Cells are highly plastic. They grow, move and acquire new functions or cell fates in response to their environment and to treatment. Capturing these changes and identifying the molecular switches that control cell plasticity are major challenges in biomedical research. Meeting these challenges is essential if we are to better understand how diseases develop and how they can be treated effectively.
Single-cell sequencing has transformed biomedical research. Its success rests partly on the ability to analyse large numbers of cells and compare each experiment against the same reference genome or transcriptome. The thousands of genes or transcripts in these references act as a shared vocabulary.
Image analysis has lacked an equivalent standard. Researchers often have to choose a new set of features for each experiment or focus on selected time points because analysing videos at scale is difficult. This makes it harder to compare findings between studies. To make full use of live-cell imaging, researchers need both a common vocabulary for describing images and a tool capable of reading it.
In two complementary studies published in Nature Communications, researchers led by Professor Xin Lu at the Ludwig Institute for Cancer Research, University of Oxford, and Dr Felix Zhou at Vanderbilt University set out to address this problem.
A standardised vocabulary for reading images and videos
In the first study, the researchers defined 2,185 measurable features describing object shape, appearance and motion. Together, these features make up the SAM phenome.
They also developed the SAM Phenotype Observation Tool, or SPOT, to measure these features and follow how they change over time. By representing every experiment using the same feature set, researchers can compare, combine and cluster imaging data without having to design a new analytical pipeline for each study. The researchers were even able to demonstrate broad applicability, such as reading everyday YouTube videos.
In benchmarks using more than one million cell images, the SAM phenome performed better than several feature sets generated by deep-learning models. It also remained interpretable: each SAM feature describes a named, measurable property that researchers can examine directly.
Connecting multicellular behaviour over time with gene activity
In the companion study, the researchers applied SAM-SPOT to organoids, three-dimensional multicellular cultures that reproduce selected structural and functional features of organs. The framework detected differences in organoid growth and behaviour between various drugs, genotypes, and culture conditions. Some of these changes were difficult to identify using conventional methods. The researchers observed a small number of organoids with similar phenotypes among vastly heterogeneous organoid cultures, grown in conditions with seemingly opposing signalling pathway activities. When combined with single cell RNA sequencing from the same set of organoids, it was revealed that the organoids with the same unusual phenotype are carrying the same genotype.
SAM-SPOT works with labelled or unlabelled images and videos, across imaging modalities. It can be run locally on a normal laptop, and no model training is required. By measuring many SAM features simultaneously, SAM-SPOT can identify complex or unexpected changes while multicellular cultures are followed over time. The researchers suggest that SAM-SPOT could support large-scale genetic and drug screens using live-cell images and videos. It could also be adapted for digital pathology and multiplex imaging, where a shared vocabulary may help researchers decode spatial circuitry of signalling, and patterns of cell arrangement in tissue.
Image analysis papers from the Lu Lab
Zhou, F.Y., Norton-Steele, A., Marsh, L. et al. Development of a universal imaging 'phenome' using shape, appearance and motion (SAM) features and the SAM Phenotype Observation Tool (SPOT). Nature Communications 17, 8409 (2026).
doi.org/10.1038/s41467-026-75505-8
Zhou, F.Y., Jacobs, B.A., Norton-Steele, A. et al. Identifying phenotype-genotype-function coupling in 3D organoid imaging using Shape, Appearance and Motion Phenotype Observation Tool (SPOT). Nature Communications 17, 8410 (2026).
doi.org/10.1038/s41467-026-75506-7
Zhou, F.Y., Ruiz-Puig, C., Owen, R.P. et al. Motion sensing superpixels (MOSES) is a systematic computational framework to quantify and discover cellular motion phenotypes. eLife 8 (2019).