{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T18:00:56Z","timestamp":1781200856674,"version":"3.54.1"},"reference-count":59,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T00:00:00Z","timestamp":1781136000000},"content-version":"vor","delay-in-days":41,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The efficiency of directed protein evolution largely relies on computational methods to enrich mutants with high fitness. Traditional strategies, such as zero-shot approaches based on Protein Language Models (PLMs), primarily leverage general \u201cplausibility\u201d priors learned from natural sequences. However, in the absence of experimental feedback, their ability to guide evolution toward specific functions (\u201cspecificity\u201d) remains limited. Here, we introduce the Deep Prior Framework (DPF), a novel paradigm that integrates universal structural plausibility with task-oriented specificity priors. DPF incorporates an innovative Bernoulli-Attention (BATT) module within a Mixture of Experts architecture, enabling efficient screening of high-fitness mutants. Benchmarking on nine deep mutational scanning datasets, DPF outperforms existing methods in terms of PLM-based method. More importantly, our method also shows high performance on in silico directed evolution of Blastobotrys adeninivorans xanthine dehydrogenase (BaXD) without intermediate experimental feedback. Experimental validation of the top-ranked mutants showed an average activity enhancement of over four-fold compared with WT, with the best mutant achieving more than a nine-fold improvement. Furthermore, we applied DPF to a large-scale annotation of unreviewed sequences in UniProt Knowledgebase (UniProtKB). Of the 42\u00a0913\u00a0366 predicted samples (~21.56% of the total), 90.07% (38\u00a0934\u00a0581 proteins) were assigned high-confidence functional labels. In summary, this study demonstrates that DPF, by incorporating specificity-aware functional priors, can significantly advance efficient and targeted protein engineering.<\/jats:p>","DOI":"10.1093\/bib\/bbag279","type":"journal-article","created":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T11:53:08Z","timestamp":1778673188000},"source":"Crossref","is-referenced-by-count":0,"title":["Deep Prior Framework: integrating functional specificity with general plausibility for targeted protein evolution"],"prefix":"10.1093","volume":"27","author":[{"given":"Senxin","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Mathematics, Shanghai Normal University , No. 100 Guilin Road, Xuhui District, Shanghai 200234 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yining","family":"Qin","sequence":"additional","affiliation":[{"name":"Key Laboratory of RNA Innovation, Science and Engineering, Shanghai Academy of Natural Sciences (SANS), Shanghai Institute of Biochemistry and Cell Biology, Center for Excellence in Molecular Cell Science, Chinese Academy of Sciences, University of Chinese Academy of Sciences , No. 320 Yueyang Road, Xuhui District, Shanghai 200031 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanwen","family":"Zhu","sequence":"additional","affiliation":[{"name":"The Guangxi Key Laboratory of Intelligent Precision Medicine, 25 East Section of Gaoxin Avenue, High-tech District, Guangxi Zhuang Autonomous Region , Nanning 530007 ,","place":["China"]},{"name":"Department of Biomedical Informatics, School of Basic Medical Sciences, Peking University Health Science Center , No. 38 Xueyuan Road, Haidian District, Beijing 100191 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feilong","family":"Meng","sequence":"additional","affiliation":[{"name":"Key Laboratory of RNA Innovation, Science and Engineering, Shanghai Academy of Natural Sciences (SANS), Shanghai Institute of Biochemistry and Cell Biology, Center for Excellence in Molecular Cell Science, Chinese Academy of Sciences, University of Chinese Academy of Sciences , No. 320 Yueyang Road, Xuhui District, Shanghai 200031 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Jia","sequence":"additional","affiliation":[{"name":"Biomaterials and Stem Cell Research Laboratory, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science , No. 88 Keling Road, High-tech District, Suzhou 215011 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1832-4404","authenticated-orcid":false,"given":"Xiaoqi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Center for Single-Cell Omics, School of Public Health, Shanghai Jiao Tong University School of Medicine , No. 1 Banxia Road, Pudong District, Shanghai 201318 ,","place":["China"]},{"name":"Hainan International Medical Center, Shanghai Jiao Tong University School of Medicine , No. 1 Guangci Road, Qiongha 571400, Hainan ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,6,11]]},"reference":[{"key":"2026061113285849100_ref1","volume-title":"Evolutionary Biology","author":"Futuyma","year":"1997"},{"key":"2026061113285849100_ref2","first-page":"355","volume-title":"Jones DF (ed.) Proceedings of the VI International Congress of