Artificial intelligence (AI) has been advancing rapidly, but its inner workings often remain obscure, characterized by a “black box” nature where the process of reaching conclusions is not visible. However, a significant breakthrough has been made by Prof. Dr. Jürgen Bajorath and his team, cheminformatics experts at the University of Bonn. They have devised a technique that uncovers the operational mechanisms of certain AI systems used in pharmaceutical research.

Surprisingly, their findings indicate that these AI models primarily rely on recalling existing data rather than learning specific chemical interactions for predicting the effectiveness of drugs. Their results have recently been published in Nature Machine Intelligence.

Which drug molecule is most effective? Researchers are feverishly searching for efficient active substances to combat diseases. These compounds often dock onto protein, which usually are enzymes or receptors that trigger a specific chain of physiological actions.