MicroRNA Ratios Distinguish Melanomas from Nevi

Application of machine learning for high-throughput tumor marker screening

High-throughput sequencing and multiomics technologies have allowed increasing numbers of biomarkers to be mined and used for disease diagnosis, risk stratification, efficacy assessment, and prognosis prediction. However, the large number and complexity of tumor markers make screening them a substantial challenge. Machine learning (ML) offers new and effective ways to solve the screening problem. ML goes beyond mere data processing and is instrumental in recognizing intricate patterns within data. ML also has a crucial role in modeling dynamic changes associated with diseases. Used together, ML techniques have been included in automatic pipelines for tumor marker screening, thereby enhancing the efficiency and accuracy of the screening process. In this review, we discuss the general processes and common ML algorithms, and highlight recent applications of ML in tumor marker screening of genomic, transcriptomic, proteomic, and metabolomic data of patients with various types of cancers. Finally, the challenges and future prospects of the application of ML in tumor therapy are discussed.

Artificial intelligence and skin cancer

Artificial intelligence is poised to rapidly reshape many fields, including that of skin cancer screening and diagnosis, both as a disruptive and assistive technology. Together with the collection and availability of large medical data sets, artificial intelligence will become a powerful tool that can be leveraged by physicians in their diagnoses and treatment plans for patients. This comprehensive review focuses on current progress toward AI applications for patients, primary care providers, dermatologists, and dermatopathologists, explores the diverse applications of image and molecular processing for skin cancer, and highlights AI's potential for patient self-screening and improving diagnostic accuracy for non-dermatologists. We additionally delve into the challenges and barriers to clinical implementation, paths forward for implementation and areas of active research.

Quantitative melanoma diagnosis using spectral phasor analysis of hyperspectral imaging from label-free slices

Introduction

Melanoma diagnosis traditionally relies on microscopic examination of hematoxylin and eosin (H&E) slides by dermatopathologists to search for specific architectural and cytological features. Unfortunately, no single molecular marker exists to reliably differentiate melanoma from benign lesions such as nevi. This study explored the potential of autofluorescent molecules within tissues to provide molecular fingerprints indicative of degenerated melanocytes in melanoma.

Methods

Using hyperspectral imaging (HSI) and spectral phasor analysis, we investigated autofluorescence patterns in melanoma compared to intradermal nevi. Using UV excitation and a commercial spectral confocal microscope, we acquired label-free HSI data from the whole-slice samples.

Results

Our findings revealed distinct spectral phasor distributions between melanoma and intradermal nevi, with melanoma displaying a broader phasor phase distribution, signifying a more heterogeneous autofluorescence pattern. Notably, longer wavelengths associated with larger phases correlated with regions identified as melanoma by expert dermatopathologists using H&E staining. Quantitative analysis of phase and modulation histograms within the phasor clusters of five melanomas (with Breslow thicknesses ranging from 0.5 mm to 6 mm) and five intradermal nevi consistently highlighted differences between the two groups. We further demonstrated the potential for the discrimination of several melanocytic lesions using center-of-mass comparisons of phase and modulation variables. Remarkably, modulation versus phase center of mass comparisons revealed strong statistical significance among the groups. Additionally, we identified the molecular endogenous markers responsible for tissue autofluorescence, including collagen, elastin, NADH, FAD, and melanin. In melanoma, autofluorescence is characterized by a higher phase contribution, indicating an increase in FAD and melanin in melanocyte nests. In contrast, NADH, elastin, and collagen dominate the autofluorescence of the nevus.

Discussion

This work underscores the potential of autofluorescence and HSI-phasor analysis as valuable tools for quantifying tissue molecular fingerprints, thereby supporting more effective and quantitative melanoma diagnosis.

