{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:07:20Z","timestamp":1775606840916,"version":"3.50.1"},"reference-count":53,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"vor","delay-in-days":14,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["20Z103070002"],"award-info":[{"award-number":["20Z103070002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Accurate prediction of enzyme function is crucial for elucidating biological mechanisms and driving innovation across various sectors. Existing deep learning methods tend to rely solely on either sequence data or structural data and predict the Enzyme Commission (EC) number as a whole, neglecting the intrinsic hierarchical structure of EC numbers. To address these limitations, we introduce Multi-scale multi-modality Autoregressive Predictor (MAPred), a novel multi-modality and multi-scale model designed to autoregressively predict the EC number of proteins. MAPred integrates both the primary amino acid sequence and the 3D tokens of proteins, employing a dual-pathway approach to capture comprehensive protein characteristics and essential local functional sites. Additionally, MAPred utilizes an autoregressive prediction network to sequentially predict the digits of the EC number, leveraging the hierarchical organization of EC classifications. Evaluations on benchmark datasets, including New-392, Price, and New-815, demonstrate that our method outperforms existing models, marking a significant advance in the reliability and granularity of protein function prediction within bioinformatics.<\/jats:p>","DOI":"10.1093\/bib\/bbaf476","type":"journal-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T20:18:04Z","timestamp":1758313084000},"source":"Crossref","is-referenced-by-count":3,"title":["Autoregressive enzyme function prediction with multi-scale multi-modality fusion"],"prefix":"10.1093","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6623-4390","authenticated-orcid":false,"given":"Dingyi","family":"Rong","sequence":"first","affiliation":[{"name":"School of Information and Electronic Engineering, Shanghai Jiao Tong University , 800 Dongchuan Road, Minhang District, Shanghai 200240 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9363-6099","authenticated-orcid":false,"given":"Bozitao","family":"Zhong","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, The Chinese University of Hong Kong , Shatin 999077, NT, Hong Kong SAR ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenzhuo","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Information and Electronic Engineering, Shanghai Jiao Tong University , 800 Dongchuan Road, Minhang District, Shanghai 200240 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Physics and Astronomy & Institute of Natural Sciences, Shanghai Jiao Tong University , 800 Dongchuan Road, Minhang District, Shanghai 200240 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information and Electronic Engineering, Shanghai Jiao Tong University , 800 Dongchuan Road, Minhang District, Shanghai 200240 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,9,15]]},"reference":[{"key":"2025091916175647800_ref1","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1093\/nar\/28.1.304","article-title":"The enzyme database in 2000","volume":"28","author":"Bairoch","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2025091916175647800_ref2","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1080\/07352689.2011.616075","article-title":"Production of plant made pharmaceuticals: from plant host to functional protein","volume":"31","author":"Bieke Nagels","year":"2012","journal-title":"Crit Rev Plant Sci"},{"key":"2025091916175647800_ref3","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1007\/s11095-009-0045-6","article-title":"Stability of protein pharmaceuticals: an update","volume":"27","author":"Manning","year":"2010","journal-title":"Pharm Res"},{"key":"2025091916175647800_ref4","doi-asserted-by":"crossref","first-page":"882","DOI":"10.1111\/1541-4337.13094","article-title":"Precision cellular agriculture: the future role of recombinantly expressed protein as food","volume":"22","author":"Dupuis","year":"2023","journal-title":"Compr Rev Food Sci Food Saf"},{"key":"2025091916175647800_ref5","doi-asserted-by":"crossref","first-page":"102686","DOI":"10.1016\/j.copbio.2022.102686","article-title":"The role of single cell protein in cellular agriculture","volume":"75","author":"Nyyss\u00f6l\u00e4","year":"2022","journal-title":"Curr Opin Biotechnol"},{"key":"2025091916175647800_ref6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-019-1835-8","article-title":"The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens","volume":"20","author":"Zhou","year":"2019","journal-title":"Genome Biol"},{"key":"2025091916175647800_ref7","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1038\/s41586-018-0124-0","article-title":"Mutant phenotypes for thousands of bacterial genes of unknown function","volume":"557","author":"Price","year":"2018","journal-title":"Nature"},{"key":"2025091916175647800_ref8","doi-asserted-by":"crossref","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":"2025091916175647800_ref9","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1109\/TBCAS.2019.2943539","article-title":"BLASTP-ACC: parallel architecture and hardware accelerator design for BLAST-based protein sequence alignment","volume":"13","author":"Li","year":"2019","journal-title":"IEEE Trans Biomed Circuits Syst"},{"key":"2025091916175647800_ref10","doi-asserted-by":"crossref","first-page":"1678","DOI":"10.1109\/TCBB.2011.33","article-title":"CUDA-BLASTP: accelerating BLASTP on CUDA-enabled graphics hardware","volume":"8","author":"Liu","year":"2011","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2025091916175647800_ref11","doi-asserted-by":"crossref","first-page":"W20","DOI":"10.1093\/nar\/gkh435","article-title":"BLAST: at the core of a powerful and diverse set of sequence analysis tools","volume":"32","author":"McGinnis","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2025091916175647800_ref12","doi-asserted-by":"crossref","first-page":"13996","DOI":"10.1073\/pnas.1821905116","article-title":"Deep learning enables high-quality and high-throughput prediction of enzyme commission numbers","volume":"116","author":"Ryu","year":"2019","journal-title":"Proc Natl Acad Sci"},{"key":"2025091916175647800_ref13","doi-asserted-by":"crossref","first-page":"e80942","DOI":"10.7554\/eLife.80942","article-title":"Proteinfer, deep neural networks for protein functional inference","volume":"12","author":"Sanderson","year":"2023","journal-title":"Elife"},{"key":"2025091916175647800_ref14","doi-asserted-by":"crossref","first-page":"2401","DOI":"10.1093\/bioinformatics\/btaa003","article-title":"UDSMProt: universal deep sequence models for protein classification","volume":"36","author":"Strodthoff","year":"2020","journal-title":"Bioinformatics"},{"key":"2025091916175647800_ref15","doi-asserted-by":"crossref","first-page":"bbad401","DOI":"10.1093\/bib\/bbad401","article-title":"Evidential deep learning for trustworthy prediction of enzyme commission number","volume":"25","author":"Han","year":"2024","journal-title":"Brief Bioinform"},{"key":"2025091916175647800_ref16","doi-asserted-by":"crossref","first-page":"760","DOI":"10.1093\/bioinformatics\/btx680","article-title":"DEEPre: sequence-based enzyme EC number prediction by deep learning","volume":"34","author":"Li","year":"2018","journal-title":"Bioinformatics"},{"key":"2025091916175647800_ref17","doi-asserted-by":"crossref","DOI":"10.1101\/103994","article-title":"Deep recurrent neural network for protein function prediction from sequence","author":"Liu","year":"2017"},{"key":"2025091916175647800_ref18","doi-asserted-by":"crossref","first-page":"107584","DOI":"10.1016\/j.compbiolchem.2021.107584","article-title":"Deep_CNN_LSTM_GO: protein function prediction from amino-acid sequences","volume":"95","author":"Elhaj-Abdou","year":"2021","journal-title":"Comput Biol Chem"},{"key":"2025091916175647800_ref19","doi-asserted-by":"crossref","first-page":"btad620","DOI":"10.1093\/bioinformatics\/btad620","article-title":"Predicting enzymatic function of protein sequences with attention","volume":"39","author":"Buton","year":"2023","journal-title":"Bioinformatics"},{"key":"2025091916175647800_ref20","doi-asserted-by":"crossref","first-page":"7370","DOI":"10.1038\/s41467-023-43216-z","article-title":"Functional annotation of enzyme-encoding genes using deep learning with transformer layers","volume":"14","author":"Kim","year":"2023","journal-title":"Nat