AI Tool Fragle Simplifies and Speeds Up Cancer Monitoring Through Blood DNA Analysis

Scientists from the ASTAR Genome Institute of Singapore (ASTAR GIS) have developed an innovative artificial intelligence (AI) tool called "Fragle" that simplifies and accelerates cancer monitoring through blood tests. Published in Nature Biomedical Engineering in March 2025, this research aims to make cancer treatment response tracking more accurate and frequent, thereby improving patient outcomes. Traditional methods for measuring circulating tumor DNA (ctDNA) in the blood often rely on complex and expensive DNA sequencing techniques that screen for common cancer mutations. However, since cancer mutations vary widely among patients, these methods can produce inconsistent results, making it challenging for doctors to monitor the effectiveness of cancer treatments effectively. Fragle addresses this issue by focusing on the physical characteristics of DNA fragments rather than their sequences. Specifically, it uses AI to analyze the size distribution of DNA fragments in the blood, where cancer DNA typically exhibits distinct size patterns compared to healthy DNA. This novel approach requires only a small blood sample and can identify these unique patterns rapidly and at a lower cost. The high reliability of Fragle has been demonstrated through extensive testing on hundreds of blood samples from cancer patients, including various types of cancers. Moreover, the method’s versatility means it can integrate seamlessly with most DNA profiling techniques already in use in hospitals or available through commercial providers. Associate Professor Daniel Tan, a Senior Consultant at the National Cancer Center Singapore (NCCS) and co-author of the study, highlighted the potential of Fragle in early relapse detection, stating, "We are excited to initiate studies on how methods such as Fragle can detect disease relapse earlier in local lung cancer patients." The NCCS and A*STAR GIS have embarked on a joint study involving over 100 clinical trial participants. These patients are being monitored every two months during treatment to detect early signs of relapse and predict treatment responses, which could lead to more personalized and effective treatment plans. Dr. Anders Skanderup, the lead author and Senior Principal Scientist at A*STAR GIS Laboratory of Computational Cancer Genomics, drew an interesting parallel between the use of Fragle and the monitoring of viral particles in wastewater for COVID-19. He explained, "Just as scientists tracked COVID-19 outbreaks by detecting viral particles in wastewater, Fragle analyzes DNA fragments in blood to monitor cancer treatment response and detect relapse early." This analogy underscores the non-invasive and continuous nature of the monitoring process, much like how wastewater surveillance provided real-time data on viral spread. The team is actively working on enhancing Fragle's sensitivity to detect even lower levels of cancer DNA, which is crucial for identifying early signs of disease recurrence. Dr. Skanderup added, "While existing methods have their strengths, they are often complex and expensive. We wanted to develop a simpler, more affordable, and accessible approach—one that could support accurate monitoring without adding burden to clinical workflows." To ensure broader implementation and impact, the researchers are collaborating with the NCCS to identify practical clinical applications and opportunities. The ultimate goal is to integrate Fragle into routine clinical practices, allowing healthcare professionals to detect and track cancer more precisely and monitor treatments more effectively. Executive Director Dr. Wan Yue of A*STAR GIS emphasized this point, saying, "We are very excited about the potential Fragle brings, to help our health care professionals detect and track cancer more accurately and monitor treatments more effectively, leading to better cancer care for patients. It is our hope that our genomic research can be translated to benefit population health not only in Singapore but worldwide." Fragle's development marks a significant milestone in the field of liquid biopsy for cancer monitoring. By leveraging AI to analyze physical properties of DNA, it offers a more streamlined and cost-effective solution compared to traditional sequencing methods. Industry experts commend this advancement, noting that it could revolutionize the way clinicians manage cancer by providing more frequent and reliable data points. This could lead to more timely interventions and better outcomes for patients. A*STAR GIS, a leading research institute in genomics and computational biology, has a strong track record of translating cutting-edge research into practical clinical tools. The collaboration with NCCS further strengthens the potential for Fragle to make a meaningful impact on cancer care. The ongoing clinical trials are expected to provide valuable insights into the tool's effectiveness and pave the way for its widespread adoption in cancer monitoring strategies.