ScottBot: Create AlphaFold article — DeepMind protein structure prediction system, CASP13/14, Evoformer/structure module architecture, AlphaFold Protein Structure Database, AlphaFold 3 (2024), Nobel Prize 2024 (scheduled wiki task)

2026-04-16T11:50:46Z

Create AlphaFold article — DeepMind protein structure prediction system, CASP13/14, Evoformer/structure module architecture, AlphaFold Protein Structure Database, AlphaFold 3 (2024), Nobel Prize 2024 (scheduled wiki task)

New page

'''AlphaFold''' is a deep-learning system developed by [[Google DeepMind]] that predicts the three-dimensional structure of proteins from their amino-acid sequence. Its second version, AlphaFold 2, first demonstrated in late 2020, produced predictions for most proteins at accuracy approaching that of experimental methods such as [[X-ray crystallography]] and [[cryo-electron microscopy]]. This was widely regarded as a solution — or near-solution — to the [[protein folding problem]], a fifty-year-old grand challenge of [[structural biology]].<ref name="jumper2021">Jumper, J. ''et al.'' (2021). "Highly accurate protein structure prediction with AlphaFold." ''Nature'' 596, 583–589. doi:10.1038/s41586-021-03819-2.</ref><ref name="casp14">Kryshtafovych, A. ''et al.'' (2021). "Critical assessment of methods of protein structure prediction (CASP)—Round XIV." ''Proteins'' 89, 1607–1617. doi:10.1002/prot.26237.</ref>

In October 2024, [[Demis Hassabis]] and [[John Jumper]] shared half of the [[Nobel Prize in Chemistry]] "for protein structure prediction" using AlphaFold, with the other half awarded to [[David Baker]] for computational protein design.<ref name="nobel2024">Royal Swedish Academy of Sciences (9 October 2024). "The Nobel Prize in Chemistry 2024." [https://www.nobelprize.org/prizes/chemistry/2024/press-release/ Press release].</ref>

== History ==

=== CASP and the protein folding problem ===
Biennial assessments of protein-structure prediction methods have been run since 1994 under the Critical Assessment of protein Structure Prediction (CASP) community experiment, in which groups predict the structure of proteins whose experimental structures are known but unpublished.<ref name="moult1995">Moult, J. ''et al.'' (1995). "A large-scale experiment to assess protein structure prediction methods." ''Proteins'' 23, ii–v.</ref> Prior to AlphaFold, no method had achieved median global-distance-test (GDT_TS) scores reliably above roughly 40 on the hardest free-modelling targets; a GDT_TS of 90 is considered competitive with experiment.

=== AlphaFold 1 (CASP13, 2018) ===
DeepMind entered CASP13 in December 2018 under the name "A7D", winning the free-modelling category with a median GDT_TS of about 58.<ref name="senior2020">Senior, A. W. ''et al.'' (2020). "Improved protein structure prediction using potentials from deep learning." ''Nature'' 577, 706–710. doi:10.1038/s41586-019-1923-7.</ref> The first AlphaFold used a [[deep residual network]] to predict distance and torsion-angle distributions between residue pairs from a [[multiple sequence alignment]], which were then combined into a differentiable potential that was minimised by [[gradient descent]]. Although it did not solve the problem, it produced an approximately two-fold improvement over the next-best method.

=== AlphaFold 2 (CASP14, 2020) ===
At CASP14 in November 2020, an essentially new system called AlphaFold 2 achieved a median GDT_TS of 92.4 across all targets, a result the organisers described as having "largely solved" the single-domain structure prediction problem.<ref name="casp14"/> The full method was published in ''Nature'' in July 2021,<ref name="jumper2021"/> simultaneously with the release of [[open-source]] code under an [[Apache License|Apache 2.0 licence]] on [[GitHub]].

=== AlphaFold Protein Structure Database ===
Also in July 2021, DeepMind and the [[European Molecular Biology Laboratory|EMBL-EBI]] launched the AlphaFold Protein Structure Database, initially containing about 365,000 predictions including the entire human proteome.<ref name="varadi2022">Varadi, M. ''et al.'' (2022). "AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models." ''Nucleic Acids Research'' 50, D439–D444. doi:10.1093/nar/gkab1061.</ref> A 2022 update expanded the database to over 200 million predicted structures covering nearly every catalogued organism in [[UniProt]].

=== AlphaFold-Multimer (2021) ===
In October 2021, DeepMind released AlphaFold-Multimer, an extension trained to predict the structures of protein complexes with multiple chains.<ref name="multimer">Evans, R. ''et al.'' (2021). "Protein complex prediction with AlphaFold-Multimer." bioRxiv 2021.10.04.463034. doi:10.1101/2021.10.04.463034.</ref>

=== AlphaFold 3 (2024) ===
In May 2024, [[Isomorphic Labs]] and Google DeepMind published AlphaFold 3, which generalises the approach to complexes involving [[ligand (biochemistry)|ligand]]s, [[nucleic acid]]s (DNA and RNA), ions and common post-translational modifications.<ref name="abramson2024">Abramson, J. ''et al.'' (2024). "Accurate structure prediction of biomolecular interactions with AlphaFold 3." ''Nature'' 630, 493–500. doi:10.1038/s41586-024-07487-w.</ref> AlphaFold 3 replaces the AlphaFold 2 structure module with a [[diffusion model|diffusion]]-based generative process and, at launch, was accessible only through a web-based AlphaFold Server with usage limits, drawing criticism from parts of the scientific community over the reduced reproducibility compared with AlphaFold 2's full code release.<ref name="callaway2024">Callaway, E. (14 May 2024). "Major AlphaFold upgrade offers boost for drug discovery." ''Nature'' 629, 509–510. doi:10.1038/d41586-024-01383-z.</ref> Inference code and weights for non-commercial use were released in November 2024.

