Can AI Transform DNA Evidence?
Mon, April 19, 2021

Can AI Transform DNA Evidence?

Scientists are developing more artificial techniques to extract DNA profiles / Credits: natalimis via 123RF

 

DNA evidence has played a critical role in solving various cases across the world. However, flawed techniques can send innocent people to prison. For instance, a man named David Butler was arrested for allegedly murdering Anne Marie Foy, a 46-year-old sex worker who had been battered and strangled in Liverpool in 2005. The authorities reported that his DNA information “provides compelling evidence that the defendant was in contact with Anne Marie Foy at the time immediately before she died.”

However, Butler is sure of one thing: he had never met Foy. This isn’t the first time this has happened. A study by Ruth Morgan, the director of the Centre for Forensic Sciences at University College London, and her team argued that DNA evidence had been misleading. According to The Guardian, a British daily newspaper, the researchers raised main issues on DNA evidence such as the relevance, validity, or usefulness of it. 

To address this issue, scientists are developing more artificial techniques to extract DNA profiles and try to work out whether a DNA sample came directly from someone who was at the crime scene, or whether it had just been innocently transferred. However, they are still not certain whether or not this would work, which can affect police investigations. It can allow to even more miscarriages of justice. As of now, many experiments are still underway to find ways of more accurately quantifying DNA transfer in different circumstances. 

According to Tech Xplore, an online site that covers the latest engineering, electronics, and technology advances, AI has the potential to analyze the data from these experiments and use it to indicate the origin of DNA in a sample. To do this, the technology uses mathematical algorithms to complete tasks such as matching a facial expression to a particular set of emotions. The only problem is that AI learns through a process of trial and error and gradually manipulates its underlying algorithms to become more efficient.