Sobolev Alignment: aligning deep general models with large-scale kernel machines¶

_images/workflow.png

Sobolev Alignment identifies commonalities between cell lines and tumors at the single cell level using Sobolev Alignment of deep generative models. Using scVI as a backbone for generative models (VAE), latent variable models are approximated by means of large-scale kernel machines, using FalkonML. This allows a systematic appro

Contents:

  • sobolev_alignment
    • sobolev_alignment package
      • Submodules
      • sobolev_alignment.SobolevAlignment module
      • sobolev_alignment.feature_analysis module
        • basis()
        • combinatorial_product()
        • higher_order_contribution()
      • sobolev_alignment.generate_artificial_sample module
        • generate_samples()
        • parallel_generate_samples()
      • sobolev_alignment.interpolated_features module
        • compute_optimal_tau()
        • project_on_interpolate_PV()
      • sobolev_alignment.kernel_operations module
        • mat_inv_sqrt()
      • sobolev_alignment.krr_approx module
        • KRRApprox
      • sobolev_alignment.krr_model_selection module
        • model_alignment_penalization()
        • model_selection_nu()
      • sobolev_alignment.multi_krr_approx module
        • MultiKRRApprox
      • sobolev_alignment.scvi_model_search module
        • make_objective_function()
        • model_selection()
        • split_dataset()
      • Module contents

    Indices and tables¶

    • Index

    • Module Index

    • Search Page

    Sobolev Alignment

    Navigation

    Contents:

    • sobolev_alignment
    • sobolev_alignment package

    Related Topics

    • Documentation overview
      • Next: sobolev_alignment

    Quick search

    ©2023, Soufiane Mourragui. | Powered by Sphinx 5.3.0 & Alabaster 0.7.13 | Page source