New open-source platforms accelerate single-cell phenotypic analysis

Researchers have introduced new computational methods to address the growing data demands of high-content microscopy and Cell Painting (CP) assays.

SPACe (Swift Phenotypic Analysis of Cells) is a new open-source, Python-based platform designed for analyzing single-cell image-based morphological profiles. It is capable of processing typical datasets approximately ten times faster than CellProfiler on standard desktop computers while maintaining accuracy in mechanism of action recognition. SPACe also utilizes Earth Mover’s Distance (EMD) for quality control and hit calling, offering sensitivity to cell-to-cell response variations.

Complementing these developments, new workflows are being established to scale single-cell phenotyping by pairing Cellpose-SAM with on-demand cloud GPU compute. This approach aims to streamline the transition from raw image acquisition to biological interpretation by automating segmentation, parallel execution, and per-cell measurement, which is particularly useful for high-throughput microscopy datasets.