Researchers at City of Hope and Translational Genomics Research Institute (TGen) have made significant progress in developing a machine-learning tool that has the potential to detect cancer at earlier stages using smaller blood draws. The study, published in the journal Science Translational Medicine, demonstrates the enormous potential of this new technology.
The team’s goal is to enable the earlier detection of cancer in patients when it is more treatable and possibly curable. According to Cristian Tomasetti, Ph.D., director of City of Hope’s Center for Cancer Prevention and Early Detection, detecting cancer at later stages significantly reduces the chances of survival. For example, if breast cancer is diagnosed at Stage 1, the five-year survival rate is 99%, but if it is found at Stage 4, the survival rate drops to only 31%.
The researchers developed and tested an algorithm called Alu Profile Learning Using Sequencing (A-Plus), which was able to accurately identify half of the cancers across 11 different types. Moreover, the false positive rate was only one out of every 100 tested, making the algorithm highly accurate.
The technology relies on the fact that when cells die, some of their DNA material leaks into the bloodstream. By analyzing the cell-free DNA (cfDNA) found in the blood, researchers can detect cancer signals. Cancer cfDNA fragments break down at altered spots in repetitive regions of the genome, which is hypothesized to be more prevalent in cancer cells compared to normal cells.
The novelty of this approach lies in its focus on analyzing the difference in fragmentation patterns in repetitive regions of cancer and normal cfDNA, rather than specific DNA mutations. This method, known as fragmentomics, requires only about eight times less blood than traditional whole genome sequencing, making it more practical for clinical applications.
The team is now preparing to open a clinical trial in summer 2024 to compare the fragmentomics blood testing approach to standard-of-care methods in adults aged 65-75. This trial will evaluate the effectiveness of the biomarker panel in detecting cancer at earlier stages when it is more treatable. The ultimate goal is to revolutionize cancer detection and make routine blood tests for cancer a reality.
City of Hope’s Center for Cancer Prevention and Early Detection aims to develop innovative technologies based on noninvasive blood tests and imaging to detect cancers years before conventional diagnostic methods. Their continuous success in this field and validation through clinical trials could potentially change the landscape of cancer detection and improve patient outcomes.
