{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T03:56:50Z","timestamp":1792727810923,"version":"4.5.0"},"reference-count":23,"publisher":"National Academy of Sciences","issue":"41","license":[{"start":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T00:00:00Z","timestamp":1759708800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.pnas.org"],"crossmark-restriction":true},"short-container-title":["Proc. Natl. Acad. Sci. U.S.A."],"published-print":{"date-parts":[[2025,10,14]]},"abstract":"<jats:p>AI models have shown great potential in structure-based drug design, generating ligands with high binding affinities. However, existing models have often overlooked a crucial physical prior: Atoms must maintain a minimum pairwise distance to avoid atomic collision, a phenomenon governed by the balance of attractive and repulsive forces. To mitigate such atomic collisions, we propose NucleusDiff. It enforces spatial distance constraints between atomic nuclei and auxiliary mesh points placed on a spherical surface around each atom, approximating van der Waals boundaries to reduce atomic collisions. We quantitatively evaluate NucleusDiff using the CrossDocked2020 dataset and a COVID-19 therapeutic target, demonstrating that NucleusDiff reduces collision rate by up to 100.00% and enhances binding affinity by up to 22.16%, surpassing state-of-the-art models for structure-based drug design. We also provide qualitative analysis through manifold sampling, visually confirming the effectiveness of NucleusDiff in reducing atomic collisions and improving binding affinities.<\/jats:p>","DOI":"10.1073\/pnas.2415666122","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T19:04:23Z","timestamp":1759777463000},"update-policy":"https:\/\/doi.org\/10.1073\/pnas.cm10313","source":"Crossref","is-referenced-by-count":7,"title":["Manifold-constrained nucleus-level denoising diffusion model for structure-based drug design"],"prefix":"10.1073","volume":"122","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2030-2367","authenticated-orcid":false,"given":"Shengchao","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Computer Sciences (EECS)","place":["Berkeley"]},{"name":"University of California","place":["Berkeley"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2880-3124","authenticated-orcid":false,"given":"Liang","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Computing and Mathematical Sciences (CMS)","place":["Pasadena"]},{"name":"California Institute of Technology","place":["Pasadena"]},{"name":"Institute of Science and Technology for Brain-Inspired Intelligence (ISTBI)","place":["Shanghai, China"]},{"name":"Fudan University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7643-4671","authenticated-orcid":false,"given":"Weitao","family":"Du","sequence":"additional","affiliation":[{"name":"Alibaba DAMO Academy","place":["Bellevue"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8234-3263","authenticated-orcid":false,"given":"Weiyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems","place":["T\u00fcbingen, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuoxinran","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Human Geography","place":["Toronto, Canada"]},{"name":"University of Toronto","place":["Toronto, Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7663-2421","authenticated-orcid":false,"given":"Hongyu","family":"Guo","sequence":"additional","affiliation":[{"name":"National Research Council Canada","place":["Ottawa, Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5653-0498","authenticated-orcid":false,"given":"Christian","family":"Borgs","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Sciences (EECS)","place":["Berkeley"]},{"name":"University of California","place":["Berkeley"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4020-8618","authenticated-orcid":false,"given":"Jennifer","family":"Chayes","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Sciences (EECS)","place":["Berkeley"]},{"name":"University of California","place":["Berkeley"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6974-6797","authenticated-orcid":false,"given":"Anima","family":"Anandkumar","sequence":"additional","affiliation":[{"name":"Department of Computing and Mathematical Sciences (CMS)","place":["Pasadena"]},{"name":"California Institute of Technology","place":["Pasadena"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"341","published-online":{"date-parts":[[2025,10,6]]},"reference":[{"key":"e_1_3_4_1_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1002951"},{"key":"e_1_3_4_2_2","unstructured":"N. Thomas Tensor field networks: Rotation-and translation-equivariant neural networks for 3d point clouds. arXiv [Preprint] (2028). https:\/\/arxiv.org\/abs\/1802.08219 (Accessed 18 November 2024)."