Background B7 molecules play significant roles in regulating tumor immunity, but their expression patterns and immuno-biological correlations in pancreatic cancer (PaCa) have not been fully discussed. Methods RNA-sequencing data of B7 molecules of PaCa samples in the Cancer Genome Atlas (TCGA) dataset was downloaded from the UCSC Xena to assess the expression, correlation, and mutation of the B7 family in PaCa. Next, two PaCa tissue microarrays (TMAs, Cat. HPanA150CS02 and HPanA120Su02) were obtained from Outdo BioTech (Shanghai, China). To detect the expression levels of PD-L1, B7-H3 and B7-H4, immunohistochemistry (IHC) staining was performed on these TMAs. Results Most B7 molecules, including B7–1, B7–2, PD-L1, B7-DC, B7-H2, and B7-H5 exhibited similar expression patterns, but B7-H3, B7-H4, B7-H6, and B7-H7 showed outlier expression patterns compared with other B7 molecules. Besides, B7 molecules were genetically stable and exhibited low alteration frequency. IHC staining indicated PD-L1, B7-H3, and B7-H4 were up-regulated in PaCa tissues and showed uncorrelated expression patterns. Furthermore, high expression of PD-L1 and B7-H3 indicated poor-differentiated grades in PaCa. PD-L1 was positively, but B7-H4 was negatively correlated with CD8+ TILs infiltration in PaCa. Moreover, combined PD-L1 and B7-H4 expression was a novel subtyping strategy in PaCa, namely patients with both high PD-L1 and B7-H4 expression exhibited decreased CD8+ TILs infiltration in tumor tissues. Conclusion Overall, we systemically analyzed the expression patterns of B7 molecules and proposed a novel subtyping strategy in PaCa. Patients with both high PD-L1 and B7-H4 expression exhibited the immuno-cold phenotype, which may be not suitable for immunotherapy.

Purpose: This study aims to develop a prediction model to categorize the risk of early death among breast cancer patients with bone metastases using machine learning models.Methods: This study examined 16,189 bone metastatic breast cancer patients between 2010 and 2019 from a large oncological database in the United States. The patients were divided into two groups at random in a 90:10 ratio. The majority of patients (n = 14,582, 90%) were served as the training group to train and optimize prediction models, whereas patients in the validation group (n = 1,607, 10%) were utilized to validate the prediction models. Four models were introduced in the study: the logistic regression model, gradient boosting tree model, decision tree model, and random forest model.Results: Early death accounted for 17.4% of all included patients. Multivariate analysis demonstrated that older age; a separated, divorced, or widowed marital status; nonmetropolitan counties; brain metastasis; liver metastasis; lung metastasis; and histologic type of unspecified neoplasms were significantly associated with more early death, whereas a lower grade, a positive estrogen receptor (ER) status, cancer-directed surgery, radiation, and chemotherapy were significantly the protective factors. For the purpose of developing prediction models, the 12 variables were used. Among all the four models, the gradient boosting tree had the greatest AUC [0.829, 95% confident interval (CI): 0.802–0.856], and the random forest (0.828, 95% CI: 0.801–0.855) and logistic regression (0.819, 95% CI: 0.791–0.847) models came in second and third, respectively. The discrimination slopes for the three models were 0.258, 0.223, and 0.240, respectively, and the corresponding accuracy rates were 0.801, 0.770, and 0.762, respectively. The Brier score of gradient boosting tree was the lowest (0.109), followed by the random forest (0.111) and logistic regression (0.112) models. Risk stratification showed that patients in the high-risk group (46.31%) had a greater six-fold chance of early death than those in the low-risk group (7.50%).Conclusion: The gradient boosting tree model demonstrates promising performance with favorable discrimination and calibration in the study, and this model can stratify the risk probability of early death among bone metastatic breast cancer patients.