Papanicolau-Sengos et. al studied and classified subtypes of existing renal neoplasms using machine learning models to assist with future diagnostic measures. Analyzing DNA methylation profiles for renal neoplasm samples (n=2026) using hierarchical clustering and Uniform Manifold Approximation and Projection for Dimension Reduction (UMAP), the researchers identified distinct methylation signatures and created 23 neoplastic methylation classes. Moreover, they made a predictive classification algorithm using a support vector machine model to classify renal neoplasms and performed differential methylation promoter analysis on the samples. These models and analyses demonstrate the ability to define specific subclasses, including clear cell RCC and papillary RCC, each defined into more specific epigenetic classes despite having a standard methylation profile across cases. Certain categories, such as pRRC D, that were highly stable, had significant co-occurring mutations, leading to the poorest prognosis within these subgroups. Overall, the study highlights how DNA methylation profiling can resolve tumor heterogeneity and refine classification systems within renal neoplasms.