},{"key":"e_1_3_4_3_2","first-page":"66084","article-title":"Symmetry-informed geometric representation for molecules, proteins, and crystalline materials","volume":"36","author":"Liu S.","year":"2023","unstructured":"S. Liu , Symmetry-informed geometric representation for molecules, proteins, and crystalline materials. Adv. Neural Inf. Process. Syst. 36, 66084\u201366101 (2023).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_4_4_2","first-page":"10446","article-title":"A 3D generative model for structure-based drug design","volume":"34","author":"Luo S.","year":"2021","unstructured":"S. Luo, J. Guan, J. Ma, J. Peng, A 3D generative model for structure-based drug design. Adv. Neural Inf. Process. Syst. 34, 10446 (2021).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_4_5_2","unstructured":"M. Liu Y. Luo K. Uchino K. Maruhashi S. Ji \u201cGenerating 3D molecules for target protein binding\u201d in Proceedings of the 39th International Conference on Machine Learning K. Chaudhuri Eds. (Proceedings of Machine Learning Research 2022) pp. 13912\u201313924."},{"key":"e_1_3_4_6_2","unstructured":"X. Peng Pocket2mol: Efficient molecular sampling based on 3D protein pockets. arXiv [Preprint] (2022). http:\/\/arxiv.org\/abs\/2205.07249 (Accessed 23 November 2024)."},{"key":"e_1_3_4_7_2","unstructured":"J. Guan \u201c3D equivariant diffusion for target-aware molecule generation and affinity prediction\u201d in The Eleventh International Conference on Learning Representations (The Eleventh International Conference on Learning Representations 2023)."},{"key":"e_1_3_4_8_2","unstructured":"J. Abramson Accurate Structure Prediction of Biomolecular Interactions with AlphaFold3 (Nature Publishing Group UK London 2024) pp. 1\u20133."},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.0c00411"},{"key":"e_1_3_4_10_2","unstructured":"Y. Wang \u201cLearning harmonic molecular representations on Riemannian manifold\u201d in The Eleventh International Conference on Learning Representations (The Eleventh International Conference on Learning Representations 2023)."},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-023-00530-2"},{"key":"e_1_3_4_12_2","unstructured":"V. Mallet S. Attaiki M. Ovsjanikov Atomsurf: Surface representation for learning on protein structures. arXiv [Preprint] (2023). http:\/\/arxiv.org\/abs\/2309.16519 (Accessed 27 November 2024)."},{"key":"e_1_3_4_13_2","unstructured":"Q. Zhou Pymesh\u2013geometry processing library for python. Github. https:\/\/github.com\/PyMesh\/PyMesh. Accessed 30 November 2024."},{"key":"e_1_3_4_14_2","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho J.","year":"2020","unstructured":"J. Ho, A. Jain, P. Abbeel, Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"e_1_3_4_16_2","first-page":"11918","article-title":"Generative modeling by estimating gradients of the data distribution","volume":"32","author":"Song Y.","year":"2019","unstructured":"Y. Song, S. Ermon, Generative modeling by estimating gradients of the data distribution. Adv. Neural Inf. Process. Syst. 32, 11918\u201311930 (2019).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btq322"},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","DOI":"10.1039\/D1SC05976A"},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-46569-1"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.21256"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btv082"},{"key":"e_1_3_4_22_2","first-page":"05379","article-title":"Argmax flows and multinomial diffusion: Learning categorical distributions","volume":"34","author":"Hoogeboom E.","year":"2021","unstructured":"E. Hoogeboom, D. Nielsen, P. Jaini, P. Forr\u00e9, M. Welling, Argmax flows and multinomial diffusion: Learning categorical distributions. Adv. Neural Inf. Process. Syst. 34, 05379 (2021).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_4_23_2","unstructured":"S. Liu Manifold-constrained nucleus-level denoising diffusion model for structure-based drug design. Zenodo. https:\/\/doi.org\/10.5281\/zenodo.17093932. Accessed 10 September 2025."}],"container-title":["Proceedings of the National Academy of Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pnas.org\/doi\/pdf\/10.1073\/pnas.2415666122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T19:06:52Z","timestamp":1759777612000},"score":1,"resource":{"primary":{"URL":"https:\/\/pnas.org\/doi\/10.1073\/pnas.2415666122"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,6]]},"references-count":23,"journal-issue":{"issue":"41","published-print":{"date-parts":[[2025,10,14]]}},"alternative-id":["10.1073\/pnas.2415666122"],"URL":"https:\/\/doi.org\/10.1073\/pnas.2415666122","relation":{},"ISSN":["0027-8424","1091-6490"],"issn-type":[{"value":"0027-8424","type":"print"},{"value":"1091-6490","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,6]]},"assertion":[{"value":"2024-09-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2415666122"}}