Loading...

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

Rohban, M. H ; Sharif University of Technology | 2019

811 Viewed
  1. Type of Document: Article
  2. DOI: 10.1038/s41467-019-10154-8
  3. Publisher: Nature Publishing Group , 2019
  4. Abstract:
  5. 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. © 2019, The Author(s)
  6. Keywords:
  7. Cell ; Comparative study ; Heterogeneity ; Image analysis ; Article ; Cell heterogeneity ; Cell population ; Covariance ; Protein fingerprinting ; Biology ; Cell culture ; Drug development ; Drug effect ; Information processing ; Preclinical study ; Procedures ; Single cell analysis ; Cells, Cultured ; Computational Biology ; Data Analysis ; Datasets as Topic ; Drug Discovery ; Drug Evaluation, Preclinical ; Single-Cell Analysis
  8. Source: Nature Communications ; Volume 10, Issue 1 , 2019 ; 20411723 (ISSN)
  9. URL: https://www.nature.com/articles/s41467-019-10154-8