Abstract

The morphology of cell structures can reveal intricate and important details about their mechanisms and functions, and microscopists have excelled at identifying interesting phenomena. Yet it is becoming increasingly clear that images of cell structures contain far more information than meets the eye. The tremendous, rich information in cell images can now be captured and quantified by image analysis, including via deep learning, and put to good use for applications in basic biology research and drug discovery. For example, image analysis can reveal how diseases, drugs, and genes affect cells, which can uncover small molecules’ mechanism of action, discover disease-associated phenotypes, identify the functional impact of disease-associated alleles, and identify novel therapeutics. This "image-based profiling", using fluorescence microscopy assays such as Cell Painting or label-free images, can identify leukemic cells, stage the degradation of red blood cells or their infection by malaria, predict the biological impact and toxicity of compounds, identify screenable phenotypes associated with intractable diseases, detect cancer cells' response to drugs, and more. Together, these applications are beginning to impact progress in the pharmaceutical industry, as cell morphology takes its place among molecular -omics readouts as a powerful data source for systems biology.