Fast and accurate protein structure search with Foldseek
2023/05/08 by Michel van Kempen, Stephanie Kim, Charlotte Tumescheit +5 · 154 citations
Biochemistry, Genetics and Molecular Biology · #Machine Learning in Bioinformatics #Protein Structure and Dynamics #RNA and protein synthesis mechanisms
paper · pdf · doi:10.1038/s41587-023-01773-0
openalex publication_date 2023/05/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30
Abstract
As structure prediction methods are generating millions of publicly available protein structures, searching these databases is becoming a bottleneck. Foldseek aligns the structure of a query protein against a database by describing tertiary amino acid interactions within proteins as sequences over a structural alphabet. Foldseek decreases computation times by four to five orders of magnitude with 86%, 88% and 133% of the sensitivities of Dali, TM-align and CE, respectively.
Citations
Cited by
- Magnetotactic <i>Bdellovibrionota</i> from a ferruginous spring
- Ancient origin and dynamic evolution of bivalent spider toxins
- Revealing deep evolutionary relationships between RNA viruses using predicted structural models of viral RNA polymerases
- Viromics approaches for the study of viral diversity and ecology in microbiomes
- ProGen2: Exploring the boundaries of protein language models
- B-PPI: A Cross-Attention Model for Large-Scale Bacterial Protein-Protein Interaction Prediction
- Protein <i>O</i> ‐glycosylation in the Bacteroidota phylum
- Viroid-like colonists of human microbiomes
- The kinetoplastid kinetochore protein KKT23 acetyltransferase is a structural homolog of GCN5 that acetylates the histone H2A C-terminal tail
- Sla2 is a core interaction hub for Clathrin Light Chain and the Pan1/End3/Sla1 Complex
- Evolving strategies for virus discovery
- The discovery of 5mC-selective deaminases and their application to ultra-sensitive direct sequencing of methylated sites at base resolution
- Evolutionary analysis of transcription elongation factors reveals conserved and lineage-specific regulatory domains
- Isolation and characterization of broad-range Staphylococcus epidermidis sepunaviruses
- Crystal structure of methanogen MtxX (Methanogen Marker Protein MMP4) from <i>Methanothermobacter thermautotrophicus</i> ΔH
- Origin and Evolution of Very Large Extracellular Proteins in Fructophilic Lactic Acid Bacteria
- Structural and evolutionary insights into understudied bacterial serine–threonine pseudokinase families
- AlphaFold3 for Structure-guided Ligand Discovery
- Recent advances in the inference of deep viral evolutionary history
- Structural Basis of Membrane Potential Coupled Vectorial CO <sub>2</sub> Hydration by the DAB2 Complex in Chemolithoautotrophs
- FrustrAI-Seq: Scaling Local Energetic Frustration to the Protein Sequence Space
- Metabolic capacity is maintained despite shifts in microbial diversity in estuary sediments
- Cyanobacteriochrome-like GAF folds in phages revealed via AlphaFold proteomic modelling
- Learning the language of plant immunity: opportunities and challenges for AI-assisted modelling of fungal effector x host protein complexes
- Artificial intelligence-driven computational methods for antibody design and optimization
- Function and firing of the Streptomyces coelicolor contractile injection system requires the membrane protein CisA
- A new heme enzyme family forms hydrazine groups in diverse biosynthetic pathways
- Thiotemplated Polyketide Chain Fusion and Reductive Cyclization Build the Reactive Butenolide Core of Malleicyprol
- Mobile integrons encode phage defense systems
- Variant effect predictor correlation with functional assays is reflective of clinical classification performance
- Barlow Twins deep neural network for advanced 1D drug–target interaction prediction
- TM-search: An Efficient and Effective Tool for Protein Structure Database Search
- Cleavage of an engulfment peptidoglycan hydrolase by a sporulation signature protease in <i>Clostridioides difficile</i>