Genetics","author":"Wright","year":"1932"},{"key":"2026061113285849100_ref3","doi-asserted-by":"publisher","first-page":"4143","DOI":"10.1002\/anie.201708408","article-title":"Directed Evolution: Bringing New Chemistry to Life","volume":"57","author":"Arnold","year":"2018","journal-title":"Angew Chem Int Ed Engl"},{"key":"2026061113285849100_ref4","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1038\/nmeth.3027","article-title":"Deep mutational scanning: a new style of protein science","volume":"11","author":"Fowler","year":"2014","journal-title":"Nat Methods"},{"key":"2026061113285849100_ref5","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/bs.mie.2016.05.002","article-title":"Cell-binding assays for determining the affinity of protein\u2013protein interactions","volume":"580","author":"Hunter","year":"2016","journal-title":"Methods in Enzymology Academic Press"},{"key":"2026061113285849100_ref6","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":"2026061113285849100_ref7","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1016\/j.tig.2011.06.002","article-title":"The molecular origins of evolutionary innovations","volume":"27","author":"Andreas","year":"2011","journal-title":"Trends Genet"},{"key":"2026061113285849100_ref8","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1126\/science.aba3304","article-title":"An evolution-based model for designing chorismate mutase enzymes","volume":"369","author":"Russ","year":"2020","journal-title":"Science"},{"key":"2026061113285849100_ref9","doi-asserted-by":"publisher","first-page":"554","DOI":"10.1002\/(SICI)1097-0290(19980605)58:5&lt;554::AID-BIT12&gt;3.0.CO;2-B","article-title":"Directed evolution of an esterase for the stereoselective resolution of a key intermediate in the synthesis of epothilones","volume":"58","author":"Bornscheuer","year":"1998","journal-title":"Biotechnol Bioeng"},{"key":"2026061113285849100_ref10","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1016\/S0076-6879(04)88027-3","article-title":"Engineering antibody affinity by yeast surface display","volume":"388","author":"Colby","year":"2004","journal-title":"Methods Enzymol"},{"key":"2026061113285849100_ref11","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1038\/nchembio.1276","article-title":"Evolution of a designed retro-aldolase leads to complete active site remodeling","volume":"9","author":"Giger","year":"2013","journal-title":"Nat Chem Biol"},{"key":"2026061113285849100_ref12","doi-asserted-by":"publisher","first-page":"e19230","DOI":"10.1371\/journal.pone.0019230","article-title":"De novo enzyme design using Rosetta3","volume":"6","author":"Florian","year":"2011","journal-title":"PLoS One"},{"key":"2026061113285849100_ref13","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1038\/s41586-018-0830-7","article-title":"De novo design of potent and selective mimics of IL-2 and IL-15","volume":"565","author":"Silva","year":"2019","journal-title":"Nature"},{"key":"2026061113285849100_ref14","doi-asserted-by":"publisher","first-page":"3812","DOI":"10.1093\/nar\/gkg509","article-title":"SIFT: predicting amino acid changes that affect protein function","volume":"31","author":"Ng","year":"2003","journal-title":"Nucleic Acids Res"},{"key":"2026061113285849100_ref15","doi-asserted-by":"publisher","first-page":"2745","DOI":"10.1093\/bioinformatics\/btv195","article-title":"PROVEAN web server: a tool to predict the functional effect of amino acid substitutions and indels","volume":"31","author":"Choi","year":"2015","journal-title":"Bioinformatics"},{"key":"2026061113285849100_ref16","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1038\/nmeth0410-248","article-title":"A method and server for predicting damaging missense mutations","volume":"7","author":"Adzhubei","year":"2010","journal-title":"Nat Methods"},{"key":"2026061113285849100_ref17","article-title":"PANTHER version 16: a revised family classification, tree-based classification tool, enhancer regions and extensive API","volume":"49","author":"Huaiyu","journal-title":"Nucleic Acids Res"},{"key":"2026061113285849100_ref18","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1038\/s41592-018-0138-4","article-title":"Deep generative models of genetic variation capture the effects of mutations","volume":"15","author":"Riesselman","year":"2018","journal-title":"Nat Methods"},{"key":"2026061113285849100_ref19","article-title":"Amino acid difference formula to help explain protein evolution","volume-title":"Science","year":"1974"},{"key":"2026061113285849100_ref20","doi-asserted-by":"publisher","first-page":"10915","DOI":"10.1073\/pnas.89.22.10915","article-title":"Amino acid substitution matrices from protein blocks","volume":"89","author":"Henikoff","year":"1992","journal-title":"Proc Natl Acad Sci"},{"key":"2026061113285849100_ref21","doi-asserted-by":"publisher","first-page":"2692","DOI":"10.1016\/j.jmb.2014.04.026","article-title":"SuSPect: enhanced prediction of single amino acid variant (SAV) phenotype using network features","volume":"426","author":"Yates","year":"2014","journal-title":"J Mol