the bioinformatics chat

#36 scVI with Romain Lopez and Gabriel Misrachi

Listen Later

In this episode, we hear from Romain Lopez and Gabriel Misrachi about

scVI—Single-cell Variational Inference.
scVI is a probabilistic model for single-cell gene expression data that
combines a hierarchical Bayesian model with deep neural networks encoding the
conditional distributions. scVI scales to over one million cells and can be
used for scRNA-seq normalization and batch effect removal, dimensionality
reduction, visualization, and differential expression. We also
discuss the recently implemented in scVI automatic hyperparameter selection
via Bayesian optimization.

Links:

  • Deep generative modeling for single-cell transcriptomics (Romain Lopez, Jeffrey Regier, Michael Cole, Michael I. Jordan, Nir Yosef)
  • scVI on GitHub
  • Should we zero-inflate scVI?
  • Hyperparameter search for scVI
  • Droplet scRNA-seq is not zero inflated (Valentine Svensson)

    • If you enjoyed this episode, please consider supporting the podcast on Patreon.

    ...more
    View all episodesView all episodes
    Download on the App Store
    the bioinformatics chatBy Roman Cheplyaka
    • 4.8
    • 4.8
    • 4.8
    • 4.8
    • 4.8

    4.8

    34 ratings

    More shows like the bioinformatics chat

    View all
    Radiolab by WNYC Studios

    Radiolab

    43,909 Listeners

    This American Life by This American Life

    This American Life

    90,830 Listeners

    The Bioinformatics and Beyond Podcast by Leo Elworth

    The Bioinformatics and Beyond Podcast

    10 Listeners

    If Books Could Kill by Michael Hobbes & Peter Shamshiri

    If Books Could Kill

    8,747 Listeners

    the bioinformatics lab by The Bioinformatics Lab

    the bioinformatics lab

    0 Listeners