- Functionally comparable but evolutionarily distinct nucleotide-targeting effectors help identify conserved paradigms across diverse immune systems
- Evidence for lanthanide and PQQ dependent dehydrogenases in Eukarya
- Exploring the diversity of anti-defense systems across prokaryotes, phages and mobile genetic elements
- Sequence and structural alignments reveal insights into <scp>ANKLE2</scp> evolution and function
- Mind the gap: the challenges and opportunities for genomics-driven harnessing of plant metabolic diversity for therapeutic applications
- CsmR controls both, motility and cell shape, in Haloferax volcanii
- Pregnancy and Early-Life Gut Virome in the Lifelines NEXT cohort: Origin, Persistence, Influencing Factors and Health Implications
- Integrating glycosylation in <i>de novo</i> protein design with ReGlyco Binder Design Filter
- Repeated duplications and losses shaped SMC complex evolution from archaeal ancestors to modern eukaryotes
- DefensePredictor: A machine learning model to discover prokaryotic immune systems
- Beyond sequences: structure-guided discovery of novel protein functions in plants
- A Comparative Analysis of Receptor‐Like Kinases in <scp> <i>Chlorophyta</i> </scp> Reveals the Presence of Putative Cell Wall Integrity Sensors
- Structure of the Methanosarcina mazei Mtr complex bound to the oxygen-stress responsive small protein MtrI
- Long-read metagenomics and methylation-based binning allow the description of the emerging high-risk antibiotic resistance genes and their hidden hosts in complex communities
- Taxonomic expansion and reorganization of Flaviviridae
- The Diverse Evolutionary Histories of Domesticated Metaviral Capsid Genes in Mammals
- A family of lethal exotoxins defined by cell entry via the Attractin receptor
- A cellular entity retaining only its replicative core: Hidden archaeal lineage with an ultra-reduced genome
- Structural basis of the catalytic and allosteric mechanism of bacterial acetyltransferase PatZ
- ExplainBind: Explainable Physicochemical Determinants of Protein–Ligand Binding via Non-Covalent Interactions
- Microbial <scp>dl</scp> -Peptidases Enable Predator Defense and Facilitate Structure Elucidation of Complex Natural Products
- The Type <scp>VI</scp> Secretion System of <scp> <i>Sinorhizobium fredii</i> USDA257 </scp> Is Required for Successful Nodulation With <scp> <i>Glycine max</i> </scp> cv Pekin
- Regulation of a phage defence island by RptR, a novel repressor that controls restriction–modification systems in diverse bacteria
- Evolutionary Insights into the Length Variation of DNA Damage Response Proteins Across Eukaryotes
- ODesign: A World Model for Biomolecular Interaction Design
- Graph Identification of Proteins in Tomograms (GRIP-Tomo) 2.0: Topologically Aware Classification for Proteins
- Triangle Multiplication Is All You Need For Biomolecular Structure Representations
- Metagenomic mining reveals novel viral histones in dsDNA viruses
- AlphaFold 2, but not AlphaFold 3, predicts confident but unrealistic β-solenoid structures for repeat proteins
- Domainator, a flexible software suite for domain-based annotation and neighborhood analysis, identifies proteins involved in antiviral systems
- Flows, straight but not so fast: Exploring the design space of Rectified Flows in Protein Design
- Fast and Interpretable Protein Substructure Alignment via Optimal Transport
- ProteinAE: Protein Diffusion Autoencoders for Structure Encoding
- Higher-order assembly of a type IX retron enables exploitation for designer antimicrobials
- Tepsin and AP4 mediate transport from the trans-Golgi to the plant-like vacuole in toxoplasma
- Unveiling the functional fate of duplicated genes through expression profiling and structural analysis
- Evolutionary Profiles for Protein Fitness Prediction
- Biochemical and structural studies reveal the substrate specificity and catalytic mechanism of MYG1 as a two-metal ion-dependent 3′→5′ exonuclease
