While network algorithms are usually associated with finding friends on social media, researchers in the UK have shown how they can be used to improve the effectiveness of cancer treatment by predicting the interactions between genes. Cancer is the second leading cause of death around the world and is estimated to account for 9.6 million deaths in 2018, a figure that is expected to rise this year. Existing treatments like chemotherapy involve non-selective agents that have limited effectiveness and strong side-effects. As a result, scientists believe there is a desperate need for improved treatments which are more personalized and more targeted towards cancerous cells. There are a number of such cancer therapies already being developed that exploit a gene relationship called ‘synthetic lethal interactions’ – which means that “cells can cope if either one of its proteins does not work, but will die if neither of the protein is functioning”. Finding such synthetically lethal pairs has proved to be effective in offering more personalized therapies, but the problem is that there are many millions of potential pairs and finding new ones is both difficult and time-consuming. Thanks to the use of artificial intelligence, the researchers have successfully created an algorithm which can solve this problem by predicting where these interactions may occur. Knowing the locations of these relationships is important because they can help identify where potential drug treatments should target just the cancer cells while leaving healthy cells unharmed, creating a more effective, gentler treatment. This novel computational approach shows how emerging technology and AI can rapidly speed up the work that leads to new treatments for cancer and other medical issues.