Commun"},{"key":"2025091916175647800_ref21","doi-asserted-by":"crossref","first-page":"1358","DOI":"10.1126\/science.adf2465","article-title":"Enzyme function prediction using contrastive learning","volume":"379","author":"Tianhao","year":"2023","journal-title":"Science"},{"key":"2025091916175647800_ref22","doi-asserted-by":"crossref","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":"2025091916175647800_ref23","doi-asserted-by":"crossref","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":"2021","journal-title":"Proc Natl Acad Sci"},{"key":"2025091916175647800_ref24","doi-asserted-by":"crossref","first-page":"bbae225","DOI":"10.1093\/bib\/bbae225","article-title":"ifDEEPre: large protein language-based deep learning enables interpretable and fast predictions of enzyme commission numbers","volume":"25","author":"Tan","year":"2024","journal-title":"Brief Bioinform"},{"key":"2025091916175647800_ref25","doi-asserted-by":"crossref","first-page":"e4750","DOI":"10.7717\/peerj.4750","article-title":"EnzyNet: enzyme classification using 3D convolutional neural networks on spatial representation","volume":"6","author":"Amidi","year":"2018","journal-title":"PeerJ"},{"key":"2025091916175647800_ref26","doi-asserted-by":"crossref","first-page":"4046","DOI":"10.1093\/bioinformatics\/bty494","article-title":"Deep convolutional networks for quality assessment of protein folds","volume":"34","author":"Derevyanko","year":"2018","journal-title":"Bioinformatics"},{"key":"2025091916175647800_ref27","doi-asserted-by":"crossref","first-page":"2845","DOI":"10.3390\/ijms20112845","article-title":"Prediction of enzyme function based on three parallel deep CNN and amino acid mutation","volume":"20","author":"Gao","year":"2019","journal-title":"Int J Mol Sci"},{"key":"2025091916175647800_ref28","article-title":"Intrinsic-extrinsic convolution and pooling for learning on 3D protein structures","volume-title":"International Conference on Learning Representations","author":"Hermosilla","year":"2021"},{"key":"2025091916175647800_ref29","article-title":"Enhancing protein language model with structure-based encoder and pre-training","volume-title":"ICLR 2023-Machine Learning for Drug Discovery Workshop","author":"Zhang","year":"2023"},{"key":"2025091916175647800_ref30","article-title":"Contrastive representation learning for 3D protein structures","author":"Hermosilla","year":"2022"},{"key":"2025091916175647800_ref31","article-title":"Protein representation learning by geometric structure pretraining","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhang","year":"2023"},{"key":"2025091916175647800_ref32","doi-asserted-by":"crossref","first-page":"3168","DOI":"10.1038\/s41467-021-23303-9","article-title":"Structure-based protein function prediction using graph convolutional networks","volume":"12","author":"Vladimir Gligorijevi\u0107","year":"2021","journal-title":"Nat Commun"},{"key":"2025091916175647800_ref33","doi-asserted-by":"crossref","first-page":"8180","DOI":"10.1038\/s41467-024-52533-w","article-title":"Accurately predicting enzyme functions through geometric graph learning on esmfold-predicted structures","volume":"15","author":"Song","year":"2024","journal-title":"Nat Commun"},{"key":"2025091916175647800_ref34","doi-asserted-by":"crossref","first-page":"bbae559","DOI":"10.1093\/bib\/bbae559","article-title":"GGN-GO: geometric graph networks for predicting protein function by multi-scale structure features","volume":"25","author":"Mi","year":"2024","journal-title":"Brief Bioinform"},{"key":"2025091916175647800_ref35","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with alphafold","volume":"596","author":"Jumper","year":"2021","journal-title":"nature"},{"key":"2025091916175647800_ref36","first-page":"500902","article-title":"Language models of protein sequences at the scale of evolution enable accurate structure prediction","volume":"2022","author":"Lin","year":"2022","journal-title":"BioRxiv"},{"key":"2025091916175647800_ref37","doi-asserted-by":"publisher","DOI":"10.1101\/2024.01.12.575459","article-title":"Enzymecage: a geometric foundation model for enzyme retrieval with evolutionary insights","author":"Liu","year":"2024","journal-title":"bioRxiv"},{"key":"2025091916175647800_ref38","doi-asserted-by":"crossref","first-page":"2737","DOI":"10.1038\/s41467-025-57324-5","article-title":"TopEC: