Three million images and morphological profiles of cells treated with matched chemical and genetic perturbations

Srinivas Niranj Chandrasekaran, Beth A Cimini, Amy Goodale, Lisa Miller, Maria Kost-Alimova, Nasim Jamali, John Doench, Briana Fritchman, Adam Skepner, Michelle Melanson, Daniel Kuhn, Desiree Hernandez, Jim Berstler, Hamdah Shafqat-Abbasi, David Root, Susanne E Swalley, Shantanu Singh, Anne E Carpenter

Keywords: Image-based profiling, chemical perturbations, genetic perturbations, CRISPR, ORF, target identification, target deconvolution, representation learning

TL;DR: A new Cell Painting image dataset that captures how cells respond to chemical and genetic perturbations and can be used for benchmarking machine learning methods for several drug discovery applications

Abstract: We present a new, carefully designed and well-annotated dataset of images and image-based profiles of cells that have been treated with chemical compounds and genetic perturbations. Each gene that is perturbed is a known target of at least two compounds in the dataset. The dataset can thus serve as a benchmark to evaluate methods for predicting similarities between compounds and between genes and compounds, measuring the effect size of a perturbation, developing style-transfer methods to predict one experimental condition from another, and more generally, learning effective representations for measuring cellular state from microscopy images.

URL: https://broad.io/neurips-cpjump1