Construction of ceRNA prognostic model based on the CCR7/CCL19 chemokine axis as a biomarker in breast cancer.

BACKGROUND: The study of CCR7/CCL19 chemokine axis and breast cancer (BC) prognosis and metastasis is a current hot topic. We constructed a ceRNA network and risk-prognosis model based on CCR7/CCL19. METHODS: Based on the lncRNA, miRNA and mRNA expression data downloaded from the TCGA database, we used the starbase website to find the lncRNA and miRNA of CCR7/CCL19 and established the ceRNA network. The 1008 BC samples containing survival data were divided into Train group (504 cases) and Test group (504 cases) using R "caret" package. Then we constructed a prognostic risk model using RNA screened by univariate Cox analysis in the Train group and validated it in the Test and All groups. In addition, we explored the correlation between riskScores and clinical trials and immune-related factors (22 immune-infiltrating cells, tumor microenvironment, 13 immune-related pathways and 24 HLA genes). After transfection with knockdown CCR7, we observed the activity and migration ability of MDA-MB-231 and MCF-7 cells using CCK8, scratch assays and angiogenesis assays. Finally, qPCR was used to detect the expression levels of five RNAs in the prognostic risk model in MDA-MB-231 and MCF-7 cell. RESULTS: Patients with high expression of CCR7 and CCL19 had significantly higher overall survival times than those with low expression. The ceRNA network is constructed by 3 pairs of mRNA-miRNA pairs and 8 pairs of miRNA-lncRNA. After multivariate Cox analysis, we obtained a risk prognostic model: riskScore= -1.544 *`TRG-AS1`+ 0.936 * AC010327.5 + 0.553 *CCR7 -0.208 *CCL19 -0.315 *`hsa-let-7b-5p. Age, stage and riskScore can all be used as independent risk factors for BC prognosis. By drug sensitivity analysis, we found 5 drugs targeting CCR7 (convolamine, amikacin, AH-23,848, ondansetron, flucloxacillin). After transfection with knockdown CCR7, we found a significant reduction in cell activity and migration capacity in MDA-MB-231 cells. CONCLUSION: We constructed the first prognostic model based on the CCR7/CCL19 chemokine axis in BC and explored its role in immune infiltration, tumor microenvironment, and HLA genes.

Construction of the XGBoost model for early lung cancer prediction based on metabolic indices.

BACKGROUND: Lung cancer is a malignant tumour, and early diagnosis has been shown to improve the survival rate of lung cancer patients. In this study, we assessed the use of plasma metabolites as biomarkers for lung cancer diagnosis. In this work, we used a novel interdisciplinary mechanism, applied for the first time to lung cancer, to detect biomarkers for early lung cancer diagnosis by combining metabolomics and machine learning approaches. RESULTS: In total, 478 lung cancer patients and 370 subjects with benign lung nodules were enrolled from a hospital in Dalian, Liaoning Province. We selected 47 serum amino acid and carnitine indicators from targeted metabolomics studies using LC‒MS/MS and age and sex demographic indicators of the subjects. After screening by a stepwise regression algorithm, 16 metrics were included. The XGBoost model in the machine learning algorithm showed superior predictive power (AUC = 0.81, accuracy = 75.29%, sensitivity = 74%), with the metabolic biomarkers ornithine and palmitoylcarnitine being potential biomarkers to screen for lung cancer. The machine learning model XGBoost is proposed as an tool for early lung cancer prediction. This study provides strong support for the feasibility of blood-based screening for metabolites and provide a safer, faster and more accurate tool for early diagnosis of lung cancer. CONCLUSIONS: This study proposes an interdisciplinary approach combining metabolomics with a machine learning model (XGBoost) to predict early the occurrence of lung cancer. The metabolic biomarkers ornithine and palmitoylcarnitine showed significant power for early lung cancer diagnosis.