Purpose: Isoborneol has been used in the treatment of cardiovascular disease for several years in China. However, the mechanism is still unclear. The aim of this study was to identify the novel mechanism of isoborneol for its application in atherosclerotic disease. Materials and Methods: The whole-genome gene expression profiles of MCF-7 cells treated with/or without isoborneol were detected by mRNA microarray analysis. The degree of similarity between the gene expression profiles was compared with the Connectivity Map (CMAP) database. An MTT assay was used to assess the toxicity of isoborneol on RAW 264.7 cells. Oil red O staining and a Dil-ox-LDL uptake assay in RAW 264.7 cells were also used to detect the accumulation of lipids in the macrophages and the uptake of oxidized low-density lipoprotein (ox-LDL). Results: Isoborneol was proved to have mRNA expression profiles similar to that of ikarugamycin which can inhibit the uptake of ox-LDL. This process has proved to be an important cause of foam cell formation and early atherosclerotic lesions. It is speculated, therefore, that isoborneol may show similar activity to that shown by ikarugamycin. Subsequently, it was shown that RAW 264.7 cells reduced the absorption of ox-LDL and the accumulation of intracellular lipids after treatment with different concentrations of isoborneol. Conclusion: The results indicate that isoborneol inhibits macrophage consumption of ox-LDL, thereby preventing the accumulation of lipids in the macrophages. These results provide evidence for the application of isoborneol in atherosclerotic disease.
3 January 2022 in IEEE Transactions on Instrumentation and Measurement
In machine learning applications, the reliability of predictions is significant for assisted decision and risk control. As an effective framework to quantify the prediction reliability, conformal prediction (CP) was commonly developed with $k$ -nearest neighbor, known as CPKNN. However, the conventional CPKNN suffers from high variance and bias, and long computational time as the feature dimensionality increases. To address these limitations, a new CP framework-CP with shrunken centroids (CPSC) is proposed. It regularizes the class centroids to attenuate the irrelevant features and shrink the sample space for predictions and reliability quantification. We have also compared the CPSC with CP based on SVM, LightGBM, RF on the herbal medicine dataset, with the electronic nose as a case and assessed them in two tasks: 1) off-line prediction: the training set was fixed, and the accuracy on the testing set was evaluated and 2) online prediction with data augmentation: CPKNN and CPSC filtered unlabeled data to augment the training data based on the prediction reliability, and the final accuracy of the testing set was compared. The result shows that CPSC significantly outperformed CPKNN in both two tasks: 1) CPSC reached a significantly higher accuracy with lower computation cost, and with the same credibility output, CPSC generally achieved higher accuracy and 2) the data augmentation process with CPSC robustly manifested a statistically significant improvement in prediction accuracy with different reliability thresholds, and the augmented data were more balanced in classes. This novel CPSC provides higher prediction accuracy and better reliability quantification, which can assist in reliable decision support.