{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T19:46:17Z","timestamp":1793043977810,"version":"4.5.0"},"reference-count":48,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T00:00:00Z","timestamp":1792972800000},"content-version":"vor","delay-in-days":55,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100008562","name":"Nanjing Agricultural University","doi-asserted-by":"publisher","award":["106\/804001"],"award-info":[{"award-number":["106\/804001"]}],"id":[{"id":"10.13039\/501100008562","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Funds for the Foreign Experts","award":["H20251073"],"award-info":[{"award-number":["H20251073"]}]},{"name":"The National Natural Science Foundation of China","award":["62676196"],"award-info":[{"award-number":["62676196"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Designing amino acid sequences that uniquely fold into target three-dimensional conformations defines the protein inverse folding problem, a formidable bottleneck in de novo protein design. Current computational paradigms, including deep learning-based approaches, often struggle to reconcile high sequence accuracy with structural stability, computational efficiency, and generalizability across diverse protein families. Here, we present EquiDesign, a deep learning framework that surmounts these constraints via a novel multistep Equiformer-enhanced architecture. By disentangling geometric features into invariant scalars and equivariant vectors, EquiDesign preserves the intrinsic directional topology of the protein backbone during message passing. This is achieved through spatial K-nearest neighbor graph construction and geometric attention mechanisms that hierarchically fuse multiscale contextual information, yielding a physically grounded representation of protein conformations. Extensive benchmarking demonstrates that EquiDesign achieves superior sequence recovery on standard and challenging test sets compared with state-of-the-art methods. Critically, the generated sequences exhibit exceptional structural fidelity, folding stability, and sequence diversity, as validated by comprehensive controls against training-set memorization, compositional bias, and physical energy landscapes, alongside targeted diversity sampling. These results establish EquiDesign as a robust, scalable, and generalizable inverse folding solution, driven by SE(3)-equivariant encoding and multiscale geometric attention, thus propelling de novo protein design toward unprecedented structural precision.<\/jats:p>","DOI":"10.1093\/bib\/bbag581","type":"journal-article","created":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T19:30:26Z","timestamp":1793043026000},"source":"Crossref","is-referenced-by-count":0,"title":["EquiDesign: a versatile computational framework for\n                    <i>de novo<\/i>\n                    protein sequence design"],"prefix":"10.1093","volume":"27","author":[{"given":"Qiang","family":"Gao","sequence":"first","affiliation":[{"name":"College of Artificial Intelligence, Nanjing Agricultural University , No. 666 Binjiang Avenue, Nanjing, Jiangsu 211800 ,","place":["China"]},{"name":"Center for Data Science and Intelligent Computing, Nanjing Agricultural University , No. 666 Binjiang Avenue, Nanjing, Jiangsu 211800 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongyu","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nanjing Agricultural University , No. 666 Binjiang Avenue, Nanjing, Jiangsu 211800 ,","place":["China"]},{"name":"Center for Data Science and Intelligent Computing, Nanjing Agricultural University , No. 666 Binjiang Avenue, Nanjing, Jiangsu 211800 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"Research and Development-Statistics, Eli Lilly and Company , Lilly Corporate Center, Indianapolis, IN 46285 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaochen","family":"Cen","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nanjing Agricultural University , No. 666 Binjiang Avenue, Nanjing, Jiangsu 211800 ,","place":["China"]},{"name":"Center for Data Science and Intelligent Computing, Nanjing Agricultural University , No. 666 Binjiang Avenue, Nanjing, Jiangsu 211800 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of the Built Environment, College of Design and Engineering, National University of Singapore , 4 Architecture Drive, Singapore 117566 ,","place":["Singapore"]},{"name":"College of Mechanical and Vehicle Engineering, Hunan University , Changsha 410082 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Laboratory of Gastrointestinal Microbiology, College of