Synergy of the microRNA Ratio as a Promising Diagnosis Biomarker for Mucinous Borderline and Malignant Ovarian Tumors

Epithelial ovarian cancers (EOCs) are a heterogeneous collection of malignancies, each with their own developmental origin, clinical behavior and molecular profile. With less than 5% of EOC cases, mucinous ovarian carcinoma is a rare form with a poor prognosis and a 5-year survival of 11% for advanced stages (III/IV). At the early stages, these malignant forms are clinically difficult to distinguish from borderline (15%) and benign (80%) forms with a better prognosis due to the large size and heterogeneity of mucinous tumors. Improving their diagnosis is therefore a challenge with regard to the risk of under-treating a malignant form or of unnecessarily undertaking radical surgical excision. The involvement of microRNAs (miRNAs) in tumor progression and their potential as biomarkers of diagnosis are becoming increasingly recognized. In this study, the comparison of miRNA microarray expression profiles between malignant and borderline tumor FFPE samples identified 10 down-regulated and 5 up-regulated malignant miRNAs, which were validated by individual RT-qPCR. To overcome normalization issues and to improve the accuracy of the results, a ratio analysis combining paired up-regulated and down-regulated miRNAs was performed. Although 21/50 miRNA expression ratios were significantly different between malignant and borderline tumor samples, any ratio could perfectly discriminate the two groups. However, a combination of 14 pairs of miRNA ratios (double ratio) showed high discriminatory potential, with 100% of accuracy in distinguishing malignant and borderline ovarian tumors, which suggests that miRNAs may hold significant clinical potential as a diagnostic tool. In summary, these ratio miRNA-based signatures may help to improve the precision of histological diagnosis, likely to provide a preoperative diagnosis in order to adapt surgical procedures.

Determination of Common microRNA Biomarker Candidates in Stage IV Melanoma Patients and a Human Melanoma Cell Line: A Potential Anti-Melanoma Agent Screening Model

MicroRNAs (miRNAs) are small, non-coding RNAs that play an important role in regulating gene expression. Dysregulation of miRNA expression is commonly observed in cancer, and it can contribute to malignant cell growth. Melanoma is the most fatal type of skin malignant neoplasia. Some microRNAs can be prospective biomarkers for melanoma in stage IV (advanced) at higher risk of relapses and require validation for diagnostic purposes. This work aimed to (1) determine the most significant microRNA biomarker candidates in melanoma using content analysis of the scientific literature, (2) to show microRNA biomarker candidates' diagnostic efficacy between melanoma patients and healthy control groups in a small-scale preliminary study by blood plasma PCR analysis, (3) to determine significant microRNA markers of the MelCher human melanoma cell line, which are also detected in patients with melanoma, that can be used as markers of drug anti-melanoma activity, and (4) test anti-melanoma activity of humic substances and chitosan by their ability to reduce level of marker microRNAs. The content analysis of the scientific literature showed that hsa-miR-149-3p, hsa-miR-150-5p, hsa-miR-193a-3p, hsa-miR-21-5p, and hsa-miR-155-5p are promising microRNA biomarker candidates for diagnosing melanoma. Estimating microRNA in plasma samples showed that hsa-miR-150-5p and hsa-miR-155-5p may have a diagnostic value for melanoma in stage IV (advanced). When comparing ΔCt hsa-miR-150-5p and ΔCt hsa-miR-155-5p levels in melanoma patients and healthy donors, statistically significant differences were found (p = 0.001 and p = 0.001 respectively). Rates ΔCt were significantly higher among melanoma patients (medians concerning the reference gene miR-320a were 1.63 (1.435; 2.975) and 6.345 (4.45; 6.98), respectively). Therefore, they persist only in plasma from the melanoma patients group but not in the healthy donors group. In human wild-type stage IV melanoma (MelCher) cell culture, the presence of hsa-miR-150-5p and hsa-miR-155-5p in supernatant was detected. The ability of humic substance fractions and chitosan to reduce levels of hsa-miR-150-5p and hsa-miR-155-5p was tested on MelCher cultures, which is associated with anti-melanoma activity. It was found that the hymatomelanic acid (HMA) fraction and its subfraction UPLC-HMA statistically significantly reduced the expression of miR-150-5p and miR-155-5p (p ≤ 0.05). For the humic acid (HA) fraction, this activity was determined only to reduce miR-155-5p (p ≤ 0.05). Ability to reduce miR-150-5p and miR-155-5p expression on MelCher cultures was not determined for chitosan fractions with a molecular weight of 10 kDa, 120 kDa, or 500 kDa. Anti-melanoma activity was also determined in the MTT test on MelCher cultures for explored substances. The median toxic concentration (TC50) was determined for HA, HMA and UPLC-HMA (39.3, 39.7 and 52.0 μg/mL, respectively). For 10 kDa, 120 kDa, or 500 kDa chitosan fractions TC50 was much higher compared to humic substances (508.9, 6615.9, 11352.3 μg/mL, respectively). Thus, our pilot study identified significant microRNAs for testing the in vitro anti-melanoma activity of promising drugs and melanoma diagnostics in patients. Using human melanoma cell cultures gives opportunities to test new drugs on a culture that has a microRNA profile similar to that of patients with melanoma, unlike, for example, murine melanoma cell cultures. It is necessary to conduct further studies with a large number of volunteers, which will make it possible to correlate the profile of individual microRNAs with specific patient data, including the correlation of the microRNA profile with the stage of melanoma.

Critical Considerations for Investigating MicroRNAs during Tumorigenesis: A Case Study in Conceptual and Contextual Nuances of miR-211-5p in Melanoma

MicroRNAs are non-coding RNAs fundamental to metazoan development and disease. Although the aberrant regulation of microRNAs during mammalian tumorigenesis is well established, investigations into the contributions of individual microRNAs are wrought with conflicting observations. The underlying cause of these inconsistencies is often attributed to context-specific functions of microRNAs. We propose that consideration of both context-specific factors, as well as underappreciated fundamental concepts of microRNA biology, will permit a more harmonious interpretation of ostensibly diverging data. We discuss the theory that the biological function of microRNAs is to confer robustness to specific cell states. Through this lens, we then consider the role of miR-211-5p in melanoma progression. Using literature review and meta-analyses, we demonstrate how a deep understating of domain-specific contexts is critical for moving toward a concordant understanding of miR-211-5p and other microRNAs in cancer biology.

The journey from melanocytes to melanoma

Over the past decade, melanoma has led the field in new cancer treatments, with impressive gains in on-treatment survival but more modest improvements in overall survival. Melanoma presents heterogeneity and transcriptional plasticity that recapitulates distinct melanocyte developmental states and phenotypes, allowing it to adapt to and eventually escape even the most advanced treatments. Despite remarkable advances in our understanding of melanoma biology and genetics, the melanoma cell of origin is still fiercely debated because both melanocyte stem cells and mature melanocytes can be transformed. Animal models and high-throughput single-cell sequencing approaches have opened new opportunities to address this question. Here, we discuss the melanocytic journey from the neural crest, where they emerge as melanoblasts, to the fully mature pigmented melanocytes resident in several tissues. We describe a new understanding of melanocyte biology and the different melanocyte subpopulations and microenvironments they inhabit, and how this provides unique insights into melanoma initiation and progression. We highlight recent findings on melanoma heterogeneity and transcriptional plasticity and their implications for exciting new research areas and treatment opportunities. The lessons from melanocyte biology reveal how cells that are present to protect us from the damaging effects of ultraviolet radiation reach back to their origins to become a potentially deadly cancer.

Genomic and proteomic findings in early melanoma and opportunities for early diagnosis

Overdiagnosis of early melanoma is a significant problem. Due to subtle unique and overlapping clinical and histological criteria between pigmented lesions and the risk of mortality from melanoma, some benign pigmented lesions are diagnosed as melanoma. Although histopathology is the gold standard to diagnose melanoma, there is a demand to find alternatives that are more accurate and cost-effective. In the current "omics" era, there is gaining interest in biomarkers to help diagnose melanoma early and to further understand the mechanisms driving tumor progression. Genomic investigations have attempted to differentiate malignant melanoma from benign pigmented lesions. However, genetic biomarkers of early melanoma diagnosis have not yet proven their value in the clinical setting. Protein biomarkers may be more promising since they directly influence tissue phenotype, a result of by-products of genomic mutations, posttranslational modifications and environmental factors. Uncovering relevant protein biomarkers could increase confidence in their use as diagnostic signatures. Currently, proteomic investigations of melanoma progression from pigmented lesions are limited. Studies have previously characterised the melanoma proteome from cultured cell lines and clinical samples such as serum and tissue. This has been useful in understanding how melanoma progresses into metastasis and development of resistance to adjuvant therapies. Currently, most studies focus on metastatic melanoma to find potential drug therapy targets, prognostic factors and markers of resistance. This paper reviews recent advancements in the genomics and proteomic fields and reports potential avenues, which could help identify and differentiate melanoma from benign pigmented lesions and prevent the progression of melanoma.

