Technology can already be programmed to recognise patterns and images and text beyond humans’ own capabilities. This opens up a huge range of possibilities for the discovery of new molecules and drugs. For machines to be able to do this, they need to be trained to sort through the many characteristics of molecules and determine which properties should be retained, suppressed or enhanced to optimise antimicrobial activity.

This session will discuss how to teach a computer to run a Darwinian evolutionary algorithm to select the best molecular structures to interact with bacterial membranes, leading to the first artificial antimicrobials.