Deep-learning models for lipid nanoparticle-based drug delivery.

Journal: Nanomedicine (London, England)
Published Date:

Abstract

Early prediction of time-lapse microscopy experiments enables intelligent data management and decision-making. Using time-lapse data of HepG2 cells exposed to lipid nanoparticles loaded with mRNA for expression of GFP, the authors hypothesized that it is possible to predict in advance whether a cell will express GFP. The first modeling approach used a convolutional neural network extracting per-cell features at early time points. These features were then combined and explored using either a long short-term memory network (approach 2) or time series feature extraction and gradient boosting machines (approach 3). Accounting for the temporal dynamics significantly improved performance. The results highlight the benefit of accounting for temporal dynamics when studying drug delivery using high-content imaging.

Authors

  • Philip J Harrison
    Department of Pharmaceutical Biosciences, Uppsala University, Uppsala, 75124, Sweden.
  • Håkan Wieslander
    Centre for Image Analysis, Uppsala University, Uppsala, 75124, Sweden.
  • Alan Sabirsh
    Advanced Drug Delivery, Pharmaceutical Sciences, Research and Development, AstraZeneca, Gothenburg, Sweden.
  • Johan Karlsson
  • Victor Malmsjö
    Department of Pharmaceutical Biosciences, Uppsala University, Uppsala, Sweden.
  • Andreas Hellander
    Scaleout Systems AB, Sweden.
  • Carolina Wählby
    1 Centre for Image Analysis/SciLifeLab, Uppsala University, Uppsala, Sweden.
  • Ola Spjuth
    Department of Pharmaceutical Biosciences , Uppsala University , Box 591, SE-75124 , Uppsala Sweden.