{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T11:02:39Z","timestamp":1785409359343,"version":"3.56.0"},"reference-count":72,"publisher":"National Academy of Sciences","issue":"24","license":[{"start":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T00:00:00Z","timestamp":1780963200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100011195","name":"CAS | Shanghai Institute of Organic Chemistry, Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["NA"],"award-info":[{"award-number":["NA"]}],"id":[{"id":"10.13039\/501100011195","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.pnas.org"],"crossmark-restriction":true},"short-container-title":["Proc. Natl. Acad. Sci. U.S.A."],"published-print":{"date-parts":[[2026,6,16]]},"abstract":"<jats:p>Generative AI algorithms such as the transformer and diffusion models have greatly empowered de novo design of proteins capable of specifically interacting with designated structural sites on another protein. Most of these design methods employ a top\u2013down approach, in which an overall protein shape is generated by an AI model to pack against a given structural site, followed by sequence design to optimize the interaction. Despite being trained on limited protein complex structures available in the database, the top\u2013down approach has yielded encouraging results. Here, we propose a bottom\u2013up approach that generates atom clusters for optimal packing against a specified structured region for informing the design of protein\u2013protein interactions. To this end, we trained a masked discrete diffusion model, named Void-X, that uses the diffusion transformer to learn atomic-level interactions and fill atomic voids in protein interaction interfaces. Void-X was trained using 8.7 million spherical clusters of atoms from experimental structures in the Protein Data Bank. In each cluster, ~70% of the atoms are used as context (or prompt), and ~30% are masked for information recovery (or answer). By training the model with 172 million parameters, Void-X achieves an overall accuracy of 78.3% and 68.2% for intra- and interchain spherical clusters, respectively. Furthermore, we find that information entropy is a reliable indicator of the prediction accuracy for Void-X. This level of performance allows de novo generation of molecular interactions at the atomic level, offering an alternative approach of protein design complementary to the existing ones.<\/jats:p>","DOI":"10.1073\/pnas.2607035123","type":"journal-article","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T17:36:04Z","timestamp":1781026564000},"update-policy":"https:\/\/doi.org\/10.1073\/pnas.cm10313","source":"Crossref","is-referenced-by-count":0,"title":["Void-X: A generative void-filling model for predicting atomic packing in proteins"],"prefix":"10.1073","volume":"123","author":[{"given":"Jing","family":"Yang","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/034t30j35","id-type":"ROR","asserted-by":"publisher"}],"name":"Interdisciplinary Research Center on Biology and Chemistry, Shanghai Institute of Organic Chemistry, Chinese Academy of Sciences","place":["Shanghai, China"]},{"id":[{"id":"https:\/\/ror.org\/034t30j35","id-type":"ROR","asserted-by":"publisher"}],"name":"State Key Laboratory of Chemical Biology, Chinese Academy of Sciences","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2405-6036","authenticated-orcid":false,"given":"Junying","family":"Yuan","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/034t30j35","id-type":"ROR","asserted-by":"publisher"}],"name":"Interdisciplinary Research Center on Biology and Chemistry, Shanghai Institute of Organic Chemistry, Chinese Academy of Sciences","place":["Shanghai, China"]},{"name":"Shanghai Key Laboratory of Aging Studies","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James J.","family":"Chou","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/034t30j35","id-type":"ROR","asserted-by":"publisher"}],"name":"Interdisciplinary Research Center on Biology and Chemistry, Shanghai Institute of Organic Chemistry, Chinese Academy of Sciences","place":["Shanghai, China"]},{"id":[{"id":"https:\/\/ror.org\/034t30j35","id-type":"ROR","asserted-by":"publisher"}],"name":"State Key Laboratory of Chemical Biology, Chinese Academy of