Login / Signup

Capturing single-cell heterogeneity via data fusion improves image-based profiling.

Mohammad H RohbanHamdah S AbbasiShantanu SinghAnne E Carpenter
Published in: Nature communications (2019)
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.
Keyphrases
  • single cell
  • rna seq
  • high throughput
  • electronic health record
  • deep learning
  • big data
  • copy number
  • genome wide
  • data analysis
  • artificial intelligence