Animal Science and Technology, Nanjing Agricultural University , No. 1 Weigang Road, Nanjing 210095 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0891-7118","authenticated-orcid":false,"given":"Zhiwei","family":"Ji","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nanjing Agricultural University , No. 666 Binjiang Avenue, Nanjing, Jiangsu 211800 ,","place":["China"]},{"name":"Center for Data Science and Intelligent Computing, Nanjing Agricultural University , No. 666 Binjiang Avenue, Nanjing, Jiangsu 211800 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,10,26]]},"reference":[{"key":"2026102615141522600_ref1","doi-asserted-by":"publisher","first-page":"3168","DOI":"10.1038\/s41467-021-23303-9","article-title":"Structure-based protein function prediction using graph convolutional networks","volume":"12","author":"Gligorijevic","year":"2021","journal-title":"Nat Commun"},{"key":"2026102615141522600_ref2","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad261","article-title":"HNSPPI: a hybrid computational model combing network and sequence information for predicting protein-protein interaction","volume":"24","author":"Xie","year":"2023","journal-title":"Brief Bioinform"},{"key":"2026102615141522600_ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijbiomac.2025.149883","article-title":"MsipNet: a multi-scale representation learning framework for predicting protein-RNA interaction","volume":"339","author":"Song","year":"2026","journal-title":"Int J Biol Macromol"},{"key":"2026102615141522600_ref4","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbae135","article-title":"Graphormer supervised de novo protein design method and function validation","volume":"25","author":"Mu","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026102615141522600_ref5","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.tibtech.2013.10.008","article-title":"Protein folding and de novo protein design for biotechnological applications","volume":"32","author":"Khoury","year":"2014","journal-title":"Trends Biotechnol"},{"key":"2026102615141522600_ref6","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/978-1-4939-6637-0_10","article-title":"Computational protein design under a given backbone structure with the ABACUS statistical energy function","volume":"1529","author":"Xiong","year":"2017","journal-title":"Methods Mol Biol"},{"key":"2026102615141522600_ref7","doi-asserted-by":"publisher","first-page":"e2017228118","DOI":"10.1073\/pnas.2017228118","article-title":"Protein sequence design by conformational landscape optimization","volume":"118","author":"Norn","year":"2021","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026102615141522600_ref8","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1038\/s41580-024-00718-y","article-title":"Opportunities and challenges in design and optimization of protein function","volume":"25","author":"Listov","year":"2024","journal-title":"Nat Rev Mol Cell Biol"},{"key":"2026102615141522600_ref9","doi-asserted-by":"publisher","first-page":"e1004889","DOI":"10.1371\/journal.pcbi.1004889","article-title":"Benchmarking inverse statistical approaches for protein structure and design with exactly solvable models","volume":"12","author":"Jacquin","year":"2016","journal-title":"PLoS Comput Biol"},{"key":"2026102615141522600_ref10","doi-asserted-by":"publisher","DOI":"10.1101\/cshperspect.a041471","article-title":"Exploring the protein sequence space with global generative models","volume":"15","author":"Romero-Romero","year":"2023","journal-title":"Cold Spring Harb Perspect Biol"},{"key":"2026102615141522600_ref11","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1038\/s44222-025-00349-8","article-title":"AI-driven protein design","volume":"3","author":"Koh","year":"2025","journal-title":"Nat Rev Bioeng"},{"key":"2026102615141522600_ref12","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1186\/1471-2105-9-487","article-title":"Use of machine learning algorithms to classify binary protein sequences as highly-designable or poorly-designable","volume":"9","author":"Peto","year":"2008","journal-title":"BMC Bioinformatics"},{"key":"2026102615141522600_ref13","doi-asserted-by":"publisher","first-page":"2565","DOI":"10.1002\/prot.24620","article-title":"Direct prediction of profiles of sequences compatible with a protein structure by neural networks with fragment-based local and energy-based nonlocal profiles","volume":"82","author":"Li","year":"2014","journal-title":"Proteins"},{"key":"2026102615141522600_ref14","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.jbiotec.2026.03.012","article-title":"Deep