miRNAs: The Road from Bench to Bedside

miRNAs are small noncoding RNAs that control gene expression at the posttranscriptional level. It has been recognised that miRNA dysregulation reflects the state and function of cells and tissues, contributing to their dysfunction. The identification of hundreds of extracellular miRNAs in biological fluids has underscored their potential in the field of biomarker research. In addition, the therapeutic potential of miRNAs is receiving increasing attention in numerous conditions. On the other hand, many operative problems including stability, delivery systems, and bioavailability, still need to be solved. In this dynamic field, biopharmaceutical companies are increasingly engaged, and ongoing clinical trials point to anti-miR and miR-mimic molecules as an innovative class of molecules for upcoming therapeutic applications. This article aims to provide a comprehensive overview of current knowledge on several pending issues and new opportunities offered by miRNAs in the treatment of diseases and as early diagnostic tools in next-generation medicine.

Distinguish the Value of the Benign Nevus and Melanomas Using Machine Learning: A Meta-Analysis and Systematic Review

Background

Melanomas, the most common human malignancy, are primarily diagnosed visually, beginning with an initial clinical screening and followed potentially by dermoscopic analysis, a biopsy, and histopathological examination. We aimed to systematically review the performance and quality of machine learning-based methods in distinguishing melanoma and benign nevus in the relevant literature.

Method

Four databases (Web of Science, PubMed, Embase, and the Cochrane library) were searched to retrieve the relevant studies published until March 26, 2022. The Predictive model Deviation Risk Assessment tool (PROBAST) was used to assess the deviation risk of opposing law.

Result

This systematic review included thirty researches with 114007 subjects and 71 machine learning models. The convolutional neural network was the main machine learning method. The pooled sensitivity was 85% (95% CI 82–87%), the specificity was 86% (82–88%), and the C-index was 0.87 (0.84–0.90).

Conclusion

The findings of our study showed that ML algorithms had high sensitivity and specificity for distinguishing between melanoma and benign nevi. This suggests that state-of-the-art ML-based algorithms for distinguishing melanoma from benign nevi may be ready for clinical use. However, a large proportion of the earlier published studies had methodological flaws, such as lack of external validation and lack of clinician comparisons. The results of these studies should be interpreted with caution.

Dysplastic nevi and melanoma: microRNAs tell a divergent story

BACKGROUND

dysplastic nevi (DN) share some clinical and histological features with melanoma and have been considered intermediate lesions toward malignant transformation. However, scientific evidence of DN representing melanoma precursors is still incomplete, and many observations pointed toward their being a distinct biological entity. The current definition of DN is also confusing and the practical consequence of this uncertainty is the excessive excision of DN with severe atypia. MicroRNAs (miRNAs) are small RNAs that regulate gene expression and whose global expression can classify normal and pathological tissues.

OBJECTIVES

given these considerations, we decided to perform a small RNA profiling study in a group of DN and invasive melanomas obtained from the same patient, to assess tumor evolution according to the global microRNA expression.

METHODS

we performed a small-RNA sequencing of 6 DN, 2 congenital nevi and 4 cutaneous melanomas obtained from 4 subjects and evaluated the global miRNA expression correlation between samples.

RESULTS AND CONCLUSIONS

the hierarchical clustering and principal component analyses of global miRNA expression, independently grouped together DN and their matching congenital nevi and showed a divergence of DN miRNA profile from melanoma. Our study suggests that DN have a peculiar and different miRNA expression profile compared to melanomas developed in the same patient, thus supporting the hypothesis that DN are distinct biological entities and not melanoma precursors.