- Need for speed: advances in the era of high throughput interaction proteomics
- Functional convergence in Z-containing DNA biosynthesis highlighted by the characterization of nucleotide metabolism enzymes in bacteriophages
- Effector–host interactome map links type III secretion systems in healthy gut microbiomes to immune modulation
- A SWI/SNF-specific Ig-like domain, SWIFT, is a transcription factor binding platform
- PneumoBrowse 2: an integrated visual platform for curated genome annotation and multiomics data analysis of <i>Streptococcus pneumoniae</i>
- An Evolutionarily Conserved Laterally Acquired Toolkit Enables Microbiota Targeting by <i>Trichomonas</i>
- High-throughput prediction of protein–protein interactions uncovers hidden molecular networks in biosynthetic gene clusters
- Structural diversity of axonemes across mammalian motile cilia
- An atlas of protein homo-oligomerization across domains of life
- The crystal structure of human transport and Golgi organization 2 homolog (TANGO2) suggests a cysteine N-terminal nucleophile (Ntn) hydrolase
- High stability of the genome of <i>Akkermansia muciniphila</i> Muc <sup>T</sup> under long-term culturing conditions
- DrosGB: An integrated multi-omics database for comparative genomics and functional annotation of 35 Drosophila species
- A virus associated with the zoonotic pathogen <i>Plasmodium knowlesi</i> causing human malaria is a member of a diverse and unclassified viral taxon
- Naiavirus: an enveloped giant virus with a pleomorphic, flexible tail
- Coupling chromosome organization to genome segregation in Archaea
- Origin and Evolution of Bacterial Periplasmic Force Transducers
- Mapping the ultrastructural topology of the corynebacterial cell surface
- Mapping the ultrastructural topology of the corynebacterial cell surface
- BFVD—a large repository of predicted viral protein structures
- Rational Design Principles for <i>De Novo</i> α-Helical Peptide Barrels with Dynamic Conductive Channels
- Defense arsenal of the strict anaerobe <i>Clostridioides difficile</i> against reactive oxygen species encountered during its infection cycle
- paraCell: a novel software tool for the interactive analysis and visualization of standard and dual host–parasite single-cell RNA-seq data
- Structure and function of the EDEM:PDI ERAD checkpoint complex
- Investigating the ability of deep learning-based structure prediction to extrapolate and/or enrich the set of antibody CDR canonical forms
- Repeated co-option of HMG-box genes for sex determination in brown algae and animals
- Is Protein BLAST a thing of the past?
- Pithoviruses Are Invaded by Repeats That Contribute to Their Evolution and Divergence from Cedratviruses
- Identification of a conserved gene family with an essential role in <i>Leishmania</i> parasite–insect vector adhesion
- Discovery and characterization of a nickel enzyme family that catalyses intermolecular hydride shuttling
- The honey bee triad: a comprehensive catalogue of phages in the Apis mellifera gut microbiome
- Computing the Human Interactome
- Structural and Transcriptional Diversity in the Repertoire of <i>Sclerotinia sclerotiorum</i> Effector Candidates
- Computational enzyme design by catalytic motif scaffolding
- Water mass specific genes dominate the Southern Ocean microbiome
- The molecular architecture of the Arabidopsis callose synthase complex
- Origin and Evolution of Key Enzymes in the Anammox Pathway Revisited
- Definition and Discovery of Tandem SH3-Binding Motifs Interacting with Members of the p47phox-Related Protein Family
- Protein design drives synthetic biology research of plant natural products
- Squidly: Enzyme Catalytic Residue Prediction Harnessing a Biology-Informed Contrastive Learning Framework
- An RGAE Homolog in <i>Fusarium graminearum</i> Is Critical for Initial Infection in Wheat and Barley
- From Binding to Catalysis: Emergence of a Rudimentary Enzyme Conferring Intrinsic Antibiotic Resistance
