{"doi":"10.1126/science.aba3304","title":"An evolution-based model for designing chorismate mutase enzymes","abstract":"The rational design of enzymes is an important goal for both fundamental and practical reasons. Here, we describe a process to learn the constraints for specifying proteins purely from evolutionary sequence data, design and build libraries of synthetic genes, and test them for activity in vivo using a quantitative complementation assay. For chorismate mutase, a key enzyme in the biosynthesis of aromatic amino acids, we demonstrate the design of natural-like catalytic function with substantial sequence diversity. Further optimization focuses the generative model toward function in a specific genomic context. The data show that sequence-based statistical models suffice to specify proteins and provide access to an enormous space of functional sequences. This result provides a foundation for a general process for evolution-based design of artificial proteins.","journal":"Science","year":2020,"id":48663,"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":365,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9521,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2020-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":231422,"name":"Matteo Figliuzzi","orcid":"0000-0003-1279-1711","position":1,"is_corresponding":false},{"id":231423,"name":"Christian Stocker","orcid":"0000-0002-6192-0383","position":2,"is_corresponding":false},{"id":231424,"name":"Pierre Barrat-Charlaix","orcid":"0000-0002-3816-3724","position":3,"is_corresponding":false},{"id":231425,"name":"Michael Socolich","orcid":"0000-0002-0702-1061","position":4,"is_corresponding":false},{"id":231426,"name":"Peter Kast","orcid":"0000-0002-0209-8975","position":5,"is_corresponding":false},{"id":231427,"name":"Donald Hilvert","orcid":"0000-0002-3941-621X","position":6,"is_corresponding":false},{"id":231428,"name":"Rémi Monasson","orcid":"0000-0002-4459-0204","position":7,"is_corresponding":false},{"id":231429,"name":"Simona Cocco","orcid":"0000-0002-1852-7789","position":8,"is_corresponding":false},{"id":231430,"name":"Martin Weigt","orcid":"0000-0002-0492-3684","position":9,"is_corresponding":false},{"id":231431,"name":"Rama Ranganathan","orcid":"0000-0001-5463-8956","position":10,"is_corresponding":false},{"id":231421,"name":"William P. Russ","orcid":"0000-0001-6402-1159","position":0,"is_corresponding":true}],"reference_count":57,"raw_metadata":null,"created_at":"2026-07-18T20:35:18.908826Z","pmid":"32703877","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":[]}