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:

Artificial intelligence-guided design of LNPs for in vivo targeted mRNA delivery via analysis of the spatial conformation of ionizable lipids

Nature Biomedical Engineering (2026)Cite this article

Subjects

Abstract

Efficient mRNA delivery to specific tissues requires optimized ionizable lipids, yet the role of lipid spatial conformation in organ targeting and endosomal escape remains underexplored. Here we developed a library of lipids with diverse amino heads, degradable linkers and hydrophobic tails, generating distinct three-dimensional conformations. Molecular dynamics simulations revealed the dynamic conformations of these lipids during organic–aqueous phase transitions, and experimental validation confirmed that head and tail arrangements are key determinants of delivery efficiency and organ specificity. To accelerate lipid discovery, dynamic conformation data were converted into 2D density images to train machine learning models for lipid selection. AI-guided candidates, notably lipid P1, adopted stable three-tail cone-shaped conformations that promoted IgM protein corona formation and enabled spleen-targeted mRNA delivery. In preclinical models, P1-based mRNA vaccines triggered strong antibody and T-cell responses, leading to marked tumour suppression. These results highlight the pivotal role of lipid spatial conformation and the potential of AI-driven strategies to optimize lipid nanoparticles for organ-specific mRNA delivery.

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: Rational design of ionizable lipids with different spatial conformations for building an AI model.
Fig. 2: Spatial conformations of ionizable lipids from MD simulations.
Fig. 3: The spatial conformation of ionizable lipids assists in mRNA delivery both in vitro and in vivo.
Fig. 4: AI accelerates the discovery and screening of ionizable lipids.
Fig. 5: The spatial conformation of ionizable lipids improves assembly with mRNA and endosomal escape.
Fig. 6: The spatial conformation of ionizable lipids facilitates the targeted delivery of mRNA.
Fig. 7: The protein corona endows LNPs with organ-specific mRNA delivery ability in vivo.
Fig. 8: Spleen-targeting LNP-mediated vaccination induces both antibody-based and T cell-based antitumour immune responses in melanoma tumour models.

Similar content being viewed by others

Data availability

All relevant data supporting the findings of this study are available within the Article, its Supplementary Information files or Source Data files. Source data are provided with this paper.

Code availability

The custom code for constructing the 2D density maps of lipids in ML is available in Supplementary Information files.

References

  1. Su, L.-J. et al. Delivery of mRNA for cancer therapy: progress and prospects. Nano Today 53, 102013 (2023).

    Article  CAS  Google Scholar 

  2. Huang, X. G. et al. The landscape of mRNA nanomedicine. Nat. Med. 28, 2273–2287 (2022).

    Article  CAS  PubMed  Google Scholar 

  3. 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 

  4. 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 

  5. Zhang, Y., Sun, C., Wang, C., Jankovic, K. E. & Dong, Y. Lipids and lipid derivatives for RNA delivery. Chem. Rev. 121, 12181–12277 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Sabnis, S. et al. A novel amino lipid series for mRNA delivery: improved endosomal escape and sustained pharmacology and safety in non-human primates. Mol. Ther. 26, 1509–1519 (2018).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  7. Akinc, A. et al. The Onpattro story and the clinical translation of nanomedicines containing nucleic acid-based drugs. Nat. Nanotechnol. 14, 1084–1087 (2019).

    Article  CAS  PubMed  Google Scholar 

  8. Zhang, Y. et al. Close the cancer–immunity cycle by integrating lipid nanoparticle–mRNA formulations and dendritic cell therapy. Nat. Nanotechnol. 18, 1364–1374 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  9. Lee, S. M. et al. A systematic study of unsaturation in lipid nanoparticles leads to improved mRNA transfection in vivo. Angew. Chem. Int. Ed. 60, 5848–5853 (2021).

    Article  CAS  Google Scholar 

  10. Hajj, K. A. et al. Branched-tail lipid nanoparticles potently deliver mRNA in vivo due to enhanced ionization at endosomal pH. Small 15, e1805097 (2019).

    Article  PubMed  Google Scholar 

  11. Hou, X. et al. Vitamin lipid nanoparticles enable adoptive macrophage transfer for the treatment of multidrug-resistant bacterial sepsis. Nat. Nanotechnol. 15, 41–46 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  12. Zhao, X. et al. Imidazole-based synthetic lipidoids for in vivo mRNA delivery into primary T lymphocytes. Angew. Chem. Int. Ed. 59, 20083–20089 (2020).

    Article  CAS  Google Scholar 

  13. 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 

  14. Cheng, Q. et al. Selective organ targeting (SORT) nanoparticles for tissue-specific mRNA delivery and CRISPR-Cas gene editing. Nat. Nanotechnol. 15, 313–320 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  15. Liu, S. et al. Membrane-destabilizing ionizable phospholipids for organ-selective mRNA delivery and CRISPR-Cas gene editing. Nat. Mater. 20, 701–710 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Hatit, M. Z. C. et al. Nanoparticle stereochemistry-dependent endocytic processing improves in vivo mRNA delivery. Nat. Chem. 15, 508–515 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  17. Han, X. et al. An ionizable lipid toolbox for RNA delivery. Nat. Commun. 12, 7233 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  18. Dong, W. et al. Multicomponent synthesis of imidazole-based ionizable lipids for highly efficient and spleen-selective messenger RNA delivery. J. Am. Chem. Soc. 146, 15085–15095 (2024).

    Article  CAS  PubMed  Google Scholar 

  19. Chen, I. J. & Foloppe, N. Is conformational sampling of drug-like molecules a solved problem? Drug Dev. Res. 72, 85–94 (2010).

    Article  Google Scholar 

  20. 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 

  21. 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 

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

    Article  CAS  PubMed  Google Scholar 

  23. Philipp, J. et al. pH-dependent structural transitions in cationic ionizable lipid mesophases are critical for lipid nanoparticle function. Proc. Natl Acad. Sci. USA 120, e2310491120 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  24. Yu, H. et al. Real-time pH-dependent self-assembly of ionisable lipids from COVID-19 vaccines and in situ nucleic acid complexation. Angew. Chem. Int. Ed. 62, e202304977 (2023).

    Article  CAS  Google Scholar 

  25. Akinc, A. et al. A combinatorial library of lipid-like materials for delivery of RNAi therapeutics. Nat. Biotechnol. 26, 561–569 (2008).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  26. Patel, P., Ibrahim, N. M. & Cheng, K. The importance of apparent pKa in the development of nanoparticles encapsulating siRNA and mRNA. Trends Pharmacol. Sci. 42, 448–460 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  27. Jayaraman, M. et al. Maximizing the potency of siRNA lipid nanoparticles for hepatic gene silencing in vivo. Angew. Chem. Int. Ed. 51, 8529–8533 (2012).

    Article  CAS  Google Scholar 

  28. Zong, Y., Lin, Y., Wei, T. & Cheng, Q. Lipid nanoparticle (LNP) enables mRNA delivery for cancer therapy. Adv. Mater. 35, e2303261 (2023).

    Article  PubMed  Google Scholar 

  29. Ouyang, R., Curtarolo, S., Ahmetcik, E., Scheffler, M. & Ghiringhelli, L. M. SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates. Phys. Rev. Mater. 2, 083802 (2018).

    Article  CAS  Google Scholar 

  30. Ouyang, R., Yoo, S.-H. & Jang, W. Small dataset machine-learning approach for efficient design space exploration: engineering ZnTe-based high-entropy alloys for water splitting. npj Comput. Mater. 10, 166 (2024).

    Article  Google Scholar 

  31. Liu, X. et al. Finding predictive models for singlet fission by machine learning. npj Comput. Mater. 8, 70 (2022).

    Article  CAS  Google Scholar 

  32. Wang, T. et al. Nature of metal–support interaction for metal catalysts on oxide supports. Science 386, 915–920 (2024).

