{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T20:06:54Z","timestamp":1789762014212,"version":"4.0.1"},"reference-count":55,"publisher":"American Chemical Society (ACS)","issue":"9","license":[{"start":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T00:00:00Z","timestamp":1786320000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T00:00:00Z","timestamp":1786320000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T00:00:00Z","timestamp":1786320000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Traditional protein design is fundamentally constrained by known sequences and folds. To break free from these limitations, we introduce a new alternative: designing proteins directly from plain-language specifications. To achieve this, we trained MP4, a transformer-based model that maps natural language prompts to protein sequences, on a dataset of 3.2 billion points and 138k tokens. In a benchmark of 96 prompts representing a wide array of functions and contexts, MP4 excelled by simultaneously improving on three key metrics: sequence realism, predicted fold quality, and alignment to the requested function. This high performance is particularly significant as it was achieved using only text as input which is a major departure from other models. Experimental validation confirmed our computational predictions: two de novo designs were experimentally shown to be both expressible and thermostable, with high-resolution crystallography (1.30 \u00c5 and 1.77 \u00c5) ultimately revealing one to possess a paradigm-shifting novel fold. Functionally, the designs were also active, demonstrating both ATP binding and hydrolysis in vitro. This work demonstrates the realization of natural-language intent as functional proteins that express, crystallize, and catalyze. Although the underlying approach is still in early development with incomplete coverage and controllability, MP4 delivers a profound impact: it lowers the barrier to protein design and vastly expands the space for creative exploration in molecular programming.<\/jats:p>","DOI":"10.1021\/acssynbio.6c00246","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T14:02:46Z","timestamp":1786629766000},"page":"3645-3652","source":"Crossref","is-referenced-by-count":0,"title":["An Artificial Intelligence Model for Translating Natural Language into Functional De Novo Proteins"],"prefix":"10.1021","volume":"15","author":[{"given":"Timothy P.","family":"Riley","sequence":"first","affiliation":[{"name":"310 AI , , ,","place":["San Francisco, California, United States, 94107"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3416-739X","authenticated-orcid":true,"given":"Mohammad S.","family":"Parsa","sequence":"additional","affiliation":[{"name":"University of California, Berkeley , , ,","place":["Berkeley, California, United States, 94720-7000"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pourya","family":"Kalantari","sequence":"additional","affiliation":[{"name":"310 AI , , ,","place":["San Francisco, California, United States, 94107"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ismail","family":"Naderi","sequence":"additional","affiliation":[{"name":"310 AI , , ,","place":["San Francisco, California, United States, 94107"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kiana","family":"Azimian","sequence":"additional","affiliation":[{"name":"310 AI , , ,","place":["San Francisco, California, United States, 94107"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nemya","family":"Begloo","sequence":"additional","affiliation":[{"name":"310 AI , , ,","place":["San Francisco, California, United States, 94107"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oleg","family":"Matusovsky","sequence":"additional","affiliation":[{"name":"McGill University , , ,","place":["Montreal, Quebec, Canada, H3A 0G4"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eliot","family":"Osher","sequence":"additional","affiliation":[{"name":"Arctoris , ,","place":["Oxford, U.K., OX14 4SA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Devika","family":"Prabhakaran","sequence":"additional","affiliation":[{"name":"Arctoris , ,","place":["Oxford, U.K., OX14 