ML Algorithm Boosts Gene Therapy Virus Yield to 99%

Researchers at UNC-Chapel Hill developed a machine learning algorithm to optimize virus purification for gene therapy ^[1]. The tool autonomously identifies and tests specific parameters to streamline the manufacturing process ^[1]. This innovation aims to resolve long-standing bottlenecks in medical research and production ^[1]. The algorithm increased viral yields from 70% to 99% during experimental testing ^[1]. This improvement significantly reduces both production costs and the time required for traditional manual experimentation ^[1]. Efficiency gains from this tool could accelerate the delivery of essential gene therapies to patients ^[1].