The research published in the journal Nature holds promise of being able to find cancer earlier when it is more easily treated and long before symptoms ever appear.
Led by Dr. Daniel De Carvalho Senior Scientist at Princess Margaret Cancer Centre, the researchers profiled epigenetic alterations instead of mutations, allowing them to identify thousands of modifications unique to each cancer type. Then, using a big data approach, they applied machine learning to create classifiers able to identify the presence of cancer-derived DNA within blood samples and to determine what cancer type.
In essence the approach 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 scientists tracked the cancer origin and type by comparing 300 patient tumour 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 every sample, the "floating" plasma DNA matched the tumour DNA.
Since that initial test run, the researchers have now profiled and successfully matched more than 700 tumour and blood samples from more cancer types.
While the approach is a long way from being validated for clinical use, the results promise to take a large step closer to a meaningful blood test for cancer. To get there the researchers next will analyze blood from large population studies of cancer that collected blood samples. After that the approach will need to be tested in prospective studies where the new test will be used alongside conventional cancer diagnostic tests to see if it works in patients before their cancer status is known.
No comments:
Post a Comment