MicroRNA Ratios Distinguish Melanomas from Nevi

Abstract

The use of microRNAs as biomarkers has been proposed for many diseases, including the diagnosis of melanoma. Although hundreds of microRNAs have been identified as differentially expressed in melanomas as compared to benign melanocytic lesions, a limited consensus has been achieved across studies, constraining the effective use of these potentially useful markers. In this study, we applied a machine learning-based pipeline to a dataset consisting of genetic features, clinical features, and next-generation microRNA sequencing from micro-dissected formalin-fixed paraffin embedded melanomas and their adjacent benign precursor nevi. We identified patient age and tumor cellularity as variables that frequently confound the measured expression of potentially diagnostic microRNAs. By employing the ratios of microRNAs that were either enriched or depleted in melanoma compared to the nevi as a normalization strategy, we developed a model that classified all the available published cohorts with an area under the receiver operating characteristic curve of 0.98. External validation on an independent cohort classified lesions with 81% sensitivity and 88% specificity and was uninfluenced by the tumor content of the sample or patient age.

Clinical Implications of Primary Cilia in Skin Cancer

“…Although different combinations of mutations in a variety of genes underlie the diversity of melanocytic neoplasms, they all share the common denominator of activating the mitogen-activated protein kinase (MAPK) pathway. Beyond DNA mutations, deletions and amplifications, DNA methylation [81], microRNAs [82], transcription [83], and translation [84] also play important roles in determining the malignant potential of a particular melanocytic neoplasm [85]. Finally, the tumor's microenvironment and interaction with an individual's immune system also contribute to the clinical course of melanoma [86].…”

“…There is now a greater appreciation that a purely genetic analysis may miss critical post-transcriptional and post-translational changes. Techniques such as mass spectrometry [90] and micro-RNA profiling [82] are emerging to address this gap. Each of these tests provides additional information that the pathologist can then use to integrate with the histopathology to reach their best estimate of malignant potential.…”

BRAFV600E induces reversible mitotic arrest in human melanocytes via microRNA-mediated suppression of AURKB

“…To first identify miRNAs down-regulated during transformation, we analyzed small RNA-sequencing from a previously established cohort of nevus with adjacent melanoma. Melanocytic nevus and melanoma portions of each tissue section were isolated and subjected to targeted exon, mRNA, and small RNA sequencing (33) (34) (Fig. 1B).…”

Human against Machine? Machine Learning Identifies MicroRNA Ratios as Biomarkers for Melanoma

“…However, there is a high level of discrepancy among these studies (Elmore et al, 2017;Jayawardana et al, 2016;Witwer and Halushka, 2016). In a meta-analysis, including seven publicly available miRNA datasets, Torres et al (2020) found that no single miRNA was differentially expressed across all datasets, and only four miRNAs were differentially expressed when limiting the analysis to four of the seven datasets. Thus, there is a substantial discrepancy in miRNA signatures for melanoma versus nevi, which needs to be addressed before any miRNA signature will be valuable for clinical use.…”

“…Discrepancies have been attributed to multiple confounding variables, including sample-to-sample variation of FFPE biopsies, with differing amounts of contamination from nontumor cells, as well as platformto-platform variation of quantification for miRNA expression (Witwer and Halushka, 2016). By utilizing machine learning, Torres et al (2020) first aimed to find genetic or clinical confounding variables that affect the quantification of miRNA expression in FFPE samples of melanoma and nevi. Torres et al (2020) established a well-curated dataset by meticulously assembling and annotating an initial training cohort of microdissected primary melanomas with their adjacent nevi.…”