Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Machine learning brings cell imaging promises into focus
Recursion, Janssen, insitro and others are combining high-content phenotypic screening with machine learning to zoom in on emerging opportunities in target discovery, hit identification, toxicity testing and more.
If a cell image is worth a thousand words, drug hunters haven’t been paying attention to most of these. Despite the impressive capabilities of high-content imaging systems to peer into the cell, biopharma researchers tend to use these phenotypic screening platforms only to understand whether a small molecule impacts a particular biological process of interest. But biology is complicated, and many small molecules affect pathways all over the place and mess with morphology throughout the cell. What if machine vision and machine learning could see deeper patterns in the images these screens provide?