AI-Powered Robots Conduct 10,000 Scientific Experiments Per Day, Accelerating Discoveries

An AI system called BacterAI has been developed that can conduct up to 10,000 scientific experiments per day, with the potential to revolutionize research in fields ranging from medicine to agriculture to environmental science. BacterAI mapped the metabolism of two microbes associated with oral health, discovering the amino acid requirements for the growth of both Streptococcus gordonii and Streptococcus sanguinis. Unlike conventional methods that feed labeled data sets into a machine-learning model, BacterAI creates its own data set through a series of experiments, producing accurate predictions 90% of the time. Little research has been conducted on roughly 90% of bacteria, and the amount of time and resources needed to learn even basic scientific information about them using conventional methods is daunting. Automated experimentation can drastically speed up these discoveries.