Capturing single-cell heterogeneity via data fusion improves image-based profiling.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 31064985.
- Also identified by DOI 10.1038/s41467-019-10154-8 and PMC identifier 6504923.
- Licence recorded as CC BY.
- The licence permits redistribution, so the abstract is shown in full and the full text is available from the publisher.
Abstract
Single-cell resolution technologies warrant computational methods that capture cell heterogeneity while allowing efficient comparisons of populations. Here, we summarize cell populations by adding features' dispersion and covariances to population averages, in the context of image-based profiling. We find that data fusion is critical for these metrics to improve results over the prior alternatives, providing at least ~20% better performance in predicting a compound's mechanism of action (MoA) and a gene's pathway.
Medical subject headings
- Computational Biology
- Drug Evaluation, Preclinical
- Single-Cell Analysis