4SA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rahul","family":"Yadav","sequence":"additional","affiliation":[{"name":"Arctoris , ,","place":["Oxford, U.K., OX14 4SA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Klem","family":"Simelis","sequence":"additional","affiliation":[{"name":"Arctoris , ,","place":["Oxford, U.K., OX14 4SA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Indran","family":"Mathavan","sequence":"additional","affiliation":[{"name":"Arctoris , ,","place":["Oxford, U.K., OX14 4SA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeeven","family":"Singh","sequence":"additional","affiliation":[{"name":"Arctoris , ,","place":["Oxford, U.K., OX14 4SA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kooshiar","family":"Azimian","sequence":"additional","affiliation":[{"name":"310 AI , , ,","place":["San Francisco, California, United States, 94107"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8794-1385","authenticated-orcid":true,"given":"Kathy Y.","family":"Wei","sequence":"additional","affiliation":[{"name":"310 AI , , ,","place":["San Francisco, California, United States, 94107"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,10]]},"reference":[{"key":"2026091815073208500_cit1","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1126\/science.add2187","article-title":"Robust deep learning-based protein sequence design using ProteinMPNN","volume":"378","author":"Dauparas","year":"2022","journal-title":"Science"},{"key":"2026091815073208500_cit2","doi-asserted-by":"publisher","first-page":"2024.09.30.615802","DOI":"10.1101\/2024.09.30.615802","article-title":"BindCraft: one-shot design of functional protein binders","author":"Pacesa","year":"2024","journal-title":"BioRxiv"},{"key":"2026091815073208500_cit3","doi-asserted-by":"publisher","first-page":"arXiv:2409.08022","DOI":"10.48550\/arXiv.2409.08022","article-title":"De novo design of high-affinity protein binders with AlphaProteo","author":"Zambaldi","year":"2024","journal-title":"arXiv"},{"key":"2026091815073208500_cit4","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.1038\/s41586-023-06415-8","article-title":"De novo design of protein structure and function with RFdiffusion","volume":"620","author":"Watson","year":"2023","journal-title":"Nature"},{"key":"2026091815073208500_cit5","doi-asserted-by":"publisher","first-page":"1070","DOI":"10.1038\/s41586-023-06728-8","article-title":"Illuminating protein space with a programmable generative model","volume":"623","author":"Ingraham","year":"2023","journal-title":"Nature"},{"key":"2026091815073208500_cit6","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1038\/s41587-023-01763-2","article-title":"Efficient evolution of human antibodies from general protein language models","volume":"42","author":"Hie","year":"2024","journal-title":"Nat. Biotechnol."},{"key":"2026091815073208500_cit7","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1016\/B978-0-12-381270-4.00019-6","article-title":"ROSETTA3: an object-oriented software suite for the simulation and design of macromolecules","volume":"487","author":"Leaver-Fay","year":"2011","journal-title":"Methods Enzymol."},{"key":"2026091815073208500_cit8","doi-asserted-by":"publisher","first-page":"979","DOI":"10.1016\/j.cels.2023.10.001","article-title":"IgLM: Infilling language modeling for antibody sequence design","volume":"14","author":"Shuai","year":"2023","journal-title":"Cell Syst."},{"key":"2026091815073208500_cit9","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1126\/science.ads0018","article-title":"Simulating 500 million years of evolution with a language model","volume":"387","author":"Hayes","year":"2025","journal-title":"Science"},{"key":"2026091815073208500_cit10","doi-asserted-by":"publisher","first-page":"2024.08.01.606258","DOI":"10.1101\/2024.08.01.606258","article-title":"Toward De Novo Protein Design from Natural Language","author":"Dai","year":"2024","journal-title":"BioRxiv"},{"key":"2026091815073208500_cit11","doi-asserted-by":"publisher","first-page":"1099","DOI":"10.1038\/s41587-022-01618-2","article-title":"Large language models generate functional protein sequences across diverse families","volume":"41","author":"Madani","year":"2023","journal-title":"Nat. Biotechnol."