    Article  CAS  PubMed  Google Scholar 

  33. Chen, V. et al. Applying interpretable machine learning in computational biology—pitfalls, recommendations and opportunities for new developments. Nat. Methods 21, 1454–1461 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  34. Nel, A. E. et al. Understanding biophysicochemical interactions at the nano–bio interface. Nat. Mater. 8, 543–557 (2009).

    Article  CAS  PubMed  Google Scholar 

  35. Dilliard, S. A., Cheng, Q. & Siegwart, D. J. On the mechanism of tissue-specific mRNA delivery by selective organ targeting nanoparticles. Proc. Natl Acad. Sci. USA 118, e2109256118 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  36. Schvartz, I., Seger, D. & Shaltiel, S. Vitronectin. Int. J. Biochem. Cell Biol. 31, 539–544 (1999).

    Article  CAS  PubMed  Google Scholar 

  37. Dormond, O., Foletti, A., Paroz, C. & Rüegg, C. NSAIDs inhibit alpha V beta 3 integrin-mediated and Cdc42/Rac-dependent endothelial-cell spreading, migration and angiogenesis. Nat. Med. 7, 1041–1047 (2001).

    Article  CAS  PubMed  Google Scholar 

  38. Ehrenstein, M. R. & Notley, C. A. The importance of natural IgM: scavenger, protector and regulator. Nat. Rev. Immunol. 10, 778–786 (2010).

    Article  CAS  PubMed  Google Scholar 

  39. Li, Y. et al. Immunoglobulin M perception by FcμR. Nature 615, 907–912 (2023).

    Article  CAS  PubMed  Google Scholar 

  40. Helmink, B. A. et al. B cells and tertiary lymphoid structures promote immunotherapy response. Nature 577, 549–555 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  41. Hu, X. et al. Landscape of B cell immunity and related immune evasion in human cancers. Nat. Genet. 51, 560–567 (2019).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  42. Zhu, Y. et al. Screening for lipid nanoparticles that modulate the immune activity of helper T cells towards enhanced antitumour activity. Nat. Biomed. Eng. 8, 544–560 (2024).

    Article  CAS  PubMed  Google Scholar 

  43. Zhao, S. et al. Acid-degradable lipid nanoparticles enhance the delivery of mRNA. Nat. Nanotechnol. 19, 1702–1711 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  44. 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 

  45. Chaudhary, N. et al. Amine headgroups in ionizable lipids drive immune responses to lipid nanoparticles by binding to the receptors TLR4 and CD1d. Nat. Biomed. Eng. 8, 1483–1498 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  46. Miao, L. et al. Delivery of mRNA vaccines with heterocyclic lipids increases anti-tumor efficacy by STING-mediated immune cell activation. Nat. Biotechnol. 37, 1174–1185 (2019).

    Article  CAS  PubMed  Google Scholar 

  47. He, Z. et al. A multidimensional approach to modulating ionizable lipids for high-performing and organ-selective mRNA delivery. Angew. Chem. Int. Ed. 62, e202310401 (2023).

  48. Xue, L. et al. Combinatorial design of siloxane-incorporated lipid nanoparticles augments intracellular processing for tissue-specific mRNA therapeutic delivery. Nat. Nanotechnol. 20, 132–143 (2025).

    Article  CAS  PubMed  Google Scholar 

  49. Han, X. et al. Fast and facile synthesis of amidine-incorporated degradable lipids for versatile mRNA delivery in vivo. Nat. Chem. 16, 1687–1697 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  50. Van Der Spoel, D. et al. GROMACS: fast, flexible, and free. J. Comput. Chem. 26, 1701–1718 (2005).

    Article  PubMed  Google Scholar 

  51. Lee, J. et al. CHARMM-GUI input generator for NAMD, GROMACS, AMBER, OpenMM, and CHARMM/OpenMM simulations using the CHARMM36 additive force field. J. Chem. Theory Comput. 12, 405–413 (2016).

