DE tutorial update #118
DE tutorial update #118
Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
|
View / edit / reply to this conversation on ReviewNB adamgayoso commented on 2023-05-16T21:31:42Z "Differential expression on C. elegans data" |
|
View / edit / reply to this conversation on ReviewNB adamgayoso commented on 2023-05-16T21:31:42Z edit the first sentence to be more accurate |
|
View / edit / reply to this conversation on ReviewNB adamgayoso commented on 2023-05-16T21:31:43Z remove the comment |
|
View / edit / reply to this conversation on ReviewNB adamgayoso commented on 2023-05-16T21:31:44Z remove, colab has plotnine.
Let's not use opentsne, we can just use scanpy |
|
View / edit / reply to this conversation on ReviewNB adamgayoso commented on 2023-05-16T21:31:45Z use the backup url option of |
|
View / edit / reply to this conversation on ReviewNB adamgayoso commented on 2023-05-16T21:31:46Z we need to say something about why you need to do gene selection and why this method is or isn't appropriate. You can use a "Note" admonition (open another notebook to see how to code this. |
|
View / edit / reply to this conversation on ReviewNB adamgayoso commented on 2023-05-16T21:31:46Z this cell is an extra detail that doesn't add much value |
|
View / edit / reply to this conversation on ReviewNB adamgayoso commented on 2023-05-16T21:31:47Z no need to define the learning rate as it's default? |
|
View / edit / reply to this conversation on ReviewNB adamgayoso commented on 2023-05-16T21:31:48Z exclude the first 10 epochs? |
|
View / edit / reply to this conversation on ReviewNB adamgayoso commented on 2023-05-16T21:31:49Z use scanpy |
|
View / edit / reply to this conversation on ReviewNB adamgayoso commented on 2023-05-16T21:31:50Z use scanpy |
|
View / edit / reply to this conversation on ReviewNB adamgayoso commented on 2023-05-16T21:31:50Z can you explain why one should use uniform or importance? Can you compare the two results head to head? Perhaps uniform has a lot of lowly expressed bad genes as top hits? |
|
View / edit / reply to this conversation on ReviewNB adamgayoso commented on 2023-05-16T21:31:51Z better y axis name so we don't confuse with p values |
|
View / edit / reply to this conversation on ReviewNB adamgayoso commented on 2023-05-16T21:31:52Z it's not cpm. I'd remove target sum as median is better anyway and remove the comment. |
for more information, see https://pre-commit.ci
No description provided.