Sciences","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"341","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"e_1_3_4_1_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.89.6.2195"},{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gki481"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1002\/prot.21419"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkn216"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btu097"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmb.2015.09.014"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1038\/nchem.2785"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1815431116"},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2210249119"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.2c00743"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41589-025-01879-3"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbi.2025.103080"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0900266106"},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.1002\/advs.202405404"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cels.2021.08.010"},{"key":"e_1_3_4_16_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2311887121"},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbae359"},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-64512-w"},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-32007-7"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-022-01618-2"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2016239118"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade2574"},{"key":"e_1_3_4_23_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.ads0018"},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-025-02636-z"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gky1049"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac1080"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-023-01763-2"},{"key":"e_1_3_4_28_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.adk8946"},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2418918121"},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-50698-y"},{"key":"e_1_3_4_31_2","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adr2641"},{"key":"e_1_3_4_32_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_3_4_33_2","doi-asserted-by":"crossref","unstructured":"R. Evans Protein complex prediction with AlphaFold-Multimer. bioRxiv [Preprint] (2022). https:\/\/doi.org\/10.1101\/2021.10.04.463034 (Accessed 10 March 2022).","DOI":"10.1101\/2021.10.04.463034"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07487-w"},{"key":"e_1_3_4_35_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0161879"},{"key":"e_1_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06415-8"},{"key":"e_1_3_4_37_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41589-025-01929-w"},{"key":"e_1_3_4_38_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09429-6"},{"key":"e_1_3_4_39_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09721-5"},{"key":"e_1_3_4_40_2","doi-asserted-by":"crossref","unstructured":"H. Stark BoltzGen: Toward universal binder design. bioRxiv [Preprint] (2025). https:\/\/doi.org\/10.1101\/2025.11.20.689494 (Accessed 24 November 2025).","DOI":"10.1101\/2025.11.20.689494"},{"key":"e_1_3_4_41_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-025-02975-x"},{"key":"e_1_3_4_42_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05993-x"},{"key":"e_1_3_4_43_2","unstructured":"V. Zambaldi De novo design of high-affinity protein binders with AlphaProteo. arXiv [Preprint] (2024). https:\/\/doi.org\/10.48550\/arXiv.2409.08022 (Accessed 12 September 2024)."},{"key":"e_1_3_4_44_2","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani A.","unstructured":"A. Vaswani , \u201cAttention is all you need\u201d in Advances in Neural Information Processing Systems, I. Guyon ., Eds. (Curran Associates, Inc., 2017), pp. 5998\u20136008."},{"key":"e_1_3_4_45_2","unstructured":"J. Sohl-Dickstein E. Weiss N. Maheswaranathan S. Ganguli \u201cDeep unsupervised learning using nonequilibrium thermodynamics\u201d in International Conference on Machine Learning (PMLR 2015) pp. 2256\u20132265."},{"key":"e_1_3_4_46_2","unstructured":"J. Ho A. Jain P. Abbeel \u201cDenoising diffusion probabilistic models\u201d in Advances in Neural Information Processing Systems H. Larochelle M. Ranzato R. Hadsell M. Balcan H. Lin Eds. (Curran Associates Inc. 2020) pp 6840\u20136851."},{"key":"e_1_3_4_47_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.add2187"},{"key":"e_1_3_4_48_2","doi-asserted-by":"crossref","unstructured":"T. Chai Discovery Zero-shot antibody design in a 24-well plate. bioRxiv [Preprint] (2025). https:\/\/doi.org\/10.1101\/2025.07.05.663018 (Accessed 6 July 2025).","DOI":"10.1101\/2025.07.05.663018"},{"key":"e_1_3_4_49_2","doi-asserted-by":"crossref","unstructured":"L. S. Mille-Fragoso Efficient generation of epitope-targeted de novo antibodies with Germinal. bioRxiv [Preprint] (2025). https:\/\/doi.org\/10.1101\/2025.09.19.677421 (Accessed 25 September 2025).","DOI":"10.1101\/2025.09.19.677421"},{"key":"e_1_3_4_50_2","doi-asserted-by":"crossref","unstructured":"E. Swanson M. Nichols S. Ravichandran P. Ogden mBER: Controllable de novo antibody design with million-scale experimental screening. bioRxiv [Preprint] (2025). https:\/\/doi.org\/10.1101\/2025.09.26.678877 (Accessed 28 September 2025).","DOI":"10.1101\/2025.09.26.678877"},{"key":"e_1_3_4_51_2","unstructured":"J. Austin D. D. Johnson J. Ho D. Tarlow R. Van Den Berg \u201cStructured denoising diffusion models in discrete state-spaces\u201d in Advances in Neural Information Processing Systems M. Ranzato A. Beygelzimer Y. Dauphin P. S. Liang J. Wortman Vaughan Eds. (Curran Associates Inc. 2021) pp 17981\u201317993."