Predicting breast cancer metastasis by using serum biomarkers and clinicopathological data with machine learning technologies.

BACKGROUND: Approximately 10%-15% of patients with breast cancer die of cancer metastasis or recurrence, and early diagnosis of it can improve prognosis. Breast cancer outcomes may be prognosticated on the basis of surface markers of tumor cells and serum tests. However, evaluation of a combination of clinicopathological features may offer a more comprehensive overview for breast cancer prognosis. MATERIALS AND METHODS: We evaluated serum human epidermal growth factor receptor 2 (sHER2) as part of a combination of clinicopathological features used to predict breast cancer metastasis using machine learning algorithms, namely random forest, support vector machine, logistic regression, and Bayesian classification algorithms. The sample cohort comprised 302 patients who were diagnosed with and treated for breast cancer and received at least one sHER2 test at Chang Gung Memorial Hospital at Linkou between 2003 and 2016. RESULTS: The random-forest-based model was determined to be the optimal model to predict breast cancer metastasis at least 3 months in advance; the correspondingarea under the receiver operating characteristic curve value was 0. 75 (p < 0. 001). CONCLUSION: The random-forest-based model presented in this study may be helpful as part of a follow-up intervention decision support system and may lead to early detection of recurrence, early treatment, and more favorable outcomes.

Fas ligand enhances malignant behavior of tumor cells through interaction with Met, hepatocyte growth factor receptor, in lipid rafts.

Many late-stage cancer cells express Fas ligand (FasL) and show high malignancy with metastatic potential. We report here a novel signaling mechanism for FasL that hijacks the Met signal pathway to promote tumor metastasis. FasL-expressing human tumor cells express a significant amount of phosphorylated Met. The down-regulation of FasL in these cells led to decreased Met activity and reduced cell motility. Ectopic expression of human FasL in NIH3T3 cells significantly stimulated their migration and invasion. The inhibition of Met and Stat3 activities reverted the FasL-associated phenotype. Notably, FasL variants activated the Met pathway, even though most of their intracellular domain or Fas binding sites were deleted. FasL interacted with Met through the FasL(105-130) extracellular region in lipid rafts, which consequently led to Met activation. Knocking down Met gene expression by RNAi technology reverted the FasL-associated motility to basal levels. Furthermore, treatment with synthetic peptides corresponding to FasL(117-126) significantly reduced the FasL/Met interaction, Met phosphorylation, and cell motility of FasL(+) transfectants and tumor cells. Finally, the transfectants of truncated FasL showed strong anchorage-independent growth and lung metastasis potential in null mice. Collectively, our results establish the FasL-Met-Stat3 signaling pathway and explains the metastatic phenotype of FasL-expressing tumors.