begin EDA of sc time-lapse profiles #5
Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
|
It looks like you're removing many other files in this repo, including some analysis. I think it would be useful to provide a change log for the software gardening decisions made in this pr. Also, it may be useful to answer some of these questions: WayScience/nf1_schwann_cell_morphology_signature#52 (comment) |
There was a problem hiding this comment.
What is the NA label here? Consider changing this label
There was a problem hiding this comment.
Is it common to use the means of the UMAP space in this way?
There was a problem hiding this comment.
What does plotting the means of the UMAP components tell us?
There was a problem hiding this comment.
Consider changing the x and y axis label to reflect the mean of the UMAP components (same for the other mean umap plots as well)
There was a problem hiding this comment.
I'm not seeing all of the time points here. If they're not present, consider removing them from the legend (same for the other mean umap plots as well)
There was a problem hiding this comment.
It is difficult for me to distinguish between some of these time points. For example, between the 360 min and 330 min time points. Consider changing the color scheme to make the colors more distinguishable
There was a problem hiding this comment.
Is this the same figure as the top row of the 0.EDA/figures/CP/umap_plot_time.png figure? If so, consider only keeping one copy to be more DRY.
There was a problem hiding this comment.
Consider including a title describing details of the experiment, such as the compound used
(same comment for 0.EDA/figures/combined/umap_plot_time_part_of_doses.png)
There was a problem hiding this comment.
Are these visualizations also present in 0.EDA/figures/combined/umap_plot_time.png If so, consider only keeping one copy to be more DRY.
This PR begins the single cell time-lapse EDA by generating UMAP embeddings and plotting the UMAP embedding space.