medwireNews: Researchers have developed a method that not only detects the presence of cancer from a blood sample, but also identifies the tissue of origin.
The method, called CancerLocator, relies on identifying atypical DNA methylation patterns in cell-free DNA isolated from blood samples. The developers behind it explain that tumor cells often show aberrant DNA methylation, making it “an ideal target for cancer diagnosis in clinical practice.”
To create the program, the investigators used data from The Cancer Genome Atlas to identify the defining DNA methylation features of different tumor types; they also analyzed healthy samples to establish the methylation pattern of noncancerous tissue. Using this information, the program determines the likelihood of a methylation profile derived from a patient’s sample being cancerous, and if so, identifying the primary tumor type.
As reported in Genome Biology, CancerLocator outperformed two established general-purpose classification methods, with an overall error rate of 0.265, compared with 0.646 and 0.604 for the Random Forest and Support Vector Machine methods, respectively.
Study author Xianghong Jasmine Zhou, from the University of California at Los Angeles in the USA, told the press that “[t]he technology is in its infancy and requires further validation, but the potential benefits to patients are huge.”
medwireNews is an independent medical news service provided by Springer Healthcare. © 2017 Springer Healthcare part of the Springer Nature group