Dataset Information

Bladder cancer biomarker discovery using global metabolomic profiling of urine.

ABSTRACT: Bladder cancer (BCa) is a common malignancy worldwide and has a high probability of recurrence after initial diagnosis and treatment. As a result, recurrent surveillance, primarily involving repeated cystoscopies, is a critical component of post diagnosis patient management. Since cystoscopy is invasive, expensive and a possible deterrent to patient compliance with regular follow-up screening, new non-invasive technologies to aid in the detection of recurrent and/or primary bladder cancer are strongly needed. In this study, mass spectrometry based metabolomics was employed to identify biochemical signatures in human urine that differentiate bladder cancer from non-cancer controls. Over 1000 distinct compounds were measured including 587 named compounds of known chemical identity. Initial biomarker identification was conducted using a 332 subject sample set of retrospective urine samples (cohort 1), which included 66 BCa positive samples. A set of 25 candidate biomarkers was selected based on statistical significance, fold difference and metabolic pathway coverage. The 25 candidate biomarkers were tested against an independent urine sample set (cohort 2) using random forest analysis, with palmitoyl sphingomyelin, lactate, adenosine and succinate providing the strongest predictive power for differentiating cohort 2 cancer from non-cancer urines. Cohort 2 metabolite profiling revealed additional metabolites, including arachidonate, that were higher in cohort 2 cancer vs. non-cancer controls, but were below quantitation limits in the cohort 1 profiling. Metabolites related to lipid metabolism may be especially interesting biomarkers. The results suggest that urine metabolites may provide a much needed non-invasive adjunct diagnostic to cystoscopy for detection of bladder cancer and recurrent disease management.

SUBMITTER: Wittmann BM

PROVIDER: S-EPMC4277370 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Bladder cancer biomarker discovery using global metabolomic profiling of urine.

Wittmann Bryan M BM Stirdivant Steven M SM Mitchell Matthew W MW Wulff Jacob E JE McDunn Jonathan E JE Li Zhen Z Dennis-Barrie Aphrihl A Neri Bruce P BP Milburn Michael V MV Lotan Yair Y Wolfert Robert L RL

PloS one 20141226 12

Bladder cancer (BCa) is a common malignancy worldwide and has a high probability of recurrence after initial diagnosis and treatment. As a result, recurrent surveillance, primarily involving repeated cystoscopies, is a critical component of post diagnosis patient management. Since cystoscopy is invasive, expensive and a possible deterrent to patient compliance with regular follow-up screening, new non-invasive technologies to aid in the detection of recurrent and/or primary bladder cancer are st ...[more]

PMID: 25541698

Similar Datasets

Project description:Untargeted metabolomics is a powerful phenotyping tool for better understanding biological mechanisms involved in human pathology development and identifying early predictive biomarkers. This approach, based on multiple analytical platforms, such as mass spectrometry (MS), chemometrics and bioinformatics, generates massive and complex data that need appropriate analyses to extract the biologically meaningful information. Despite various tools available, it is still a challenge to handle such large and noisy datasets with limited number of individuals without risking overfitting. Moreover, when the objective is focused on the identification of early predictive markers of clinical outcome, few years before occurrence, it becomes essential to use the appropriate algorithms and workflow to be able to discover subtle effects among this large amount of data. In this context, this work consists in studying a workflow describing the general feature selection process, using knowledge discovery and data mining methodologies to propose advanced solutions for predictive biomarker discovery. The strategy was focused on evaluating a combination of numeric-symbolic approaches for feature selection with the objective of obtaining the best combination of metabolites producing an effective and accurate predictive model. Relying first on numerical approaches, and especially on machine learning methods (SVM-RFE, RF, RF-RFE) and on univariate statistical analyses (ANOVA), a comparative study was performed on an original metabolomic dataset and reduced subsets. As resampling method, LOOCV was applied to minimize the risk of overfitting. The best k-features obtained with different scores of importance from the combination of these different approaches were compared and allowed determining the variable stabilities using Formal Concept Analysis. The results revealed the interest of RF-Gini combined with ANOVA for feature selection as these two complementary methods allowed selecting the 48 best candidates for prediction. Using linear logistic regression on this reduced dataset enabled us to obtain the best performances in terms of prediction accuracy and number of false positive with a model including 5 top variables. Therefore, these results highlighted the interest of feature selection methods and the importance of working on reduced datasets for the identification of predictive biomarkers issued from untargeted metabolomics data.

Dataset Information

Bladder cancer biomarker discovery using global metabolomic profiling of urine.

Publications

Bladder cancer biomarker discovery using global metabolomic profiling of urine.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets