journal article·2025-09Open access

Machine Learning Guided Design of Nerve‐On‐A‐Chip Platforms with Promoted Neurite Outgrowth

Tsai‐Chun Chung, Chu‐Chun Liang, Min‐Wei Huang, Tianle Chen, Joshua M. Little, Snehi Shrestha, Yi‐Chen Ethan Li, I‐Chi Lee, Po‐Yen Chen

Advanced Functional Materials· Volume 35· Issue 38

Abstract

Abstract Nerve‐on‐a‐chip platforms transform neurological research by providing customized microenvironments, thereby reducing reliance on animal testing. However, optimizing these biochips remains challenging due to complex interdependencies among critical fabrication parameters. Here, a machine learning (ML)–guided workflow is developed combining cell viability assays, data augmentation, ensemble modeling, and model interpretation to predict the viability of isolated cortical rat neural stem/progenitor cells (rat NSPCs) and extract data‐driven insights. Initially, rat NSPCs are cultured on 102 distinct hydrogels fabricated with varying parameters, and their attachment conditions and cell viability are evaluated. To mitigate overfitting issue, 10–20 times more virtual data points are generated from characterized NSPC attachment and viability data. A support vector machine classifier is trained on attachment data to define a feasible parameter space where NSPCs consistently adhere to biointerfaces. Subsequently, a prediction model is constructed to predict rat NSPC viability. Model interpretation reveals that biointerface stiffness is the primary factor for rat NSPC attachment and viability, with peptide loading also contributing. Leveraging these insights, the stiffness of a nerve‐on‐a‐chip platform is optimized by adjusting the bilayer number of a polyelectrolyte multilayer, successfully enhancing neurite outgrowth. This versatile ML workflow can be extended to other bioengineering systems.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Machine Learning in Materials Science · Advanced Memory and Neural Computing · Neuroscience and Neural Engineering

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Chemical and Biomolecular Engineering University of Maryland College Park MD 20742 USA

Department of Biomedical Engineering and Environmental Sciences National Tsing Hua University Hsinchu 300044 Taiwan

Department of Chemical Engineering Feng Chia University Taichung 407102 Taiwan

Maryland Robotics Center College Park MD 20742 USA

Artificial Intelligence Interdisciplinary Institute College Park MD USA

Funding

Ministry of Science and Technology, Taiwan · Air Force Office of Scientific Research · University of Maryland

References (69)

