AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models

By Mihaly Varadi, S. Anyango, M. Deshpande, S. Nair, Cindy Natassia, Galabina Yordanova, D. Yuan, Oana Stroe, G. Wood, Agata Laydon and 17 more. 2021

3,102 citations recorded by the source corpus.

Abstract The AlphaFold Protein Structure Database (AlphaFold DB, https://alphafold.ebi.ac.uk) is an openly accessible, extensive database of high-accuracy protein-structure predictions. Powered by AlphaFold v2.0 of DeepMind, it has enabled an unprecedented expansion of the structural coverage of the known protein-sequence space. AlphaFold DB provides programmatic access to and interactive visualization of predicted atomic coordinates, per-residue and pairwise model-confidence estimates and predicted aligned errors. The initial release of AlphaFold DB contains over 360,000 predicted structures across 21 model-organism proteomes, which will soon be expanded to cover most of the (over 100 million) representative sequences from the UniRef90 data set.

Subfields: Materials Chemistry, Molecular Biology, Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Materials Chemistry

In Molecular Biology

In Computational Biology & Bioinformatics

Citations in the corpus

The Statistical Trends of Protein Evolution: A Lesson from AlphaFold Database (2022, methodology): “The database provides free access to over 365,000 predicted protein structures across the proteomes of 21 different species ranging from bacteria, archaea, unicellular and multicellular eukaryotes to humans, and such a database is still expanding (21).”
InterPro in 2022 (2022, neutral): “DeepMind and EMBL’s European Bioinformatics Institute (EMBL-EBI) have launched the AlphaFold Protein Structure Database (AlphaFold DB) (27), a joint project to openly and freely share millions of AlphaFold protein structure predictions with the scientific community.”
Clustering predicted structures at the scale of the known protein universe (2023, background): “(4) Structural alignment is performed in two stages: first an ungapped alignment based on shared diagonal information is performed, hits are pre-clustered and second the remaining sequences are aligned using Foldseek's structural smithwaterman .”
Dali server: structural unification of protein families (2022, neutral): “The publically available AlphaFold Database version 1 (AF-DB) covers the Uniprot reference proteomes of human and 20 other key organisms (9).”
Ensembl 2023 (2022, methodology): “Structures from AlphaFold DB (25) for 19 013 human protein-coding genes are now viewable through our new AlphaFold browser widget, accessible via the ‘AlphaFold predicted model’ link in the left-hand menu of any transcript page.”
Protein Representation Learning by Geometric Structure Pretraining (2022, methodology): “Residue Type Prediction is based on the masked language modeling objective, which has been widely used in pretraining large protein language models (Bepler & Berger, 2021).”
Intrinsic protein disorder and conditional folding in AlphaFoldDB (2022, background): “6 AlphaFold-pLDDT uses 1 - pLDDT as output.”
Prediction of multiple conformational states by combining sequence clustering with AlphaFold2 (2022, background): “The AlphaFold protein structure prediction database 43 contained 214 million predictions of single structures as of September 2022.”
SaProt: Protein Language Modeling with Structure-aware Vocabulary (2024, methodology): “Following ESM-2 and BERT, during training, 15% of the SA tokens in each batch are masked.”
FlyBase: updates to the Drosophila genes and genomes database (2024, positive): “To this end, we have added images of 3D protein structures predicted by AlphaFold (Varadi et al .”
RCSB Protein Data Bank (RCSB.org): delivery of experimentally-determined PDB structures alongside one million computed structure models of proteins from artificial intelligence/machine learning (2022, methodology): “At the time of writing, CSMs for nearly every protein sequence represented in UniProt (43) are publicly accessible from AlphaFold DB (41,44,45).”
MODOMICS: a database of RNA modifications and related information. 2023 update (2023, methodology): “Whenever available, we linked the MODOMICS entries to 3D structural predictions from the Al-phaFold database ( 25 ).”
Integrative modeling reveals the molecular architecture of the intraflagellar transport A (IFT-A) complex (2022, methodology): “AlphaFold2 has been used to create databases of proteome-wide structure predictions (70), enabling the identification of proteins with similar architectures that are dissimilar in sequence.”
SwissDock 2024: major enhancements for small-molecule docking with Attracting Cavities and AutoDock Vina (2024, methodology): “SwissDock 2024 also provides an advanced target search option in three different structural databases: PDBe ( 26 ), SWISS-MODEL ( 29 ), and the AlphaFold protein structure database ( 28 ,37 ).”
Masked Inverse Folding with Sequence Transfer for Protein Representation Learning (2023, background): “However, only training on sequences ignores the rich information contained in experimental and predicted protein structures, especially as the number of high-quality structures from AlphaFold (Jumper et al., 2021; Varadi et al., 2022) increases.”