search

greenelab / czi-rfa

Application to "Collaborative Computational Tools for the Human Cell Atlas" https://chanzuckerberg.com/initiatives/rfa
Other
6 stars 9 forks source link

Aim 3 - Arjun's Data and Experimental Design #5

Closed gwaybio closed 7 years ago

gwaybio commented 7 years ago

As @cgreene noted in #3

We will need more detail from Arjun to provide an example. I think you should make a hypothetical example of the latent space arithmetic experimental design. What about doing it as single cell data + bulk perturbation & comparing to single cell + perturbation? That seems like the cleanest design to test your hypothesis.

We will use this issue to discuss the nature of the data and experimental design to test the hypothesis:

that the latent space will preserve vector arithmetic operations between state transitions within benchmark perturbation expression datasets.

The issue can be closed once the experimental design is updated in aim 3.

gwaybio commented 7 years ago

It appears that the data will consist of homogenized cell-types under various perturbations.

The purpose/assumption being that under various different stresses, the essence of a "cell-type" will become clear. The cell-type essence features will remain invariant and provide the essential representations for a manifold learning algorithm (i.e. VAE, GAN) to characterize.

cgreene commented 7 years ago

Tried to more clearly note alternative datasets also work in #15