RT Journal Article
SR Electronic
T1 Machine Classification of Methylomes in Cancer
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2020.04.04.025155
DO 10.1101/2020.04.04.025155
A1 Newsham, Isabelle
A1 Sendera, Marcin
A1 Jammula, SriGanesh
A1 Fitzgerald, Rebecca
A1 Massie, Charles
A1 Samarajiwa, Shamith A.
YR 2020
UL http://biorxiv.org/content/early/2020/04/05/2020.04.04.025155.abstract
AB 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.TCGAThe Cancer Genome AtlasBLCABladder urothelial carcinomaBRCABreast invasive carcinomaCOADColon adenocarcinomaESCAEsophageal carcinomaHNSCHead and neck squamous cell carcinomaKIRCKidney renal clear cell carcinomaKIRPKidney renal papillary cell carcinomaLIHCLiver hepatocellular carcinomaLUADLung adenocarcinomaLUSCLung squamous cell carcinomaPRADProstate adenocarcinomaTHCAThyroid carcinomaUCECUterine corpus endometrial carcinomaAUCArea Under the CurveROCReceiver Operating CharacteristicMCCMatthews Correlation CoefficientUMAPUniform manifold approximation and projection