    Article  CAS  PubMed  Google Scholar 

  52. Huang, J. & MacKerell, A. D. Jr. CHARMM36 all-atom additive protein force field: validation based on comparison to NMR data. J. Comput. Chem. 34, 2135–2145 (2013).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  53. Vanommeslaeghe, K. et al. CHARMM general force field: a force field for drug-like molecules compatible with the CHARMM all-atom additive biological force fields. J. Comput. Chem. 31, 671–690 (2010).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  54. Yu, W., He, X., Vanommeslaeghe, K. & MacKerell, A. D. Jr. Extension of the CHARMM General Force Field to sulfonyl-containing compounds and its utility in biomolecular simulations. J. Comput. Chem. 33, 2451–2468 (2012).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  55. Sarzynska, J., Popenda, M., Antczak, M. & Szachniuk, M. RNA tertiary structure prediction using RNAComposer in CASP15. Proteins 91, 1790–1799 (2023).

    Article  CAS  PubMed  Google Scholar 

  56. Popenda, M. et al. Automated 3D structure composition for large RNAs. Nucleic Acids Res. 40, e112 (2012).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  57. Jo, S., Kim, T., Iyer, V. G. & Im, W. CHARMM-GUI: a web-based graphical user interface for CHARMM. J. Comput. Chem. 29, 1859–1865 (2008).

    Article  CAS  PubMed  Google Scholar 

  58. Humphrey, W., Dalke, A. & Schulten, K. VMD: visual molecular dynamics. J. Mol. Graph. 14, 27–28 (1996).

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the National Key R&D Program of China (2022YFA1205700 to Y.-X.L. and H.W., 2024YFD2101600 to Y.-X.L., 2024YFA1509600 and 2022YFA1203200 to Y.G.), the National Natural Science Foundation of China (32371458 to Y.-X.L., 22273014 to Y.G.), the Beijing Natural Science Foundation (L242036 to Y.-X.L.), the Basic Research Cooperation Special Foundation of Beijing–Tianjin–Hebei (22J00017 to Y.-X.L.) and the Strategic Priority Research Program of the Chinese Academy of Sciences (XDB1030000 to Y.G.). Y.-X. L. acknowledges the start-up funding from the National Center for Nanoscience and Technology and the Chinese Academy of Sciences. The funders had no roles in the study design, data collection and analysis, decision to publish, and preparation of the manuscript.

Author information

Author notes

  1. These authors contributed equally: Lin-Jia Su, Nan-Nan Wang, Rui Luo, Zi-Han Ji.

Authors and Affiliations

  1. CAS Key Laboratory for Biomedical Effects of Nanomaterials and Nanosafety, National Center for Nanoscience and Technology (NCNST), Beijing, P. R. China

    Lin-Jia Su, Nan-Nan Wang, Zi-Han Ji, Haiyan Gu, Chao Yang, Mo-Xi Xu, Juchen Zhang, Qinghua Chen, Meng-Zhen Yu, Chenglin Li, Yuliang Zhao, Yi Wang, Hao Wang & Yao-Xin Lin

  2. University of Chinese Academy of Sciences (UCAS), Beijing, P. R. China

    Nan-Nan Wang, Rui Luo, Zi-Han Ji, Mo-Xi Xu, Meng-Zhen Yu, Kelong Fan, Yurui Gao, Hao Wang & Yao-Xin Lin

  3. Laboratory of Theoretical and Computational Nanoscience, National Center for Nanoscience and Technology (NCNST), Beijing, P. R. China

    Rui Luo & Yurui Gao

  4. Tianjin Key Laboratory of Biomedical Materials, Key Laboratory of Biomaterials and Nanotechnology for Cancer Immunotherapy, Institute of Biomedical Engineering, Chinese Academy of Medical Sciences and Peking Union Medical College, Tianjin, P. R. China

    Juchen Zhang & Lin Mei

  5. CAS Engineering Laboratory for Nanozyme, Key Laboratory of Biomacromolecules (CAS), CAS Center for Excellence in Biomacromolecules, Institute of Biophysics, Chinese Academy of Sciences, Beijing, P. R. China

    Kelong Fan

  6. College of Chemistry and Materials Science, and Institute of Nanotechnology and Intelligence (INAI), Jinan University, Guangzhou, P. R. China

