search

greenelab / tybalt

Training and evaluating a variational autoencoder for pan-cancer gene expression data
BSD 3-Clause "New" or "Revised" License
162 stars 61 forks source link

Latent feature comparison (Part I) #83

Closed gwaybio closed 6 years ago

gwaybio commented 6 years ago

Adding latent feature subtraction comparison analysis across different dimensionality reduction algorithms.

The notebook is a two part script.

  1. First part performs the subtraction and visualizes the activation difference for Mesenchymal - Immunoreactive subtype vectors across different algorithms.
  2. Second part obtains the high weight genes for the most explanatory features

This is a two part pull request. The second part adds a pathway analysis for the high weight genes of interest.

gwaybio commented 6 years ago

Thanks for your review @jaclyn-taroni - I believe I addressed your comments in the most recent series of commits

jaclyn-taroni commented 6 years ago

Looks like you've addressed all my comments! Let's see what @danich1 thinks :snake: