No abstract

Classifying indolent prostate cancer represents a significant clinical challenge. We investigated whether integrating data from different omic platforms could identify a biomarker panel with improved performance compared to individual platforms alone. DNA methylation, transcripts, protein and glycosylation biomarkers were assessed in a single cohort of patients treated by radical prostatectomy. Novel multiblock statistical data integration approaches were used to deal with missing data and modelled via stepwise multinomial logistic regression, or LASSO. After applying leave‐one‐out cross‐validation to each model, the probabilistic predictions of disease type for each individual panel were aggregated to improve prediction accuracy using all available information for a given patient. Through assessment of three performance parameters of area under the curve (AUC) values, calibration and decision curve analysis, the study identified an integrated biomarker panel which predicts disease type with a high level of accuracy, with Multi AUC value of 0.91 (0.89, 0.94) and Ordinal C‐Index (ORC) value of 0.94 (0.91, 0.96), which was significantly improved compared to the values for the clinical panel alone of 0.67 (0.62, 0.72) Multi AUC and 0.72 (0.67, 0.78) ORC. Biomarker integration across different omic platforms significantly improves prediction accuracy. We provide a novel multiplatform approach for the analysis, determination and performance assessment of novel panels which can be applied to other diseases. With further refinement and validation, this panel could form a tool to help inform appropriate treatment strategies impacting on patient outcome in early stage prostate cancer.

As the leading culprit in cancer incidence for American men, prostate cancer continues to pose significant diagnostic, prognostic, and therapeutic tribulations for clinicians. The vast spectrum of disease behavior warrants better molecular classification to facilitate the development of more robust biomarkers that can identify the more aggressive and clinically significant tumor subtypes that require treatment. The untranslated portion of the human transcriptome, namely noncoding RNAs (ncRNA), is emerging as a key player in cancer initiation and progression and boasts many attractive features for both biomarker and therapeutic research. Genetic linkage studies show that many ncRNAs are located in cancer-associated genomic regions that are frequently deleted or amplified in prostate cancer, whereas aberrant ncRNA expression patterns have well-established links with prostate tumor cell proliferation and survival. The dysregulation of pathways controlled by ncRNAs results in a cascade of multicellular events leading to carcinogenesis and tumor progression. The characterization of RNA species, their functions, and their clinical applicability is a major area of biologic and clinical importance. This review summarizes the growing body of evidence, supporting a pivotal role for ncRNAs in the pathogenesis of prostate cancer. We highlight the most promising ncRNA biomarkers for detection and risk stratification and present the state-of-play for RNA-based personalized medicine in treating the "untreatable" prostate tumors. Clin Cancer Res; 20(1); 35-43. Ó2013 AACR. Disclosure of Potential Conflicts of InterestNo potential conflicts of interest were disclosed. CME Staff Planners' DisclosuresThe members of the planning committee have no real or apparent conflict of interest to disclose. Learning Objective(s)Upon completion of this article, the reader should have a good understanding of the major small and long noncoding RNAs involved in prostate carcinogenesis, their potential as biomarkers, and the biologic rationale underlying novel therapeutic strategies using noncoding RNAs for castration-resistant prostate cancer.