Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

A multiobjective AI model for LNP engineering enhances tissue-selective mRNA delivery

Nature Biotechnology (2026) Cite this article

Subjects

Abstract

Lipid nanoparticle (LNP) delivery of RNA therapeutics is constrained by poor tissue selectivity and off-target toxicity. Most high-throughput screening approaches have focused on single-target efficacy while overlooking off-target uptake. Here we report multiobjective LNP engineering with artificial intelligence (MOLEA), a system that integrates high-dimensional lipid representations, cell-type-resolved transfection data and multitask optimization to design ionizable lipids with both high potency and biological selectivity. MOLEA learns structure–function relationships across diverse cellular contexts to identify lipids that preferentially deliver mRNA to target tissue while minimizing hepatocyte transfection. Applying MOLEA to cartilage, we developed K9 LNPs, which achieve >90% transfection efficiency in mouse joint chondrocytes and a 13.5-fold increase in knee-to-liver selectivity compared to the clinical benchmark SM-102. We demonstrate chondrocyte-specific Mmp13 editing in osteoarthritis mouse models, leading to sustained cartilage protection and suppression of disease-associated immune and matrix remodeling. Our findings demonstrate how artificial-intelligence-guided multiobjective optimization can enable precision RNA delivery with potential applications to other tissues.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Overview of the MOLEA system for cell-type-targeted LNP delivery.
The alternative text for this image may have been generated using AI.
Fig. 2: High-throughput lipid screening on multiple objectives for fine-tuning and experimental validation of the MOLEA-predicted lipid.
The alternative text for this image may have been generated using AI.
Fig. 3: In vitro and in vivo validation of MOLEA-predicted LNPs.
The alternative text for this image may have been generated using AI.
Fig. 4: K9 LNP enables efficient and chondrocyte-selective mRNA delivery in vivo.
The alternative text for this image may have been generated using AI.
Fig. 5: K9 LNP mediates efficient genome editing in vivo.
The alternative text for this image may have been generated using AI.
Fig. 6: K9 LNP-mediated intra-articular genome editing ameliorates acute arthritis.
The alternative text for this image may have been generated using AI.

Similar content being viewed by others

Data availability

All data are available in the main text or Supplementary Information. Sequencing data from amplicon NGS experiments were deposited to the National Center for Biotechnology Information Sequence Read Archive under BioProject PRJNA1440167. Source data are provided with this paper.

Code availability

The codebase data and code used in this study are available from the GitHub (https://github.com/bowenli-lab/MOLEA) and Zenodo (https://doi.org/10.5281/zenodo.18943783)58 repositories with the MIT license.

References

  1. Polack, F. P. et al. Safety and efficacy of the BNT162b2 mRNA COVID-19 vaccine. N. Engl. J. Med. 383, 2603–2615 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  2. Baden, L. R. et al. Efficacy and safety of the mRNA-1273 SARS-CoV-2 vaccine. N. Engl. J. Med. 384, 403–416 (2021).

    Article  CAS  PubMed  Google Scholar 

  3. Adams, D. et al. Patisiran, an RNAi therapeutic, for hereditary transthyretin amyloidosis. N. Engl. J. Med. 379, 11–21 (2018).

    Article  CAS  PubMed  Google Scholar 

  4. Nasreen, S. et al. Effectiveness of COVID-19 vaccines against symptomatic SARS-CoV-2 infection and severe outcomes with variants of concern in Ontario. Nat. Microbiol. 7, 379–385 (2022).

    Article  CAS  PubMed  Google Scholar 

  5. Hou, X., Zaks, T., Langer, R. & Dong, Y. Lipid nanoparticles for mRNA delivery. Nat. Rev. Mater. 6, 1078–1094 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Vasileva, O., Zaborova, O., Shmykov, B., Ivanov, R. & Reshetnikov, V. Composition of lipid nanoparticles for targeted delivery: application to mRNA therapeutics. Front. Pharmacol. 15, 1466337 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  7. Wittrup, A. et al. Visualizing lipid-formulated siRNA release from endosomes and target gene knockdown. Nat. Biotechnol. 33, 870–876 (2015).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  8. Kim, M. et al. Engineered ionizable lipid nanoparticles for targeted delivery of RNA therapeutics into different types of cells in the liver. Sci. Adv. 7, eabf4398 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  9. Qiu, M. et al. Lung-selective mRNA delivery of synthetic lipid nanoparticles for the treatment of pulmonary lymphangioleiomyomatosis. Proc. Natl Acad. Sci. USA 119, e2116271119 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  10. Hosseini-Kharat, M., Bremmell, K. E. & Prestidge, C. A. Why do lipid nanoparticles target the liver? Understanding of biodistribution and liver-specific tropism. Mol. Ther. Methods Clin. Dev. 33, 101436 (2025).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  11. Akinc, A. et al. Targeted delivery of RNAi therapeutics with endogenous and exogenous ligand-based mechanisms. Mol. Ther. 18, 1357–1364 (2010).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  12. Jain, R. et al. MicroRNAs enable mRNA therapeutics to selectively program cancer cells to self-destruct. Nucleic Acid Ther. 28, 285–296 (2018).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  13. Ramishetti, S. et al. A combinatorial library of lipid nanoparticles for RNA delivery to leukocytes. Adv. Mater. 32, e1906128 (2020).

    Article  PubMed  Google Scholar 

  14. Chen, J. et al. Combinatorial design of ionizable lipid nanoparticles for muscle-selective mRNA delivery with minimized off-target effects. Proc. Natl Acad. Sci. USA 120, e2309472120 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  15. Li, B. et al. Combinatorial design of nanoparticles for pulmonary mRNA delivery and genome editing. Nat. Biotechnol. 41, 1410–1415 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Han, X. et al. In situ combinatorial synthesis of degradable branched lipidoids for systemic delivery of mRNA therapeutics and gene editors. Nat. Commun. 15, 1762 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  17. Peña, Á et al. Multicomponent thiolactone-based ionizable lipid screening platform for efficient and tunable mRNA delivery to the lungs. Commun. Chem. 8, 116 (2025).

    Article  PubMed  PubMed Central  Google Scholar 

  18. Isaac, I. et al. Tetrahydropyrimidine ionizable lipids for efficient mRNA delivery. ACS Nano 18, 29045–29058 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  19. Hamilton, A. G. et al. High-throughput in vivo screening identifies differential influences on mRNA lipid nanoparticle immune cell delivery by administration route. ACS Nano 18, 16151–16165 (2024).

    Article  CAS  PubMed  Google Scholar 

  20. Kauffman, K. J. et al. Optimization of lipid nanoparticle formulations for mRNA delivery in vivo with fractional factorial and definitive screening designs. Nano Lett. 15, 7300–7306 (2015).

    Article  CAS  PubMed  Google Scholar 

  21. Ly, H. H., Daniel, S., Soriano, S. K. V., Kis, Z. & Blakney, A. K. Optimization of lipid nanoparticles for saRNA expression and cellular activation using a design-of-experiment approach. Mol. Pharm. 19, 1892–1905 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  22. Su, K. et al. Reformulating lipid nanoparticles for organ-targeted mRNA accumulation and translation. Nat. Commun. 15, 5659 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  23. Wang, C. et al. Blood–brain-barrier-crossing lipid nanoparticles for mRNA delivery to the central nervous system. Nat. Mater. 24, 1653–1663 (2025).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  24. Yamankurt, G. et al. Exploration of the nanomedicine-design space with high-throughput screening and machine learning. Nat. Biomed. Eng. 3, 318–327 (2019).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  25. Xu, Y. et al. LUMI-lab: a foundation model-driven autonomous platform enabling discovery of ionizable lipid designs for mRNA delivery. Cell 189, 1620–1635 (2026).

  26. Xu, Y. et al. AGILE platform: a deep learning powered approach to accelerate LNP development for mRNA delivery. Nat. Commun. 15, 6305 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  27. Wang, W. et al. Artificial intelligence-driven rational design of ionizable lipids for mRNA delivery. Nat. Commun. 15, 10804 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  28. Witten, J. et al. Artificial intelligence-guided design of lipid nanoparticles for pulmonary gene therapy. Nat. Biotechnol. 43, 1790–1799 (2025).

  29. Li, B. et al. Accelerating ionizable lipid discovery for mRNA delivery using machine learning and combinatorial chemistry. Nat. Mater. 23, 1002–1008 (2024).

    Article  CAS  PubMed  Google Scholar 

  30. Sengprasert, P., Kamenkit, O., Tanavalee, A. & Reantragoon, R. The immunological facets of chondrocytes in osteoarthritis: a narrative review. J. Rheumatol. 51, 13–24 (2024).

  31. Aigner, T., Söder, S., Gebhard, P. M., McAlinden, A. & Haag, J. Mechanisms of disease: role of chondrocytes in the pathogenesis of osteoarthritis–structure, chaos and senescence. Nat. Clin. Pract. Rheumatol. 3, 391–399 (2007).

    Article  CAS  PubMed  Google Scholar 

  32. Zheng, L., Zhang, Z., Sheng, P. & Mobasheri, A. The role of metabolism in chondrocyte dysfunction and the progression of osteoarthritis. Ageing Res. Rev. 66, 101249 (2021).

    Article  CAS  PubMed  Google Scholar 

  33. Madry, H. & Trippel, S. B. Efficient lipid-mediated gene transfer to articular chondrocytes. Gene Ther. 7, 286–291 (2000).

    Article  CAS  PubMed  Google Scholar 

  34. Hamm, A., Krott, N., Breibach, I., Blindt, R. & Bosserhoff, A. K. Efficient transfection method for primary cells. Tissue Eng. 8, 235–245 (2002).

    Article  CAS  PubMed  Google Scholar 

  35. Li, X., Shen, L., Deng, Z. & Huang, Z. New treatment for osteoarthritis: gene therapy. Precis. Clin. Med. 6, pbad014 (2023).

    Article  PubMed  PubMed Central  Google Scholar 

  36. Wang, Y., Wang, J., Cao, Z. & Barati Farimani, A. Molecular contrastive learning of representations via graph neural networks. Nat. Mach. Intell. 4, 279–287 (2022).

    Article  Google Scholar 

  37. Moriwaki, H., Tian, Y.-S., Kawashita, N. & Takagi, T. Mordred: a molecular descriptor calculator. J. Cheminform. 10, 4 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

  38. McInnes, L., Healy, J., Saul, N. & Großberger, L. UMAP: uniform manifold approximation and projection. J. Open Source Softw. 3, 861 (2018).

  39. Schwab, W. et al. Characterization of caveolins from human knee joint cartilage: expression of caveolin-1, -2, and -3 in chondrocytes and association with integrin β1. Histochem. Cell Biol. 113, 221–225 (2000).

    Article  CAS  PubMed  Google Scholar 

  40. Wang, P., Zhu, F., Tong, Z. & Konstantopoulos, K. Response of chondrocytes to shear stress: antagonistic effects of the binding partners Toll-like receptor 4 and caveolin-1. FASEB J. 25, 3401–3415 (2011).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  41. Guan, F. et al. Tissue macrophages: origin, heterogenity, biological functions, diseases and therapeutic targets. Signal Transduct. Target. Ther. 10, 93 (2025).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  42. Gustafson, H. H., Holt-Casper, D., Grainger, D. W. & Ghandehari, H. Nanoparticle UPTAKE: THE PHAGOCYTE PROBLEM. Nano Today 10, 487–510 (2015).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  43. Madisen, L. et al. A robust and high-throughput Cre reporting and characterization system for the whole mouse brain. Nat. Neurosci. 13, 133–140 (2010).

    Article  CAS  PubMed  Google Scholar 

  44. Staahl, B. T. et al. Efficient genome editing in the mouse brain by local delivery of engineered Cas9 ribonucleoprotein complexes. Nat. Biotechnol. 35, 431–434 (2017).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  45. Finn, J. D. et al. A single administration of CRISPR/Cas9 lipid nanoparticles achieves robust and persistent in vivo genome editing. Cell Rep. 22, 2227–2235 (2018).

