Researchers at the Technical University of Denmark (DTU) have developed a new computer program that can fully diagnose the origin of hard to identify cancers in just two days, reports Sciencealert.
At present, clinical techniques can successfully diagnose the majority of cancers and their primary site, but in some cases, approximately one in 20, doctors cannot find the source of a cancer.
In these cases, patients will require a range of further diagnostic tests before the origin can be fully determined.
These additional stages of investigation take time, and time is precious when it comes to cancer. The need for further tests can lead to delays in treatment, delays that can prove to be critical in defining a patient’s long-term prognosis and their chances of surviving cancer.
Even after extensive testing, there are still 2-3 percent of cases where it is simply not possible to locate the origin of a cancer using existing methods. The cancer will then be deemed as a CUP – cancer of unknown primary origin.
This has implications for the quality and precision of cancer treatment that can be prescribed. When the location of a cancer’s origin is unclear, patients are given a cocktail of chemotherapy drugs which employ an element of guesswork. As a result, the treatment may not even target the appropriate cells and greatly reduces the chances of successful treatment.
It is precisely this two to three percent of problem cases that DTU’s new computer program can target through a fusion of genetics and computer science.
Called “TumorTrace” by researchers, this new program is a self-learning set of algorithms, which uses DNA analysis of mutations in cancer tissue samples taken from patients with metastasized cancer – cancer that has spread.
By comparing thousands of samples, patterns of mutations are collated with computing power. The program is then able to assess a biopsy, provide a number of scenarios for where the cancer may have developed and indicate the probability of those scenarios.
In doing so, it can identify the most likely primary localization of a cancer within a time frame of 48 hours.
The program was tested by researchers on thousands of samples where the primary tumor had already been identified, and achieved an 85 percent success rate.
The next stage of development will involve testing the method on patients that have unknown primary tumors.
Aron Eklund, Associate Professor from DTU Systems Biology, writing on the Department’s website, said, “We are very pleased that we can now use sequencing data together with our new algorithms to provide a much faster diagnosis for cancer cases that are difficult to diagnose, and in cases which are currently impossible to diagnose.”
“At the moment, it takes researchers two days to obtain a biopsy result, but we expect this time to be reduced as it becomes possible to do the sequencing increasingly faster. And it will be straightforward to integrate the method with the methods already being used by doctors.”
DTU Systems Biology is an interdisciplinary research department that covers the fields of cellular, molecular and structural biology, bioinformatics, computational biology, industrial biotechnology, biomedicine and health.
The DTU Researchers say they hope that in the future such programs, which blend computing power with DNA sequencing, will be used to identify the sources of free cancer cells from just a mere blood sample.
It could also provide an easy, quick and reliable way of regularly screening and monitoring those individuals who are known to be at a higher risk of developing cancer due to their genetic disposition.
[Image courtesy of DTU Systems]