In the age of big data, and particularly in specialisations such as artificial intelligence, biology, and medicine, researchers often generate large and complex datasets that are challenging to analyse. This is particularly true for multi-view data, otherwise known as multimodal data, which are data that encompass multiple perspectives concerning a single entity or phenomenon. In the case of single-cell genomics, for instance, researchers can measure a huge range of different characteristics concerning an individual cell, such as RNA expression levels or protein levels. While multi-view datasets provide vast amounts of information, they are difficult to analyse because looking at each type of data within them provides only a small part of the overall picture. A new computational approach called Covering Point Set-merge analysis, or CPS-merge analysis for short, has been developed by Lixiang Zhang of Pennsylvania State University and colleagues, and it aims to assist researchers to merge the different types of data present in multi-view datasets into one coherent and meaningful set of results, without misrepresenting the individual contributions of each type of data.