    Article  CAS  PubMed  Google Scholar 

  46. Yu, S. Y. et al. A luciferase reporter mouse model to optimize in vivo gene editing validated by lipid nanoparticle delivery of adenine base editors. Mol. Ther. 31, 1159–1166 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  47. Bedingfield, S. K. et al. Amelioration of post-traumatic osteoarthritis via nanoparticle depots delivering small interfering RNA to damaged cartilage. Nat. Biomed. Eng. 5, 1069–1083 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  48. Colazo, J. M. et al. siRNA conjugate with high albumin affinity and degradation resistance for delivery and treatment of arthritis in mice and guinea pigs. Nat. Biomed. Eng. 9, 1366–1383 (2025).

    Article  CAS  PubMed  Google Scholar 

  49. Bedingfield, S. K. et al. Top-down fabricated microPlates for prolonged, intra-articular matrix metalloproteinase 13 siRNA nanocarrier delivery to reduce post-traumatic osteoarthritis. ACS Nano 15, 14475–14491 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  50. Hu, Q. & Ecker, M. Overview of MMP-13 as a promising target for the treatment of osteoarthritis. Int. J. Mol. Sci. 22, 1742 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  51. Wang, M. et al. MMP13 is a critical target gene during the progression of osteoarthritis. Arthritis Res. Ther. 15, R5 (2013).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  52. Takaishi, H., Kimura, T., Dalal, S., Okada, Y. & D’Armiento, J. Joint diseases and matrix metalloproteinases: a role for MMP-13. Curr. Pharm. Biotechnol. 9, 47–54 (2008).

    Article  CAS  PubMed  Google Scholar 

  53. Zenhausern, R. et al. Lipid nanoparticle screening in nonhuman primates with minimal loss of life. Nat. Biotechnol. https://doi.org/10.1038/s41587-025-02711-y (2025).

  54. Kim, H. et al. Lipid nanoparticle-mediated mRNA delivery to CD34+ cells in rhesus monkeys. Nat. Biotechnol. 43, 1813–1820 (2025).

  55. Charni-Natan, M. & Goldstein, I. Protocol for primary mouse hepatocyte isolation. STAR Protoc. 1, 100086 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  56. Gosset, M., Berenbaum, F., Thirion, S. & Jacques, C. Primary culture and phenotyping of murine chondrocytes. Nat. Protoc. 3, 1253–1260 (2008).

    Article  CAS  PubMed  Google Scholar 

  57. Saeki, N. & Imai, Y. Isolation and culture of primary synovial macrophages and fibroblasts from murine arthritis tissue. J. Vis. Exp. 192, e65196 (2023).

  58. Li, B. & Li, G. bowenli-lab/MOLEA: v1.0.0. Zenodo https://doi.org/10.5281/zenodo.18943783 (2026).

Download references

Acknowledgements

This research was funded by the Accelerate Translation grant from the Acceleration Consortium (518240), the GSK Chair Professorship, the startup fund from the Leslie Dan Faculty of Pharmacy, the operating fund from the Princess Margaret Cancer Center, the Connaught Fund (514681), the J.P. Bickell Foundation (515159), the Canada Research Chairs Program (CRC-2022-00575), the Canadian Institutes of Health Research (CIHR; PJH-185722, PJT-192011 and PJT-195669), the Natural Sciences and Engineering Research Council of Canada (RGPIN-2023-05124), the National Institutes of Health (1R01HL174773) and the Canada Foundation for Innovation John R. Evans Leaders Fund (43711). This research was made possible in part through computing resources provided by Calcul Québec (https://www.calculquebec.ca/) and the Digital Research Alliance of Canada (https://www.alliancecan.ca). Jingan Chen acknowledges the doctoral-level graduate award from the NanoMedicines Innovation Network. M.S. acknowledges the support from the CIHR Canada Graduate Scholarship Master’s (CGS-M) program. B.S. acknowledges the support from the Ontario Graduate Scholarship. T.T. acknowledges the support from the Ontario Graduate Scholarship. D.C. acknowledges the support from the CIHR CGS-M program. We acknowledge the technical support from the Center for Pharmaceutical Oncology in Flow Cytometry and Imaging Facilities, the Princess Margaret Cancer Center for the use of NMR and animal facilities and the Donnelly Sequencing Center. Illustrations in figures were created in BioRender; Li, B. https://biorender.com/z0nhgnn (2026).

