Brainstorm: Capabilities

[gwaybio]

I'll use a couple issues to discuss capabilities/challenges/evaluation tactics

• Encodes gene expression representation into less dimensions (i.e. dimensionality reduction)
  • Nonlinear feature generation
    • What do the feature represent? What about intermediate layers?
  • The representation is a reflection of the data generating manifold
    • Possibility of exploring/observing samples along data manifold
      • Where are various covariates?
      • Where are expression sigatures? (TP53, Ras/NF1?)
      • Provide metric for sample similarity along expression signatures (HGSC subtypes?)
• Provides ability to generate samples
  • Can this help with adding more data to other learning tasks?
  • Some sort of in silico drug response to hypothetical sample analysis?

[stale]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.