Using a machine learning approach to identify key prognostic molecules for esophageal squamous cell carcinoma.

BACKGROUND: A plethora of prognostic biomarkers for esophageal squamous cell carcinoma (ESCC) that have hitherto been reported are challenged with low reproducibility due to high molecular heterogeneity of ESCC. The purpose of this study was to identify the optimal biomarkers for ESCC using machine learning algorithms. METHODS: Biomarkers related to clinical survival, recurrence or therapeutic response of patients with ESCC were determined through literature database searching. Forty-eight biomarkers linked to recurrence or prognosis of ESCC were used to construct a molecular interaction network based on NetBox and then to identify the functional modules. Publicably available mRNA transcriptome data of ESCC downloaded from Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA) datasets included GSE53625 and TCGA-ESCC. Five machine learning algorithms, including logical regression (LR), support vector machine (SVM), artificial neural network (ANN), random forest (RF) and XGBoost, were used to develop classifiers for prognostic classification for feature selection. The area under ROC curve (AUC) was used to evaluate the performance of the prognostic classifiers. The importances of identified molecules were ranked by their occurrence frequencies in the prognostic classifiers. Kaplan-Meier survival analysis and log-rank test were performed to determine the statistical significance of overall survival. RESULTS: A total of 48 clinically proven molecules associated with ESCC progression were used to construct a molecular interaction network with 3 functional modules comprising 17 component molecules. The 131,071 prognostic classifiers using these 17 molecules were built for each machine learning algorithm. Using the occurrence frequencies in the prognostic classifiers with AUCs greater than the mean value of all 131,071 AUCs to rank importances of these 17 molecules, stratifin encoded by SFN was identified as the optimal prognostic biomarker for ESCC, whose performance was further validated in another 2 independent cohorts. CONCLUSION: The occurrence frequencies across various feature selection approaches reflect the degree of clinical importance and stratifin is an optimal prognostic biomarker for ESCC.

Comparison of the Effects of Intraperitoneal Injection with Carbon Tetrachloride on Acute Liver Toxicity in Male and Female Kunming Mice.

BACKGROUND Acute chemical liver injury needs to be further explored. The present study aimed to compare the effects of intraperitoneal injection with carbon tetrachloride on acute liver toxicity after 24 h in male and female Kunming mice. MATERIAL AND METHODS In this study, female and male mice were simultaneously divided into 3 different groups. Each group was treated differently, and after 24 h, blood samples were collected to check for changes in the activity of alanine aminotransferase (ALT) and aspartate aminotransferase (AST), which were used to assess liver toxicity. Liver samples were used for hematoxylin-eosin staining, and periodic acid Schiff reagent staining was performed to detect the pathological changes of each group. The expression level of biomarker molecules in liver cells was also systematically analyzed. RESULTS Our results showed that, compared with male mice, female mice showed more serious damage: reduced glycogen and higher degree of necrosis, and the levels of heatshock protein 27 (HSP27), heat-shock protein 70 (HSP70), proliferating cell nuclear antigen (PCNA) and B cell lymphoma/lewkmia-2 (Bcl-2) were significantly lower than in the male group (P<0.05 or P<0.01), while the results of Bcl-2-associated X protein (Bax), cysteinyl aspartate specific proteinase 3 (Caspase3), and cytochrome P450 2E1 (CYP2E1) were the opposite (P<0.05 or P<0.01). CONCLUSIONS The findings from this study showed that, compared with male mice, at 24 h after CCl4 toxicity, female mice showed more severe changes of hepatocyte necrosis and PAS-positivity, with significantly reduced expression of HSP27, HSP70, PCNA, and Bcl-2, and significantly increased expression of Bax, caspase-3, and CYP2E1.

[Expression of deleted in liver cancer 1 and phosphorelated focal adhesion kinase in breast cancer].

OBJECTIVE: To analyze the expression of deleted in liver cancer 1 (DLC1) and phosphorelated focal adhesion kinase (p-FAK) in breast cancer tissue to further understand the molecular mechanisms of the carcinogenesis and metastasis of breast cancer. METHODS: Immunohistochemistry was employed to determine the protein level of DLC1 and p-FAK in 61 breast cancer, 30 benign breast disease and the adjacent normal breast tissues. RESULTS: The positivity rates of DLC1 differed significantly between breast cancer, benign and normal tissues (34.43%, 80.00% and 76.67%, respectively, P<0.001). The positivity rates of p-FAK in the 3 tissues were 77.05%, 33.33% and 26.67%, also showing significant differences (P<0.001). The aberrant expression of DLC1 showed an inverse correlation to p-FAK (κ=-0.4591). Both DLC1 and p-FAK were closely correlated to the carcinogenesis, clinical stage, PR and lymphatic metastasis of breast cancer (P<0.05), but not to the patients age, pathological subtype, familial history, ER or CerbB-2 (P>0.05). CONCLUSION: The abnormal expression of DLC1 and p-FAK might participate in the carcinogenesis, progression, and metastasis of breast cancer. The role of DLC1 and p-FAK might be related to the regulation of progestone. DLC1 and p-FAK may serve as candidate markers for early diagnosis, prognostic evaluation and target treatment of breast cancer.