learning revolutionizes protein research: advances in structure prediction, functional annotation, and engineered design","volume":"414","author":"Zhang","year":"2026","journal-title":"J Biotechnol"},{"key":"2026102615141522600_ref15","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":"2026102615141522600_ref16","volume-title":"International Conference on Learning Representations (ICLR 2023)","author":"Gao","year":"2023"},{"key":"2026102615141522600_ref17","doi-asserted-by":"publisher","DOI":"10.1002\/anie.202411461","article-title":"All-atom protein sequence design based on geometric deep learning","volume":"63","author":"Liu","year":"2024","journal-title":"Angew Chem Int Ed Engl"},{"key":"2026102615141522600_ref18","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.1038\/s44320-025-00119-z","article-title":"AlphaDesign: a de novo protein design framework based on AlphaFold","volume":"21","author":"Jendrusch","year":"2025","journal-title":"Mol Syst Biol"},{"key":"2026102615141522600_ref19","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1126\/science.adq1741","article-title":"Scalable protein design using optimization in a relaxed sequence space","volume":"386","author":"Frank","year":"2024","journal-title":"Science"},{"key":"2026102615141522600_ref20","doi-asserted-by":"publisher","first-page":"bbag095","DOI":"10.1093\/bib\/bbag095","article-title":"De novo functional protein sequence generation: overcoming data scarcity through regeneration and large language models","volume":"27","author":"Ren","year":"2026","journal-title":"Brief Bioinform"},{"key":"2026102615141522600_ref21","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1186\/s12859-026-06482-4","article-title":"ProtSeqGen: a novel deep learning model for protein sequence design","volume":"27","author":"Gao","year":"2026","journal-title":"BMC Bioinformatics"},{"key":"2026102615141522600_ref22","first-page":"1","article-title":"Equiformer: equivariant graph attention transformer for 3D atomistic graphs","volume":"2023","author":"Liao","year":"2023","journal-title":"ICLR"},{"key":"2026102615141522600_ref23","doi-asserted-by":"publisher","first-page":"D348","DOI":"10.1093\/nar\/gkae1087","article-title":"CATH v4.4: major expansion of CATH by experimental and predicted structural data","volume":"53","author":"Waman","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026102615141522600_ref24","doi-asserted-by":"publisher","first-page":"bbaf156","DOI":"10.1093\/bib\/bbaf156","article-title":"ScFold: a GNN-based model for efficient inverse folding of short-chain proteins via spatial reduction","volume":"26","author":"Zhong","year":"2025","journal-title":"Brief Bioinform"},{"key":"2026102615141522600_ref25","doi-asserted-by":"publisher","first-page":"i362","DOI":"10.1093\/bioinformatics\/btaf228","article-title":"CATH-ddG: towards robust mutation effect prediction on protein-protein interactions out of CATH homologous superfamily","volume":"41","author":"Yu","year":"2025","journal-title":"Bioinformatics"},{"key":"2026102615141522600_ref26","volume-title":"Advances in Neural Information Processing Systems 32 (NeurIPS 2019)","author":"Ingraham","year":"2019"},{"key":"2026102615141522600_ref27","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1038\/s41586-023-07004-5","article-title":"Conformational ensembles of the human intrinsically disordered proteome","volume":"626","author":"Tesei","year":"2024","journal-title":"Nature"},{"key":"2026102615141522600_ref28","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1038\/s41580-023-00673-0","article-title":"The molecular basis for cellular function of intrinsically disordered protein regions","volume":"25","author":"Holehouse","year":"2024","journal-title":"Nat Rev Mol Cell Biol"},{"key":"2026102615141522600_ref29","doi-asserted-by":"publisher","first-page":"1558","DOI":"10.1002\/prot.26533","article-title":"To split or not to split: CASP15 targets and their processing into tertiary structure evaluation units","volume":"91","author":"Kryshtafovych","year":"2023","journal-title":"Proteins"},{"key":"2026102615141522600_ref30","doi-asserted-by":"publisher","first-page":"1616","DOI":"10.1002\/prot.26593","article-title":"Tertiary structure assessment at CASP15","volume":"91","author":"Simpkin","year":"2023","journal-title":"Proteins"},{"key":"2026102615141522600_ref31","first-page":"1","article-title":"ProtInvTree: deliberate protein inverse folding with reward-guided tree search","volume":"2026","author":"Liu","year":"2026","journal-title":"NeurlPS"},{"key":"2026102615141522600_ref32","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1107\/S2052252517008466","article-title":"A