Bacterial growth depends on the complex interactions of a multitude of chemical components. Microbiologists have long attempted to predict bacterial growth according to culture media components, and have employed a variety of mathematical and computational models to this end. Dr Bei-Wen Ying and her colleagues at the University of Tsukuba, Japan, successfully applied machine learning to understand the contribution of media culture components to bacterial growth. Their work makes a significant contribution to growth prediction and demonstrates that machine learning can be employed in the exploration of the complex dynamics that regulate living systems.