ABSTRACT
Severe injuries to the peripheral nervous system (PNS) require Schwann cells to aid in neuronal regeneration. Low-frequency electrical stimulation is known to induce the cogrowth of neurons and Schwann cells in an injured PNS. However, the correlations between electrical stimulation and Schwann cell viability are complex and not well understood. In this work, we develop a machine learning (ML)-integrated workflow that uses conductive hydrogel biointerfaces to evaluate the impacts of fabrication parameters and electrical stimulation on the Schwann cell viability. First, a hydrogel array with varying MXene and peptide loadings is fabricated, which serves as conductive biointerfaces to incubate Schwann cells and introduce various electrical stimulation (at different voltages and frequencies). Upon specific fabrication parameters and stimulation, the cell viability is evaluated and input into an artificial neural network model to train the model. Additionally, a data augmentation method is applied to synthesize 1000-fold virtual data points, enabling the construction of a high-accuracy prediction model (with a testing mean absolute error ≤11%). By harnessing the model's predictive power, we can accurately predict Schwann cell viability based on a given set of fabrication/stimulation parameters. Finally, the SHapley Additive exPlanations model interpretation provides several data-scientific insights that are validated by microscopic cellular observations. Our hybrid approach, involving conductive biointerface fabrication, ML algorithms, and data analysis, offers an unconventional platform to construct a preclinical prediction model at the cellular level.
ABSTRACT
Andrographolide (ANDRO) is a lactone diterpenoid compound present in the medicinal plant Andrographis paniculata which is clinically applied for multiple human diseases in Asia and Europe. The pharmacological activities of andrographolide have been widely demonstrated, including anti-inflammation, anti-cancer and hepatoprotection. However, the pharmacological mechanism of andrographolide remains unclear. Therefore, further characterization on the kinetics and molecular targets of andrographolide is essential. In this study, we described the synthesis and characterization of a novel fluorescent andrographolide derivative (ANDRO-NBD). ANDRO-NBD exhibited a comparable anti-cancer spectrum to andrographolide: ANDRO-NBD was cytotoxic to various types of cancer cells and suppressed the migration activity of melanoma cells; ANDRO-NBD treatment induced the cleavage of heat shock protein 90 (Hsp90) and the downregulation of its client oncoproteins, v-Src and Bcr-abl. Notably, ANDRO-NBD showed superior inhibitory effects to andrographolide in all anticancer assays we have performed. In addition, ANDRO-NBD was further used as a fluorescent probe to investigate the uptake kinetics, cellular distribution and molecular targets of andrographolide. Our data revealed that ANDRO-NBD entered cells rapidly and its fluorescent signal could be detected in nucleus, cytoplasm, mitochondria, and lysosome. Moreover, we demonstrated that ANDRO-NBD was covalently bound to several putative target proteins of andrographolide, including NF-κB and hnRNPK. In summary, we developed a fluorescent andrographolide probe with comparable bioactivity to andrographolide, which serves as a powerful tool to explore the pharmacological mechanism of andrographolide.