},{"key":"e_1_3_4_52_2","doi-asserted-by":"crossref","unstructured":"W. Peebles S. Xie \u201cScalable diffusion models with transformers\u201d in Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023) pp. 4195\u20134205.","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_4_53_2","unstructured":"J. Achiam GPT-4 technical report. arXiv [Preprint] (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.08774 (Accessed 19 December 2023)."},{"key":"e_1_3_4_54_2","unstructured":"A. Ramesh P. Dhariwal A. Nichol C. Chu M. Chen Hierarchical text-conditional image generation with CLIP latents. arXiv [Preprint] (2022). https:\/\/doi.org\/10.48550\/arXiv.2204.06125 (Accessed 13 April 2022)."},{"key":"e_1_3_4_55_2","doi-asserted-by":"crossref","unstructured":"R. Girshick \u201cFast R-CNN\u201d in Proceedings of the IEEE\/CVF International Conference on Computer Vision (2015) pp. 1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_4_56_2","doi-asserted-by":"crossref","unstructured":"J. Davis M. Goadrich \u201cThe relationship between precision-recall and ROC curves\u201d in International Conference on Machine Learning (PMLR 2006) pp. 233\u2013240.","DOI":"10.1145\/1143844.1143874"},{"key":"e_1_3_4_57_2","doi-asserted-by":"publisher","DOI":"10.1121\/1.2016299"},{"key":"e_1_3_4_58_2","first-page":"31","article-title":"An estimate of an upper bound for the entropy of English","volume":"18","author":"Brown P. F.","year":"1992","unstructured":"P. F. Brown, V. J. D. Pietra, R. L. Mercer, S. A. D. Pietra, J. C. Lai, An estimate of an upper bound for the entropy of English. Comput. Linguist. 18, 31\u201340 (1992).","journal-title":"Comput. Linguist."},{"key":"e_1_3_4_59_2","doi-asserted-by":"publisher","DOI":"10.1006\/jmbi.2000.4474"},{"key":"e_1_3_4_60_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.adx6931"},{"key":"e_1_3_4_61_2","doi-asserted-by":"crossref","unstructured":"J. Su \u201cSaProt: Protein language modeling with structure-aware vocabulary\u201d in International Conference on Learning Representations (2024).","DOI":"10.1101\/2023.10.01.560349"},{"key":"e_1_3_4_62_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-023-01773-0"},{"key":"e_1_3_4_63_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jpcb.3c06662"},{"key":"e_1_3_4_64_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00454-005-1210-2"},{"key":"e_1_3_4_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2016.140952"},{"key":"e_1_3_4_66_2","unstructured":"A. Q. Nichol P. Dhariwal \u201cImproved denoising diffusion probabilistic models\u201d in International Conference on Machine Learning (PMLR 2021) pp. 8162\u20138171."},{"key":"e_1_3_4_67_2","doi-asserted-by":"crossref","unstructured":"E. Perez F. Strub H. De Vries V. Dumoulin A. Courville \u201cFilm: Visual reasoning with a general conditioning layer\u201d in Proceedings of the AAAI Conference on Artificial Intelligence (2018).","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"e_1_3_4_68_2","unstructured":"V. G. Satorras E. Hoogeboom M. Welling \u201cE(n) equivariant graph neural networks\u201d in International Conference on Machine Learning (PMLR 2021) pp. 9323\u20139332."},{"key":"e_1_3_4_69_2","doi-asserted-by":"crossref","unstructured":"G. Zhou \u201cUni-mol: A universal 3D molecular representation learning framework\u201d in International Conference on Learning Representations (2023).","DOI":"10.26434\/chemrxiv-2022-jjm0j-v4"},{"key":"e_1_3_4_70_2","unstructured":"I. Loshchilov F. Hutter \u201cDecoupled weight decay regularization\u201d in International Conference on Learning Representations (2017)."},{"key":"e_1_3_4_71_2","unstructured":"H. M. Berman K. Henrick H. Nakamura Announcing the worldwide Protein Data Bank. Protein Data Bank. https:\/\/files.wwpdb.org\/pub\/pdb\/data\/structures\/. Accessed 30 October 2025."},{"key":"e_1_3_4_72_2","unstructured":"H. M. Berman . The Protein Data Bank. https:\/\/cdn.rcsb.org\/resources\/sequence\/clusters\/clusters-by-entity-40.txt. Accessed 30 October 2025."}],"container-title":["Proceedings of the National Academy of Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pnas.org\/doi\/pdf\/10.1073\/pnas.2607035123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T17:36:35Z","timestamp":1781026595000},"score":1,"resource":{"primary":{"URL":"https:\/\/pnas.org\/doi\/10.1073\/pnas.2607035123"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,9]]},"references-count":72,"journal-issue":{"issue":"24","published-print":{"date-parts":[[2026,6,16]]}},"alternative-id":["10.1073\/pnas.2607035123"],"URL":"https:\/\/doi.org\/10.1073\/pnas.2607035123","relation":{},"ISSN":["0027-8424","1091-6490"],"issn-type":[{"value":"0027-8424","type":"print"},{"value":"1091-6490","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,9]]},"assertion":[{"value":"2026-02-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2607035123"}}