distance geometry-based description and validation of protein main-chain conformation","volume":"4","author":"Pereira","year":"2017","journal-title":"IUCrJ"},{"key":"2026102615141522600_ref33","doi-asserted-by":"publisher","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":"2026102615141522600_ref34","doi-asserted-by":"publisher","first-page":"1496","DOI":"10.1073\/pnas.1914677117","article-title":"Improved protein structure prediction using predicted interresidue orientations","volume":"117","author":"Yang","year":"2020","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026102615141522600_ref35","first-page":"3408","volume-title":"Proceedings of the 40th International conference on machine learning (ICML2023)","author":"Cai"},{"key":"2026102615141522600_ref36","volume-title":"The first learning on graphs conference (IoG 2022); 9-12 Dec 2022","author":"Hwang"},{"key":"2026102615141522600_ref37","volume-title":"Advances in Neural Information Processing Systems 37 (NeurIPS 2024)","author":"Kalra","year":"2024"},{"key":"2026102615141522600_ref38","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1002\/prot.25489","article-title":"SPIN2: predicting sequence profiles from protein structures using deep neural networks","volume":"86","author":"O'Connell","year":"2018","journal-title":"Proteins"},{"key":"2026102615141522600_ref39","doi-asserted-by":"publisher","first-page":"6349","DOI":"10.1038\/s41598-018-24760-x","article-title":"Computational protein design with deep learning neural networks","volume":"8","author":"Wang","year":"2018","journal-title":"Sci Rep"},{"key":"2026102615141522600_ref40","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1021\/acs.jcim.9b00438","article-title":"To improve protein sequence profile prediction through image captioning on pairwise residue distance map","volume":"60","author":"Chen","year":"2020","journal-title":"J Chem Inf Model"},{"key":"2026102615141522600_ref41","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1002\/prot.25868","article-title":"ProDCoNN: protein design using a convolutional neural network","volume":"88","author":"Zhang","year":"2020","journal-title":"Proteins"},{"key":"2026102615141522600_ref42","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1021\/acs.jcim.0c00043","article-title":"DenseCPD: improving the accuracy of neural-network-based computational protein sequence design with DenseNet","volume":"60","author":"Qi","year":"2020","journal-title":"J Chem Inf Model"},{"key":"2026102615141522600_ref43","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1011330","article-title":"SPIN-CGNN: improved fixed backbone protein design with contact map-based graph construction and contact graph neural network","volume":"19","author":"Zhang","year":"2023","journal-title":"PLoS Comput Biol"},{"key":"2026102615141522600_ref44","volume-title":"International Conference on Learning Representations (ICLR 2021)","author":"Jing","year":"2021"},{"key":"2026102615141522600_ref45","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaf666","article-title":"SurfFold: a unified model for protein inverse folding by integrating surface and structural information","volume":"42","author":"Li","year":"2026","journal-title":"Bioinformatics"},{"key":"2026102615141522600_ref46","doi-asserted-by":"publisher","first-page":"D280","DOI":"10.1093\/nar\/gky1097","article-title":"CATH: expanding the horizons of structure-based functional annotations for genome sequences","volume":"47","author":"Sillitoe","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2026102615141522600_ref47","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1038\/nbt.3988","article-title":"MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets","volume":"35","author":"Steinegger","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2026102615141522600_ref48","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":"Kempen","year":"2024","journal-title":"Nat Biotechnol"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag581\/72524138\/bbag581.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag581\/72524138\/bbag581.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T19:30:31Z","timestamp":1793043031000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag581\/9002273"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,1]]},"references-count":48,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag581","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,9,1]]},"article-number":"bbag581"}}