AlphaFold is an artificial intelligence system developed by DeepMind, a subsidiary of Alphabet, that predicts three-dimensional protein structures from amino acid sequences with near-experimental accuracy. First introduced in 2018 and significantly improved with AlphaFold 2 in 2020, the system achieved a breakthrough in the long-standing protein folding problem, which had remained one of biology's grand challenges for over 50 years. AlphaFold uses deep learning techniques, including attention-based neural network architectures and multiple sequence alignment analysis, to predict the spatial coordinates of every atom in a protein chain. The AlphaFold Protein Structure Database, created in partnership with the European Molecular Biology Laboratory's European Bioinformatics Institute (EMBL-EBI), provides free and open access to over 200 million predicted protein structures, covering nearly every catalogued protein known to science. This database enables researchers worldwide to access structural predictions that would have previously required years of experimental work using techniques such as X-ray crystallography, cryo-electron microscopy, or nuclear magnetic resonance spectroscopy. AlphaFold 3, released in 2024, extended the system's capabilities to predict the structures of complexes containing proteins, DNA, RNA, ligands, and other biomolecules, significantly broadening its applicability to drug discovery, molecular biology, and biochemical research. The system has been widely adopted in pharmaceutical research for understanding disease mechanisms, identifying potential drug targets, designing novel enzymes, and accelerating the early stages of drug development pipelines. AlphaFold's source code and model weights are available as open-source software under the Apache 2.0 license, and the prediction database is freely accessible to all researchers. DeepMind also provides the AlphaFold Server, a free web-based tool that allows scientists to generate predictions for protein complexes without requiring computational infrastructure.
alphafold.ebi.ac.uk →