Urine cell-based DNA methylation classifier for monitoring bladder cancer

Antoine G Van Der Heijden,Cristian Moldoveanud,Juan J Lozano,Bogdan Czerniak,Jack A Schalken,Antonio Alcaraz,Montserrat Baixauli,Colin P Dinney,Cindy C M Van Rijt-Van De Westerlo,Bogdan Geavlete,Maria J Ribal,J Alfred Witjes,Cosmin Ene,Lourdes Mengual,Mercedes Ingelmo-Torres,Lambertus A L M Kiemeney

doi:10.1186/s13148-018-0496-x

Abstract

BackgroundCurrent standard methods used to detect and monitor bladder cancer (BC) are invasive or have low sensitivity. This study aimed to develop a urine methylation biomarker classifier for BC monitoring and validate this classifier in patients in follow-up for bladder cancer (PFBC).MethodsVoided urine samples (N = 725) from BC patients, controls, and PFBC were prospectively collected in four centers. Finally, 626 urine samples were available for analysis. DNA was extracted from the urinary cells and bisulfite modificated, and methylation status was analyzed using pyrosequencing. Cytology was available from a subset of patients (N = 399). In the discovery phase, seven selected genes from the literature (CDH13, CFTR, NID2, SALL3, TMEFF2, TWIST1, and VIM2) were studied in 111 BC and 57 control samples. This training set was used to develop a gene classifier by logistic regression and was validated in 458 PFBC samples (173 with recurrence).ResultsA three-gene methylation classifier containing CFTR, SALL3, and TWIST1 was developed in the training set (AUC 0.874). The classifier achieved an AUC of 0.741 in the validation series. Cytology results were available for 308 samples from the validation set. Cytology achieved AUC 0.696 whereas the classifier in this subset of patients reached an AUC 0.768. Combining the methylation classifier with cytology results achieved an AUC 0.86 in the validation set, with a sensitivity of 96%, a specificity of 40%, and a positive and negative predictive value of 56 and 92%, respectively.ConclusionsThe combination of the three-gene methylation classifier and cytology results has high sensitivity and high negative predictive value in a real clinical scenario (PFBC). The proposed classifier is a useful test for predicting BC recurrence and decrease the number of cystoscopies in the follow-up of BC patients. If only patients with a positive combined classifier result would be cystoscopied, 36% of all cystoscopies can be prevented.

Highlights

Current standard methods used to detect and monitor bladder cancer (BC) are invasive or have low sensitivity
Training set DNA methylation of all seven selected genes was significantly increased in urine sediments from BC patients compared to controls (Fig. 1)
The best possible biomarker combination based on Area under the curve (AUC) was provided by the combination of CFTR, SALL3, and TWIST1

Summary

Introduction

Current standard methods used to detect and monitor bladder cancer (BC) are invasive or have low sensitivity. This study aimed to develop a urine methylation biomarker classifier for BC monitoring and validate this classifier in patients in follow-up for bladder cancer (PFBC). Up to 34% of these high-risk patients will develop muscle-invasive bladder cancer (MIBC) [2]. For this reason, an intensive follow-up schedule is mandatory in patients with intermediate- or high-risk NMIBC. On the other hand, has a high specificity (SP) but lacks sensitivity (SN) especially in low-risk tumors [6]. Several non-invasive methods, NMP-22, bladder tumor antigen, and UroVysion FISH, have shown to help increase the sensitivity of urine cytology. There is a clear clinical need to find reliable markers to monitor the recurrence in NMIBC [8]

Objectives

Methods

Results

Discussion

Conclusion