High-Content Screening and Analysis of Stem Cell-Derived Neural Interfaces Using a Combinatorial Nanotechnology and Machine Learning Approach

Yang, Letao; Conley, Brian; Yoon, Jinho; Rathnam, Christopher; Pongkulapa, Thanapat; Conklin, Brandon; Hou, Yannan; Lee, Ki‐Bum

doi:10.34133/2022/9784273

Cited by 5 publications

(3 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This may be the rst report in the English literature to apply CelTrac1000 and NIR-II to tracking the transplanted stem cells after repairing peripheral nerve defects, which was different from rat model of sciatic nerve suture reported by Dong in 2021 [34]. Our data further con rmed the high labeling e ciency of CelTrac1000 and stable imaging capabilities of NIR-II in vivo in animal models [35,36].…”

Section: Discussionsupporting

confidence: 59%

See 1 more Smart Citation

Application of second near infrared fluorescence imaging to trace CelTrac1000-labeled hair follicle epidermal neural crest stem cells in repairing rat facial nerve defects

Lv,

Zhu,

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

Background Tissue engineering based on stem cells has achieved satisfactory results in repairing facial nerve defects. However, the in vivo process of the transplanted cells has not been fully clear until now, although it is critical to understand the process and the underlying mechanism of regeneration for better therapeutic outcomes. Recently, second near-infrared window (NIR-II) fluorescence imaging has emerged as a rapidly evolving bio-imaging technique capable of visualizing and quantifying biological processes at the cellular level of living organisms. Methods Firstly, rat hair follicle epidermal neural crest stem cells (EPI-NCSCs) were isolated, cultured and identified by expression of SOX10 and Nestin, and then labeled with CelTrac1000. Rat acellular nerve allografts (ANAs) were prepared by chemical extraction. Secondly, 30 adult male rats were randomly and equally assigned into three groups: ANA + cells group, ANA group, and autograft group. The buccal branch of the facial nerve on right side was exposed and a 10-mm-long gap was bridged by ANA laden with CelTrac1000-labeled EPI-NCSCs, ANA laden with CelTrac1000 dye, and autologous nerve, respectively. Thirdly, CelTrac1000-labeled EPI-NCSCs were detected by NIR-II optical imaging system to visualize the behavior of the transplanted cells in vivo postoperatively. Finally, vibrissa movement, compound muscle action potentials (CMAPs) of vibrissal muscle, facial motoneurons retrotraced by Fluorogold, morphology and histology of the regenerated nerves in three groups were analyzed after surgery, respectively. Results Through 14 weeks of dynamic observation, we found that EPI-NCSCs successfully survived in the ANAs in vivo. Meanwhile, the region of the NIR-II fluorescence signals was gradually limited to be consistent with the route of the regenerative segment of the facial nerve. Furthermore, the degree of the vibrissa movement, the recovery value of the onset latency and amplitude of CMAPs, the number of Fluorogold-labeled cells, the CD31 positive area/total area, the mean gray value of S100 and β-tubulin III, the number and the diameter of the myelinated nerve fibers in the ANA group were lower than the other two groups (P < 0.05), and the other two groups had similar values (P > 0.05). Additionally, the thickness of the myelin sheaths was the thinnest in the ANA group, and the thickest in the autograft group (P< 0.05). Conclusions The migration map of local CelTrac1000-labeled EPI-NCSCs was successfully monitored by the NIR-II fluorescence imaging system when EPI-NCSCs within the ANAs were applied to treat rat facial nerve defects. Additionally, EPI-NCSCs promoted the ANAs to repair facial nerve defects in a small animal model.

show abstract

Section: Discussionsupporting

confidence: 59%

“…However, the application of NIR-II and CelTrac1000 in the detection of exogenous stem cells after peripheral nerve defect has not been reported so far [19].…”

Section: Introductionmentioning

confidence: 99%

Application of second near infrared fluorescence imaging to trace CelTrac1000-labeled hair follicle epidermal neural crest stem cells in repairing rat facial nerve defects

Lv,

Zhu,

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…They are trained on labeled data to establish the function that connects input variables ( x ) to output variables ( y ) and then make predictions about unlabeled examples. In the biomedical field, ML has been successfully used for medical image analysis and diagnosis [ 46 – 48 ], gene recognition in a DNA sequence [ 49 ], protein structures prediction [ 50 , 51 ], biophysical cue screening [ 52 ], and data analysis for organ-on-chips [ 53 , 54 ]. Despite the great potential of ML, the black box nature of ML algorithms still hinders its interpretability and thus its use for interdisciplinary research.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning in Predicting Printable Biomaterial Formulations for Direct Ink Writing

et al. 2023

View full text Add to dashboard Cite

Three-dimensional (3D) printing is emerging as a transformative technology for biomedical engineering. The 3D printed product can be patient-specific by allowing customizability and direct control of the architecture. The trial-and-error approach currently used for developing the composition of printable inks is time- and resource-consuming due to the increasing number of variables requiring expert knowledge. Artificial intelligence has the potential to reshape the ink development process by forming a predictive model for printability from experimental data. In this paper, we constructed machine learning (ML) algorithms including decision tree, random forest (RF), and deep learning (DL) to predict the printability of biomaterials. A total of 210 formulations including 16 different bioactive and smart materials and 4 solvents were 3D printed, and their printability was assessed. All ML methods were able to learn and predict the printability of a variety of inks based on their biomaterial formulations. In particular, the RF algorithm has achieved the highest accuracy (88.1%), precision (90.6%), and F1 score (87.0%), indicating the best overall performance out of the 3 algorithms, while DL has the highest recall (87.3%). Furthermore, the ML algorithms have predicted the printability window of biomaterials to guide the ink development. The printability map generated with DL has finer granularity than other algorithms. ML has proven to be an effective and novel strategy for developing biomaterial formulations with desired 3D printability for biomedical engineering applications.

show abstract

Artificial intelligence (AI) meets biomaterials and biomedicine

Han,

2024

Smart Materials in Medicine

View full text Add to dashboard Cite

High-Content Screening and Analysis of Stem Cell-Derived Neural Interfaces Using a Combinatorial Nanotechnology and Machine Learning Approach

Cited by 5 publications

References 62 publications

Application of second near infrared fluorescence imaging to trace CelTrac1000-labeled hair follicle epidermal neural crest stem cells in repairing rat facial nerve defects

Application of second near infrared fluorescence imaging to trace CelTrac1000-labeled hair follicle epidermal neural crest stem cells in repairing rat facial nerve defects

Machine Learning in Predicting Printable Biomaterial Formulations for Direct Ink Writing

Artificial intelligence (AI) meets biomaterials and biomedicine

Contact Info

Product

Resources

About