prediction of enzyme commission classes by 3D graph neural networks and localized 3D protein descriptor","volume":"16","author":"van der Weg","year":"2025","journal-title":"Nat Commun"},{"key":"2025091916175647800_ref39","doi-asserted-by":"crossref","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":"2025091916175647800_ref40","doi-asserted-by":"crossref","DOI":"10.1093\/nargab\/lqae150","article-title":"ProstT5: bilingual language model for protein sequence and structure","volume":"6","author":"Heinzinger","year":"2024","journal-title":"NAR Genomics and Bioinformatics"},{"key":"2025091916175647800_ref41","first-page":"5075","article-title":"Hierarchical multi-label classification networks","volume-title":"Proceedings of the 35th International Conference on Machine Learning (PMLR)","author":"Wehrmann","year":"2018"},{"key":"2025091916175647800_ref42","doi-asserted-by":"crossref","first-page":"bbae365","DOI":"10.1093\/bib\/bbae365","article-title":"GloEC: a hierarchical-aware global model for predicting enzyme function","volume":"25","author":"Huang","year":"2024","journal-title":"Brief Bioinform"},{"key":"2025091916175647800_ref43","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025091916175647800_ref44","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1016\/S0959-440X(96)80057-1","article-title":"Protein sequence motifs","volume":"6","author":"Bork","year":"1996","journal-title":"Curr Opin Struct Biol"},{"key":"2025091916175647800_ref45","doi-asserted-by":"crossref","first-page":"2133","DOI":"10.1093\/bib\/bbz133","article-title":"MotifCNN-fold: protein fold recognition based on fold-specific features extracted by motif-based convolutional neural networks","volume":"21","author":"Li","year":"2020","journal-title":"Brief Bioinform"},{"key":"2025091916175647800_ref46","doi-asserted-by":"crossref","first-page":"1114","DOI":"10.1093\/bioinformatics\/btz699","article-title":"Protein\u2013protein interaction site prediction through combining local and global features with deep neural networks","volume":"36","author":"Zeng","year":"2020","journal-title":"Bioinformatics"},{"key":"2025091916175647800_ref47","doi-asserted-by":"crossref","first-page":"1892","DOI":"10.1021\/acs.jcim.3c01961","article-title":"Enhancing generalizability in protein\u2013ligand binding affinity prediction with multimodal contrastive learning","volume":"64","author":"Luo","year":"2024","journal-title":"J Chem Inf Model"},{"key":"2025091916175647800_ref48","doi-asserted-by":"crossref","first-page":"1690","DOI":"10.1038\/s42003-024-07359-z","article-title":"Improved enzyme functional annotation prediction using contrastive learning with structural inference","volume":"7","author":"Yang","year":"2024","journal-title":"Commun Biol"},{"key":"2025091916175647800_ref49","article-title":"Adam: A method for stochastic optimization","author":"Kingma"},{"key":"2025091916175647800_ref50","article-title":"SGDR: stochastic gradient descent with warm restarts","volume-title":"Proceedings of the 5th International Conference on Learning Representations (ICLR)","author":"Loshchilov"},{"key":"2025091916175647800_ref51","article-title":"Pytorch: an imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"2025091916175647800_ref52","article-title":"Continuous-discrete convolution for geometry-sequence modeling in proteins","volume-title":"The Eleventh International Conference on Learning Representations","author":"Fan","year":"2022"},{"key":"2025091916175647800_ref53","article-title":"Interpretable enzyme function prediction via residue-level detection","author":"Yang","year":"2025"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/5\/bbaf476\/64273824\/bbaf476.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/5\/bbaf476\/64273824\/bbaf476.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T20:18:11Z","timestamp":1758313091000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf476\/8254331"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":53,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,9,6]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf476","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,9]]},"published":{"date-parts":[[2025,9]]},"article-number":"bbaf476"}}