Revisiting miRNA Association with Melanoma Recurrence and Metastasis from a Machine Learning Point of View

The diagnostic and prognostic value of miRNAs in cutaneous melanoma (CM) has been broadly studied and supported by advanced bioinformatics tools. From early studies using miRNA arrays with several limitations, to the recent NGS-derived miRNA expression profiles, an accurate diagnostic panel of a comprehensive pre-specified set of miRNAs that could aid timely identification of specific cancer stages is still elusive, mainly because of the heterogeneity of the approaches and the samples. Herein, we summarize the existing studies that report several miRNAs as important diagnostic and prognostic biomarkers in CM. Using publicly available NGS data, we analyzed the correlation of specific miRNA expression profiles with the expression signatures of known gene targets. Combining network analytics with machine learning, we developed specific non-linear classification models that could successfully predict CM recurrence and metastasis, based on two newly identified miRNA signatures. Subsequent unbiased analyses and independent test sets (i.e., a dataset not used for training, as a validation cohort) using our prediction models resulted in 73.85% and 82.09% accuracy in predicting CM recurrence and metastasis, respectively. Overall, our approach combines detailed analysis of miRNA profiles with heuristic optimization and machine learning, which facilitates dimensionality reduction and optimization of the prediction models. Our approach provides an improved prediction strategy that could serve as an auxiliary tool towards precision treatment.

A new strategy for distinguishing menstrual blood from peripheral blood by the miR-451a/miR-21-5p ratio

Distinction between menstrual blood and peripheral blood is vital for forensic casework, as it could provide strong evidence to figure out the nature of some criminal cases. However, to date no single blood-specific gene, including the most variable microRNAs (miRNAs) could work well in identification of blood source. In this study, we developed a new strategy for identification of human blood samples by using the copy number ratios of miR-451a to miR-21-5p based on 133 samples, including 56 menstrual blood and 47 peripheral blood, as well as 30 non-blood samples of saliva (10), semen (10) and vaginal secretion (10). The cut-off value and efficacy of the identification strategy were determined through receiver operating characteristic (ROC) analysis. Our results showed that when the miR-451a/miR-21-5p ratio below 0.929, the sample should be non-blood. In contrast, when the miR-451a/miR-21-5p ratio above 0.929 and below 10.201, the sample should be menstrual blood; and when this ratio above 10.201, the sample should be peripheral blood. External validation using 86 samples (62 menstrual blood and 24 peripheral blood samples) fully supported this strategy with the 100% sensitivity and 100% specificity. We confirmed that this result accuracy was not affected by various potential confounding factors of samples and different experimental platforms. We showed that 0.2 ng of total RNA from menstrual blood and peripheral blood was sufficient for qPCR quantification. In conclusion, our results provide an accurate reference to distinguish menstrual blood from peripheral blood for forensic authentication.

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

Benign melanocytic nevi frequently emerge when an acquired BRAFV600E mutation triggers unchecked proliferation and subsequent arrest in melanocytes. Recent observations have challenged the role of oncogene-induced senescence in melanocytic nevus formation, necessitating investigations into alternative mechanisms for the establishment and maintenance of proliferation arrest in nevi. We compared the transcriptomes of melanocytes from healthy human skin, nevi, and melanomas arising from nevi and identified a set of microRNAs as highly expressed nevus-enriched transcripts. Two of these microRNAs-MIR211-5p and MIR328-3p-induced mitotic failure, genome duplication, and proliferation arrest in human melanocytes through convergent targeting of AURKB. We demonstrate that BRAFV600E induces a similar proliferation arrest in primary human melanocytes that is both reversible and conditional. Specifically, BRAFV600E expression stimulates either arrest or proliferation depending on the differentiation state of the melanocyte. We report genome duplication in human melanocytic nevi, reciprocal expression of AURKB and microRNAs in nevi and melanomas, and rescue of arrested human nevus cells with AURKB expression. Taken together, our data describe an alternative molecular mechanism for melanocytic nevus formation that is congruent with both experimental and clinical observations.

