{"doi":"10.1101/2021.03.12.435185","title":"Large-scale design and refinement of stable proteins using sequence-only models","abstract":"Abstract Engineered proteins generally must possess a stable structure in order to achieve their designed function. Stable designs, however, are astronomically rare within the space of all possible amino acid sequences. As a consequence, many designs must be tested computationally and experimentally in order to find stable ones, which is expensive in terms of time and resources. Here we report a neural network model that predicts protein stability based only on sequences of amino acids, and demonstrate its performance by evaluating the stability of almost 200,000 novel proteins. These include a wide range of sequence perturbations, providing a baseline for future work in the field. We also report a second neural network model that is able to generate novel stable proteins. Finally, we show that the predictive model can be used to substantially increase the stability of both expert-designed and model-generated proteins.","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2021,"id":214333,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":10,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.953,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2021-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":808412,"name":"Scott Novotney","orcid":null,"position":1,"is_corresponding":false},{"id":807770,"name":"Devin Strickland","orcid":"0000-0002-6468-0928","position":2,"is_corresponding":false},{"id":807771,"name":"Hugh K. Haddox","orcid":"0000-0001-8324-8324","position":3,"is_corresponding":false},{"id":808413,"name":"Nicholas Leiby","orcid":null,"position":4,"is_corresponding":false},{"id":808414,"name":"Gabriel J. Rocklin","orcid":null,"position":5,"is_corresponding":false},{"id":225386,"name":"Cameron M. Chow","orcid":"0000-0001-5351-6412","position":6,"is_corresponding":false},{"id":807772,"name":"Anindya Roy","orcid":"0000-0002-9766-4326","position":7,"is_corresponding":false},{"id":453451,"name":"Asim K. Bera","orcid":"0000-0001-9473-2912","position":8,"is_corresponding":false},{"id":287837,"name":"Francis C. Motta","orcid":"0000-0002-0364-5440","position":9,"is_corresponding":false},{"id":218557,"name":"Longxing Cao","orcid":"0000-0003-4002-3648","position":10,"is_corresponding":false},{"id":218563,"name":"Eva‐Maria Strauch","orcid":"0000-0001-7382-747X","position":11,"is_corresponding":false},{"id":615447,"name":"Tamuka M. Chidyausiku","orcid":"0000-0002-2561-782X","position":12,"is_corresponding":false},{"id":808415,"name":"Alex Ford","orcid":null,"position":13,"is_corresponding":false},{"id":391236,"name":"Ethan Ho","orcid":"0000-0002-7070-3321","position":14,"is_corresponding":false},{"id":808416,"name":"Craig O. Mackenzie","orcid":null,"position":15,"is_corresponding":false},{"id":808417,"name":"Hamed Eramian","orcid":null,"position":16,"is_corresponding":false},{"id":246362,"name":"Frank DiMaio","orcid":"0000-0002-7524-8938","position":17,"is_corresponding":false},{"id":556283,"name":"Gevorg Grigoryan","orcid":"0000-0003-4645-7666","position":18,"is_corresponding":false},{"id":34434,"name":"Matthew Vaughn","orcid":"0000-0002-1384-4283","position":19,"is_corresponding":false},{"id":218564,"name":"Lance Stewart","orcid":"0000-0003-4264-5125","position":20,"is_corresponding":false},{"id":105706,"name":"David Baker","orcid":"0000-0001-7896-6217","position":21,"is_corresponding":false},{"id":807773,"name":"Eric Klavins","orcid":"0000-0002-3805-5117","position":22,"is_corresponding":false},{"id":807769,"name":"Jedediah M. Singer","orcid":"0000-0002-5255-4473","position":0,"is_corresponding":true}],"reference_count":63,"raw_metadata":null,"created_at":"2026-07-18T23:52:46.604690Z","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":[]}