Breast cancer is the most common malignancy diagnosed in women worldwide. The prevalence and incidence of breast cancer is increasing every year; therefore, early diagnosis along with suitable relapse detection is an important strategy for prognosis improvement. This study aimed to compare different machine algorithms to select the best model for predicting breast cancer recurrence. The prediction model was developed by using eleven different machine learning (ML) algorithms, including logistic regression (LR), random forest (RF), support vector classification (SVC), extreme gradient boosting (XGBoost), gradient boosting decision tree (GBDT), decision tree, multilayer perceptron (MLP), linear discriminant analysis (LDA), adaptive boosting (AdaBoost), Gaussian naive Bayes (GaussianNB), and light gradient boosting machine (LightGBM), to predict breast cancer recurrence. The area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and F1 score were used to evaluate the performance of the prognostic model. Based on performance, the optimal ML was selected, and feature importance was ranked by Shapley Additive Explanation (SHAP) values. Compared to the other 10 algorithms, the results showed that the AdaBoost algorithm had the best prediction performance for successfully predicting breast cancer recurrence and was adopted in the establishment of the prediction model. Moreover, CA125, CEA, Fbg, and tumor diameter were found to be the most important features in our dataset to predict breast cancer recurrence. More importantly, our study is the first to use the SHAP method to improve the interpretability of clinicians to predict the recurrence model of breast cancer based on the AdaBoost algorithm. The AdaBoost algorithm offers a clinical decision support model and successfully identifies the recurrence of breast cancer.

Background: Circulating long non-coding RNAs (lncRNAs) have been demonstrated to serve as diagnostic or prognosis biomarkers for various disease. We aimed to elucidate the diagnostic efficacy of serum lncRNA SCARNA10 for the hepatocellular carcinoma (HCC). Methods: In this study, a total of 182 patients with HCC, 105 patients with benign liver disease (BLD), and 149 healthy controls (HC) were enrolled. According to different classifications, the levels of serum SCARNA10 were assessed by quantitative real-time polymerase chain reaction (qPCR). The correlations between serum SCARNA10 and clinicopathological characteristics were further analyzed. The receiver operating characteristic (ROC) curve and area under curve (AUC) were utilized to estimate the diagnostic capacity of serum SCARNA10 and its combination with AFP for HCC. Results: The results demonstrated that the levels of serum SCARNA10 were significantly higher in HCC patients than in patients with BLD and healthy controls, and significantly increased in HCC patients with hepatitis B or C infection, or with liver cirrhosis. Furthermore, positive correlations were noted between serum SCARNA10 level and some clinicopathological characteristics, including tumor size, differentiation degrees, tumor stage, vascular invasion, tumor metastasis and complications. ROC analysis revealed that SCARNA10 had a significantly predictive value for HCC (Sensitivity = 0.70, Specificity = 0.77, and AUC = 0.82), the combination of SCARNA10 and AFP gained the higher sensitivity (AUC_{SCARNA10 + AFP} = 0.92 vs AUC_AFP = 0.83, p < 0.01). SCARNA10 retained significant diagnosis capabilities for AFP-negative HCC patients. Conclusions: In summary, lncRNA SCARNA10 may serve as a novel and non-invasive biomarker with relatively high sensitivity and specificity for HCC diagnosis.

BCKDK alters the metabolism of non-small cell lung cancer Yanhui Wang, Jiawei Xiao, Wenna Jiang, Duo Zuo, Xia Wang, Yu Jin, Lu Qiao, Haohua An, Lexin Yang, Daphne W. Dumoulin, Wolfram C. M. Dempke, Sarah A. Best, Li Ren

China, which has the largest number of patients with primary liver cancer (PLCs), lacks data on the overall prevalence of hepatitis B virus (HBV) and hepatitis C virus (HCV) in PLCs. We aimed to comprehensively assess the seroprevalence of HBV and HCV among PLCs in China. We included and pooled observational studies reporting seroprevalence of HBsAg and anti-HCV antibodies among PLCs in China by searching PubMed, Web of Science, Cochrane, Scopus, Embase, CNKI, Wanfang, and CBM. Multivariate meta-regression and subgroup analyses were used to explore sources of heterogeneity, and publication bias was assessed by funnel plots and Egger's test. PROSPERO registration number is CRD42023450382. A total of 217 eligible studies were included in the meta-analysis. The estimated seroprevalence of HBV and HCV was 75.09% (95% CI 73.12-77.02) and 11.82% (95% CI 9.79-14.00), respectively. After stratifying and analysing subgroups by region and study period, we found geographic differences in HBV and HCV prevalence among PLCs, with an overall increasing trend in the proportion of HBV and a decreasing trend in the proportion of HCV as well as co-infections in the last 40 years. HBV and HCV infections still accounts for a high proportion of PLCs in China.

β-Hydroxybutyrylation (Kbhb) modification regulates protein molecular fates in either physiology or pathology, including cancer. However, the function and regulatory mechanism of Kbhb remain completely unknown in cancer metastasis. Here, we report that β-hydroxybutyrate (BHB) is clinically associated with the progression of pancreatic cancer and functionally promotes pancreatic cancer cell metastasis. Mechanistically, BHB induces Kbhb modification of Snail at lysine 152 to enhance Snail stabilization, which is regulated by Kbhb modification enzyme CREB-binding protein (CBP), and subsequently prevents Snail degradation by blocking recognition of E3 ubiquitin ligases FBXL14. Furthermore, either targeting Snail Kbhb modification or CBP inhibitor decreases cancer metastasis and enhances the therapeutic efficacy of gemcitabine in pancreatic cancer cells. Collectively, our study reveals that Kbhb of Snail is critical to promote metastasis and provides a potential therapeutic strategy.