- Potent efficacy of an IgG-specific endoglycosidase against IgG-mediated pathologies
- Cooperative reading of DECA-CCAAT composite element by the TALE/NF-Y/Sp2 transcription factors
- RNA-triggered Cas12a3 cleaves tRNA tails to execute bacterial immunity
- PLM-interact: extending protein language models to predict protein-protein interactions
- Mriyaviruses: small relatives of giant viruses
- Understanding the substrate recognition and catalytic mechanism of 2-O-methyl fucosidases from glycoside hydrolase family 139
- EZpred: improving deep learning-based enzyme function prediction using unlabeled sequence homologs
- SSAlign: Ultrafast and Sensitive Protein Structure Search at Scale
- Adaptative and ancient co-evolution of integrons with <i>Xanthomonas</i> genomes
- Adaptive Laboratory Evolution Unlocks Membrane Permeability as a Key Limitation in Long‐Chain Alcohol Metabolism by <scp> <i>Pseudomonas putida</i> KT2440 </scp>
- AlphaFold2 and ESMFold: A large-scale pairwise model comparison of human enzymes upon Pfam functional annotation
- Activity-based protein profiling reveals both canonical and novel ubiquitin pathway enzymes in Plasmodium
- Comparative transcriptomics in ferns reveals key innovations and divergent evolution of the secondary cell walls
- Complexity of the lichen symbiosis revealed by metagenome and transcriptome analysis of Xanthoria parietina
- Structural characterization of the ACDC domain from ApiAP2 proteins, a potential molecular target against apicomplexan parasites
- Enhancing predictions of protein stability changes induced by single mutations using MSA-based language models
- Computational design of serine hydrolases
- Molecular Display of the Animal Meta-Venome for Discovery of Novel Therapeutic Peptides
- Reactions of SleC, Its Structure and Inhibition in Mitigation of Spore Germination in <i>Clostridioides difficile</i>
- A Perspective on the Prospective Use of AI in Protein Structure Prediction
- Contextual protein and antibody encodings from equivariant graph transformers
- Heterologous expression of a fully active <i>Azotobacter vinelandii</i> nitrogenase Fe protein in <i>Escherichia coli</i>
- Understanding language model scaling for protein fitness prediction
- Explosive cytotoxicity of ruptoblasts bridges hormone surveillance and immune defense
- EMERALD-UI: an interactive web application to unveil novel protein biology hidden in the alternative alignment space
- Decoding the Grammar of Protein-Protein Interaction Interfaces with Multimodal Representations
- Tools For Building Artificial Biological Nanostructures
- The Synthetic Epitope Atlas: High-Throughput Design and Validation of <i>De Novo</i> Antibody-Antigen Complexes
- Screening metatranscriptomes for ultrastable RNA secondary structures reveals hidden bacteriophages and novel capsid nanomaterials
- Structure-guided discovery of ancestral CRISPR-Cas13 ribonucleases
- SHREC 2025: Protein surface shape retrieval including electrostatic potential
- Tokenizing Loops of Antibodies
- Topotein: Topological Deep Learning for Protein Representation Learning
- SafeProtein: Red-Teaming Framework and Benchmark for Protein Foundation Models
- DomainFit: Identification of protein domains in cryo-EM maps at intermediate resolution using AlphaFold2-predicted models
- Energy-Based Flow Matching for Generating 3D Molecular Structure
- Highlights of Model Quality Assessment in <scp>CASP16</scp>
- Genomic analysis of <i>Ostreococcus tauri</i> -infecting viruses reveals a hypervariable region associated with host–virus interactions
- Functional annotation of novel heat stress-responsive genes in rice utilizing public transcriptomes and structurome
- Multiple protein structure alignment at scale with FoldMason
- The Blobulator: A Toolkit for Identification and Visual Exploration of Hydrophobic Modularity in Protein Sequences
- Latent-X: An Atom-level Frontier Model for De Novo Protein Binder Design
Related