Dysplastic Nevi: Morphology and Molecular and the Controversies In-between

Dysplastic nevi are distinctive melanocytic lesions in the larger group of atypical nevi. They often are multiple and sporadic with genetic features intermediate between common acquired nevi and melanoma. Dysplastic nevi may be multiple, familial, and seen in patients with familial melanoma syndrome. Although their behavior is benign, they rarely represent a precursor to melanoma. If clinically suspicious, dysplastic nevi should be removed for adequate histopathologic examination and to exclude possibility of melanoma. Partial sampling should be avoided because reliable separation from melanoma requires visualization of the entire lesion to allow for examination of architectural histopathologic features and avoid sampling error.

Molecular Biomarkers for Melanoma Screening, Diagnosis and Prognosis: Current State and Future Prospects

Despite significant progress in the development of treatment options, melanoma remains a leading cause of death due to skin cancer. Advances in our understanding of the genetic, transcriptomic, and morphologic spectrum of benign and malignant melanocytic neoplasia have enabled the field to propose biomarkers with potential diagnostic, prognostic, and predictive value. While these proposed biomarkers have the potential to improve clinical decision making at multiple critical intervention points, most remain unvalidated. Clinical validation of even the most commonly assessed biomarkers will require substantial resources, including limited clinical specimens. It is therefore important to consider the properties that constitute a relevant and clinically-useful biomarker-based test prior to engaging in large validation studies. In this review article we adapt an established framework for determining minimally-useful biomarker test characteristics, and apply this framework to a discussion of currently used and proposed biomarkers designed to aid melanoma detection, staging, prognosis, and choice of treatment.

MicroRNA-21-Enriched Exosomes as Epigenetic Regulators in Melanomagenesis and Melanoma Progression: The Impact of Western Lifestyle Factors

DNA mutation-induced activation of RAS-BRAF-MEK-ERK signaling associated with intermittent or chronic ultraviolet (UV) irradiation cannot exclusively explain the excessive increase of malignant melanoma (MM) incidence since the 1950s. Malignant conversion of a melanocyte to an MM cell and metastatic MM is associated with a steady increase in microRNA-21 (miR-21). At the epigenetic level, miR-21 inhibits key tumor suppressors of the RAS-BRAF signaling pathway enhancing proliferation and MM progression. Increased MM cell levels of miR-21 either result from endogenous upregulation of melanocytic miR-21 expression or by uptake of miR-21-enriched exogenous exosomes. Based on epidemiological data and translational evidence, this review provides deeper insights into environmentally and metabolically induced exosomal miR-21 trafficking beyond UV-irradiation in melanomagenesis and MM progression. Sources of miR-21-enriched exosomes include UV-irradiated keratinocytes, adipocyte-derived exosomes in obesity, airway epithelium-derived exosomes generated by smoking and pollution, diet-related exosomes and inflammation-induced exosomes, which may synergistically increase the exosomal miR-21 burden of the melanocyte, the transformed MM cell and its tumor environment. Several therapeutic agents that suppress MM cell growth and proliferation attenuate miR-21 expression. These include miR-21 antagonists, metformin, kinase inhibitors, beta-blockers, vitamin D, and plant-derived bioactive compounds, which may represent new options for the prevention and treatment of MM.

Ciliation Index Is a Useful Diagnostic Tool in Challenging Spitzoid Melanocytic Neoplasms

The loss of primary cilia on melanocytes is a useful biomarker for the distinction of melanoma from conventional melanocytic nevi. It is unknown whether ciliation status is beneficial for diagnosing spitzoid tumors-a subclass of melanomas that present inherently ambiguous histology and are challenging to classify. We evaluated the Ciliation Index (CI) in 68 cases of spitzoid tumors ranging from Spitz nevi and atypical Spitz tumors to spitzoid melanoma. We found a significant decrease in CI within the spitzoid melanoma group when compared with either the Spitz nevi or atypical Spitz tumors groups. In addition, we used a machine-learning-based algorithm to determine the value of CI when considered in combination with other histopathologic and molecular features commonly used for diagnosis. We found that a low CI was consistently ranked as a top predictive feature in the diagnosis of malignancy. Predictive models trained on only the top four predictive features (CI, asymmetry, hyperchromatism, and cytologic atypia) outperformed standard histologic assessment in an independent validation cohort of 56 additional cases. The results provide an alternative approach to evaluate diagnostically challenging melanocytic lesions, and further support the use of CI as an ancillary diagnostic test.