},{"key":"2026091815073208500_cit12","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1038\/s42256-025-01011-z","article-title":"A text-guided protein design framework","volume":"7","author":"Liu","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"2026091815073208500_cit13","doi-asserted-by":"publisher","first-page":"arXiv:2506.09332","DOI":"10.48550\/arXiv.2506.09332","article-title":"InstructPro: Natural Language Guided Ligand-Binding Protein Design","author":"Song","year":"2025","journal-title":"arXiv"},{"key":"2026091815073208500_cit14","doi-asserted-by":"publisher","first-page":"arXiv:2402.17810","DOI":"10.48550\/arXiv.2402.17810","article-title":"BioT5+: Towards generalized biological understanding with IUPAC integration and multi-task tuning","author":"Pei","year":"2024","journal-title":"arXiv"},{"key":"2026091815073208500_cit15","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1038\/s42256-022-00499-z","article-title":"Controllable protein design with language models","volume":"4","author":"Ferruz","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"2026091815073208500_cit16","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1038\/s41551-025-01463-z","article-title":"CRISPR-GPT for agentic automation of gene-editing experiments","volume":"10","author":"Qu","year":"2025","journal-title":"Nat. Biomed. Eng."},{"key":"2026091815073208500_cit17","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1038\/s41586-023-06792-0","article-title":"Autonomous chemical research with large language models","volume":"624","author":"Boiko","year":"2023","journal-title":"Nature"},{"key":"2026091815073208500_cit18","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"2026091815073208500_cit19","doi-asserted-by":"publisher","first-page":"D247","DOI":"10.1093\/nar\/gkj149","article-title":"Pfam: clans, web tools and services","volume":"34","author":"Finn","year":"2005","journal-title":"Nucleic Acids Res."},{"key":"2026091815073208500_cit20","doi-asserted-by":"publisher","first-page":"D523","DOI":"10.1093\/nar\/gkae997","article-title":"The Pfam protein families database: embracing AI\/ML","volume":"53","author":"Paysan-Lafosse","year":"2025","journal-title":"Nucleic Acids Res."},{"key":"2026091815073208500_cit21","doi-asserted-by":"publisher","first-page":"arXiv:2303.08774","DOI":"10.48550\/arXiv.2303.08774","article-title":"GPT-4 Technical Report","author":"Achiam","year":"2023","journal-title":"arXiv"},{"key":"2026091815073208500_cit22","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1038\/75556","article-title":"Gene ontology: tool for the unification of biology. The Gene Ontology Consortium","volume":"25","author":"Ashburner","year":"2000","journal-title":"Nat. Genet."},{"key":"2026091815073208500_cit23","doi-asserted-by":"publisher","first-page":"D565","DOI":"10.1093\/nar\/gkr1048","article-title":"The UniProt-GO annotation database in 2011","volume":"40","author":"Dimmer","year":"2012","journal-title":"Nucleic Acids Res."},{"key":"2026091815073208500_cit24","doi-asserted-by":"publisher","first-page":"D444","DOI":"10.1093\/nar\/gkae1082","article-title":"InterPro: the protein sequence classification resource in 2025","volume":"53","author":"Blum","year":"2025","journal-title":"Nucleic Acids Res."},{"key":"2026091815073208500_cit25","doi-asserted-by":"publisher","first-page":"D609","DOI":"10.1093\/nar\/gkae1010","article-title":"UniProt: The universal protein knowledgebase in 2025","volume":"53","author":"Bateman","year":"2025","journal-title":"Nucleic Acids Res."},{"key":"2026091815073208500_cit26","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/s0022-2836(05)80360-2","article-title":"Basic local alignment search tool","volume":"215","author":"Altschul","year":"1990","journal-title":"J. Mol. Biol."},{"key":"2026091815073208500_cit27","doi-asserted-by":"publisher","first-page":"D20","DOI":"10.1093\/nar\/gkae979","article-title":"Database resources of the National Center for Biotechnology Information in 2025","volume":"53","author":"Sayers","year":"2025","journal-title":"Nucleic Acids Res."