A platelet-related signature for predicting the prognosis and immunotherapy benefit in bladder cancer based on machine learning combinations.

Abstract

Background: Bladder cancer carries a large societal burden, with over 570,000 newly diagnosed cases and 210,000 deaths globally each year. Platelets play vital functions in tumor progression and therapy benefits. We aimed to construct a platelet-related signature (PRS) for the clinical outcome of bladder cancer cases.

Methods: Ten machine learning techniques were used in the integrative operations to build PRS using the datasets from The Cancer Genome Atlas (TCGA), gene series expression (GSE)13507, GSE31684, GSE32894 and GSE48276. A number of immunotherapy datasets and prediction scores, including GSE91061, GSE78220, and IMvigor210, were utilized to assess how well the PRS predicted the benefit of immunotherapy. Vitro experiment was performed to verify the role of α1C-tubulin (TUBA1C) in bladder cancer.

Results: Enet (alpha =0.4) algorithm-based PRS had the highest average C-index of 0.73 and it was suggested as the optimal PRS. PRS acted as an independent risk factor for bladder cancer and patients with high PRS score portended a worse overall survival rate, with the area under the curve of 1-, 3- and 5-year operating characteristic curve being 0.754, 0.779 and 0.806 in TCGA dataset. A higher level of immune-activated cells, cytolytic function and T cell co-stimulation was found in the low PRS score group. Low PRS score demonstrated a higher tumor mutation burden score and programmed cell death protein 1 & cytotoxic T-lymphocyte associated protein 4 immunophenoscore, lower tumor immune dysfunction and exclusion score, intratumor heterogeneity score and immune escape score in bladder cancer, suggesting the PRS as an indicator for predicting immunotherapy benefits. Vitro experiment showed that TUBA1C was upregulated in bladder cancer and knockdown of TUBA1C obviously suppressed tumor cell proliferation.

Conclusions: The present study developed an ideal PRS for bladder cancer, which may be used as a predictor of prognosis, a risk classification system, and a therapy guide.