{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T17:05:49Z","timestamp":1781715949164,"version":"3.54.5"},"reference-count":59,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T00:00:00Z","timestamp":1760400000000},"content-version":"vor","delay-in-days":44,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Shandong Provincial Key Research and Development Program","award":["2024TSGC0226"],"award-info":[{"award-number":["2024TSGC0226"]}]},{"DOI":"10.13039\/501100004195","name":"Ocean University of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004195","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Designing high-affinity molecules for certain proteins is a fundamental and challenging problem for drug discovery, particularly when considering atomic interactions between molecules and proteins in 3D space. Current 3D molecular design methods are limited because they do not adequately capture the ligand molecular position information in Euclidean space. We proposed a diffusion model based on SE(3)-equivariant graph neural networks to enhance generated molecular binding affinity to protein targets using the long-range and distance-aware attention head mix. We also presented a molecular geometry feature enhancement strategy, further strengthening the perception of the spatial size of ligand molecules. Results show that, on the CrossDocked2020 dataset, our model outperforms the existing state-of-the-art models across various affinity-related metrics, including the Vina Score, and preserves essential drug-like properties. Our model excels in designing ligand molecules with macrocyclic structures. Additionally, it offers a moderate level of interpretability, aiding in understanding the binding interactions between 3D drug molecules and protein pockets.<\/jats:p>","DOI":"10.1093\/bib\/bbaf542","type":"journal-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T18:30:09Z","timestamp":1760553009000},"source":"Crossref","is-referenced-by-count":3,"title":["Designing high-affinity 3D drug molecules via geometric spatial perception diffusion model"],"prefix":"10.1093","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6553-6205","authenticated-orcid":false,"given":"Hao","family":"Lu","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Ocean University of China , Songling Road, 266100 Shandong Province ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Wei","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Ocean University of China , Songling Road, 266100 Shandong Province ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaming","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Ocean University of China , Songling Road, 266100 Shandong Province ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangrui","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Ocean University of China , Songling Road, 266100 Shandong Province ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Ocean University of China , Songling Road, 266100 Shandong Province ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Ocean University of China , Songling Road, 266100 Shandong Province ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,10,14]]},"reference":[{"key":"2025101514300410500_ref1","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Accurate structure prediction of biomolecular interactions with AlphaFold3","volume":"630","author":"Abramson","year":"2024","journal-title":"Nature"},{"key":"2025101514300410500_ref2","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":"2025101514300410500_ref3","volume-title":"nobel prize in chemistry campaign","author":"Springer Nature"},{"key":"2025101514300410500_ref4","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1038\/s41551-021-00689-x","article-title":"Accelerated antimicrobial discovery via deep generative models and molecular dynamics simulations","volume":"5","author":"Das","year":"2021","journal-title":"Nat Biomed Eng"},{"key":"2025101514300410500_ref5","doi-asserted-by":"publisher","first-page":"6891","DOI":"10.1038\/s41467-022-34692-w","article-title":"Generative deep learning enables the discovery of a potent and selective RIPK1 inhibitor","volume":"13","author":"Li","year":"2022","journal-title":"Nat Commun"},{"key":"2025101514300410500_ref6","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1038\/s42256-022-00448-w","article-title":"Design of potent antimalarials with generative chemistry","volume":"4","author":"Godinez","year":"2022","journal-title":"Nat Mach Intell"},{"key":"2025101514300410500_ref7","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1038\/s41587-024-02143-0","article-title":"A small-molecule TNIK inhibitor targets fibrosis in preclinical and clinical models","volume":"43","author":"Ren","year":"2025","journal-title":"Nat Biotechnol"},{"key":"2025101514300410500_ref8","doi-asserted-by":"crossref","article-title":"Diffusion models in de novo drug design","author":"Alakhdar","DOI":"10.1021\/acs.jcim.4c01107"},{"key":"2025101514300410500_ref9","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1038\/s44222-023-00114-9","article-title":"Diffusion models in bioinformatics and computational biology","volume":"2","author":"Guo","year":"2023","journal-title":"Nat Rev Bioeng"},{"key":"2025101514300410500_ref10","doi-asserted-by":"publisher","first-page":"2779","DOI":"10.1016\/j.csbj.2024.06.021","article-title":"Structure-based protein and small molecule generation using EGNN and diffusion models: a comprehensive review","volume":"23","author":"Soleymani","year":"2024","journal-title":"Comput Struct Biotechnol J"},{"key":"2025101514300410500_ref11","doi-asserted-by":"crossref","article-title":"Diffusion models: a comprehensive survey of methods and applications","author":"Yang","DOI":"10.1145\/3626235"},{"key":"2025101514300410500_ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems (NeurIPS)","author":"Ho","year":"2020"},{"key":"2025101514300410500_ref13","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)","author":"Nichol","year":"2021"},{"key":"2025101514300410500_ref14","doi-asserted-by":"publisher","first-page":"103730","DOI":"10.1016\/j.drudis.2023.103730","article-title":"Advancements in small molecule drug design: a structural perspective","volume":"28","author":"Wu","year":"2023","journal-title":"Drug Discov Today"},{"key":"2025101514300410500_ref15","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1038\/s41586-023-05905-z","article-title":"Computational approaches streamlining drug discovery","volume":"616","author":"Sadybekov","year":"2023","journal-title":"Nature"},{"key":"2025101514300410500_ref16","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1635","article-title":"Generative models for molecular discovery: recent advances and challenges","volume":"13","author":"Bilodeau","year":"2022","journal-title":"Wiley Interdiscip Rev Comput Mol Sci"},{"key":"2025101514300410500_ref17","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1038\/s43588-023-00530-2","article-title":"Learning on topological surface and geometric structure for 3D molecular generation","volume":"3","author":"Zhang","year":"2023","journal-title":"Nat Comput Sci"},{"key":"2025101514300410500_ref18","doi-asserted-by":"publisher","first-page":"10127","DOI":"10.1038\/s41467-024-54456-y","article-title":"ClickGen: directed exploration of synthesizable chemical space via modular reactions and reinforcement learning","volume":"15","author":"Wang","year":"2024","journal-title":"Nat Commun"},{"key":"2025101514300410500_ref19","doi-asserted-by":"publisher","first-page":"2657","DOI":"10.1038\/s41467-024-46569-1","article-title":"A dual diffusion model enables 3D molecule generation and lead optimization based on target pockets","volume":"15","author":"Huang","year":"2024","journal-title":"Nat Commun"},{"key":"2025101514300410500_ref20","doi-asserted-by":"crossref","article-title":"Structure-based drug design with equivariant diffusion models","author":"Schneuing","DOI":"10.1038\/s43588-024-00737-x"},{"key":"2025101514300410500_ref21","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1038\/s42256-024-00815-9","article-title":"Equivariant 3d-conditional diffusion model for molecular linker design","volume":"6","author":"Igashov","year":"2024","journal-title":"Nat Mach Intell"},{"key":"2025101514300410500_ref22","article-title":"Interaction-based retrieval-augmented diffusion models for protein-specific 3D molecule generation","volume-title":"Proceedings of the 41st International Conference on Machine Learning (ICML)","author":"Huang","year":"2024"},{"key":"2025101514300410500_ref23","doi-asserted-by":"crossref","article-title":"A survey of geometric graph neural networks: data structures, models and applications","author":"Han","DOI":"10.1007\/s11704-025-41426-w"},{"key":"2025101514300410500_ref24","article-title":"Geometrically equivariant graph neural networks: a survey","author":"Han"},{"key":"2025101514300410500_ref25","article-title":"MDM: molecular diffusion model for 3D molecule generation","volume":"37","author":"Huang","year":", , 2023","journal-title":"Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI),"},{"key":"2025101514300410500_ref26","article-title":"Geometry informed to kenization of molecules for language model generation","author":"Li"},{"key":"2025101514300410500_ref27","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-43415-0_33","article-title":"MiDi: mixed graph and 3D denoising diffusion for molecule generation","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Vignac","year":"2023"},{"key":"2025101514300410500_ref28","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1038\/s43588-023-00532-0","article-title":"Guided diffusion for inverse molecular design","volume":"3","author":"Weiss","year":"2023","journal-title":"Nat Comput Sci"},{"key":"2025101514300410500_ref29","article-title":"Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem","author":"Tripp"},{"key":"2025101514300410500_ref30","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbae284","article-title":"Morphological profiling for drug discovery in the era of deep learning","volume":"25","author":"Tang","year":"2024","journal-title":"Brief Bioinform"},{"key":"2025101514300410500_ref31","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1038\/d41573-024-00036-0","article-title":"When can AI deliver the drug discovery hits?","volume":"23","author":"Mullard","year":"2024","journal-title":"Nat Rev Drug Discov"},{"key":"2025101514300410500_ref32","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1038\/s42256-024-00843-5","article-title":"Machine learning-aided generative molecular design","volume":"6","author":"Du","year":"2024","journal-title":"Nat Mach Intell"},{"key":"2025101514300410500_ref33","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1038\/s42256-025-00997-w","article-title":"Deep lead optimization enveloped in protein pocket and its application in designing potent and selective ligands targeting LTK protein","volume":"7","author":"Chen","year":"2025","journal-title":"Nat Mach Intell"},{"key":"2025101514300410500_ref34","article-title":"3D equivariant diffusion for target-aware molecule generation and affinity prediction","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Guan","year":"2023"},{"key":"2025101514300410500_ref35","doi-asserted-by":"publisher","first-page":"bbae435","DOI":"10.1093\/bib\/bbad435","article-title":"KGDiff: towards explainable target-aware molecule generation with knowledge guidance","volume":"25","author":"Qian","year":"2023","journal-title":"Brief Bioinform"},{"key":"2025101514300410500_ref36","doi-asserted-by":"crossref","article-title":"Sigmoid-weighted