{"doi":"10.1126/science.ade2574","title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","abstract":"Recent advances in machine learning have leveraged evolutionary information in multiple sequence alignments to predict protein structure. We demonstrate direct inference of full atomic-level protein structure from primary sequence using a large language model. As language models of protein sequences are scaled up to 15 billion parameters, an atomic-resolution picture of protein structure emerges in the learned representations. This results in an order-of-magnitude acceleration of high-resolution structure prediction, which enables large-scale structural characterization of metagenomic proteins. We apply this capability to construct the ESM Metagenomic Atlas by predicting structures for >617 million metagenomic protein sequences, including >225 million that are predicted with high confidence, which gives a view into the vast breadth and diversity of natural proteins.","journal":"Science","year":2023,"id":1294,"datarank":12.189425962954886,"base_score":8.43511508038063,"endowment":8.43511508038063,"self_citation_contribution":1.2652672620570946,"citation_network_contribution":10.924158700897792,"self_endowment_contribution":1.2652672620570946,"citer_contribution":10.924158700897792,"corpus_percentile":82.9,"corpus_rank":2364,"citation_count":4605,"citer_count":196,"citers_with_citation_signal":196,"citers_with_endowment":196,"datacite_reuse_total":0,"is_dataset":false,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2023-03-17","authors":[{"id":16319,"name":"Halil Akin","orcid":"0000-0003-1666-3223","position":1,"is_corresponding":false},{"id":16320,"name":"Roshan Rao","orcid":"0000-0003-4412-3742","position":2,"is_corresponding":false},{"id":16321,"name":"Brian Hie","orcid":"0000-0003-3224-8142","position":3,"is_corresponding":false},{"id":16322,"name":"Zhongkai Zhu","orcid":"0000-0002-2721-1508","position":4,"is_corresponding":false},{"id":16323,"name":"Wenting Lu","orcid":null,"position":5,"is_corresponding":false},{"id":16324,"name":"Nikita Smetanin","orcid":null,"position":6,"is_corresponding":false},{"id":16325,"name":"Robert Verkuil","orcid":"0000-0001-9533-7623","position":7,"is_corresponding":false},{"id":16326,"name":"Ori Kabeli","orcid":"0000-0002-4153-2463","position":8,"is_corresponding":false},{"id":16327,"name":"Yaniv Shmueli","orcid":"0000-0002-3581-2485","position":9,"is_corresponding":false},{"id":16328,"name":"Allan dos Santos Costa","orcid":"0000-0001-8061-339X","position":10,"is_corresponding":false},{"id":16329,"name":"Maryam Fazel-Zarandi","orcid":null,"position":11,"is_corresponding":false},{"id":16330,"name":"Tom Sercu","orcid":"0000-0003-2947-6064","position":12,"is_corresponding":false},{"id":16331,"name":"Salvatore Candido","orcid":"0000-0002-5847-0617","position":13,"is_corresponding":false},{"id":16332,"name":"Alexander Rives","orcid":"0000-0003-2208-0796","position":14,"is_corresponding":false},{"id":16318,"name":"Zeming Lin","orcid":"0000-0002-0883-1373","position":0,"is_corresponding":true}],"reference_count":74,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-03-01T18:20:47.508186Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}