{"doi":"10.1126/science.adk8946","title":"Unsupervised evolution of protein and antibody complexes with a structure-informed language model","abstract":"<jats:p>Large language models trained on sequence information alone can learn high-level principles of protein design. However, beyond sequence, the three-dimensional structures of proteins determine their specific function, activity, and evolvability. Here, we show that a general protein language model augmented with protein structure backbone coordinates can guide evolution for diverse proteins without the need to model individual functional tasks. We also demonstrate that ESM-IF1, which was only trained on single-chain structures, can be extended to engineer protein complexes. Using this approach, we screened about 30 variants of two therapeutic clinical antibodies used to treat severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. We achieved up to 25-fold improvement in neutralization and 37-fold improvement in affinity against antibody-escaped viral variants of concern BQ.1.1 and XBB.1.5, respectively. These findings highlight the advantage of integrating structural information to identify efficient protein evolution trajectories without requiring any task-specific training data.</jats:p>","journal":"Science","year":2024,"id":638466,"datarank":0.7444266945389861,"base_score":4.962844630259907,"endowment":4.962844630259907,"self_citation_contribution":0.7444266945389861,"citation_network_contribution":0.0,"self_endowment_contribution":0.7444266945389861,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":142,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":753426,"name":"Theodora U. J. Bruun","orcid":"0000-0002-7462-2537","position":1,"is_corresponding":false},{"id":16321,"name":"Brian Hie","orcid":"0000-0003-3224-8142","position":2,"is_corresponding":false},{"id":226842,"name":"Peter S. Kim","orcid":"0000-0001-6503-4541","position":3,"is_corresponding":false},{"id":1014045,"name":"Varun R. Shanker","orcid":"0000-0003-4443-9229","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Unsupervised evolution of protein and antibody complexes with a structure-informed language model","abstract":"<jats:p>Large language models trained on sequence information alone can learn high-level principles of protein design. However, beyond sequence, the three-dimensional structures of proteins determine their specific function, activity, and evolvability. Here, we show that a general protein language model augmented with protein structure backbone coordinates can guide evolution for diverse proteins without the need to model individual functional tasks. We also demonstrate that ESM-IF1, which was only trained on single-chain structures, can be extended to engineer protein complexes. Using this approach, we screened about 30 variants of two therapeutic clinical antibodies used to treat severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. We achieved up to 25-fold improvement in neutralization and 37-fold improvement in affinity against antibody-escaped viral variants of concern BQ.1.1 and XBB.1.5, respectively. These findings highlight the advantage of integrating structural information to identify efficient protein evolution trajectories without requiring any task-specific training data.</jats:p>","is_dataset_classified":null,"base_score":0.0,"endowment":0.0,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"38963838","pmcid":"PMC11616794","openalex_id":null,"authors":[],"funders":[{"funder_name":"NIGMS NIH HHS","grant_id":"T32 GM145402","title":null},{"funder_name":"NIGMS NIH HHS","grant_id":"T32 GM007365","title":null}],"total_grants":2,"fwci":null,"citation_percentile":null,"influential_citations":0,"citation_trend":[],"oa_status":null,"license":null,"oa_locations":[{"url":"https://www.science.org/doi/pdf/10.1126/science.adk8946","host_type":"publisher"}],"fields_of_study":[],"mesh_terms":["Humans","Antibodies, Viral","Antigen-Antibody Complex","Directed Molecular Evolution","Protein Engineering","Antibody Affinity","Protein Conformation","Models, Molecular","Antibodies, Neutralizing","COVID-19","SARS-CoV-2"],"keywords":[],"sdg_mappings":[],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[{"name":"pdb"}],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-06T20:43:47.773710Z","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,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}