Mei Wang

Comprehensive bioinformatics analysis confirms RBMS3 as the central candidate biological target for ovarian cancer

Ovarian cancer (OC) is one of the most lethal malignancies in the female reproductive system. To find genes related to cancer progression targeting specific biological factors for targeted therapy, bioinformatics technology has been widely used. To screen the prognostic gene markers of OC by bioinformatics and explore their potential molecular biological mechanisms. Two data sets related to OC, GSE54388, and GSE119056, were rooted in the open comprehensive gene expression database (GEO). To correct the background of the data, standardize and screen differentially expressed genes (DEGs) using the R software limma package. The selected DEGs were enriched by Gene Ontology (GO) and through DAVID online database. Kyoto Encyclopedia of Genes and Genomes (KEGG) signal pathway analysis and protein-protein interaction network (PPI-network) map were constructed by STRING online database and Cytoscape software. Combined with the TCGA database, univariate and multivariate COX regression were used to screen prognostic genes. QRT-PCR was used to verify DEGs in clinical tissue samples. Eventually, the function of RBMS3 on the viability, migration, invasion, and apoptosis of OC cells was tested through functional experiments in vitro. 352 common DEGs were screened from GSE54388 and GSE119056 data sets. Survival analysis showed that MEIS2, TSTA3, CNTN1, RBMS3, and TRA2A were considered to be connected with the prognosis of OC. We discover that the expression level of RBMS3 was positively connected with the overall survival (OS) rate of sufferers with OC. The level of RBMS3 in OC tissues was markedly lower than that in neighboring structures and the outcomes of the GEPIA database were consistent with those of the qRT-PCR experiment. Through gene transfection technology it was found that overexpression of RBMS3 in OC cells substantially suppressed the vitality, migration, and invasion of OC cells and raised the rates of apoptosis in the OC cells. In this experiment, we distinguish 5 genes that may participate in the prognosis of OC and showed the key genes and pathways related to OC. It is speculated that RBMS3, a tumor suppressor gene, can be applied as a potential biological marker for the treatment of OC, gene expression summary, and prognosis.

Convolutional Neural Networks for Classifying Cervical Cancer Types Using Histological Images

Cervical cancer is the most common cancer among women worldwide. The diagnosis and classification of cancer are extremely important, as it influences the optimal treatment and length of survival. The objective was to develop and validate a diagnosis system based on convolutional neural networks (CNN) that identifies cervical malignancies and provides diagnostic interpretability. A total of 8496 labeled histology images were extracted from 229 cervical specimens (cervical squamous cell carcinoma, SCC, n = 37; cervical adenocarcinoma, AC, n = 8; nonmalignant cervical tissues, n = 184). AlexNet, VGG-19, Xception, and ResNet-50 with five-fold cross-validation were constructed to distinguish cervical cancer images from nonmalignant images. The performance of CNNs was quantified in terms of accuracy, precision, recall, and the area under the receiver operating curve (AUC). Six pathologists were recruited to make a comparison with the performance of CNNs. Guided Backpropagation and Gradient-weighted Class Activation Mapping (Grad-CAM) were deployed to highlight the area of high malignant probability. The Xception model had excellent performance in identifying cervical SCC and AC in test sets. For cervical SCC, AUC was 0.98 (internal validation) and 0.974 (external validation). For cervical AC, AUC was 0.966 (internal validation) and 0.958 (external validation). The performance of CNNs falls between experienced and inexperienced pathologists. Grad-CAM and Guided Gard-CAM ensured diagnoses interpretability by highlighting morphological features of malignant changes. CNN is efficient for histological image classification tasks of distinguishing cervical malignancies from benign tissues and could highlight the specific areas of concern. All these findings suggest that CNNs could serve as a diagnostic tool to aid pathologic diagnosis.