Rory Donovan-Maiye

Discussion: β-VAE vs GAN

1

## Issue summary discuss new model re old one(s) ## Details > There are a lot of interesting things to say about the beta-VAE as compared to the GAN used...

## Issue summary we underplay how good the encoded / generated cells look ## Details > It is a HUGE WIN that the model is learning appropriate organelle distributions. This...

Results: Content related to Fig. 5

1

## Issue summary Lots of stuff ## Details > It might be worth considering including some images for the Golgi in brefeldin-treated cells as well as for microtubules in taxol-treated...

Results: Figure 2

1

## Issue summary Clean up figure and move to white-background cell images ## Details > Get rid of the black boxes with white Xs; lack of data is better conveyed...

Results: Figure 1

1

## Issue summary minor aesthetics but otherwise figure 1 is fine ## Details > Figure 1 is fine. I don’t love the red boxes around “Reference structure variation” and “Image...

## Issue summary as beta changes, plot KL vs sorted(dims) and show what happens (maybe more peaked?) ## Details Another feature of the reconstruction vs. compactness trade-off explored by tuning...

## Issue summary orthogonal latent space ==> reproducible training? ## Details > If it is really true that the latent space dimensions also end up tending towards being orthogonal to...

## Issue summary talk up coupling summary stats ## Details > The contingency results summarized in part B are really great, again the specific couplings observed are a HUGE WIN...

## Issue summary top-2 dim latent space plots colored by mito annotation ## Details > I strongly suggest that we include the plot Rory made showing the distribution of the...

## Issue summary color-code by mito annotations ## Details > What is there is fine. I think it would be nice to color-code the mitotic cells by the four annotated...