A Qualitative Transcriptional Signature For Predicting Recurrence Risk Of Stage ?-? Bladder Cancer Patients After Surgical Resection

Bladder cancer is the fourth most common type of tumor among males.Nearly 25%bladder cancer patients of stage I^III die within five years after surgery due to tumor recurrence.Previously reported transcriptional signatures for predicting the prognosis of stage I-III bladder cancer?BLCA?patients after surgical resection are commonly based on risk scores summarized from quantitative measurements of gene expression levels,which are highly sensitive to the measurement variation and sample quality and thus hardly applicable under clinical settings.It is necessary to develop a transcriptional signature which can robustly predict recurrence risk of BLCA patients after surgical resection.A transcriptome qualitative signature is developed based on the within-sample relative expression orderings of genes to solve the above problems.First,the gene expression profile data of bladder cancer samples detected by the Illumina platform were used to identify genes that were significantly associated with patient's prognosis.Then,using univariate Cox regression model,for each of the gene pairs,formed from every two of the genes selected above,the REO patterns of the gene pair were identified which is considered to be significantly associated with patient's prognosis.A forward selection procedure is performed to search an optimal subset of the candidate signature gene pairs that achieves the highest C-index,and the subset of gene pairs with the highest C-index was chosen as the final prognostic gene pair signature.The signature is validated in two independent datasets.Next,the samples from the three independent datasets were reclassified into high or low-risk group by the signature to identify reproducible differentially expressed genes associated with recurrence.Finally,the methylation data of bladder cancer samples were used to identify differentially methylated genes between different prognostic groups,and then analyze the correspondence between the differentially methylated genes and differentially expressed genes.A signature consisting of 12 gene pairs?12-GPS?was identified in the study.In the first validation dataset with 114 samples,the low-risk group of 54 patients had a significantly better overall survival than the high-risk group of 60 patients(HR=3.59,95%CI:1.34⁹.62,p=6.61×10^–03).Similarly,the signature was also validated in the second validation dataset with 57 samples?HR=2.75×10⁸,95%CI:0^Inf,p=0.047?.Besides,comparison analysis showed that the differentially expressed genes cannot be reproducibly detected when the metastatic and non-metastatic samples were defined by clinical stage alone.However,after reclassifying the samples by the signature,the differentially expressed genes between the low-and high-risk groups were highly reproducible and significantly concordant with DNA methylation differences between the two groups.Besides,functional enrichment analysis showed that these differentially expressed genes were significantly enriched in some pathways typically related to tumor metastasis?FDR<0.01,hypergeometric distribution model?,which indicates the confidence in the reliability of disease progression associated transcriptional characteristics which identified by the signature.The 12-GPS signature can robustly predict the recurrence risk of stage I-III BLCA patients after surgical resection.It can also aid the identification of reproducible transcriptional and epigenomic features characterizing BLCA metastasis.