Flinders University researchers have demonstrated a novel use of machine learning that improves the quality of DNA profiling as well as improves PCR cycling condition efficiency.
While PCR DNA profiling revolutionized high throughput sampling, little has changed in the process since its development over 30 years ago. In the research, published in the journal Genes, the researchers demonstrated significant improvement in both the quality of DNA profiling and the efficiency of the PCR cycling conditions by using artificial intelligence methods.
“Our system has the potential to overcome challenges that have hindered forensic scientists for decades, especially with trace, inhibited or degraded samples,” said Caitlin McDonald, PhD candidate in the College of Science and Engineering. “By intelligently optimising 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 revolutionise 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.”
The team feels that with further research, machine learning methods could enhance the criminal justice process by significantly improving the quality of DNA, and trace DNA evidence used in criminal investigations.
“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,” said Associate Professor Russell Brinkworth.
“By utilising advances in machine learning and sensors, we have changed the process of PCR from a one-size-fits-all to a customised and optimised individual experience. Producing higher quality and quantity DNA faster than previously possible.”