Gwang-Won Cho

Introduction: The recent advancement in artificial intelligence has compelled medical research to adapt the technologies. The abundance of molecular data and AI technology has helped in explaining various diseases, even cancers. Schizophrenia is a complex neuropsychological disease whose etiology is unknown. Several gene-wide association studies attempted to narrow down the cause of the disease but did not successfully point out the mechanism behind the disease. There are studies regarding the epigenetic changes in the schizophrenia disease condition, and a classification machine-learning model has been trained using the blood methylation data. Method: In this study, we have demonstrated a novel approach to elucidating the molecular cause of the disease. We used a two-step machine-learning approach to determine the causal molecular markers. By doing so, we developed classification models using both gene expression microarray and methylation microarray data. Result: Our models, because of our novel approach, achieved good classification accuracy with the available data size. We analyzed the important features, and they add up as evidence for the glutamate hypothesis of schizophrenia. Conclusion: In this way, we have demonstrated explaining a disease through machine learning models.

The impact of metformin on the rat facial nerve following crush injury has only occasionally been documented to date. The purpose of the current investigation was to use functional and electrophysiological evaluations to investigate the effects of metformin administration on recovery following crush injury to the rat facial nerve. The rats were randomly divided into four groups: the nonDM/PBS group (n = 4), the nonDM/metformin group (n = 4), the DM/PBS group (n = 4), and the DM/metformin group (n = 4). Diabetes was generated by an intraperitoneal injection of streptozotocin. Facial nerve paralysis was induced by a crush injury 7 days after diabetes induction. The blood glucose levels of the DM/PBS and DM/metformin groups were maintained at over 300 mg/dL, whereas the blood glucose levels of the nonDM/PBS and nonDM/metformin groups were maintained at less than 150 mg/dL. There was no significant difference between the two nonDM groups. In comparison to the PBS group, the metformin group’s recurrence of vibrissa fibrillation occurred noticeably sooner over time. The nonDM/metformin group showed the highest recovery rate in the second, third, and fourth weeks post-crush, respectively. The threshold of action potential 4 weeks after crush injury showed that the nonDM/metformin group had a significantly lower mean threshold of MAP compared to other groups. The short-term effect of metformin on the recovery of facial nerve blood flow (FNBF) was significantly increased compared to the DM/PBS group. However, there was no significant difference in FNBF between the nonDM/metformin and nonDM/PBS groups. A diabetic condition promoted a delay in FN regeneration. Metformin is able to accelerate functional recovery in diabetic or nondiabetic FN-injured rats. Further studies using a morphometric or molecular approach are planned to understand the pharmacologic mechanism of metformin.