    Yuliang Zhao

Authors
  1. Lin-Jia Su
    View author publications

    Search author on:PubMed Google Scholar

  2. Nan-Nan Wang
    View author publications

    Search author on:PubMed Google Scholar

  3. Rui Luo
    View author publications

    Search author on:PubMed Google Scholar

  4. Zi-Han Ji
    View author publications

    Search author on:PubMed Google Scholar

  5. Haiyan Gu
    View author publications

    Search author on:PubMed Google Scholar

  6. Chao Yang
    View author publications

    Search author on:PubMed Google Scholar

  7. Mo-Xi Xu
    View author publications

    Search author on:PubMed Google Scholar

  8. Juchen Zhang
    View author publications

    Search author on:PubMed Google Scholar

  9. Qinghua Chen
    View author publications

    Search author on:PubMed Google Scholar

  10. Meng-Zhen Yu
    View author publications

    Search author on:PubMed Google Scholar

  11. Chenglin Li
    View author publications

    Search author on:PubMed Google Scholar

  12. Kelong Fan
    View author publications

    Search author on:PubMed Google Scholar

  13. Lin Mei
    View author publications

    Search author on:PubMed Google Scholar

  14. Yuliang Zhao
    View author publications

    Search author on:PubMed Google Scholar

  15. Yi Wang
    View author publications

    Search author on:PubMed Google Scholar

  16. Yurui Gao
    View author publications

    Search author on:PubMed Google Scholar

  17. Hao Wang
    View author publications

    Search author on:PubMed Google Scholar

  18. Yao-Xin Lin
    View author publications

    Search author on:PubMed Google Scholar

Contributions

Y.-X.L. and L.-J.S. conceived the idea and designed the experiments. Y.W. and Y.-X.L. directed this project. L.-J.S., Z.-H.J., M.-X.X., M.-Z.Y., C.L. and J.Z. performed the synthesis experiments of ionizable lipids. L.-J.S., C.Y., Q.C. and Z.-H.J. performed the in vitro and in vivo screening studies. L.-J.S. collected and analysed the cryo-transmission electron microscopy data under the supervision of K.F.; R.L. conducted the MD experiments and machine learning under the supervision of Y.G.; L.-J.S. and Z.-H.J. collected and analysed the proteomics data. N.-N.W., L.-J.S. and Z.-H.J. performed the organ-targeting experiments. N.-N.W. and H.G. performed the mRNA vaccine experiments under the supervision of Y.W. and Y.-X.L.; L.M., Y.Z. and H.W. provided reagents and conceptual advice. Z.-H.J., L.-J.S., R.L. and N.-N.W. prepared figures and the first draft of the paper. Y.W., Y.-X.L., Y.G. and H.W. revised the paper. All authors discussed the results and computational methods and commented on the paper.

Corresponding authors

Correspondence to Yi Wang, Yurui Gao, Hao Wang or Yao-Xin Lin.

Ethics declarations

Competing interests

Y.-X.L., L.-J.S., Y.G. and R.L. have applied for patent applications (202510268720.4, China, 2025; 202411880079.1, China, 2024) related to this study. Y.-X.L. and J.Z. are founders and hold equity in Messerna BioTech. The other authors declare no competing interests.

Peer review

Peer review information

Nature Biomedical Engineering thanks the anonymous reviewers for their contribution to the peer review of this work. Peer reviewer reports are available.

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 Feature extraction for ML training.

a, Twenty-two 3D spatial conformation features extracted from molecular density maps based on geometric properties (for example, angle, width and length). b, Six foundational 2D chemical structure features. c, Pearson correlation coefficient (PCC) matrix analysis of the 28 features. d, Feature importance analysis of the twenty-eight features, revealing their relative contribution to the model’s predictive performance. e, Prediction formula of the best-performing ML model (Model 1): ypre = c1D1 + c2D2 + c3D3 + c4D4 + c5D5 + c0, with coefficients and feature descriptions listed in the table.

