Scientists from the A*STAR Genome Institute of Singapore (A*STAR GIS) have developed a new artificial intelligence (AI)-based method called "Fragle" that makes tracking cancer easier and faster using blood tests.

Requiring only a small blood sample, this method analyses the size of DNA fragments in the blood to reveal distinct patterns that differentiate cancer DNA from healthy DNA, helping doctors track cancer treatment response more accurately and frequently.

The research was published in Nature Biomedical Engineering in March 2025.

Existing methods for measuring cancer DNA in the blood, also known as circulating tumour DNA (ctDNA), often require complex and expensive DNA sequencing to screen for common cancer mutations.

However, because cancer mutations vary between patients, test results can be inconsistent, making it difficult for doctors to track cancer treatment response with blood tests effectively.

Fragle uses AI to analyse the size of DNA fragments in the blood.

Cancer DNA tends to exhibit different size patterns compared to healthy DNA, and the Fragle AI-model can identify these differences using very small amounts of DNA.

As a result, the method allows for faster and more affordable cancer tracking.

It has also demonstrated high reliability, delivering accurate results across blood samples from hundreds of cancer patients and distinct cancer types.

Additionally, the method is versatile and compatible with most DNA profiling techniques commonly used in hospitals or offered by commercial providers.

Key Benefits of Fragle:

• Faster and cheaper: Fragle offers a faster and potentially more affordable way to monitor cancer through blood tests, requiring only a small amount of DNA. Conventional commercial tests can cost over SGD $1000, whereas the estimated cost of Fragle is less than SGD $50. 
• Versatile: Fragle works with widely used DNA profiling methods in hospitals and commercial labs, allowing for easy and fast adoption into existing workflows.
• Detects early signs of relapse: Fragle can identify tiny traces of cancer left after surgery and treatment (known as minimal residual disease, or MRD), helping doctors detect potential relapse early.

"Just as scientists tracked COVID-19 outbreaks by detecting viral particles in wastewater, Fragle analyses DNA fragments in blood to monitor cancer treatment response and detect relapse early," explains Dr Anders Skanderup, Senior Principal Scientist at A*STAR GIS Laboratory of Computational Cancer Genomics, and the lead author of this research.

" 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. “

The team is also looking into improving Fragle’s sensitivity to detect even lower levels of cancer DNA, which is critical for earlier detection of disease relapse in cancer patients.

To translate these findings, the team is also collaborating with the National Cancer Centre Singapore (NCCS) to identify clinical opportunities and applications.

Moving ahead, the team plans to explore how Fragle can be implemented in local hospitals to improve cancer patient care.

Associate Professor Daniel Tan, Senior Consultant, Division of Medical Oncology, National Cancer Centre Singapore and co-author of the study, “We are excited to initiate studies on how methods such as Fragle can detect disease relapse earlier in local lung cancer patients.”

In an ongoing study of over 100 clinical trial patients, the GIS-NCCS team is using Fragle to monitor ctDNA levels every two months during treatment, with the aim of catching signs of relapse before they appear on routine scans.

The team is also studying whether early changes in ctDNA can identify which patients are likely to have a favourable or poor response to the therapy.

The goal of the study is to assess the value of incorporating ctDNA tests in routine monitoring of cancer patients during treatment.

Dr Wan Yue, Executive Director at A*STAR GIS, “We are very excited about the potential Fragle brings, to help our healthcare 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.”

Source: Agency for Science, Technology and Research (A*STAR), Singapore