Biol"},{"key":"2026061113285849100_ref22","doi-asserted-by":"publisher","first-page":"e68370","DOI":"10.1371\/journal.pone.0068370","article-title":"Prediction of disease causing non-Synonymous SNPs by the artificial neural network predictor NetDiseaseSNP","volume":"8","author":"Bo","year":"2013","journal-title":"PLoS One"},{"key":"2026061113285849100_ref23","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":"2026061113285849100_ref24","author":"","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"2026061113285849100_ref25","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1016\/j.cels.2021.05.017","article-title":"Learning the protein language: evolution, structure, and function","volume":"12","author":"Bepler","year":"2021","journal-title":"Cell Systems"},{"key":"2026061113285849100_ref26","doi-asserted-by":"publisher","first-page":"2102","DOI":"10.1093\/bioinformatics\/btac020","article-title":"ProteinBERT: a universal deep-learning model of protein sequence and function","volume":"38","author":"Brandes","year":"2022","journal-title":"Bioinformatics"},{"key":"2026061113285849100_ref27","doi-asserted-by":"publisher","first-page":"lqae150","DOI":"10.1093\/nargab\/lqae150","article-title":"Bilingual language model for protein sequence and structure","volume":"6","author":"Michael","year":"2024","journal-title":"NAR Genomics and Bioinformatics"},{"key":"2026061113285849100_ref28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/bib\/bbac232","article-title":"Transfer learning in proteins: evaluating novel protein learned representations for bioinformatics tasks","volume":"23","author":"Fenoy","year":"2022","journal-title":"Brief Bioinform"},{"key":"2026061113285849100_ref29","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1038\/s41592-019-0598-1","article-title":"Unified rational protein engineering with sequence-based deep representation learning","volume":"16","author":"Alley","year":"2019","journal-title":"Nat Methods"},{"key":"2026061113285849100_ref30","doi-asserted-by":"publisher","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"ProtTrans: towards cracking the language of lfe\u2019s code through self-supervised deep learning and high performance computing","volume":"44","author":"Elnaggar","year":"2022","journal-title":"IEEE transactions on pattern analysis"},{"key":"2026061113285849100_ref31","doi-asserted-by":"publisher","first-page":"968","DOI":"10.1016\/j.cels.2023.10.002","article-title":"ProGen2: exploring the boundaries of protein language models","volume":"14","author":"Nijkamp","year":"2023","journal-title":"Cell Systems"},{"key":"2026061113285849100_ref32","doi-asserted-by":"publisher","first-page":"e2016239118","DOI":"10.1073\/pnas.2016239118","article-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume":"118","author":"Rives","year":"2020","journal-title":"Proc Natl Acad Sci"},{"key":"2026061113285849100_ref33","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1126\/science.abd7331","article-title":"Learning the language of viral evolution and escape","volume":"371","author":"Hie","year":"2021","journal-title":"Science"},{"key":"2026061113285849100_ref34","doi-asserted-by":"publisher","first-page":"1257","DOI":"10.1016\/j.molcel.2024.01.021","article-title":"Protein language models-assisted optimization of a uracil-N-glycosylase variant enables programmable T-to-G and T-to-C base editing","volume":"84","author":"He","year":"2024","journal-title":"Mol Cell"},{"key":"2026061113285849100_ref35","doi-asserted-by":"publisher","first-page":"eadr6006","DOI":"10.1126\/science.adr6006","article-title":"Rapid in silico directed evolution by a protein language model with EVOLVEpro","volume":"387","author":"Jiang","year":"2025","journal-title":"Science"},{"key":"2026061113285849100_ref36","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":"2026061113285849100_ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09298-z","article-title":"Design of highly functional genome editors by modelling CRISPR\u2013Cas sequences","volume":"645","author":"","journal-title":"Nature"},{"key":"2026061113285849100_ref38","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":"2026061113285849100_ref39","doi-asserted-by":"publisher","DOI":"10.1126\/science.aad6253","article-title":"Design and synthesis of a minimal bacterial genome","volume":"351","author":"Hutchison","year":"2016","journal-title":"Science"},{"key":"2026061113285849100_ref40","author":"","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"2026061113285849100_ref41","author":"","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"2026061113285849100_ref42","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1016\/j.cell.2015.01.035","article-title":"Evolvability as a Function of Purifying Selection in TEM-1 \u03b2-Lactamase","volume":"160","author":"Stiffler","year":"2015","journal-title":"Cell"},{"key":"2026061113285849100_ref43","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.1016\/j.celrep.2016.09.061","article-title":"Phenotypic characterization of a comprehensive set of MAPK1\/ERK2 missense mutants","volume":"17","author":"Brenan","year":"2016","journal-title":"Cell