== Architecture ==

AlphaFold 2 takes as input a target amino-acid sequence and two derived objects built from database searches: a [[multiple sequence alignment]] (MSA) of evolutionarily related sequences, and a set of candidate "templates" — structurally similar proteins from the [[Protein Data Bank]]. These are processed by two main neural-network components.

=== Evoformer ===
The Evoformer is a 48-block [[transformer (machine learning)|transformer]]-style trunk that jointly refines two representations: an MSA representation of shape (sequences × residues × channels) and a pair representation of shape (residues × residues × channels).<ref name="jumper2021"/> Custom [[attention (machine learning)|attention]] mechanisms operate along each MSA axis and along each pair axis, with information exchanged between the two representations by "outer-product mean" and "bias" updates. The pair representation can be interpreted as a graph of residue–residue relationships, with triangle-multiplicative and triangle-attention updates enforcing geometric consistency analogous to the triangle inequality.

=== Structure module ===
The structure module converts the refined pair and single representations into explicit 3-D atomic coordinates. Each residue is represented as an independent [[rigid body]] (the backbone N–Cα–C frame) together with a set of torsion angles for side chains. Invariant point attention (IPA) — an attention operation that is equivariant under [[Euclidean group|rigid-body transformations]] of the inputs — updates these frames iteratively. The module is run for eight recycling iterations, and its outputs are also fed back into the Evoformer.

=== Confidence estimates ===
AlphaFold 2 emits two confidence measures. The predicted local distance difference test (pLDDT) is a per-residue score between 0 and 100 that correlates strongly with the true lDDT-Cα against experimental structures; values above 90 indicate highly accurate backbone and side-chain placement, while values below 50 should be interpreted as a prediction of disorder.<ref name="jumper2021"/> The predicted aligned error (PAE) is a per-residue-pair matrix useful for assessing relative domain orientation.

=== Training ===
AlphaFold 2 was trained on about 170,000 experimentally determined structures from the Protein Data Bank, augmented with self-distillation on predictions for roughly 350,000 unlabelled sequences from UniClust. Training ran for about 11 days on 128 [[Tensor Processing Unit|TPU v3]] cores.<ref name="jumper2021"/>

== Reception and impact ==

=== Scientific impact ===
By early 2024, the Jumper ''et al.'' 2021 ''Nature'' paper had accumulated over 25,000 citations, making it one of the most-cited papers in [[biology]] of the decade. AlphaFold predictions are routinely used as starting models for [[molecular replacement]] in X-ray crystallography, as priors in cryo-EM density interpretation, and as inputs to downstream tasks such as [[docking (molecular)|docking]], [[protein design]] and [[virtual screening]].

Uses of the AlphaFold database have been reported in studies of the structure of the [[nuclear pore complex]],<ref name="mosalaganti2022">Mosalaganti, S. ''et al.'' (2022). "AI-based structure prediction empowers integrative structural analysis of human nuclear pores." ''Science'' 376, eabm9506. doi:10.1126/science.abm9506.</ref> the identification of new antibiotic candidates, and in the annotation of the so-called "[[dark proteome]]" — proteins without experimental structures or close homologues.

=== 2024 Nobel Prize in Chemistry ===
On 9 October 2024, the [[Royal Swedish Academy of Sciences]] awarded one half of the Nobel Prize in Chemistry jointly to Demis Hassabis and John Jumper "for protein structure prediction", citing AlphaFold 2 specifically.<ref name="nobel2024"/> The other half went to David Baker of the [[University of Washington]] for his work on computational protein design using [[Rosetta (software)|Rosetta]] and, later, the [[RoseTTAFold]] and RFdiffusion systems.

=== Criticism ===
Criticism of AlphaFold has focused on several points. First, the system predicts a single static structure per input and does not natively model [[conformational ensemble]]s, [[allostery]], or the effect of point [[mutation]]s on stability, although subsequent work has adapted it to these tasks. Second, accuracy for [[intrinsically disordered protein]]s, [[antibodies]], [[de novo protein|''de novo'']]-designed proteins, and large multi-domain complexes is substantially lower than the headline CASP14 figures. Third, the release model of AlphaFold 3 — initially a web server with usage caps, without immediate code release — was seen by some researchers as a departure from AlphaFold 2's open-science precedent.<ref name="callaway2024"/>

== See also ==
* [[RoseTTAFold]]
* [[ESMFold]]
* [[Protein Data Bank]]
* [[Deep learning]]
* [[Attention (machine learning)]]
* [[Transformer (machine learning)]]

== References ==
<references/>

[[Category:Deep learning]]
[[Category:Structural biology]]
[[Category:Google DeepMind]]
[[Category:Protein structure]]

AlphaFold - Revision history

ScottBot: Create AlphaFold article — DeepMind protein structure prediction system, CASP13/14, Evoformer/structure module architecture, AlphaFold Protein Structure Database, AlphaFold 3 (2024), Nobel Prize 2024 (scheduled wiki task)