Author information

Author notes

  1. These authors contributed equally: Muye Zhou, Yue Xu, Gen Li.

Authors and Affiliations

  1. Leslie Dan Faculty of Pharmacy, University of Toronto, Toronto, Ontario, Canada

    Muye Zhou, Yue Xu, Gen Li, Jingan Chen, Margarita Savguira, Breanna Seto, Fanglin Gong, Tyler Thomson, Rick Xing Ze Lu, Songtao Dong, David Chen, Christabel Eileen, Shiqi Wu & Bowen Li

  2. Institute of Biomedical Engineering, University of Toronto, Toronto, Ontario, Canada

    Jingan Chen, Margarita Savguira, Fanglin Gong, Tyler Thomson, David Chen, Gang Zheng & Bowen Li

  3. Department of Chemistry, University of Toronto, Toronto, Ontario, Canada

    Breanna Seto & Bowen Li

  4. Princess Margaret Cancer Center, University Health Network, Toronto, Ontario, Canada

    Juan Chen, Gang Zheng & Bowen Li

  5. Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada

    Gang Zheng

  6. Vector Institute for Artificial Intelligence, Toronto, Ontario, Canada

    Bowen Li

Authors
  1. Muye Zhou
    View author publications

    Search author on:PubMed Google Scholar

  2. Yue Xu
    View author publications

    Search author on:PubMed Google Scholar

  3. Gen Li
    View author publications

    Search author on:PubMed Google Scholar

  4. Jingan Chen
    View author publications

    Search author on:PubMed Google Scholar

  5. Margarita Savguira
    View author publications

    Search author on:PubMed Google Scholar

  6. Breanna Seto
    View author publications

    Search author on:PubMed Google Scholar

  7. Fanglin Gong
    View author publications

    Search author on:PubMed Google Scholar

  8. Tyler Thomson
    View author publications

    Search author on:PubMed Google Scholar

  9. Juan Chen
    View author publications

    Search author on:PubMed Google Scholar

  10. Rick Xing Ze Lu
    View author publications

    Search author on:PubMed Google Scholar

  11. Songtao Dong
    View author publications

    Search author on:PubMed Google Scholar

  12. David Chen
    View author publications

    Search author on:PubMed Google Scholar

  13. Christabel Eileen
    View author publications

    Search author on:PubMed Google Scholar

  14. Shiqi Wu
    View author publications

    Search author on:PubMed Google Scholar

  15. Gang Zheng
    View author publications

    Search author on:PubMed Google Scholar

  16. Bowen Li
    View author publications

    Search author on:PubMed Google Scholar

Contributions

M.Z. and B.L. conceptualized the study and designed the overall experimental framework. M.Z. and Y.X. developed the combinatorial lipid library. M.Z. and G.L. determined the methodological approach. M.Z., Y.X., G.L., Jingan Chen, B.S., F.G., T.T., Juan Chen, R.X.Z.L., S.D., D.C., C.E., S.W. and G.Z. conducted the experiments and performed the data analysis. B.L., M.Z. and M.S. wrote the paper. B.L. secured funding and supervised the project.

