Current gold standard diagnostic strategies are unable to accurately differentiate malignant from benign small renal masses preoperatively; consequently, 20% of patients undergo unnecessary surgery. Devising a more confident presurgical diagnosis is key to improving treatment decision-making. We therefore developed MethylBoostER, a machine learning model leveraging DNA methylation data from 1228 tissue samples, to classify pathological subtypes of renal tumors (benign oncocytoma, clear cell, papillary, and chromophobe RCC) and normal kidney. The prediction accuracy in the testing set was 0.960, with class-wise ROC AUCs >0.988 for all classes. External validation was performed on >500 samples from four independent datasets, achieving AUCs >0.89 for all classes and average accuracies of 0.824, 0.703, 0.875, and 0.894 for the four datasets. Furthermore, consistent classification of multiregion samples (
N
= 185) from the same patient demonstrates that methylation heterogeneity does not limit model applicability. Following further clinical studies, MethylBoostER could facilitate a more confident presurgical diagnosis to guide treatment decision-making in the future.
Cancer remains a leading cause of morbidity and mortality worldwide. Its evolutionary nature and resultant complex interactions with the tumour micro-environment and the host immune system engender heterogeneity, make developing interventions difficult. Usually detected at the advanced stages of disease, metastatic cancer accounts for 90% of cancer-associated deaths. Therefore early detection of cancer, combined with current therapies, would have a significant impact on survival and treatment of this insidious disease. Epigenetic changes such as DNA methylation are some of the early events in carcinogenesis. Here, we report on a machine learning model that can classify 13 types of cancer as well as non-cancer tissue samples using only DNA methylome data, with an accuracy of 98.2%. We utilise the features identified by this model to develop a robust deep neural network that can generalise to independent data sets. We also demonstrate that the methylation associated genomic loci detected by the classifier are associated with genes involved in cancer, providing insights into the epigenomic regulation of carcinogenesis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.