Back

Detection of Circulating Tumor-specific DNA Methylation Markers in the Blood of Patients with Pituitary Tumors.

Wells, M.; Asmaro, K. P.; Sabedot, T. S.; Malta, T. M.; Mosella, M. S.; Nelson, K.; Snyder, J.; deCarvalho, A.; Mukherjee, A.; Chitale, D.; Robin, A.; Rosemblum, M.; Mikkelsen, T.; Poisson, L. M.; Lee, I. Y.; Walbert, T.; Bahn, A.; Kalkanis, S.; Rock, J.; Noushmehr, H.; Castro, A. V.

2020-05-30 endocrinology
10.1101/2020.05.29.20116202 medRxiv
Show abstract

Genome-wide DNA methylation aberrations are pervasive and associated with clinicopathological features across pituitary tumors (PT) subtypes. The feasibility to detect CpG methylation abnormalities in circulating cell-free DNA (cfDNA) has been reported in central nervous system tumors other than PT. Here, we aimed to profile and identify methylome-based signatures in the serum of patients harboring PT (n =13). Our analysis indicated that serum cfDNA methylome from patients with PT are distinct from the counterparts in patients with other tumors (gliomas, meningiomas, colorectal carcinomas, n =134) and nontumor conditions (n = 4). Furthermore, the serum methylome patterns across PT was associated with functional status and adenohypophyseal cell lineage PT subtypes, recapitulating epigenetic features reported in PT-tissue. A machine learning algorithm using serum PT-specific signatures generated a score that distinguished PT from non-PT conditions with 100% accuracy in our validation set. These preliminary results underpin the potential clinical application of a liquid biopsy-based DNA methylation profiling as a noninvasive approach to identify clinically relevant epigenetic markers that can be used in the management of PT.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.