Researchers at Goethe University and Philipps University Marburg, in collaboration with the Fraunhofer Institute for Translational Medicine and Pharmacology ITMP, have developed a new artificial intelligence to reduce animal experiments. The AI, called genESOM, was trained to “learn” the structure of small datasets. It uses this learned information to generate new data points. These data points reproduce the properties of experimentally collected data as accurately as if they had been obtained in laboratory experiments. In the future, genESOM could reduce the number of laboratory animals needed for testing new active substances by between 30 and 50 percent.