Corresponding author

Correspondence to Bowen Li.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Biotechnology thanks Roy van der Meel, Daniel Reker and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Extended data

Extended Data Fig. 1 K9 LNP enables therapeutic genome editing in a DMM-induced osteoarthritis model.

a, Schematic of the dosing schedule in the destabilization of the medial meniscus (DMM) surgical model. Mice received either a single dose or two weekly intra-articular injections of K9 LNPs (total RNA dose: 5 μg/joint; mCas9:sgMMP-13 = 3:1), starting two months after DMM surgery. Tissues were collected for analysis four months after the final dose for analysis. b, Editing efficiency at the MMP13 locus in knee joints and liver, assessed by sequencing (n = 3 biologically independent mice per group; mean ± SD; P values were calculated by ordinary one-way ANOVA). c-d, Quantification of MMP-13 expression in the knee joint by (c) ELISA (n = 4 biologically independent mice per group; mean ± SD; P values were calculated by ordinary one-way ANOVA). and (d) RT-qPCR (n = 3 biologically independent mice per group; each sample was measured in duplicate; mean ± SD; P values were calculated by ordinary one-way ANOVA). e-f, Mechanism of the MMPSense probe and representative in vivo images showing total MMP activity with varying LNP doses (e), and the quantification result (f). Blue circles represent the area of quantified fluorescence. (n = 3 biologically independent mice per group; mean ± SD; P values were calculated by ordinary one-way ANOVA). g-h, Detection of MMP-13 protein in cartilage by (g) fluorescence imaging and (h) corresponding quantification. (n = 6 biologically independent mice per group; mean ± SD; P values were calculated by ordinary one-way ANOVA). Scale bar, 100 μm. i-j, (i) SHG imaging of articular cartilage and (j) quantification of cartilage thickness and organization. (n = 3 biologically independent mice per group; mean ± SD; P values were calculated by ordinary one-way ANOVA). k, Representative histological images of knee joints from sham control, untreated, and K9-treated DMM mice stained with Safranin O and TRAP; magnified insets highlight cartilage and osteoclast features. Healthy cartilage appears deep red due to Safranin O staining of proteoglycans, while TRAP staining highlights osteoclasts in red. Scale bar, 100 μm. l-m, Osteoarthritis severity assessed using OARSI scoring (l) and quantification of osteoclast numbers from TRAP-stained sections (m) (n = 5 biologically independent mice per group; mean ± SD; P values were calculated by ordinary one-way ANOVA). n, Representative microCT 3D reconstructions of knee joints from sham, untreated, and K9-treated DMM mice, shown in frontal (left) and posterior (right) views with magnified insets below. Red arrows highlight areas of disrupted joint architecture, ectopic ossification, and osteophyte formation. o, Quantification of trabecular bone volume fraction (BV/TV, %) from microCT scans, indicating changes in subchondral bone density across treatment groups. (n = 3 biologically independent mice per group; mean ± SD; P values were calculated by ordinary one-way ANOVA).

Source data

Extended Data Fig. 2 Proteomic analysis of DMM mouse model post-K9 LNP treatment.

a, Volcano plot showing protein expression changes in knee joints following two doses of K9 LNP (mCas9 + sgTOM) treatment, as identified by LC-MS/MS. Significantly altered proteins are highlighted in red, identified using a two-sided Student’s t-test with Benjamini-Hochberg false discovery rate (FDR) correction in Spectronaut, and visualized as a volcano plot using the SRplot platform. b, KEGG pathway enrichment analysis of differentially expressed proteins between treated and untreated groups. c-h, GO enrichment analysis of differentially expressed proteins, displayed as cnetplots and bubble plots for (c, d) biological processes, (e, f) molecular functions, and (g, h) cellular components. i, j, Gene set enrichment analysis (GSEA) plots showing enriched pathways in DMM mice with or without K9 LNP treatment. KEGG and GO enrichment analyses were performed using two-sided hypergeometric tests with Benjamini-Hochberg FDR correction for multiple testing.

Supplementary information

Source data

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhou, M., Xu, Y., Li, G. et al. A multiobjective AI model for LNP engineering enhances tissue-selective mRNA delivery. Nat Biotechnol (2026). https://doi.org/10.1038/s41587-026-03109-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • DOI: https://doi.org/10.1038/s41587-026-03109-0

Search

Advanced search

Quick links

Nature Briefing: Translational Research

Sign up for the Nature Briefing: Translational Research newsletter — top stories in biotechnology, drug discovery and pharma.

Get what matters in translational research, free to your inbox weekly. Sign up for Nature Briefing: Translational Research