In a new study, researchers have combined “liquid biopsy”, epigenetic alterations and machine learning to develop a blood test to detect and classify cancer at its earliest stages.
The study was led by cancer scientists Dr. Daniel De Carvalho at Princess Margaret Cancer Centre, University Health Network.
The findings describe not only a way to detect cancer, but hold the promise of being able to find it earlier when it is more easily treated and long before symptoms ever appear.
A major problem in cancer is how to detect it early.
It has been a ‘needle in the haystack’ problem of how to find that one-in-a-billion cancer-specific mutation in the blood, especially at earlier stages, where the amount of tumor DNA in the blood is minimal.
By profiling epigenetic alterations instead of mutations, the team was able to identify thousands of modifications unique to each cancer type.
Then, they used a big data approach and applied machine learning to create classifiers able to identify the presence of cancer-derived DNA within blood samples and to determine what cancer type.
This basically turns the ‘one needle in the haystack’ problem into a more solvable ‘thousands of needles in the haystack’, where the computer just needs to find a few needles to define which haystack has needles.
The researchers tracked the cancer origin and type by comparing 300 patient tumor samples from seven disease sites (lung, pancreatic, colorectal, breast, leukemia, bladder and kidney) and samples from healthy donors with the analysis of cell-free DNA circulating in the blood plasma.
In each sample, the “floating” plasma DNA matched the tumor DNA.
The team has since expanded the research and has now profiled and successfully matched more than 700 tumor and blood samples from more cancer types.
Their next steps to further validate this approach include analyzing data from large population health research studies already underway in several countries, where blood samples were collected months to years before cancer diagnosis.
Then the approach will need to be ultimately validated in prospective studies for cancer screening.
The findings are published in Nature.
Copyright © 2018 Knowridge Science Report. All rights reserved.