linear units for neural network function approximation in reinforcement learning","author":"Elfwing","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"2025101514300410500_ref37","doi-asserted-by":"publisher","first-page":"4200","DOI":"10.1021\/acs.jcim.0c00411","article-title":"Three-dimensional convolutional neural networks and a cross-docked data set for structure-based drug design","volume":"60","author":"Francoeur","year":"2020","journal-title":"J Chem Inf Model"},{"key":"2025101514300410500_ref38","doi-asserted-by":"publisher","first-page":"2977","DOI":"10.1021\/jm030580l","article-title":"The PDBbind database: collection of binding affinities for protein-ligand complexes with known three-dimensional structures","volume":"47","author":"Wang","year":"2004","journal-title":"J Med Chem"},{"key":"2025101514300410500_ref39","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":"2025101514300410500_ref40"},{"key":"2025101514300410500_ref41","doi-asserted-by":"publisher","first-page":"3891","DOI":"10.1021\/acs.jcim.1c00203","article-title":"AutoDock Vina 1.2.0: new docking methods, expanded force field, and python bindings","volume":"61","author":"Jerome","year":"2021","journal-title":"J Chem Inf Model"},{"key":"2025101514300410500_ref42","volume-title":"RDKit: Open-Source Cheminformatics Software","author":"RDKit"},{"key":"2025101514300410500_ref43","first-page":"6229","article-title":"A 3D generative model for structure-based drug design","volume":"34","author":"Luo","year":"2021","journal-title":"In Advances in Neural Information Processing Systems (NeurIPS),"},{"key":"2025101514300410500_ref44","article-title":"Generating 3D molecules for target protein binding","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Liu","year":"2022"},{"key":"2025101514300410500_ref45","first-page":"17644","article-title":"Pocket2Mol: efficient molecular sampling based on 3D protein pockets","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Peng","year":"2022"},{"key":"2025101514300410500_ref46","article-title":"TAGMol: target-aware gradient-guided molecule generation","author":"Dorna"},{"key":"2025101514300410500_ref47","article-title":"AUTODIFF: autoregressive diffusion modeling for structure-based drug design","author":"Li"},{"key":"2025101514300410500_ref48","doi-asserted-by":"crossref","article-title":"Binding-adaptive diffusion models for structure-based drug design","author":"Huang","DOI":"10.1609\/aaai.v38i11.29162"},{"key":"2025101514300410500_ref49","article-title":"DecompDiff: diffusion models with decomposed priors for structure-based drug design","author":"Guan"},{"key":"2025101514300410500_ref50","article-title":"Protein-ligand interaction prior for binding-aware 3D molecule diffusion models","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","author":"Huang","year":"2024"},{"key":"2025101514300410500_ref51","article-title":"DecompOpt: controllable and decomposed diffusion models for structure-based molecular optimization","author":"Zhou"},{"key":"2025101514300410500_ref52","doi-asserted-by":"crossref","article-title":"PocketFlow: a data-and-knowledge-driven structure-based molecular generative model","author":"Jiang","DOI":"10.1038\/s42256-024-00808-8"},{"key":"2025101514300410500_ref53","doi-asserted-by":"publisher","first-page":"2688","DOI":"10.1038\/s41467-024-47011-2","article-title":"3D molecular generative framework for interaction-guided drug design","volume":"15","author":"Zhong","year":"2024","journal-title":"Nat Commun"},{"key":"2025101514300410500_ref54","doi-asserted-by":"publisher","first-page":"4552","DOI":"10.1038\/s41467-023-40219-8","article-title":"Macrocyclization of linear molecules by deep learning to facilitate macrocyclic drug candidates discovery","volume":"14","author":"Diao","year":"2023","journal-title":"Nat Commun"},{"key":"2025101514300410500_ref55","doi-asserted-by":"publisher","first-page":"2778","DOI":"10.1021\/ci200227u","article-title":"LigPlot+: multiple ligand\u2013protein interaction diagrams for drug discovery","volume":"51","author":"Laskowski","year":"2011","journal-title":"J Chem Inf Model"},{"key":"2025101514300410500_ref56","doi-asserted-by":"publisher","first-page":"W289","DOI":"10.1093\/nar\/gkad324","article-title":"KVFinder-web: a web based application for detecting and characterizing biomolecular cavities","volume":"51","author":"Guerra","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2025101514300410500_ref57","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-024-04140-z","article-title":"Mdcath: a large-scale MD dataset for data-driven computational biophysics","volume-title":"Sci Data","author":"Mirarchi"},{"key":"2025101514300410500_ref58","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1038\/s43588-024-00627-2","article-title":"Misato: machine learning dataset of protein-ligand complexes for structure-based drug discovery","volume":"4","author":"Siebenmorgen","year":"2024","journal-title":"Nat Comput Sci"},{"key":"2025101514300410500_ref59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41586-024-08127-z","article-title":"Ab initio characterization of protein molecular dynamics with AI${}^2$BMD","volume":"635","author":"Wang","year":"2024","journal-title":"Nature"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/5\/bbaf542\/64702038\/bbaf542.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/5\/bbaf542\/64702038\/bbaf542.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T18:30:15Z","timestamp":1760553015000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf542\/8285924"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":59,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,8,31]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf542","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":[[2025,8,31]]},"article-number":"bbaf542"}}