Data coverage
The ESM Atlas is a large-scale public dataset of computational outputs generated by ESMC and ESMFold2, derived from a deduplicated set of over 6.8 billion publicly available protein sequences spanning all domains of life — including viral proteins and previously unannotated sequences representing metagenomic dark matter sampled from a wide range of biomes. The dataset includes two primary components. A sparse autoencoder (SAE) features for ~6.8 billion proteins, capturing interpretable biological representations from the ESMC 6B model, and predicted three-dimensional protein structures for ~1.1 billion proteins generated using ESMFold2. Proteins are organized into 7.7 million clusters based on SAE feature similarity, enabling functional grouping across the protein universe. The dataset is accessible via AWS CLI. A companion data explorer is available at https://biohub.ai/esmc/atlas.
Access & permitted use
Review the publisher’s documentation for availability, eligibility and permitted uses, including commercial analysis, model training and redistribution.
Atlas License Information Atlas Data Unless otherwise noted below under “Datasets Incorporating Third-Party Data,” data in the Atlas is compiled and made available by Chan Zuckerberg Biohub, Inc. under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This permits use, distribution, and adaptation of the data for any purpose, provided that appropriate attribution is given. A copy of the license is available at https://creativecommons.org/licenses/by/4.0/. Datasets Incorporating Third-Party Data The “Sequences” and “All Data” datasets include data from third-party sources in addition to data generated by Biohub. These specific datasets are compiled and made available by Chan Zuckerberg Biohub, Inc. and are provided under the Creative Commons Attribution Share Alike 4.0 International (CC BY SA 4.0) license. A copy of the license is available at https://creativecommons.org/licenses/by-sa/4.0/. These datasets include data from the following sources: | Data Set | Source | License | | --- | --- | --- | | UniRef | uniprot.org/uniref | CC BY 4.0 | | UniProt Archive (UniParc) | ftp.uniprot.org/pub/databases/uniprot/uniparc/ | CC BY 4.0 | | MGnify (202205) | ftp.ebi.ac.uk/pub/databases/metagenomics/peptidedatabase/202205/ | CC0 1.0 | | MGnify (202404) | ftp.ebi.ac.uk/pub/databases/metagenomics/peptidedatabase/202404/ | CC0 1.0 | | UHGG | ftp.ebi.ac.uk/pub/databases/metagenomics/mgnifygenomes/human-gut/ | EMBL-EBI Terms of Use | | SPIRE | spire.embl.de | CC BY-SA 4.0 | | Joint Genome Institute IMGM Dataset | img.jgi.doe.gov | JGI custom license | | JGI IMG/M NR | genome.jgi.doe.gov/portal/IMGNR/ | JGI custom license | | JGI IMG/VR | genome.jgi.doe.gov/portal/IMGVR/ | JGI custom license | | JGI IMG UMAG (Prok) | genome.jgi.doe.gov/portal/IMG-UMAG/ | JGI custom license | | JGI IMG UMAG (Euk) | genome.jgi.doe.gov/portal/IMG-UMAG/ | JGI custom license | | Protein Data Bank (PDB) | files.wwpdb.org/pub/pdb/data/assemblies/mmCIF/ | CC0 1.0 | | AlphaFold Protein Structure Database | alphafold.ebi.ac.uk | CC BY 4.0 |
Need help sourcing data?
Tell us your required fields, population, geography and time period. We can review suitable sources and licensing options.
Request sourcing help