Show source-provided references
1. 10.1038/s41467-018-06895-710.1038/s41467-018-06895-7 ↗
2. 10.1038/nmeth.120310.1038/nmeth.1203 ↗
3. 10.1126/science.aaw789410.1126/science.aaw7894 ↗
4. 10.1002/advs.20220753610.1002/advs.202207536 ↗
5. 10.1002/adhm.20150039710.1002/adhm.201500397 ↗
6. 10.1016/j.copbio.2016.11.01910.1016/j.copbio.2016.11.019 ↗
7. 10.1039/C4LC01513D10.1039/C4LC01513D ↗
8. 10.1038/s41578-018-0034-710.1038/s41578-018-0034-7 ↗
9. 10.1007/s12035-019-01777-510.1007/s12035-019-01777-5 ↗
10. 10.1021/acschemneuro.8b0048310.1021/acschemneuro.8b00483 ↗
11. 10.1073/pnas.080861610510.1073/pnas.0808616105 ↗
12. 10.3390/cells1008204510.3390/cells10082045 ↗
13. 10.1038/s41380-024-02827-810.1038/s41380-024-02827-8 ↗
14. 10.1016/j.cej.2024.15021010.1016/j.cej.2024.150210 ↗
15. 10.1016/j.biomaterials.2011.09.07310.1016/j.biomaterials.2011.09.073 ↗
16. 10.1016/j.actbio.2017.01.02310.1016/j.actbio.2017.01.023 ↗
17. 10.1021/acsbiomaterials.0c0118410.1021/acsbiomaterials.0c01184 ↗
18. 10.1002/adma.20190204210.1002/adma.201902042 ↗
19. 10.1038/nmeth.383910.1038/nmeth.3839 ↗
20. 10.1002/adma.20130295810.1002/adma.201302958 ↗
21. 10.1021/acsami.9b0851010.1021/acsami.9b08510 ↗
22. 10.1073/pnas.19245719910.1073/pnas.192457199 ↗
23. 10.1021/acsami.3c0807010.1021/acsami.3c08070 ↗
24. 10.1039/c003385e10.1039/c003385e ↗
25. 10.1038/nrn172710.1038/nrn1727 ↗
26. 10.1016/j.biomaterials.2022.12153110.1016/j.biomaterials.2022.121531 ↗
27. 10.1063/1.512055510.1063/1.5120555 ↗
28. 10.1016/j.addr.2023.11477710.1016/j.addr.2023.114777 ↗
29. 10.1002/jnr.2479410.1002/jnr.24794 ↗
30. 10.1039/C7IB00051K10.1039/C7IB00051K ↗
31. 10.1039/b918640a10.1039/b918640a ↗
32. 10.1039/b922143c10.1039/b922143c ↗
33. 10.1038/s41467-023-37187-410.1038/s41467-023-37187-4 ↗
34. 10.1038/s41586-018-0337-210.1038/s41586-018-0337-2 ↗
35. 10.1038/s42256-020-00236-410.1038/s42256-020-00236-4 ↗
36. 10.1038/s41524-019-0221-010.1038/s41524-019-0221-0 ↗
37. 10.1038/s41560-022-01112-810.1038/s41560-022-01112-8 ↗
38. 10.1021/acs.chemrev.2c0006110.1021/acs.chemrev.2c00061 ↗
39. 10.1038/s41573-019-0024-510.1038/s41573-019-0024-5 ↗
40. 10.1016/j.drudis.2014.10.01210.1016/j.drudis.2014.10.012 ↗
41. 10.1038/s41467-020-17835-910.1038/s41467-020-17835-9 ↗
42. 10.1021/acsnano.9b0386410.1021/acsnano.9b03864 ↗
43. 10.1038/s41524-018-0081-z10.1038/s41524-018-0081-z ↗
44. 10.1038/s41524-021-00678-310.1038/s41524-021-00678-3 ↗
45. 10.1016/j.mtbio.2020.10004310.1016/j.mtbio.2020.100043 ↗
46. 10.1002/adbi.20220022710.1002/adbi.202200227 ↗
47. 10.1038/s41524-022-00929-x10.1038/s41524-022-00929-x ↗
48. 10.1186/s40537-023-00727-210.1186/s40537-023-00727-2 ↗
49. 10.1002/biot.20200035510.1002/biot.202000355 ↗
50. 10.1016/j.bios.2018.08.07510.1016/j.bios.2018.08.075 ↗
51. 10.1038/srep0478410.1038/srep04784 ↗
52. 10.3892/etm.2020.928510.3892/etm.2020.9285 ↗
53. 10.1016/j.actbio.2012.04.03610.1016/j.actbio.2012.04.036 ↗
54. 10.1002/mabi.20120047110.1002/mabi.201200471 ↗
55. 10.3390/gels808049610.3390/gels8080496 ↗
56. 10.1038/s41596-021-00495-410.1038/s41596-021-00495-4 ↗
57. 10.1126/science.119103510.1126/science.1191035 ↗
58. 10.1038/s41467-021-22758-010.1038/s41467-021-22758-0 ↗
59. 10.1002/adma.20221063710.1002/adma.202210637 ↗
60. 10.1038/s41536-023-00277-410.1038/s41536-023-00277-4 ↗
61. 10.7150/thno.8726610.7150/thno.87266 ↗
62. 10.1038/s41467-023-42415-y10.1038/s41467-023-42415-y ↗
63. 10.1038/s41578-021-00339-310.1038/s41578-021-00339-3 ↗
64. 10.1038/nbt71210.1038/nbt712 ↗
65. 10.3390/polym1601002510.3390/polym16010025 ↗
66. 10.1016/j.colsurfb.2014.05.03310.1016/j.colsurfb.2014.05.033 ↗
67. 10.1177/088532821456334110.1177/0885328214563341 ↗
68. 10.1021/acsami.7b1786310.1021/acsami.7b17863 ↗
69. 10.1021/la503923810.1021/la5039238 ↗