AI Promises to Ramp Up PCR Tests for Faster DNA Diagnostics and Forensics
Promising new inroads into critical DNA testing forecast by experts applying machine learning to DNA profiling
From medical diagnostics to forensic tests and national security, PCR (polymerase chain reaction) DNA profiling has revolutionized high-throughput sampling this century—but little has changed since it was developed in the 1980s.
“Even a small improvement in PCR performance could have a huge impact on the hundreds of thousands of forensic and intelligence DNA samples amplified every year—notably when samples are degraded,” say experts, including Flinders University professor Duncan Taylor, PhD, from Forensic Science SA, a forensic consultant agency in Australia.
The new research, published in Genes, discovered significant improvements both in the quality of DNA profiling and more efficient PCR cycling conditions with the use of artificial intelligence methods, says College of Science and Engineering PhD candidate Caitlin McDonald, who led the study.
“Our system has the potential to overcome challenges that have hindered forensic scientists for decades, especially with trace, inhibited, or degraded samples,” says McDonald, who recently presented on the study at the International Society of Forensic Genetics conference.
“By intelligently optimizing PCR for a wide variety of sample types, it can dramatically enhance amplification success, delivering more reliable results in even the most complex cases.
“Beyond forensics, this system has the capacity to revolutionize other fields that depend on PCR, such as clinical diagnostics and environmental monitoring, by boosting efficiency, reducing errors, and enabling high-throughput analysis across diverse applications.”
PCR is a common laboratory technique used to amplify or copy small segments of genetic material, for example, in DNA fingerprinting, diagnosing genetic disorders, or detecting bacteria or viruses such as COVID-19.
Backed by other Flinders University’s College of Science and Engineering experts, including professor Adrian Linacre and AI computer scientist associate professor Russell Brinkworth, the study used machine learning to create new “smart PCR” systems—targeting large-scale potential alterations and faster cycling conditions for rapid and more accurate results.
The latest article in Genes develops and then conducts large-scale tests of the new smart PCR system.
Linacre, who focuses on DNA forensic technologies, says PCR is widely used across various fields and applications, including forensic science, animal research, medicine, and national security.
“AI and machine learning are so new, yet harnessed correctly, have the possibility to greatly increase the sensitivity of PCR testing,” says Linacre.
He says research on noncoding sections of DNA has been carried out in forensic testing since 1994.
“With further research, these AI-ML methods have potential to improve the quality of DNA evidence used in criminal investigations, and to increase the quality of trace DNA samples, enhancing the criminal justice process.”
Brinkworth says improving existing processes will further define AI applications in the future.
“Traditionally DNA amplification required all settings to be in place before the process commenced. This did not take into account the many possible differences between samples and conditions,” adds Brinkworth.
“By utilizing advances in machine learning and sensors, we have changed the process of PCR from a one-size-fits-all to a customized and optimized individual experience. Producing higher quality and quantity DNA faster than previously possible.”
References:
- Caitlin McDonald et al. Developing a machine-learning 'smart' PCR thermocycler, part 1: Construction of a theoretical framework. Genes (2024). DOI: 10.3390/genes15091196
- Caitlin McDonald et al. Developing a machine learning 'Smart' polymerase chain reaction thermocycler part 2: Putting the theoretical framework into practice. Genes (2024). DOI: 10.3390/genes15091199