@article {Collin422675, author = {Francois Collin and Yuhong Ning and Tierney Phillips and Erin McCarthy and Aaron Scott and Chris Ellison and Chin-Jen Ku and Gulfem D Guler and Kim Chau and Alan Ashworth and Stephen R Quake and Samuel Levy}, title = {Detection of early stage pancreatic cancer using 5-hydroxymethylcytosine signatures in circulating cell free DNA}, elocation-id = {422675}, year = {2018}, doi = {10.1101/422675}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Pancreatic cancers are typically diagnosed at late stage where disease prognosis is poor as exemplified by a 5-year survival rate of 8.2\%. Earlier diagnosis would be beneficial by enabling surgical resection or earlier application of therapeutic regimens. We investigated the detection of pancreatic ductal adenocarcinoma (PDAC) in a non-invasive manner by interrogating changes in 5-hydroxymethylation cytosine status (5hmC) of circulating cell free DNA in the plasma of a PDAC cohort (n=51) in comparison with a non-cancer cohort (n=41). We found that 5hmC sites are enriched in a disease and stage specific manner in exons, 3{\textquoteright}UTRs and transcription termination sites. Our data show that 5hmC density in H3K4me3 sites is reduced in progressive disease suggesting increased transcriptional activity. 5hmC density is differentially represented in thousands of genes, and a stringently filtered set of the most significant genes exhibited biology related to pancreas (GATA4, GATA6, PROX1, ONECUT1) and/or cancer development (YAP1, TEAD1, PROX1, ONECUT1, ONECUT2, IGF1 and IGF2). Regularized regression models were built using 5hmC densities in statistically filtered genes or a comprehensive set of highly variable gene counts and performed with an AUC = 0.94-0.96 on training data. We were able to test the ability to classify PDAC and non-cancer samples with the elastic net and lasso models on two external pancreatic cancer 5hmC data sets and found validation performance to be AUC = 0.74-0.97. The findings suggest that 5hmC changes enable classification of PDAC patients with high fidelity and are worthy of further investigation on larger cohorts of patient samples.}, URL = {https://www.biorxiv.org/content/early/2018/09/20/422675}, eprint = {https://www.biorxiv.org/content/early/2018/09/20/422675.full.pdf}, journal = {bioRxiv} }