Rep"},{"key":"2026061113285849100_ref44","doi-asserted-by":"publisher","first-page":"e1006114","DOI":"10.1371\/journal.ppat.1006114","article-title":"Experimental estimation of the effects of all amino-acid mutations to HIV\u2019s envelope protein on viral replication in cell culture","volume":"12","author":"Haddox","year":"2016","journal-title":"PLoS Pathog"},{"key":"2026061113285849100_ref45","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1016\/j.cels.2016.11.004","article-title":"RNA structural determinants of optimal codons revealed by MAGE-Seq","volume":"3","author":"Kelsic","year":"2016","journal-title":"Cell Systems"},{"key":"2026061113285849100_ref46","doi-asserted-by":"publisher","first-page":"155","DOI":"10.3390\/v8060155","article-title":"Accurate measurement of the effects of all amino-acid mutations on influenza hemagglutinin","volume":"8","author":"Michael","year":"2016","journal-title":"Viruses"},{"key":"2026061113285849100_ref47","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.1038\/s41588-018-0204-y","article-title":"Mutational processes shape the landscape of TP53 mutations in human cancer","volume":"50","author":"Giacomelli","year":"2018","journal-title":"Nat Genet"},{"key":"2026061113285849100_ref48","doi-asserted-by":"publisher","first-page":"E8276","DOI":"10.1073\/pnas.1806133115","article-title":"Deep mutational scanning of hemagglutinin helps predict evolutionary fates of human H3N2 influenza variants","volume":"115","author":"Lee","year":"2018","journal-title":"Proc Natl Acad Sci"},{"key":"2026061113285849100_ref49","doi-asserted-by":"publisher","first-page":"e54895","DOI":"10.7554\/eLife.54895","article-title":"Structural and functional characterization of G protein-coupled receptors with deep mutational scanning","volume":"9","author":"Jones","year":"2020","journal-title":"eLife Sciences"},{"key":"2026061113285849100_ref50","doi-asserted-by":"publisher","first-page":"e9380","DOI":"10.15252\/msb.20199380","article-title":"Using deep mutational scanning to benchmark variant effect predictors and identify disease mutations","volume":"16","author":"Livesey","year":"2020","journal-title":"Mol Syst Biol"},{"key":"2026061113285849100_ref51","doi-asserted-by":"publisher","first-page":"eabf8761","DOI":"10.1126\/science.abf8761","article-title":"Revealing enzyme functional architecture via high-throughput microfluidic enzyme kinetics","volume":"373","author":"Markin","year":"2021","journal-title":"Science"},{"key":"2026061113285849100_ref52","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1016\/j.cels.2022.01.003","article-title":"Evolutionary velocity with protein language models predicts evolutionary dynamics of diverse proteins","volume":"13","author":"Hie","year":"2022","journal-title":"Cell Systems"},{"key":"2026061113285849100_ref53","article-title":"Language models enable zero-shot prediction of the effects of mutations on protein function","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":""},{"key":"2026061113285849100_ref54","doi-asserted-by":"publisher","first-page":"D609","DOI":"10.1093\/nar\/gkae1010","article-title":"UniProt: the Universal Protein Knowledgebase in 2025","volume":"53","author":"Consortium TU","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026061113285849100_ref55","doi-asserted-by":"publisher","first-page":"D506","DOI":"10.1093\/nar\/gky1049","article-title":"UniProt: a worldwide hub of protein knowledge","volume":"47","author":"Consortium UP","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2026061113285849100_ref56","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1093\/oxfordjournals.jbchem.a002941","article-title":"Demonstration of the importance and usefulness of manipulating non-active-site residues in protein design","volume":"129","author":"Akie","year":"2001","journal-title":"J Biochem"},{"key":"2026061113285849100_ref57","doi-asserted-by":"publisher","first-page":"e2118979119","DOI":"10.1073\/pnas.2118979119","article-title":"Leveraging intrinsic flexibility to engineer enhanced enzyme catalytic activity","volume":"119","author":"Karamitros","year":"2022","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026061113285849100_ref58","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1038\/s41556-023-01342-2","article-title":"C-to-G editing generates double-strand breaks causing deletion, transversion and translocation","volume":"26","author":"Huang","year":"2024","journal-title":"Nat Cell Biol"},{"key":"2026061113285849100_ref59","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Proces Syst"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/3\/bbag279\/68514516\/bbag279.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/3\/bbag279\/68514516\/bbag279.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T17:29:11Z","timestamp":1781198951000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag279\/8706540"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":59,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag279","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,5]]},"published":{"date-parts":[[2026,5]]},"article-number":"bbag279"}}