},{"key":"2026091815073208500_cit28","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"key":"2026091815073208500_cit29","unstructured":"Gane, A.; Bileschi, M. L.; Dohan, D.; Speretta, E.; He\u0301liou, A.; Meng-Papaxanthos, L.; Zellner, H.; Brevdo, E.; Parikh, A.; Martin, M. J.; Orchard, S.; Colwell, L. J.\n          ProtNLM: Model-based natural language protein annotation. 6\/11\/24. https:\/\/storage.googleapis.com\/brain-genomics-public\/research\/proteins\/protnlm\/uniprot_2022_04\/protnlm_preprint_draft.pdf."},{"key":"2026091815073208500_cit30","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1093\/bioinformatics\/btu031","article-title":"InterProScan 5: genome-scale protein function classification","volume":"30","author":"Jones","year":"2014","journal-title":"Bioinformatics"},{"key":"2026091815073208500_cit31","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1038\/nmeth932","article-title":"In vivo and in vitro protein solubility assays using split GFP","volume":"3","author":"Cabantous","year":"2006","journal-title":"Nat. Methods"},{"key":"2026091815073208500_cit32","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1002\/bip.360310111","article-title":"Study of the \u201cmolten globule\u201d intermediate state in protein folding by a hydrophobic fluorescent probe","volume":"31","author":"Semisotnov","year":"1991","journal-title":"Biopolymers"},{"key":"2026091815073208500_cit33","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1111\/febs.14696","article-title":"nanoDSF as screening tool for enzyme libraries and biotechnology development","volume":"286","author":"Magnusson","year":"2019","journal-title":"FEBS J."},{"key":"2026091815073208500_cit34","doi-asserted-by":"crossref","DOI":"10.1002\/9780470027318.a9092","article-title":"Dynamic light scattering for protein characterization","volume-title":"Encyclopedia of Analytical Chemistry","author":"Schmidt","year":"2010"},{"key":"2026091815073208500_cit35","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1038\/nature19946","article-title":"The coming of age of de novo protein design","volume":"537","author":"Huang","year":"2016","journal-title":"Nature"},{"key":"2026091815073208500_cit36","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1016\/j.cell.2023.12.028","article-title":"De novo protein design-From new structures to programmable functions","volume":"187","author":"Kortemme","year":"2024","journal-title":"Cell"},{"key":"2026091815073208500_cit37","doi-asserted-by":"publisher","first-page":"D29","DOI":"10.1093\/nar\/gkac1032","article-title":"Database resources of the National Center for Biotechnology Information in 2023","volume":"51","author":"Sayers","year":"2023","journal-title":"Nucleic Acids Res."},{"key":"2026091815073208500_cit38","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.omto.2021.08.015","article-title":"Defueling the cancer: ATP synthase as an emerging target in cancer therapy","volume":"23","author":"Wang","year":"2021","journal-title":"Mol. Ther. Oncolytics"},{"key":"2026091815073208500_cit39","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1124\/pharmrev.121.000528","article-title":"ATP and adenosine metabolism in cancer: Exploitation for therapeutic gain","volume":"74","author":"Yegutkin","year":"2022","journal-title":"Pharmacol. Rev."},{"key":"2026091815073208500_cit40","doi-asserted-by":"publisher","first-page":"2650","DOI":"10.1038\/s41598-018-37072-x","article-title":"Isothermal Analysis of ThermoFluor Data can readily provide Quantitative Binding Affinities","volume":"9","author":"Bai","year":"2019","journal-title":"Sci. Rep."},{"key":"2026091815073208500_cit41","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/0003-9861(75)90373-2","article-title":"Action of the adenosine triphosphate analog, adenylyl imidodiphosphate in mitochondria","volume":"166","author":"Melnick","year":"1975","journal-title":"Arch. Biochem. Biophys."},{"key":"2026091815073208500_cit42","doi-asserted-by":"publisher","first-page":"arXiv:2210.01776","DOI":"10.48550\/arXiv.2210.01776","article-title":"DiffDock: Diffusion steps, twists, and turns for molecular docking","author":"Corso","year":"2022","journal-title":"arXiv"},{"key":"2026091815073208500_cit43","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1038\/s41587-023-01773-0","article-title":"Fast and accurate protein structure search with Foldseek","volume":"42","author":"van Kempen","year":"2024","journal-title":"Nat. Biotechnol."