Defining the Prognostic Role of MicroRNAs in Cutaneous Melanoma

Breslow thickness (BT) is the most important histopathologic factor for primary melanoma staging. BT determines the margins for wide local excision whether sentinel lymph node biopsy should be performed and subsequent melanoma staging, and patient management. The correct determination of a 0.8-mm cutoff in melanoma is important for pathologists because discrepancies leading to a change in stage can have significant clinical implications, including incorrect and/or inappropriate prognostic information, investigation, management, and follow-up. Difficulties in BT determination are mostly represented by the presence of regression or melanoma associated with a pre-existing nevus. This study aimed at investigating a molecular parameter, namely microRNA (miRNA) expression, in reference to BT assessment. Melanoma cell proliferation is influenced by miRNA dysregulation. Indeed, some miRNAs sustain and induce proliferative signals or repress growth-suppressive pathways, thereby promoting melanoma carcinogenesis. To identify the miRNAs correlating with BT, we analyzed our global miRNA expression data of 20 thin melanomas and identified two potential candidates, miR-21-5p and miR-146a-5p. We assessed the expression of these two specific miRNAs in 90 archive formalin-fixed and paraffin-embedded samples of superficially spreading melanomas (SSMs) and 25 nodular melanomas from two independent cohorts and correlated the individual and combined miRNA expression with BT and other tumor characteristics. The individually normalized expression of miR-21-5p and miR-146a-5p showed a highly significant and linear correlation with BT in SSM, and their combined expression value was more strongly correlated (Pearson's r = 0.799, 95% CI = 0.71-0.86) than their individual expressions. This correlation was not significant in nodular melanoma. In SSM, we observed that the combined miRNA expression above or below 1.5 was significantly associated with overall survival and successfully identified all patients with relapsing SSM. We concluded that the combined assessment of miR-21-5p and miR-146a-5p expression in superficially spreading melanoma, in association with BT measurement, could aid pathologists in SSM staging.

Clinical Implications of Primary Cilia in Skin Cancer

The primary cilium is a cell surface organelle that is an important component of cellular biology. While it was once believed to be a vestigial structure without biologic function, it is now known to have essential roles in critical cellular signaling pathways such as Hedgehog (HH) and Wnt. The HH and Wnt pathways are involved in pathogenesis of basal cell carcinoma and melanoma, respectively, and this knowledge is now beginning to inform therapeutic and diagnostic options for patients. The purpose of this review is to familiarize clinicians with primary cilia biology and how this complex cellular organelle has started to translate into clinical care.

The miRNAs Role in Melanoma and in Its Resistance to Therapy

Melanoma is the less common but the most malignant skin cancer. Since the survival rate of melanoma metastasis is about 10–15%, many different studies have been carried out in order to find a more effective treatment. Although the development of target-based therapies and immunotherapeutic strategies has improved chances for patient survival, melanoma treatment still remains a big challenge for oncologists. Here, we collect recent data about the emerging role of melanoma-associated microRNAs (miRNAs) currently available treatments, and their involvement in drug resistance. We also reviewed miRNAs as prognostic factors, because of their chemical stability and resistance to RNase activity, in melanoma progression. Moreover, despite miRNAs being considered small conserved regulators with the limitation of target specificity, we outline the dual role of melanoma-associated miRNAs, as oncogenic and/or tumor suppressive factors, compared to other tumors.

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

Identification of quantitative molecular biomarkers to distinguish melanoma from nevi is highly desirable. Expressions of microRNAs (miRNAs) are promising candidates but lack consensus in many studies. Torres et al. (2020) utilized a machine learning pipeline to identify miRNA ratios as strong biomarkers. Results indicate that machine learning, although powerful, requires human input to identify high quality biomarker signatures.