Rational Design of Safer Inorganic Nanoparticles via Mechanistic Modeling-Informed Machine Learning
Source abstract
Abstract
High Resolution Image Download MS PowerPoint Slide The safety of inorganic nanoparticles (NPs) remains a critical challenge for their clinical translation. To address this, we developed a machine learning (ML) framework that predicts NP toxicity both in vitro and in vivo, leveraging physicochemical properties and experimental conditions. A curated in vitro cytotoxicity dataset was used to train and validate binary classification models, with top-performing models undergoing explainability analysis to identify key determinants of toxicity and establish structure-toxicity relationships. External testing with diverse inorganic NPs validated the predictive accuracy of the framework for in vitro settings. To enable organ-specific toxicity predictions in vivo, we integrated a physiologically based pharmacokinetic (PBPK) model into the ML pipeline to quantify NP exposure across organs. Retraining the ML models with PBPK-derived exposure metrics yielded robust predictions of organ-specific nanotoxicity, further validating the framework. This PBPK-informed ML approach can thus serve as a potential alternative approach to streamline NP safety assessment, enabling the rational design of safer NPs and expediting their clinical translation.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Nanoparticle-Based Drug Delivery · Nanoparticles: synthesis and applications · Graphene and Nanomaterials Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Mathematics in Medicine Program, Department of Medicine
Houston Methodist Research Institute
Physiology, Biophysics, and Systems Biology Program, Graduate School of Medical Sciences
Weill Cornell Medicine
Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology
Department of Chemical, Materials, and Industrial Production Engineering
University of Naples Federico II
Department of Medicine, Houston Methodist
Department of Medicine
Neal Cancer Center
Department of Imaging Physics
University of Texas M.D. Anderson Cancer Center
Rutgers Cancer Institute
Division of Cancer Biology, Department of Radiation Oncology
Rutgers New Jersey Medical School
Division of Hematology/Oncology, Department of Medicine
Department of Chemical and Biological Engineering
University of New Mexico
College of Pharmacy
Department of Physiology and Biophysics
Weill Cornell Medical College
Department of Electrical and Computer Engineering
University of Houston
Funding
National Cancer Institute · National Institute of Biomedical Imaging and Bioengineering
References (82)
Show source-provided references
1. 10.1016/j.addr.2020.06.02010.1016/j.addr.2020.06.020 ↗
2. 10.1038/s41573-020-0090-810.1038/s41573-020-0090-8 ↗
3. 10.1007/s13346-024-01579-w10.1007/s13346-024-01579-w ↗
4. 10.1007/s10971-021-05695-810.1007/s10971-021-05695-8 ↗
5. 10.1021/acsmedchemlett.0c0007510.1021/acsmedchemlett.0c00075 ↗
6. 10.1186/s11671-023-03943-010.1186/s11671-023-03943-0 ↗
7. 10.1038/s41467-021-23250-510.1038/s41467-021-23250-5 ↗
8. 10.1038/s41566-024-01517-910.1038/s41566-024-01517-9 ↗
9. 10.1021/acsnano.4c0613810.1021/acsnano.4c06138 ↗
10. 10.1021/acsabm.4c0131810.1021/acsabm.4c01318 ↗
11. 10.1016/j.coche.2022.10087210.1016/j.coche.2022.100872 ↗
12. 10.1038/s41420-024-02236-410.1038/s41420-024-02236-4 ↗
13. 10.1021/acs.analchem.9b0499610.1021/acs.analchem.9b04996 ↗
14. 10.1038/s41467-023-39423-310.1038/s41467-023-39423-3 ↗
15. 10.1038/s44222-024-00257-310.1038/s44222-024-00257-3 ↗
16. 10.1038/s42003-024-06043-610.1038/s42003-024-06043-6 ↗
17. 10.1002/btm2.1024610.1002/btm2.10246 ↗
18. 10.1021/acs.accounts.9b0012610.1021/acs.accounts.9b00126 ↗
