Prospective identification of hematopoietic lineage choice by deep learning

Nat Methods. 2017 Apr;14(4):403-406. doi: 10.1038/nmeth.4182. Epub 2017 Feb 20.

Abstract

Differentiation alters molecular properties of stem and progenitor cells, leading to changes in their shape and movement characteristics. We present a deep neural network that prospectively predicts lineage choice in differentiating primary hematopoietic progenitors using image patches from brightfield microscopy and cellular movement. Surprisingly, lineage choice can be detected up to three generations before conventional molecular markers are observable. Our approach allows identification of cells with differentially expressed lineage-specifying genes without molecular labeling.

MeSH terms

  • Animals
  • Area Under Curve
  • Biomarkers / metabolism
  • Cell Differentiation
  • Cell Lineage
  • Gene Knock-In Techniques
  • Hematopoietic Stem Cells / cytology*
  • Hematopoietic Stem Cells / physiology*
  • Image Processing, Computer-Assisted / methods*
  • Machine Learning
  • Male
  • Mice, Mutant Strains
  • Neural Networks, Computer*
  • Proto-Oncogene Proteins / genetics
  • Proto-Oncogene Proteins / metabolism
  • Time-Lapse Imaging / methods*
  • Trans-Activators / genetics
  • Trans-Activators / metabolism

Substances

  • Biomarkers
  • Proto-Oncogene Proteins
  • Trans-Activators
  • proto-oncogene protein Spi-1