Accurate structure prediction of biomolecular interactions with AlphaFold 3
Точное предсказание структуры биомолекулярных взаимодействий с помощью AlphaFold 3
2024-05-08
SCID: 54.1/7wt3h86c
Discuss with AI
AlphaFold 3biomolecular interaction structure predictiondiffusion-based architectureprotein–ligand interactionsprotein–nucleic acid interactions
Figures from the paper
Abstract (AI)
Abstract The introduction of AlphaFold 2 1 has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design 2–6 . Here we describe our AlphaFold 3 model with a substantially updated diffusion-based architecture that is capable of predicting the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues. The new AlphaFold model demonstrates substantially improved accuracy over many previous specialized tools: far greater accuracy for protein–ligand interactions compared with state-of-the-art docking tools, much higher accuracy for protein–nucleic acid interactions compared with nucleic-acid-specific predictors and substantially higher antibody–antigen prediction accuracy compared with AlphaFold-Multimer v.2.3 7,8 . Together, these results show that high-accuracy modelling across biomolecular space is possible within a single unified deep-learning framework.
Key Findings
1
AlphaFold 3 achieves substantially greater accuracy for protein–ligand interactions than state-of-the-art docking tools.
2
AlphaFold 3 substantially improves antibody–antigen prediction accuracy compared with AlphaFold-Multimer v.2.3.
3
AlphaFold 3 uses an substantially updated diffusion-based architecture to predict joint structures of complexes containing proteins, nucleic acids, small molecules, ions, and modified residues.
4
The model provides much higher accuracy for protein–nucleic acid interactions than nucleic-acid-specific predictors.
5
The results demonstrate that accurate modelling across diverse biomolecular interactions is possible within one unified deep-learning framework.
Research Object
Biomolecular complexes comprising proteins, nucleic acids, small molecules, ions, and modified residues
Research Subject
Accurate prediction of joint complex structures and biomolecular interactions across protein–ligand, protein–nucleic acid, and antibody–antigen systems
Publication Details
Publication Date
2024-05-08
Journal
Publisher
ISSN
Cited by
15742
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai4
Cited by20
The BCL2 family: from apoptosis mechanisms to new advances in targeted therapy2025
Scalable emulation of protein equilibrium ensembles with generative deep learning2025
Applied Artificial Intelligence in Materials Science and Material Design2025
Protein language models trained on biophysical dynamics inform mutation effects2026
Large Language Model Agent for Modular Task Execution in Drug Discovery2026
Surface immune signaling unlocks NLR activation through mRNA alternative splicing2026
A secreted endosymbiont protein essential for colonizing host cells2026
Structural Snapshots of Human tRNA Modifying Enzymes2025
Investigating the determinants of performance in machine learning for protein fitness prediction2025
Metabolite glues as a means of purine sensing and chemotherapeutic response2026
Tat-dependent bundling pilus of a halophilic archaeon assembles by a strand donation mechanism and facilitates biofilm formation2025
A viral ORFeome library for systems-level genetic dissection of host-pathogen interactions2026
Structure of the pre-initiation complex explains CMGE biogenesis2026
Linear-time prediction of proteome-scale microbial protein interactions2026
A genome-wide CRISPR screen reveals how diatoms thrive in dynamic light2026
Mapping in-cell protein contact sites reveals hijacking of paraspeckles during influenza A virus infection2026
Understanding Lignin Oxidation by a Two-Domain Multicopper Oxidase from Cellvibrio japonicus2026
Luminespib and AZ5104 are effective antithrombotic drugs via targeting the platelet Ero1α-PDI pathway2026
A teleost-specific oxygen–immunity axis where FIH activates NF-κB via competitive IκBα binding2026
Pyrodictium abyssi AbpX reveals a calcium-responsive family of microbial biomatrix proteins that form thermostable hydrogels2026