Santosh Hariharan

The paper updates the Cell Painting assay protocol to improve morphological profiling, finding that simplified steps and reduced stain concentrations maintain robust outputs.

Cell Painting images and profiles for 115,796 compounds in U2OS cells from 12 laboratories; 15.2% of analyzed compounds are phenotypically active, and cross-laboratory replicates cut reference-compound activity by 34%.

The paper introduces MOAProfiler, a deep learning encoder that improves the accuracy of drug mechanism of action classification from Cell Painting images compared to traditional and existing deep learning methods.