Source data

Extended Data Fig. 2 ML model selection and testing.

a, Performance evaluation of the top four ML models based on accuracy, precision, recall, and F1-score, showing Model 1 as the best one. b, Comparison of ML-predicted and experimental measured delivery efficiencies for 15 test lipids, with MC3 served as a benchmark. c, Luciferase expression after treatment of HEK293T cells with LNPs (1 μg mL−1 mFluc, 24 h, n = 3 biologically independent samples). d, GFP expression after treatment of HEK293T cells with LNPs (1 μg mL−1 mGFP, 24 h, n = 3 independent biological samples). e, Representative confocal images of d. Scale bar, 50 μm. The data are presented as the mean ± s.d.

Source data

Extended Data Fig. 3 Changes in spatial conformations of lipid P1 in different media.

Conformational change of lipid P1 upon transition from ethanol to an acidic aqueous phase during LNP preparation. Part of this figure was created with Biorender.com.

Extended Data Fig. 4 Changes in spatial conformations of lipid P1 and lipid 9 during protonation.

Conformational change of lipids P1 (a) and 9 (b) in the medium transitioning from neutral pH to acidic pH, simulating the endosomal escape process.

Extended Data Fig. 5 An in-depth performance evaluation of lipid T2.

a, The chemical structure and spatial conformation of lipid T2. b, Representative bioluminescence images of the local injection alongside quantification of lipid T2 and ALC-0315 (positive control) after i.m. injection (0.75 mg kg−1 mFluc, 6 h, n = 3 biologically independent mice). c, Representative snapshots of MD simulations demonstrating the binding processes of lipids T2 and ALC-0315 (positive control). d, Calculated binding probability of lipid T2/ALC-0315 (positive control) to mRNA (n = 4 independent calculations). e, Snapshots of MD simulations showing the rapid binding of excess lipid T2/ALC-0315 (positive control) to mRNA at 10 ns and 30 ns. f, Binding ratio of lipid T2/ALC-0315 (positive control). g, Representative confocal images of the cellular uptake of lipids T2 and ALC-0315 (positive control) LNPs encapsulating Cy5-labelled mRNA in HEK293T cells at 2 h, 4 h, and 6 h, respectively. Scale bar, 10 μm. h, Quantification of cellular uptake in g (n = 6 biologically independent samples). i, Representative magnified confocal images and fluorescence colocalization analysis profiles of HEK293T cells after coincubation for 6 h, from three independent experiments. Scale bar, 5 μm. The data are all presented as the mean ± s.d. Statistical significance in d was analysed using a two-tailed unpaired Student’s t test. P values < 0.05 (*), P < 0.01 (**), P < 0.001 (***) and P < 0.0001 (****) were considered statistically significant. ns, not significant.

Source data

Supplementary information

Supplementary Information (download PDF )

Supplementary Figs. 1–32, Tables 1–5, Notes and Methods.

Reporting Summary (download PDF )

Peer Review File (download PDF )

Supplementary Data 1 (download XLSX )

Source data for Supplementary Figs. 8–10, 13, 16, 18–21, 23, 25, 26, 28, 31, 32.

Supplementary Data 2 (download XLSX )

Source data for spatial conformation density maps in Figs. 2b, 4c, 5a, 5h, 6d; Extended Data Figs. 3, 4, 5a; Supplementary Figs. 2a, 3a, 4a, 5a, 6a, 11a, 14a, 15a, 17, 22, 24a.

Supplementary Data 3 (download ZIP )

Source data for machine learning models.

Supplementary Data 4 (download ZIP )

Source data for spatial conformation density maps preparation.

Supplementary Code 1 (download ZIP )

Source code for spatial conformation density maps data acquisition.

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

Su, LJ., Wang, NN., Luo, R. et al. Artificial intelligence-guided design of LNPs for in vivo targeted mRNA delivery via analysis of the spatial conformation of ionizable lipids. Nat. Biomed. Eng (2026). https://doi.org/10.1038/s41551-026-01640-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • DOI: https://doi.org/10.1038/s41551-026-01640-8

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