Research Progress
AI helps researchers design microneedle patches that restore hair in balding mice
Post: 2022-11-06 12:58  View:119

Most people with substantial hair loss have the condition androgenic alopecia, also called male- or female-pattern baldness. In this condition, hair follicles can be damaged by androgens, inflammation or an overabundance of reactive oxygen species, such as oxygen free radicals. When the levels of oxygen free radicals are too high, they can overwhelm the body's antioxidant enzymes that typically keep them in check. Superoxide dismutase (SOD) is one of these enzymes, and researchers have recently created SOD mimics called "nanozymes." But so far, those that have been reported aren't very good at removing oxygen free radicals. So, Lina Wang, Zhiling Zhu and colleagues wanted to see whether machine learning, a form of AI, could help them design a better nanozyme for treating hair loss.

The researchers chose transition-metal thiophosphate compounds as potential nanozyme candidates. They tested machine-learning models with 91 different transition-metal, phosphate and sulfate combinations, and the techniques predicted that MnPS3 would have the most powerful SOD-like ability. Next, MnPS3 nanosheets were synthesized through chemical vapor transport of manganese, red phosphorus and sulfur powders. In initial tests with human skin fibroblast cells, the nanosheets significantly reduced the levels of reactive oxygen species without causing harm.

Based on these results, the team prepared MnPS3 microneedle patches and treated androgenic alopecia-affected mouse models with them. Within 13 days, the animals regenerated thicker hair strands that more densely covered their previously bald backsides than mice treated with testosterone or minoxidil. The researchers say that their study both produced a nanozyme treatment for regenerating hair, and indicated the potential for computer-based methods for use in the design of future nanozyme therapeutics.

The authors acknowledge funding from the National Natural Science Foundation of China and the Natural Science Foundation of Shandong Province China.

Figure 1. Machine learning guided discovery of SOD-like nanozymes. (A) Workflow diagram of ML-assisted screening and prediction of nanozymes to regulate oxidative stress for AGA treatment. (B) The composition of MxPySz (x = 1–7; y = 1–4; z = 1–29). (C) Correlation matrix of processed data colored by Pearson’s correlation coefficient. (D) 3D surface plot of output data set of ΔG1, ΔG2, and ΔG3. The parameters (E) accuracy, R2 and (F) error, RMSE of the model prediction plots. (G) 5-fold cross validation of R2 for ΔG1, ΔG2, and ΔG3. (H–J) Scatter plot of predictions for the train data set and test data set. (K) Radar map of SOD-like activity of CrPS4, VPS3, CoPS3, FePS3, Cu7PS6, and MnPS3.

Figure 2. Characterizations of MnPS3. (A) TEM image of scaly MnPS3. (B) HR-TEM image of scaly MnPS3. The inset is the selected area electron diffraction (SAED). (C–F) TEM-mapping images of scaly MnPS3: (C) high-angle annular dark field, (D) manganese, (E) phosphorus, and (F) sulfur. (G) AFM image of scaly MnPS3. (H) XRD spectra of scaly MnPS3. (I) Raman spectra of scaly MnPS3. (J–M) XPS spectra of scaly MnPS3: (J) survey and high-resolution spectra of (K) Mn 2p, (L) P 2p, and (M) S 2p.

Figure 3. SOD-like activity of MnPS3. (A) Comparison of ABTS free radical scavenging ability between MnPS3 and SOD. (B) Comparison of ·OH scavenging ability between MnPS3 and SOD. (C) Comparison of ·O2– scavenging ability between MnPS3 and SOD. (D) Comparison of DPPH free radical scavenging ability between MnPS3 and SOD. (E) Inhibition of pyrogallol autoxidation rate of MnPS3. (F) SOD-like activity of MnPS3 tested by WST-8. (G) EPR spectra for ·O2– scavenging ability of MnPS3. (H) IC50 comparison diagram of various SOD mimics. (11?13,32) (I) Schematic diagram of SOD-like reaction mechanism of MnPS3. (J) Gibbs free energy diagram of SOD-like reaction of MnPS3.

Figure 4. Characterization of the morphological and physical properties of the MnMNP system. (A) Schematic illustration of AGA therapy by MnMNP. (B) Photographic image of MnMNP. (C–I) SEM and mapping images of MnMNP for (C) SEM image, (D) carbon, (E) nitrogen, (F) phosphorus, (G) oxygen, (H) manganese, and (I) sulfur. (J) Side view photographic image of MnMNP. (K) Fluorescence microscopy image of the FITC integrated MnMNP. (L) Mechanical strength of MNPs with or without MnPS3. (M) Stereoscopic photomicrograph of the porcine cadaver skin after MB loaded MnMNP insertion. (N) Microscopic image of porcine skin stained with H&E after MnMNP application. Black arrows indicate the location of the microneedle holes. Solubility test of MnMNP (O) before and (P) after pressing into the mouse skin for 5 min. (Q) Release kinetics of MnPS3 from MnMNP (n = 3). All data are presented as mean ± SD.

Figure 5. In vivo AGA treatment by the MnMNP system. (A) Schematic diagram of treatment strategy in the AGA mouse model. (B) Photographic images of hair regeneration over time. (C) SEM images of regenerated hairs at day 14. (D) The expression level of Ki67 in HFs in the alopecia area. (E) DHE staining of skin tissues from different groups at day 14 postdepilation to detect ROS. (F) H&E staining of the treated skins at day 14 postdepilation. (G) Diameter of regenerated hairs at day 14 postdepilation (n = 20). (H) Coverage rate of regenerated hairs at day 14 postdepilation. (I) Quantification of MDA in the treated skins on day 14 postdepilation (n = 3).

Address: C508 Dingxin Building, Jilin University, 2699 Qianjin Street, Changchun 130012, P. R. China
Copyright © 2022 International Society of Bionic Engineering All Rights Reserved