},{"key":"2026091815073208500_cit44","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1089\/adt.2009.0230","article-title":"Comparison of bioluminescent kinase assays using substrate depletion and product formation","volume":"7","author":"Tanega","year":"2009","journal-title":"Assay Drug Dev. Technol."},{"key":"2026091815073208500_cit45","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1089\/adt.2009.0222","article-title":"ADP-Glo: A Bioluminescent and homogeneous ADP monitoring assay for kinases","volume":"7","author":"Zegzouti","year":"2009","journal-title":"Assay Drug Dev. Technol."},{"key":"2026091815073208500_cit46","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1038\/s41586-022-04599-z","article-title":"Machine learning-aided engineering of hydrolases for PET depolymerization","volume":"604","author":"Lu","year":"2022","journal-title":"Nature"},{"key":"2026091815073208500_cit47","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1038\/s42256-021-00310-5","article-title":"Expanding functional protein sequence spaces using generative adversarial networks","volume":"3","author":"Repecka","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"2026091815073208500_cit48","doi-asserted-by":"publisher","DOI":"10.1126\/science.adu2454","article-title":"Computational design of serine hydrolases","volume":"388","author":"Lauko","year":"2025","journal-title":"Science"},{"key":"2026091815073208500_cit49","doi-asserted-by":"publisher","first-page":"arXiv:2205.11487","DOI":"10.48550\/arXiv.2205.11487","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"arXiv"},{"key":"2026091815073208500_cit50","doi-asserted-by":"publisher","first-page":"arXiv:2203.02155","DOI":"10.48550\/arXiv.2203.02155","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"arXiv"},{"key":"2026091815073208500_cit51","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1107\/s0021889807021206","article-title":"Phaser crystallographic software","volume":"40","author":"McCoy","year":"2007","journal-title":"J. Appl. Crystallogr."},{"key":"2026091815073208500_cit52","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Accurate structure prediction of biomolecular interactions with AlphaFold 3","volume":"630","author":"Abramson","year":"2024","journal-title":"Nature"},{"key":"2026091815073208500_cit53","doi-asserted-by":"publisher","first-page":"2126","DOI":"10.1107\/s0907444904019158","article-title":"Coot: model-building tools for molecular graphics","volume":"60","author":"Emsley","year":"2004","journal-title":"Acta Crystallogr., Sect. D:Biol. Crystallogr."},{"key":"2026091815073208500_cit54","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1107\/s0907444996012255","article-title":"Refinement of macromolecular structures by the maximum-likelihood method","volume":"53","author":"Murshudov","year":"1997","journal-title":"Acta Crystallogr., Sect. D:Biol. Crystallogr."},{"key":"2026091815073208500_cit55","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1107\/S0907444909042073","article-title":"MolProbity: all-atom structure validation for macromolecular crystallography","volume":"66","author":"Chen","year":"2010","journal-title":"Acta Crystallogr., Sect. D:Biol. Crystallogr."}],"container-title":["ACS Synthetic Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acssynbio.6c00246","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/asbcd6\/article-pdf\/15\/9\/3645\/66527066\/sb6c00246.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/asbcd6\/article-pdf\/15\/9\/3645\/66527066\/sb6c00246.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T19:22:36Z","timestamp":1789759356000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/asbcd6\/article\/15\/9\/3645\/5254330\/An-Artificial-Intelligence-Model-for-Translating"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,10]]},"references-count":55,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,8,10]]},"published-print":{"date-parts":[[2026,9,18]]}},"URL":"https:\/\/doi.org\/10.1021\/acssynbio.6c00246","relation":{},"ISSN":["2161-5063"],"issn-type":[{"value":"2161-5063","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,10]]}}}