Rapid screening and identification of potential candidate compounds are very important to understand the mechanism of drugs for the treatment of Alzheimer's disease (AD) and greatly promote the development of new drugs. In order to greatly improve the success rate of screening and reduce the cost and workload of research and development, this study proposes a novel Alzheimer-related compound identification algorithm namely forgeNet_SVM. First, Alzheimer related and unrelated compounds are collected using the data mining method from the literature databases. Three molecular descriptors (ECFP6, MACCS, and RDKit) are utilized to obtain the feature sets of compounds, which are fused into the all_feature set. The all_feature set is input to forgeNet_SVM, in which forgeNet is utilized to provide the importance of each feature and select the important features for feature extraction. The selected features are input to support vector machines (SVM) algorithm to identify the new compounds in Traditional Chinese Medicine (TCM) prescription. The experiment results show that the selected feature set performs better than the all_feature set and three single feature sets (ECFP6, MACCS, and RDKit). The performances of TPR, FPR, Precision, Specificity, F1, and AUC reveal that forgeNet_SVM could identify more accurately Alzheimer-related compounds than other classical classifiers.

Background: The molecular mechanisms associated with thoracic aortic dissection (TAD) remain poorly understood. A comprehensive high-throughput sequencing-based analysis of the circRNA–miRNA–mRNA competitive endogenous RNA (ceRNA) regulatory network in TAD has not been conducted. The purpose of this study is to identify and verify the key ceRNA networks which may have crucial biological functions in the pathogenesis of TAD. Methods: Gene expression profiles of the GSE97745, GSE98770, and GSE52093 datasets were acquired from the Gene Expression Omnibus (GEO) database. Differentially expressed genes (DEGs) were identified using the GEO2R tools. Protein–protein interaction (PPI) networks of the hub genes were constructed using STRING; the hub genes and modules were identified by MCODE and CytoHubba plugins of the Cytoscape. We analyzed the hub genes using Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathway enrichment analysis. The functions of these hub genes were assessed using Cytoscape software. Our data—along with data from GSE97745, GSE98770, and GSE52093—were used to verify the findings. Results: Upon combined biological prediction, a total of 11 ce-circRNAs, 11 ce-miRNAs, and 26 ce-mRNAs were screened to construct a circRNA–miRNA–mRNA ceRNA network. PPI network and module analysis identified four hub nodes, including IGF1R, JAK2, CSF1, and GAB1. Genes associated with the Ras and PI3K-Akt signaling pathways were clustered in the four hub node modules in TAD. The node degrees were most significant for IGF1R, which were also the most significant in the two modules (up module and hub module). IGF1R was selected as a key gene, and the hsa_circ_0007386/miR-1271–5P/IGF1R/AKT regulatory axis was established. The relative expression levels of the regulatory axis members were confirmed by RT-PCR in 12 samples, including TAD tissues and normal tissues. Downregulation of IGF1R expression in smooth muscle cells (SMCs) was found to induce apoptosis by regulating the AKT levels. In addition, IGF1R showed high diagnostic efficacy in both AD tissue and blood samples. Conclusions: The hsa_circ_0007386/miR-1271-5P/IGF1R/AKT axis may aggravate the progression of TAD by inducing VSMCs apoptosis. CeRNA networks could provide new insights into the underlying molecular mechanisms of TAD. In addition, IGF1R showed high diagnostic efficacy in both tissue and plasma samples in TAD, which can be considered as a diagnostic marker for TAD.