{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T06:15:36Z","timestamp":1788156936971,"version":"build-2803163510"},"reference-count":16,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Large Language Models (LLMs) have transformed protein engineering by capturing complex sequence patterns from large datasets, enabling applications such as structure prediction and functional annotation. Finenzyme applies conditional transfer learning to generate biologically plausible enzyme sequences conditioned on Enzyme Commission (EC) numbers.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this work, we extended Finenzyme with an in silico selection pipeline that first identifies generated sequences most likely to preserve or enhance the functional characteristics of specific EC categories and then evaluates them through molecular dynamics (MD) simulations to assess their structural stability and conformational dynamics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      MD simulations of 236 Finenzyme-generated enzymes across four EC classes (59\n                      <jats:italic>\u00b5<\/jats:italic>\n                      s total simulation time) confirmed high structural stability. Across all enzyme classes, 74-95% of the models maintained stable tertiary structures and correct folding throughout the trajectories, with 195 out of 236 structures (82.6%) exhibiting sustained stability.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>By combining conditional pre-trained language model fine-tuning with dynamic structural evaluation, our framework advances beyond static sequence-based predictions to address the structural and functional dimensions of enzyme behavior, key aspects for both biomedical and industrial applications.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1844189","type":"journal-article","created":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T05:39:50Z","timestamp":1788154790000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Protein language model-generated enzyme sequences exhibit high stability in molecular dynamics simulations"],"prefix":"10.3389","volume":"9","author":[{"given":"Enrico Mario Alessandro","family":"Fassi","sequence":"first","affiliation":[{"name":"Dipartimento di Scienze Farmaceutiche, Universit\u00e0 degli Studi di Milano","place":["Milan, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Nicolini","sequence":"additional","affiliation":[{"name":"AnacletoLab \u2013 Dipartimento di Informatica, Universit\u00e0 degli Studi di Milano","place":["Milan, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emanuele","family":"Saitto","sequence":"additional","affiliation":[{"name":"AnacletoLab \u2013 Dipartimento di Informatica, Universit\u00e0 degli Studi di Milano","place":["Milan, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giorgio","family":"Valentini","sequence":"additional","affiliation":[{"name":"AnacletoLab \u2013 Dipartimento di Informatica, Universit\u00e0 degli Studi di Milano","place":["Milan, Italy"]},{"name":"ELLIS \u2013 European Laboratory for Learning and Intelligent Systems","place":["Milan, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elena","family":"Casiraghi","sequence":"additional","affiliation":[{"name":"AnacletoLab \u2013 Dipartimento di Informatica, Universit\u00e0 degli Studi di Milano","place":["Milan, Italy"]},{"name":"ELLIS \u2013 European Laboratory for Learning and Intelligent Systems","place":["Milan, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giovanni","family":"Grazioso","sequence":"additional","affiliation":[{"name":"Dipartimento di Scienze Farmaceutiche, Universit\u00e0 degli Studi di Milano","place":["Milan, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,31]]},"reference":[{"key":"ref1","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":"ref2","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1016\/j.jmb.2005.08.032","article-title":"Crystal structures of biotin protein ligase from Pyrococcus horikoshii OT3 and its complexes: structural basis of biotin activation","volume":"353","author":"Bagautdinov","year":"2005","journal-title":"J. Mol. Biol."},{"key":"ref3","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":"ref4","doi-asserted-by":"publisher","first-page":"1463750","DOI":"10.3389\/fbinf.2024.1463750","article-title":"Molecular docking and molecular dynamic simulation studies to identify potential terpenes against Internalin a protein of Listeria monocytogenes","volume":"4","author":"K","year":"2024","journal-title":"Front. Bioinform."},{"key":"ref5","article-title":"Ctrl: a conditional transformer language model for controllable generation","author":"Keskar","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1990","DOI":"10.1021\/acschembio.9b00463","article-title":"Sulfonamide-based inhibitors of biotin protein ligase as new antibiotic leads","volume":"14","author":"Lee","year":"2019","journal-title":"ACS Chem. Biol."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1547","DOI":"10.1110\/ps.03531404","article-title":"The ternary complex of Pseudomonas aeruginosa alcohol dehydrogenase with NADH and ethylene glycol","volume":"13","author":"Levin","year":"2004","journal-title":"Protein Sci."},{"key":"ref8","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":"ref9","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":"ref10","doi-asserted-by":"publisher","first-page":"3696","DOI":"10.1021\/acs.jctc.5b00255","article-title":"ff14SB: improving the accuracy of protein side chain and backbone parameters from ff99SB","volume":"11","author":"Maier","year":"2015","journal-title":"J. Chem. Theory Comput."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.1016\/j.csbj.2025.03.037","article-title":"Fine-tuning of conditional transformers improves in silico enzyme prediction and generation","volume":"27","author":"Nicolini","year":"2025","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/0092-8674(95)90060-8","article-title":"The crystal structure of HaeIII methyltransferase convalently complexed to DNA: an extrahelical cytosine and rearranged base pairing","volume":"82","author":"Reinisch","year":"1995","journal-title":"Cell"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"2699","DOI":"10.1093\/nar\/gky092","article-title":"UniProt: the universal protein knowledgebase","volume":"46","year":"2018","journal-title":"Nucl. Acids Res."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1304099","DOI":"10.3389\/fbinf.2023.1304099","article-title":"The promises of large language models for protein design and modeling","volume":"3","author":"Valentini","year":"2023","journal-title":"Front. Bioinform."},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","first-page":"1722","DOI":"10.1038\/s41587-022-01582-x","article-title":"Biopharmaceutical benchmarks 2022","volume":"40","author":"Walsh","year":"2022","journal-title":"Nat. Biotechnol."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1844189\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T05:39:55Z","timestamp":1788154795000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1844189\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,31]]},"references-count":16,"alternative-id":["10.3389\/frai.2026.1844189"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1844189","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,31]]},"article-number":"1844189"}}