designed using deep learning techniques. AlphaFold 1 (2018) placed first in the overall rankings of the 13th Critical Assessment of Structure Prediction (CASP) in December 2018. It was particularly successful at predicting the most accurate structures for targets rated as most difficult by the competition organizers, where no existing template structures were available from proteins with partially similar sequences. AlphaFold 2 (2020) repeated this placement in the CASP14 competition in November 2020. It achieved a level of accuracy much higher than any other entry. It scored above 90 on CASP's global distance test (GDT) for approximately two-thirds of the proteins, a test measuring the similarity between a computationally predicted structure and the experimentally determined structure, where 100 represents a complete match. The inclusion of metagenomic data has improved the quality of the prediction of MSAs. One of the biggest sources of the training data was the custom-built Big Fantastic Database (BFD) of 65,983,866 protein families, represented as MSAs and hidden Markov models (HMMs), covering 2,204,359,010 protein sequences from reference databases, metagenomes, and metatranscriptomes. AlphaFold 2's results at CASP14 were described as "astounding" and "transformational". However, some researchers noted that the accuracy was insufficient for a third of its predictions, and that it did not reveal the underlying mechanism or rules of protein folding for the protein folding problem, which remains unsolved. Despite this, the technical achievement was widely recognized. On 15 July 2021, the AlphaFold 2 paper was published in Nature as an advance access publication alongside open source software and a searchable database of species proteomes. As of February 2025, the paper had been cited nearly 35,000 times. AlphaFold 3 was announced on 8 May 2024. It can predict the structure of complexes created by proteins with DNA, RNA, various ligands, and ions. The new prediction method shows a minimum 50% improvement in accuracy for protein interactions with other molecules compared to existing methods. Moreover, for certain key categories of interactions, the prediction accuracy has effectively doubled. Demis Hassabis and John Jumper of Google DeepMind shared one half of the 2024 Nobel Prize in Chemistry, awarded "for protein structure prediction," while the other half went to David Baker "for computational protein design." Hassabis and Jumper had previously won the Breakthrough Prize in Life Sciences and the Albert Lasker Award for Basic Medical Research in 2023 for their leadership of the AlphaFold project.

Web Search Results

• Accurate structure prediction of biomolecular interactions ... - Nature

  Here we present AlphaFold 3 (AF3)—a model that is capable of high-accuracy prediction of complexes containing nearly all molecular types present in the Protein Data Bank32.") (PDB) (Fig. 1a,b). In all but one category, it achieves a substantially higher performance than strong methods that specialize in just the given task (Fig. 1c and Extended Data Table 1), including higher accuracy at protein structure and the structure of protein–protein interactions. [...] While expanding in modelling abilities, AF3 has also improved in protein complex accuracy relative to AlphaFold-Multimer (v.2.3)7."),8."). Generally, protein–protein prediction success (DockQ > 0.23)40.") has increased (paired Wilcoxon signed-rank test, P = 1.8 × 10−18), with antibody–protein interaction prediction in particular showing a marked improvement (Fig. 1c (right); paired Wilcoxon signed-rank test, P = 6.5 × 10−5, predictions top-ranked from 1,000 rather than the typical 5 seeds;

• AlphaFold - Wikipedia

  Announced on 8 May 2024, AlphaFold 3 was co-developed by Google DeepMind and Isomorphic Labs, both subsidiaries of Alphabet. AlphaFold 3 is not limited to single-chain proteins, as it can also predict the structures of protein complexes with DNA, RNA, post-translational modifications and selected ligands and ions.( [...] AlphaFold 3 was announced on 8 May 2024. It can predict the structure of complexes created by proteins with DNA, RNA, various ligands "Ligand (biochemistry)"), and ions.( The new prediction method shows a minimum 50% improvement in accuracy for protein interactions with other molecules compared to existing methods. Moreover, for certain key categories of interactions, the prediction accuracy has effectively doubled.( [...] AlphaFold 3 introduces the "Pairformer," a deep learning architecture inspired by the transformer, which is considered similar to, but simpler than, the Evoformer used in AlphaFold 2.( The Pairformer module's initial predictions are refined by a diffusion model. This model begins with a cloud of atoms and iteratively refines their positions, guided by the Pairformer's output, to generate a 3D representation of the molecular structure.(

• AlphaFold 3 predicts the structure and interactions of all of life's ...

  Introducing AlphaFold 3, a new AI model developed by Google DeepMind and Isomorphic Labs. By accurately predicting the structure of proteins, DNA, RNA, ligands and more, and how they interact, we hope it will transform our understanding of the biological world and drug discovery. G Google DeepMind AlphaFold team I Isomorphic Labs Share TwitterFacebookLinkedInMail Copy link Image 1: Colorful protein structure against an abstract gradient background. In this story In this story [...] Google DeepMind’s newly launched AlphaFold Server is the most accurate tool in the world for predicting how proteins interact with other molecules throughout the cell. It is a free platform that scientists around the world can use for non-commercial research. With just a few clicks, biologists can harness the power of AlphaFold 3 to model structures composed of proteins, DNA, RNA and a selection of ligands, ions and chemical modifications. [...] AlphaFold 3 achieves unprecedented accuracy in predicting drug-like interactions, including the binding of proteins with ligands and antibodies with their target proteins. AlphaFold 3 is 50% more accurate than the best traditional methods on the PoseBusters benchmark without needing the input of any structural information, making AlphaFold 3 the first AI system to surpass physics-based tools for biomolecular structure prediction. The ability to predict antibody-protein binding is critical to

• AlphaFold gets an upgrade (and a Nobel) | Nature Medicine

  AlphaFold, the artificial intelligence tool developed by Google DeepMind to predict protein structure, marked a watershed moment in protein modeling and drug discovery. AlphaFold 2 is able to predict the three-dimensional structure of proteins with very high accuracy — close to that obtained experimentally, which takes months to years. The latest iteration, AlphaFold 3 (released in May), goes a step further, achieving greater accuracy than its predecessor, along with expanded functionality. [...] AlphaFold 3 can predict the structure of not only proteins but also complexes that contain proteins and other structures, such as nucleic acids and small molecules. Indeed, the authors expect that modeling capabilities will continue to improve, due to advances in both deep learning and experimental approaches. In recognition of the importance of these advances, half of the Nobel Prize for chemistry has been awarded to John Jumper and Demis Hassabis, who led the development of AlphaFold (with

• AlphaFold Server

  Introducing AlphaFold 3, an AI model developed by Google DeepMind and Isomorphic Labs. By accurately predicting the structure of proteins, DNA, RNA, ligands and more, and how they interact, we expect it to transform our understanding of the biological world and drug discovery. arrow_forward ### Technology Accelerating research in nearly every field of biology [...] What is different about the new AlphaFold3 model compared to AlphaFold2? link expand_more AlphaFold3 can predict many biomolecules in addition to proteins. AlphaFold2 predicts structures of proteins and protein-protein complexes. AlphaFold3 can generate predictions containing proteins, DNA, RNA, ions,ligands, and chemical modifications . The new model also improves the protein complex modelling accuracy Please refer to our paper for more information on performance improvements. [...] AlphaFold Server is a web-service that offers customized biomolecular structure prediction. It makes several newer AlphaFold3 capabilities available, including support for a wider range of molecule types (DNA, RNA, ions, ligands, chemical modifications). The service is free for non-commercial use and requires a simple sign up involving accepting non-commercial use terms. How can I increase the diversity of my predictions? link expand_more