19. 10.1038/s41467-024-48838-510.1038/s41467-024-48838-5 ↗
20. 10.1038/nmat471810.1038/nmat4718 ↗
21. 10.1021/acsnano.3c0403710.1021/acsnano.3c04037 ↗
22. 10.1038/natrevmats.2016.1410.1038/natrevmats.2016.14 ↗
23. 10.1038/s41598-023-37178-x10.1038/s41598-023-37178-x ↗
24. 10.1186/s12951-020-00599-110.1186/s12951-020-00599-1 ↗
25. 10.1002/mco2.32710.1002/mco2.327 ↗
26. 10.1016/j.addr.2019.07.00610.1016/j.addr.2019.07.006 ↗
27. 10.1016/j.jconrel.2020.07.01410.1016/j.jconrel.2020.07.014 ↗
28. 10.1016/j.addr.2023.11470810.1016/j.addr.2023.114708 ↗
29. 10.1186/s11671-024-04118-110.1186/s11671-024-04118-1 ↗
30. 10.1155/2021/995444310.1155/2021/9954443 ↗
31. 10.1038/s41467-018-06730-z10.1038/s41467-018-06730-z ↗
32. 10.1186/s11671-020-03344-710.1186/s11671-020-03344-7 ↗
33. 10.3389/fgene.2021.72825010.3389/fgene.2021.728250 ↗
34. 10.1073/pnas.200473611710.1073/pnas.2004736117 ↗
35. 10.1186/s11671-017-2242-210.1186/s11671-017-2242-2 ↗
36. 10.1016/j.addr.2021.11402210.1016/j.addr.2021.114022 ↗
37. 10.1016/j.ecoenv.2022.11395510.1016/j.ecoenv.2022.113955 ↗
38. 10.1021/acsnano.2c1196810.1021/acsnano.2c11968 ↗
39. 10.1021/acsnano.8b0756210.1021/acsnano.8b07562 ↗
40. 10.1021/acsanm.4c0226910.1021/acsanm.4c02269 ↗
41. 10.1126/sciadv.abf413010.1126/sciadv.abf4130 ↗
42. 10.1186/s12989-023-00530-010.1186/s12989-023-00530-0 ↗
43. 10.1016/j.tox.2023.15369710.1016/j.tox.2023.153697 ↗
44. 10.1039/C4NR01285B10.1039/C4NR01285B ↗
45. 10.1080/17435390.2017.137956710.1080/17435390.2017.1379567 ↗
46. 10.1186/s12951-024-02660-910.1186/s12951-024-02660-9 ↗
47. 10.1016/j.jtbi.2017.01.01210.1016/j.jtbi.2017.01.012 ↗
48. 10.3390/molecules2506129210.3390/molecules25061292 ↗
49. 10.1021/acs.jcim.9b0029510.1021/acs.jcim.9b00295 ↗
50. 10.1186/s13321-021-00508-010.1186/s13321-021-00508-0 ↗
51. 10.1080/17435390.2019.159520610.1080/17435390.2019.1595206 ↗
52. 10.1007/s11051-023-05806-210.1007/s11051-023-05806-2 ↗
53. 10.1016/j.tiv.2022.10541810.1016/j.tiv.2022.105418 ↗
54. 10.1016/j.envint.2022.10725810.1016/j.envint.2022.107258 ↗
55. 10.1038/s41598-018-24483-z10.1038/s41598-018-24483-z ↗
56. Bertagnolli, M. M. Statement on catalyzing the development of novel alternative methods. National Institutes of Health, 2024. https://www.nih.gov/about-nih/who-we-are/nih-director/statements/statement-catalyzing-development-novel-alternatives-methods (accessed 2024.
57. 10.1039/D0EN01240H10.1039/D0EN01240H ↗
58. 10.1007/s10462-023-10652-810.1007/s10462-023-10652-8 ↗
59. 10.1145/290707010.1145/2907070 ↗
60. Lundberg S. M. · 2017
61. 10.1186/s12951-020-00747-710.1186/s12951-020-00747-7 ↗
62. 10.1002/etc.273510.1002/etc.2735 ↗
63. 10.1007/s10068-019-00623-710.1007/s10068-019-00623-7 ↗
64. 10.1002/smll.20070037810.1002/smll.200700378 ↗
65. 10.1038/s41467-024-50020-w10.1038/s41467-024-50020-w ↗
66. 10.1186/s11671-018-2457-x10.1186/s11671-018-2457-x ↗
67. 10.1111/cpr.1219210.1111/cpr.12192 ↗
68. 10.1021/nn305929510.1021/nn3059295 ↗
69. 10.1248/jhs.51.20210.1248/jhs.51.202 ↗
70. 10.2147/IJN.S6508610.2147/IJN.S65086 ↗
71. 10.1016/j.toxlet.2009.07.00910.1016/j.toxlet.2009.07.009 ↗
72. 10.1186/1743-8977-7-2510.1186/1743-8977-7-25 ↗
73. 10.1002/jat.138510.1002/jat.1385 ↗
74. 10.1186/s12989-022-00465-y10.1186/s12989-022-00465-y ↗
75. 10.1021/acsnano.3c0762110.1021/acsnano.3c07621 ↗
76. 10.1002/adhm.20240296610.1002/adhm.202402966 ↗
77. 10.1002/adfm.20240417910.1002/adfm.202404179 ↗
78. 10.1101/2024.09.18.2431394110.1101/2024.09.18.24313941 ↗
79. 10.1016/j.csbj.2020.02.01410.1016/j.csbj.2020.02.014 ↗
80. 10.1002/smll.20190374710.1002/smll.201903747 ↗
81. 10.1007/s10544-019-0380-210.1007/s10544-019-0380-2 ↗
82. 10.1023/A:101894361312210.1023/A:1018943613122 ↗